Creating study carrel named neuroscience-from-bioarxiv
Initializing database
Creating cache from Bioarxiv xml file
10.1101/2020.09.21.305516
10_1101-2020_09_21_305516.pdf
10.1101/2021.02.10.430649
10_1101-2021_02_10_430649.pdf
10.1101/2021.02.12.431018
10_1101-2021_02_12_431018.pdf
10.1101/2021.02.11.430847
10_1101-2021_02_11_430847.pdf
10.1101/2021.02.11.430871
10_1101-2021_02_11_430871.pdf
10.1101/2021.02.12.430963
10_1101-2021_02_12_430963.pdf
10.1101/2021.02.13.429885
10_1101-2021_02_13_429885.pdf
10.1101/2021.02.12.430830
10_1101-2021_02_12_430830.pdf
10.1101/2021.02.12.430739
10_1101-2021_02_12_430739.pdf
10.1101/2021.02.12.430764
10_1101-2021_02_12_430764.pdf
10.1101/2020.01.28.923532
10_1101-2020_01_28_923532.pdf
10.1101/2021.02.11.430762
10_1101-2021_02_11_430762.pdf
10.1101/2020.09.23.308239
10_1101-2020_09_23_308239.pdf
10.1101/2020.09.23.310276
10_1101-2020_09_23_310276.pdf
10.1101/2021.02.11.430806
10_1101-2021_02_11_430806.pdf
10.1101/2021.02.11.430695
10_1101-2021_02_11_430695.pdf
10.1101/2021.02.12.430989
10_1101-2021_02_12_430989.pdf
10.1101/2021.02.12.430979
10_1101-2021_02_12_430979.pdf
10.1101/2021.02.12.430923
10_1101-2021_02_12_430923.pdf
10.1101/727867
10_1101-727867.pdf
10.1101/2020.12.24.424317
10_1101-2020_12_24_424317.pdf
10.1101/2020.10.08.327718
10_1101-2020_10_08_327718.pdf
10.1101/2021.02.09.430550
10_1101-2021_02_09_430550.pdf
10.1101/2021.02.10.430656
10_1101-2021_02_10_430656.pdf
10.1101/2021.02.10.430619
10_1101-2021_02_10_430619.pdf
10.1101/2021.02.11.430789
10_1101-2021_02_11_430789.pdf
10.1101/2021.02.10.430512
10_1101-2021_02_10_430512.pdf
10.1101/2021.02.10.430705
10_1101-2021_02_10_430705.pdf
10.1101/2021.02.10.430606
10_1101-2021_02_10_430606.pdf
10.1101/698605
10_1101-698605.pdf
10.1101/2021.02.10.430563
10_1101-2021_02_10_430563.pdf
10.1101/2020.11.17.386649
10_1101-2020_11_17_386649.pdf
10.1101/2020.05.15.090266
10_1101-2020_05_15_090266.pdf
10.1101/2021.02.01.429246
10_1101-2021_02_01_429246.pdf
10.1101/2021.02.10.430623
10_1101-2021_02_10_430623.pdf
10.1101/2021.02.09.430405
10_1101-2021_02_09_430405.pdf
10.1101/2021.02.10.430367
10_1101-2021_02_10_430367.pdf
10.1101/2021.02.09.430536
10_1101-2021_02_09_430536.pdf
10.1101/2021.02.09.430363
10_1101-2021_02_09_430363.pdf
10.1101/2021.02.09.430460
10_1101-2021_02_09_430460.pdf
10.1101/2021.02.08.430070
10_1101-2021_02_08_430070.pdf
10.1101/2021.02.09.430036
10_1101-2021_02_09_430036.pdf
10.1101/2021.02.08.428881
10_1101-2021_02_08_428881.pdf
10.1101/2021.02.08.430343
10_1101-2021_02_08_430343.pdf
10.1101/2021.02.08.430275
10_1101-2021_02_08_430275.pdf
10.1101/2021.02.08.430270
10_1101-2021_02_08_430270.pdf
10.1101/2021.02.10.430604
10_1101-2021_02_10_430604.pdf
10.1101/2021.02.08.430280
10_1101-2021_02_08_430280.pdf
10.1101/2020.09.02.279521
10_1101-2020_09_02_279521.pdf
10.1101/2020.02.04.934216
10_1101-2020_02_04_934216.pdf
2021-02-14 21:22:16 URL:https://www.biorxiv.org/content/10.1101/2021.02.12.431018v1.full.pdf [149895] -> "./cache/10_1101-2021_02_12_431018.pdf" [1]
2021-02-14 21:22:17 URL:https://www.biorxiv.org/content/10.1101/2021.02.12.430764v1.full.pdf [730138] -> "./cache/10_1101-2021_02_12_430764.pdf" [1]
2021-02-14 21:22:17 URL:https://www.biorxiv.org/content/10.1101/2021.02.12.430979v1.full.pdf [842591] -> "./cache/10_1101-2021_02_12_430979.pdf" [1]
2021-02-14 21:22:17 URL:https://www.biorxiv.org/content/10.1101/2021.02.10.430604v1.full.pdf [679851] -> "./cache/10_1101-2021_02_10_430604.pdf" [1]
2021-02-14 21:22:17 URL:https://www.biorxiv.org/content/10.1101/2020.12.24.424317v2.full.pdf [209489] -> "./cache/10_1101-2020_12_24_424317.pdf" [1]
2021-02-14 21:22:17 URL:https://www.biorxiv.org/content/10.1101/2021.02.12.430963v1.full.pdf [696163] -> "./cache/10_1101-2021_02_12_430963.pdf" [1]
2021-02-14 21:22:17 URL:https://www.biorxiv.org/content/10.1101/2021.02.11.430695v1.full.pdf [1150493] -> "./cache/10_1101-2021_02_11_430695.pdf" [1]
2021-02-14 21:22:17 URL:https://www.biorxiv.org/content/10.1101/2021.02.12.430830v1.full.pdf [643872] -> "./cache/10_1101-2021_02_12_430830.pdf" [1]
2021-02-14 21:22:17 URL:https://www.biorxiv.org/content/10.1101/2021.02.11.430762v1.full.pdf [378049] -> "./cache/10_1101-2021_02_11_430762.pdf" [1]
2021-02-14 21:22:17 URL:https://www.biorxiv.org/content/10.1101/2021.02.10.430619v1.full.pdf [661726] -> "./cache/10_1101-2021_02_10_430619.pdf" [1]
2021-02-14 21:22:17 URL:https://www.biorxiv.org/content/10.1101/2021.02.12.430989v1.full.pdf [427940] -> "./cache/10_1101-2021_02_12_430989.pdf" [1]
2021-02-14 21:22:17 URL:https://www.biorxiv.org/content/10.1101/2021.02.11.430806v1.full.pdf [577783] -> "./cache/10_1101-2021_02_11_430806.pdf" [1]
2021-02-14 21:22:17 URL:https://www.biorxiv.org/content/10.1101/2020.01.28.923532v3.full.pdf [1791954] -> "./cache/10_1101-2020_01_28_923532.pdf" [1]
2021-02-14 21:22:17 URL:https://www.biorxiv.org/content/10.1101/2021.02.12.430923v1.full.pdf [715550] -> "./cache/10_1101-2021_02_12_430923.pdf" [1]
2021-02-14 21:22:17 URL:https://www.biorxiv.org/content/10.1101/2021.02.09.430036v1.full.pdf [544464] -> "./cache/10_1101-2021_02_09_430036.pdf" [1]
2021-02-14 21:22:17 URL:https://www.biorxiv.org/content/10.1101/2020.05.15.090266v2.full.pdf [1203677] -> "./cache/10_1101-2020_05_15_090266.pdf" [1]
2021-02-14 21:22:17 URL:https://www.biorxiv.org/content/10.1101/2021.02.08.430270v1.full.pdf [804427] -> "./cache/10_1101-2021_02_08_430270.pdf" [1]
2021-02-14 21:22:17 URL:https://www.biorxiv.org/content/10.1101/2021.02.01.429246v2.full.pdf [877153] -> "./cache/10_1101-2021_02_01_429246.pdf" [1]
2021-02-14 21:22:17 URL:https://www.biorxiv.org/content/10.1101/2021.02.08.430275v1.full.pdf [1459264] -> "./cache/10_1101-2021_02_08_430275.pdf" [1]
2021-02-14 21:22:17 URL:https://www.biorxiv.org/content/10.1101/2021.02.10.430367v1.full.pdf [689268] -> "./cache/10_1101-2021_02_10_430367.pdf" [1]
2021-02-14 21:22:18 URL:https://www.biorxiv.org/content/10.1101/2021.02.10.430512v1.full.pdf [1286961] -> "./cache/10_1101-2021_02_10_430512.pdf" [1]
2021-02-14 21:22:18 URL:https://www.biorxiv.org/content/10.1101/2020.11.17.386649v2.full.pdf [956127] -> "./cache/10_1101-2020_11_17_386649.pdf" [1]
2021-02-14 21:22:18 URL:https://www.biorxiv.org/content/10.1101/2021.02.08.430280v1.full.pdf [1963137] -> "./cache/10_1101-2021_02_08_430280.pdf" [1]
2021-02-14 21:22:18 URL:https://www.biorxiv.org/content/10.1101/2020.09.02.279521v5.full.pdf [1869837] -> "./cache/10_1101-2020_09_02_279521.pdf" [1]
2021-02-14 21:22:18 URL:https://www.biorxiv.org/content/10.1101/2021.02.11.430871v1.full.pdf [1785729] -> "./cache/10_1101-2021_02_11_430871.pdf" [1]
2021-02-14 21:22:18 URL:https://www.biorxiv.org/content/10.1101/2021.02.10.430656v1.full.pdf [2480984] -> "./cache/10_1101-2021_02_10_430656.pdf" [1]
2021-02-14 21:22:18 URL:https://www.biorxiv.org/content/10.1101/2021.02.08.430343v1.full.pdf [1886281] -> "./cache/10_1101-2021_02_08_430343.pdf" [1]
2021-02-14 21:22:18 URL:https://www.biorxiv.org/content/10.1101/2020.10.08.327718v2.full.pdf [2805772] -> "./cache/10_1101-2020_10_08_327718.pdf" [1]
2021-02-14 21:22:18 URL:https://www.biorxiv.org/content/10.1101/2021.02.10.430705v1.full.pdf [4222890] -> "./cache/10_1101-2021_02_10_430705.pdf" [1]
2021-02-14 21:22:18 URL:https://www.biorxiv.org/content/10.1101/698605v3.full.pdf [1986213] -> "./cache/10_1101-698605.pdf" [1]
2021-02-14 21:22:18 URL:https://www.biorxiv.org/content/10.1101/2021.02.11.430847v1.full.pdf [3059886] -> "./cache/10_1101-2021_02_11_430847.pdf" [1]
2021-02-14 21:22:19 URL:https://www.biorxiv.org/content/10.1101/2021.02.10.430649v2.full.pdf [4971886] -> "./cache/10_1101-2021_02_10_430649.pdf" [1]
2021-02-14 21:22:19 URL:https://www.biorxiv.org/content/10.1101/2021.02.10.430623v1.full.pdf [1966479] -> "./cache/10_1101-2021_02_10_430623.pdf" [1]
2021-02-14 21:22:19 URL:https://www.biorxiv.org/content/10.1101/2021.02.08.430070v1.full.pdf [4088950] -> "./cache/10_1101-2021_02_08_430070.pdf" [1]
2021-02-14 21:22:19 URL:https://www.biorxiv.org/content/10.1101/2021.02.09.430536v1.full.pdf [2648870] -> "./cache/10_1101-2021_02_09_430536.pdf" [1]
2021-02-14 21:22:19 URL:https://www.biorxiv.org/content/10.1101/2021.02.09.430405v1.full.pdf [3503948] -> "./cache/10_1101-2021_02_09_430405.pdf" [1]
2021-02-14 21:22:19 URL:https://www.biorxiv.org/content/10.1101/2021.02.09.430550v2.full.pdf [4191549] -> "./cache/10_1101-2021_02_09_430550.pdf" [1]
2021-02-14 21:22:19 URL:https://www.biorxiv.org/content/10.1101/2021.02.09.430460v1.full.pdf [4089353] -> "./cache/10_1101-2021_02_09_430460.pdf" [1]
2021-02-14 21:22:19 URL:https://www.biorxiv.org/content/10.1101/2021.02.10.430563v1.full.pdf [3094960] -> "./cache/10_1101-2021_02_10_430563.pdf" [1]
2021-02-14 21:22:20 URL:https://www.biorxiv.org/content/10.1101/2021.02.13.429885v1.full.pdf [6052365] -> "./cache/10_1101-2021_02_13_429885.pdf" [1]
2021-02-14 21:22:20 URL:https://www.biorxiv.org/content/10.1101/2021.02.12.430739v1.full.pdf [4157988] -> "./cache/10_1101-2021_02_12_430739.pdf" [1]
2021-02-14 21:22:20 URL:https://www.biorxiv.org/content/10.1101/2021.02.08.428881v1.full.pdf [8688452] -> "./cache/10_1101-2021_02_08_428881.pdf" [1]
2021-02-14 21:22:21 URL:https://www.biorxiv.org/content/10.1101/2020.02.04.934216v2.full.pdf [9321917] -> "./cache/10_1101-2020_02_04_934216.pdf" [1]
2021-02-14 21:22:21 URL:https://www.biorxiv.org/content/10.1101/2021.02.10.430606v1.full.pdf [7489918] -> "./cache/10_1101-2021_02_10_430606.pdf" [1]
2021-02-14 21:22:22 URL:https://www.biorxiv.org/content/10.1101/727867v2.full.pdf [10837058] -> "./cache/10_1101-727867.pdf" [1]
2021-02-14 21:22:22 URL:https://www.biorxiv.org/content/10.1101/2020.09.21.305516v2.full.pdf [9506384] -> "./cache/10_1101-2020_09_21_305516.pdf" [1]
2021-02-14 21:22:27 URL:https://www.biorxiv.org/content/10.1101/2021.02.11.430789v1.full.pdf [591073] -> "./cache/10_1101-2021_02_11_430789.pdf" [1]
2021-02-14 21:22:29 URL:https://www.biorxiv.org/content/10.1101/2020.09.23.308239v4.full.pdf [22093690] -> "./cache/10_1101-2020_09_23_308239.pdf" [1]
2021-02-14 21:22:30 URL:https://www.biorxiv.org/content/10.1101/2020.09.23.310276v3.full.pdf [6105307] -> "./cache/10_1101-2020_09_23_310276.pdf" [1]
2021-02-14 21:22:34 URL:https://www.biorxiv.org/content/10.1101/2021.02.09.430363v1.full.pdf [19076613] -> "./cache/10_1101-2021_02_09_430363.pdf" [1]
=== updating bibliographic database
Building study carrel named neuroscience-from-bioarxiv
FILE: cache/10_1101-2021_02_12_431018.pdf
OUTPUT: txt/10_1101-2021_02_12_431018.txt
FILE: cache/10_1101-2020_12_24_424317.pdf
OUTPUT: txt/10_1101-2020_12_24_424317.txt
FILE: cache/10_1101-2021_02_10_430619.pdf
OUTPUT: txt/10_1101-2021_02_10_430619.txt
FILE: cache/10_1101-2021_02_12_430830.pdf
OUTPUT: txt/10_1101-2021_02_12_430830.txt
FILE: cache/10_1101-2021_02_12_430979.pdf
OUTPUT: txt/10_1101-2021_02_12_430979.txt
FILE: cache/10_1101-2020_09_21_305516.pdf
OUTPUT: txt/10_1101-2020_09_21_305516.txt
FILE: cache/10_1101-2021_02_12_430923.pdf
OUTPUT: txt/10_1101-2021_02_12_430923.txt
FILE: cache/10_1101-2020_05_15_090266.pdf
OUTPUT: txt/10_1101-2020_05_15_090266.txt
FILE: cache/10_1101-2021_02_11_430871.pdf
OUTPUT: txt/10_1101-2021_02_11_430871.txt
FILE: cache/10_1101-2021_02_11_430695.pdf
OUTPUT: txt/10_1101-2021_02_11_430695.txt
FILE: cache/10_1101-2021_02_11_430806.pdf
OUTPUT: txt/10_1101-2021_02_11_430806.txt
FILE: cache/10_1101-2021_02_11_430847.pdf
OUTPUT: txt/10_1101-2021_02_11_430847.txt
FILE: cache/10_1101-2021_02_12_430963.pdf
OUTPUT: txt/10_1101-2021_02_12_430963.txt
FILE: cache/10_1101-2021_02_08_430070.pdf
OUTPUT: txt/10_1101-2021_02_08_430070.txt
FILE: cache/10_1101-2021_02_10_430367.pdf
OUTPUT: txt/10_1101-2021_02_10_430367.txt
FILE: cache/10_1101-2021_02_09_430036.pdf
OUTPUT: txt/10_1101-2021_02_09_430036.txt
FILE: cache/10_1101-698605.pdf
OUTPUT: txt/10_1101-698605.txt
FILE: cache/10_1101-2021_02_11_430789.pdf
OUTPUT: txt/10_1101-2021_02_11_430789.txt
FILE: cache/10_1101-2020_11_17_386649.pdf
OUTPUT: txt/10_1101-2020_11_17_386649.txt
FILE: cache/10_1101-2021_02_12_430989.pdf
OUTPUT: txt/10_1101-2021_02_12_430989.txt
FILE: cache/10_1101-2021_02_12_430739.pdf
OUTPUT: txt/10_1101-2021_02_12_430739.txt
FILE: cache/10_1101-2021_02_11_430762.pdf
OUTPUT: txt/10_1101-2021_02_11_430762.txt
FILE: cache/10_1101-2021_02_10_430604.pdf
OUTPUT: txt/10_1101-2021_02_10_430604.txt
FILE: cache/10_1101-2021_02_10_430656.pdf
OUTPUT: txt/10_1101-2021_02_10_430656.txt
FILE: cache/10_1101-2021_02_10_430512.pdf
OUTPUT: txt/10_1101-2021_02_10_430512.txt
FILE: cache/10_1101-2020_10_08_327718.pdf
OUTPUT: txt/10_1101-2020_10_08_327718.txt
FILE: cache/10_1101-2020_09_23_310276.pdf
OUTPUT: txt/10_1101-2020_09_23_310276.txt
FILE: cache/10_1101-2021_02_09_430363.pdf
OUTPUT: txt/10_1101-2021_02_09_430363.txt
FILE: cache/10_1101-2021_02_10_430623.pdf
OUTPUT: txt/10_1101-2021_02_10_430623.txt
FILE: cache/10_1101-2021_02_10_430606.pdf
OUTPUT: txt/10_1101-2021_02_10_430606.txt
FILE: cache/10_1101-2020_02_04_934216.pdf
OUTPUT: txt/10_1101-2020_02_04_934216.txt
FILE: cache/10_1101-2021_02_09_430550.pdf
OUTPUT: txt/10_1101-2021_02_09_430550.txt
FILE: cache/10_1101-2021_02_08_430270.pdf
OUTPUT: txt/10_1101-2021_02_08_430270.txt
FILE: cache/10_1101-2021_02_08_430343.pdf
OUTPUT: txt/10_1101-2021_02_08_430343.txt
FILE: cache/10_1101-2021_02_01_429246.pdf
OUTPUT: txt/10_1101-2021_02_01_429246.txt
FILE: cache/10_1101-2020_09_02_279521.pdf
OUTPUT: txt/10_1101-2020_09_02_279521.txt
FILE: cache/10_1101-2021_02_08_430280.pdf
OUTPUT: txt/10_1101-2021_02_08_430280.txt
FILE: cache/10_1101-2021_02_12_430764.pdf
OUTPUT: txt/10_1101-2021_02_12_430764.txt
FILE: cache/10_1101-2020_01_28_923532.pdf
OUTPUT: txt/10_1101-2020_01_28_923532.txt
FILE: cache/10_1101-2021_02_09_430536.pdf
OUTPUT: txt/10_1101-2021_02_09_430536.txt
FILE: cache/10_1101-2021_02_10_430705.pdf
OUTPUT: txt/10_1101-2021_02_10_430705.txt
FILE: cache/10_1101-2021_02_13_429885.pdf
OUTPUT: txt/10_1101-2021_02_13_429885.txt
FILE: cache/10_1101-2021_02_09_430405.pdf
OUTPUT: txt/10_1101-2021_02_09_430405.txt
FILE: cache/10_1101-2021_02_08_430275.pdf
OUTPUT: txt/10_1101-2021_02_08_430275.txt
FILE: cache/10_1101-2021_02_10_430563.pdf
OUTPUT: txt/10_1101-2021_02_10_430563.txt
FILE: cache/10_1101-2021_02_09_430460.pdf
OUTPUT: txt/10_1101-2021_02_09_430460.txt
FILE: cache/10_1101-2021_02_10_430649.pdf
OUTPUT: txt/10_1101-2021_02_10_430649.txt
FILE: cache/10_1101-2021_02_08_428881.pdf
OUTPUT: txt/10_1101-2021_02_08_428881.txt
FILE: cache/10_1101-727867.pdf
OUTPUT: txt/10_1101-727867.txt
FILE: cache/10_1101-2020_09_23_308239.pdf
OUTPUT: txt/10_1101-2020_09_23_308239.txt
=== file2bib.sh ===
id: 10_1101-2021_02_10_430604
author: Youngblut, Nicholas D.
title: Struo2: efficient metagenome profiling database construction for ever-expanding microbial genome datasets
date: 2021
pages: 4
extension: .pdf
txt: ./txt/10_1101-2021_02_10_430604.txt
cache: ./cache/10_1101-2021_02_10_430604.pdf
Content-Type application/pdf
Creation-Date 2021-02-10T14:11:24Z
Keywords
Last-Modified 2021-02-14T18:25:42Z
Last-Save-Date 2021-02-14T18:25:42Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 109
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-10T14:11:24Z
date 2021-02-14T18:25:42Z
dc:format application/pdf; version=1.4
dc:subject
dc:title Struo2: efficient metagenome profiling database construction for ever-expanding microbial genome datasets
dcterms:created 2021-02-10T14:11:24Z
dcterms:modified 2021-02-14T18:25:42Z
meta:creation-date 2021-02-10T14:11:24Z
meta:keyword
meta:save-date 2021-02-14T18:25:42Z
modified 2021-02-14T18:25:42Z
pdf:PDFVersion 1.4
pdf:charsPerPage ['930', '4650', '2600', '3359']
pdf:docinfo:created 2021-02-10T14:11:24Z
pdf:docinfo:creator_tool Chrome
pdf:docinfo:keywords
pdf:docinfo:modified 2021-02-14T18:25:42Z
pdf:docinfo:producer macOS Version 10.14.6 (Build 18G7016) Quartz PDFContext
pdf:docinfo:title Struo2: efficient metagenome profiling database construction for ever-expanding microbial genome datasets
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0']
producer macOS Version 10.14.6 (Build 18G7016) Quartz PDFContext
resourceName b'10_1101-2021_02_10_430604.pdf'
subject
title Struo2: efficient metagenome profiling database construction for ever-expanding microbial genome datasets
xmp:CreatorTool Chrome
xmpMM:DocumentID uuid:46a164ee-1dd2-11b2-0a00-ef0927edca00
xmpTPg:NPages 4
=== file2bib.sh ===
id: 10_1101-2020_05_15_090266
author: Zhang, R.
title: SpacePHARER: Sensitive identification of phages from CRISPR spacers in prokaryotic hosts
date: 2021
pages: 6
extension: .pdf
txt: ./txt/10_1101-2020_05_15_090266.txt
cache: ./cache/10_1101-2020_05_15_090266.pdf
Appligent AppendPDF Pro 5.5 Linux Kernel 2.6 64bit Oct 2 2014 Library 10.1.0
Content-Type application/pdf
Creation-Date 2021-02-10T16:31:46Z
Last-Modified 2021-02-14T21:22:17Z
Last-Save-Date 2021-02-14T21:22:17Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 43
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-10T16:31:46Z
date 2021-02-14T21:22:17Z
dc:format application/pdf; version=1.5
dc:title 34320483
dcterms:created 2021-02-10T16:31:46Z
dcterms:modified 2021-02-14T21:22:17Z
meta:creation-date 2021-02-10T16:31:46Z
meta:save-date 2021-02-14T21:22:17Z
modified 2021-02-14T21:22:17Z
pdf:PDFVersion 1.5
pdf:charsPerPage ['4925', '4142', '2075', '344', '344', '344']
pdf:docinfo:created 2021-02-10T16:31:46Z
pdf:docinfo:creator_tool Appligent AppendPDF Pro 5.5
pdf:docinfo:custom:Appligent AppendPDF Pro 5.5 Linux Kernel 2.6 64bit Oct 2 2014 Library 10.1.0
pdf:docinfo:modified 2021-02-14T21:22:17Z
pdf:docinfo:producer xdvipdfmx (20200315)
pdf:docinfo:title 34320483
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0']
producer xdvipdfmx (20200315)
resourceName b'10_1101-2020_05_15_090266.pdf'
title 34320483
xmp:CreatorTool Appligent AppendPDF Pro 5.5
xmpMM:DocumentID uuid:11f1d5d2-b085-11b2-0a00-782dad000000
xmpTPg:NPages 6
=== file2bib.sh ===
id: 10_1101-2021_02_12_431018
author: Truong Nguyen, Phuoc
title: HaVoC, a bioinformatic pipeline for reference-based consensus assembly and lineage assignment for SARS-CoV-2 sequences.
date: 2021
pages: 14
extension: .pdf
txt: ./txt/10_1101-2021_02_12_431018.txt
cache: ./cache/10_1101-2021_02_12_431018.pdf
Content-Type application/pdf
Creation-Date 2021-02-12T22:55:36Z
Last-Modified 2021-02-14T19:16:35Z
Last-Save-Date 2021-02-14T19:16:35Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 393
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-12T22:55:36Z
date 2021-02-14T19:16:35Z
dc:format application/pdf; version=1.4
dc:title HaVoC, a bioinformatic pipeline for reference-based consensus assembly and lineage assignment for SARS-CoV-2 sequences.
dcterms:created 2021-02-12T22:55:36Z
dcterms:modified 2021-02-14T19:16:35Z
meta:creation-date 2021-02-12T22:55:36Z
meta:save-date 2021-02-14T19:16:35Z
modified 2021-02-14T19:16:35Z
pdf:PDFVersion 1.4
pdf:charsPerPage ['1876', '2014', '2602', '2132', '1961', '953', '1972', '1160', '2014', '1880', '2254', '2405', '1553', '833']
pdf:docinfo:created 2021-02-12T22:55:36Z
pdf:docinfo:creator_tool Word
pdf:docinfo:modified 2021-02-14T19:16:35Z
pdf:docinfo:producer macOS Version 11.2.1 (Build 20D74) Quartz PDFContext
pdf:docinfo:title HaVoC, a bioinformatic pipeline for reference-based consensus assembly and lineage assignment for SARS-CoV-2 sequences.
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
producer macOS Version 11.2.1 (Build 20D74) Quartz PDFContext
resourceName b'10_1101-2021_02_12_431018.pdf'
title HaVoC, a bioinformatic pipeline for reference-based consensus assembly and lineage assignment for SARS-CoV-2 sequences.
xmp:CreatorTool Word
xmpMM:DocumentID uuid:58d2adfc-1dd2-11b2-0a00-b30827bd7700
xmpTPg:NPages 14
=== file2bib.sh ===
id: 10_1101-2021_02_11_430806
author: Badaczewska-Dawid, Aleksandra
title: BIAPSS - BioInformatic Analysis of liquid-liquid Phase-Separating protein Sequences
date: 2021
pages: 3
extension: .pdf
txt: ./txt/10_1101-2021_02_11_430806.txt
cache: ./cache/10_1101-2021_02_11_430806.pdf
Author
Content-Type application/pdf
Creation-Date 2021-02-04T20:10:30Z
Keywords
Last-Modified 2021-02-14T21:22:17Z
Last-Save-Date 2021-02-14T21:22:17Z
PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.20 (TeX Live 2019) kpathsea version 6.3.1
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 35
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
cp:subject
created 2021-02-04T20:10:30Z
creator
date 2021-02-14T21:22:17Z
dc:creator
dc:format application/pdf; version=1.5
dc:subject
dc:title BIAPSS - BioInformatic Analysis of liquid-liquid Phase-Separating protein Sequences
dcterms:created 2021-02-04T20:10:30Z
dcterms:modified 2021-02-14T21:22:17Z
meta:author
meta:creation-date 2021-02-04T20:10:30Z
meta:keyword
meta:save-date 2021-02-14T21:22:17Z
modified 2021-02-14T21:22:17Z
pdf:PDFVersion 1.5
pdf:charsPerPage ['4645', '5732', '5920']
pdf:docinfo:created 2021-02-04T20:10:30Z
pdf:docinfo:creator
pdf:docinfo:creator_tool LaTeX with hyperref
pdf:docinfo:custom:PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.20 (TeX Live 2019) kpathsea version 6.3.1
pdf:docinfo:keywords
pdf:docinfo:modified 2021-02-14T21:22:17Z
pdf:docinfo:producer pdfTeX-1.40.20
pdf:docinfo:subject
pdf:docinfo:title BIAPSS - BioInformatic Analysis of liquid-liquid Phase-Separating protein Sequences
pdf:docinfo:trapped False
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['2', '0', '0']
producer pdfTeX-1.40.20
resourceName b'10_1101-2021_02_11_430806.pdf'
subject
title BIAPSS - BioInformatic Analysis of liquid-liquid Phase-Separating protein Sequences
trapped False
xmp:CreatorTool LaTeX with hyperref
xmpMM:DocumentID uuid:85c70edf-1dd2-11b2-0a00-020a27bd7700
xmpTPg:NPages 3
=== file2bib.sh ===
id: 10_1101-2021_02_09_430036
author: Goldsborough, Thibaut
title: A comparative study of genomic adaptations to low nitrogen availability in Genlisea aurea
date: 2021
pages: 7
extension: .pdf
txt: ./txt/10_1101-2021_02_09_430036.txt
cache: ./cache/10_1101-2021_02_09_430036.pdf
Author Thibaut Gold
Content-Type application/pdf
Creation-Date 2021-02-09T17:39:12Z
Keywords
Last-Modified 2021-02-14T21:22:17Z
Last-Save-Date 2021-02-14T21:22:17Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 44
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
cp:subject
created 2021-02-09T17:39:12Z
creator Thibaut Gold
date 2021-02-14T21:22:17Z
dc:creator Thibaut Gold
dc:format application/pdf; version=1.4
dc:subject
dc:title A comparative study of genomic adaptations to low nitrogen availability in Genlisea aurea
dcterms:created 2021-02-09T17:39:12Z
dcterms:modified 2021-02-14T21:22:17Z
meta:author Thibaut Gold
meta:creation-date 2021-02-09T17:39:12Z
meta:keyword
meta:save-date 2021-02-14T21:22:17Z
modified 2021-02-14T21:22:17Z
pdf:PDFVersion 1.4
pdf:charsPerPage ['3613', '3079', '2428', '2810', '1917', '3361', '1048']
pdf:docinfo:created 2021-02-09T17:39:12Z
pdf:docinfo:creator Thibaut Gold
pdf:docinfo:creator_tool Word
pdf:docinfo:keywords
pdf:docinfo:modified 2021-02-14T21:22:17Z
pdf:docinfo:producer Mac OS X 10.13.6 Quartz PDFContext
pdf:docinfo:subject
pdf:docinfo:title A comparative study of genomic adaptations to low nitrogen availability in Genlisea aurea
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0']
producer Mac OS X 10.13.6 Quartz PDFContext
resourceName b'10_1101-2021_02_09_430036.pdf'
subject
title A comparative study of genomic adaptations to low nitrogen availability in Genlisea aurea
xmp:CreatorTool Word
xmpMM:DocumentID uuid:85c6fc4a-1dd2-11b2-0a00-ca0827edca00
xmpTPg:NPages 7
=== file2bib.sh ===
id: 10_1101-2021_02_10_430367
author: Chen, Meili
title: Genome Warehouse: A Public Repository Housing Genome-scale Data
date: 2021
pages: 18
extension: .pdf
txt: ./txt/10_1101-2021_02_10_430367.txt
cache: ./cache/10_1101-2021_02_10_430367.pdf
Appligent AppendPDF Pro 5.5 Linux Kernel 2.6 64bit Oct 2 2014 Library 10.1.0
Content-Type application/pdf
Creation-Date 2021-02-11T01:56:12Z
Last-Modified 2021-02-14T20:28:35Z
Last-Save-Date 2021-02-14T20:28:35Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 50
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-11T01:56:12Z
date 2021-02-14T20:28:35Z
dc:format application/pdf; version=1.5
dc:title 9691071
dcterms:created 2021-02-11T01:56:12Z
dcterms:modified 2021-02-14T20:28:35Z
meta:creation-date 2021-02-11T01:56:12Z
meta:save-date 2021-02-14T20:28:35Z
modified 2021-02-14T20:28:35Z
pdf:PDFVersion 1.5
pdf:charsPerPage ['1753', '469', '1895', '2624', '2620', '2657', '2533', '2599', '2634', '2173', '753', '3213', '1644', '926', '1127', '344', '344', '344']
pdf:docinfo:created 2021-02-11T01:56:12Z
pdf:docinfo:creator_tool Appligent AppendPDF Pro 5.5
pdf:docinfo:custom:Appligent AppendPDF Pro 5.5 Linux Kernel 2.6 64bit Oct 2 2014 Library 10.1.0
pdf:docinfo:modified 2021-02-14T20:28:35Z
pdf:docinfo:producer Acrobat Distiller 9.0.0 (Windows)
pdf:docinfo:title 9691071
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
producer Acrobat Distiller 9.0.0 (Windows)
resourceName b'10_1101-2021_02_10_430367.pdf'
title 9691071
xmp:CreatorTool Appligent AppendPDF Pro 5.5
xmpMM:DocumentID uuid:dbcd43fb-b085-11b2-0a00-782dad000000
xmpTPg:NPages 18
=== file2bib.sh ===
id: 10_1101-2021_02_10_430619
author: Schutz, Sacha
title: Cutevariant: a GUI-based desktop application to explore genetics variations
date: 2021
pages: 8
extension: .pdf
txt: ./txt/10_1101-2021_02_10_430619.txt
cache: ./cache/10_1101-2021_02_10_430619.pdf
Author
Content-Type application/pdf
Creation-Date 2021-02-10T23:59:47Z
Keywords
Last-Modified 2021-02-14T21:22:16Z
Last-Save-Date 2021-02-14T21:22:16Z
PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.21 (TeX Live 2020) kpathsea version 6.3.2
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 68
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
cp:subject
created 2021-02-10T23:59:47Z
creator
date 2021-02-14T21:22:16Z
dc:creator
dc:format application/pdf; version=1.5
dc:subject
dc:title Cutevariant: a GUI-based desktop application to explore genetics variations
dcterms:created 2021-02-10T23:59:47Z
dcterms:modified 2021-02-14T21:22:16Z
meta:author
meta:creation-date 2021-02-10T23:59:47Z
meta:keyword
meta:save-date 2021-02-14T21:22:16Z
modified 2021-02-14T21:22:16Z
pdf:PDFVersion 1.5
pdf:charsPerPage ['4040', '3428', '2261', '3414', '3216', '4578', '5638', '627']
pdf:docinfo:created 2021-02-10T23:59:47Z
pdf:docinfo:creator
pdf:docinfo:creator_tool LaTeX with hyperref
pdf:docinfo:custom:PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.21 (TeX Live 2020) kpathsea version 6.3.2
pdf:docinfo:keywords
pdf:docinfo:modified 2021-02-14T21:22:16Z
pdf:docinfo:producer pdfTeX-1.40.21
pdf:docinfo:subject
pdf:docinfo:title Cutevariant: a GUI-based desktop application to explore genetics variations
pdf:docinfo:trapped False
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '1', '0', '0', '0', '0', '0']
producer pdfTeX-1.40.21
resourceName b'10_1101-2021_02_10_430619.pdf'
subject
title Cutevariant: a GUI-based desktop application to explore genetics variations
trapped False
xmp:CreatorTool LaTeX with hyperref
xmpMM:DocumentID uuid:85c6c1a1-1dd2-11b2-0a00-0e0a27fd5800
xmpTPg:NPages 8
=== file2bib.sh ===
id: 10_1101-2020_12_24_424317
author: Muazzam, Fariha
title: Multi-class Cancer Classification and Biomarker Identification using Deep Learning
date: 2021
pages: 12
extension: .pdf
txt: ./txt/10_1101-2020_12_24_424317.txt
cache: ./cache/10_1101-2020_12_24_424317.pdf
Content-Type application/pdf
Creation-Date 2021-02-11T09:45:39Z
Last-Modified 2021-02-14T21:22:16Z
Last-Save-Date 2021-02-14T21:22:16Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 71
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-11T09:45:39Z
date 2021-02-14T21:22:16Z
dc:format application/pdf; version=1.6
dc:language en-GB
dc:title Multi-class Cancer Classification and Biomarker Identification using Deep Learning
dcterms:created 2021-02-11T09:45:39Z
dcterms:modified 2021-02-14T21:22:16Z
language en-GB
meta:creation-date 2021-02-11T09:45:39Z
meta:save-date 2021-02-14T21:22:16Z
modified 2021-02-14T21:22:16Z
pdf:PDFVersion 1.6
pdf:charsPerPage ['2052', '4575', '4008', '1734', '1778', '1769', '1698', '1509', '909', '2553', '2652', '3042']
pdf:docinfo:created 2021-02-11T09:45:39Z
pdf:docinfo:creator_tool Writer
pdf:docinfo:modified 2021-02-14T21:22:16Z
pdf:docinfo:producer LibreOffice 7.0
pdf:docinfo:title Multi-class Cancer Classification and Biomarker Identification using Deep Learning
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
producer LibreOffice 7.0
resourceName b'10_1101-2020_12_24_424317.pdf'
title Multi-class Cancer Classification and Biomarker Identification using Deep Learning
xmp:CreatorTool Writer
xmpMM:DocumentID uuid:85c6c437-1dd2-11b2-0a00-2c09276d7200
xmpTPg:NPages 12
=== file2bib.sh ===
id: 10_1101-2021_02_09_430405
author: Quazi, Sameer
title: In-silico Structural and Molecular Docking-Based Drug Discovery Against Viral Protein (VP35) of Marburg Virus: A potent Agent of MAVD
date: 2021
pages: 23
extension: .pdf
txt: ./txt/10_1101-2021_02_09_430405.txt
cache: ./cache/10_1101-2021_02_09_430405.pdf
Author Administrator
Content-Type application/pdf
Creation-Date 2021-02-09T11:42:11Z
Last-Modified 2021-02-14T21:22:17Z
Last-Save-Date 2021-02-14T21:22:17Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 290
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-09T11:42:11Z
creator Administrator
date 2021-02-14T21:22:17Z
dc:creator Administrator
dc:format application/pdf; version=1.4
dc:title In-silico Structural and Molecular Docking-Based Drug Discovery Against Viral Protein (VP35) of Marburg Virus: A potent Agent of MAVD
dcterms:created 2021-02-09T11:42:11Z
dcterms:modified 2021-02-14T21:22:17Z
meta:author Administrator
meta:creation-date 2021-02-09T11:42:11Z
meta:save-date 2021-02-14T21:22:17Z
modified 2021-02-14T21:22:17Z
pdf:PDFVersion 1.4
pdf:charsPerPage ['1009', '1911', '2821', '2570', '2562', '2577', '1720', '428', '1276', '556', '1603', '1747', '1012', '1189', '1356', '1452', '1064', '2808', '1825', '1961', '1940', '1464', '342']
pdf:docinfo:created 2021-02-09T11:42:11Z
pdf:docinfo:creator Administrator
pdf:docinfo:creator_tool PScript5.dll Version 5.2.2
pdf:docinfo:modified 2021-02-14T21:22:17Z
pdf:docinfo:producer Acrobat Distiller 8.1.0 (Windows)
pdf:docinfo:title In-silico Structural and Molecular Docking-Based Drug Discovery Against Viral Protein (VP35) of Marburg Virus: A potent Agent of MAVD
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
producer Acrobat Distiller 8.1.0 (Windows)
resourceName b'10_1101-2021_02_09_430405.pdf'
title In-silico Structural and Molecular Docking-Based Drug Discovery Against Viral Protein (VP35) of Marburg Virus: A potent Agent of MAVD
xmp:CreatorTool PScript5.dll Version 5.2.2
xmpMM:DocumentID uuid:85c8294e-1dd2-11b2-0a00-d70827bd3700
xmpTPg:NPages 23
=== file2bib.sh ===
id: 10_1101-2020_09_23_310276
author: Greenfest-Allen, Emily
title: NIAGADS Alzheimer's GenomicsDB: A resource for exploring Alzheimer's Disease genetic and genomic knowledge
date: 2021
pages: 19
extension: .pdf
txt: ./txt/10_1101-2020_09_23_310276.txt
cache: ./cache/10_1101-2020_09_23_310276.pdf
Appligent AppendPDF Pro 5.5 Linux Kernel 2.6 64bit Oct 2 2014 Library 10.1.0
Author Emily Greenfest-Allen
Content-Type application/pdf
Creation-Date 2021-02-12T15:45:35Z
Last-Modified 2021-02-14T21:22:27Z
Last-Save-Date 2021-02-14T21:22:27Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 155
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-12T15:45:35Z
creator Emily Greenfest-Allen
date 2021-02-14T21:22:27Z
dc:creator Emily Greenfest-Allen
dc:format application/pdf; version=1.7
dc:language en-US
dc:title 97992561
dcterms:created 2021-02-12T15:45:35Z
dcterms:modified 2021-02-14T21:22:27Z
language en-US
meta:author Emily Greenfest-Allen
meta:creation-date 2021-02-12T15:45:35Z
meta:save-date 2021-02-14T21:22:27Z
modified 2021-02-14T21:22:27Z
pdf:PDFVersion 1.7
pdf:charsPerPage ['1219', '2048', '3230', '2954', '2587', '3080', '3145', '3484', '3621', '3162', '2797', '3464', '3377', '1506', '1005', '722', '265', '309', '266']
pdf:docinfo:created 2021-02-12T15:45:35Z
pdf:docinfo:creator Emily Greenfest-Allen
pdf:docinfo:creator_tool Appligent AppendPDF Pro 5.5
pdf:docinfo:custom:Appligent AppendPDF Pro 5.5 Linux Kernel 2.6 64bit Oct 2 2014 Library 10.1.0
pdf:docinfo:modified 2021-02-14T21:22:27Z
pdf:docinfo:producer Microsoft® Word for Microsoft 365
pdf:docinfo:title 97992561
pdf:encrypted false
pdf:hasMarkedContent true
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
producer Microsoft® Word for Microsoft 365
resourceName b'10_1101-2020_09_23_310276.pdf'
title 97992561
xmp:CreatorTool Appligent AppendPDF Pro 5.5
xmpMM:DocumentID uuid:076548d5-b089-11b2-0a00-782dad000000
xmpTPg:NPages 19
=== file2bib.sh ===
id: 10_1101-2021_02_12_430739
author: Malekian, Negin
title: Mutations in bdcA and valS correlate with quinolone resistance in wastewater Escherichia Coli
date: 2021
pages: 13
extension: .pdf
txt: ./txt/10_1101-2021_02_12_430739.txt
cache: ./cache/10_1101-2021_02_12_430739.pdf
Author Negin Malekian, Ali Al-Fatlawi, Thomas U. Berendonk, Michael Schroeder
Content-Type application/pdf
Creation-Date 2021-02-12T10:09:54Z
Keywords E Coli, Quinolone, Antibiotic Resistance, Genome-Wide Association Study (GWAS)
Last-Modified 2021-02-14T21:22:16Z
Last-Save-Date 2021-02-14T21:22:16Z
PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.20 (TeX Live 2019) kpathsea version 6.3.1
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 104
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
cp:subject
created 2021-02-12T10:09:54Z
creator Negin Malekian, Ali Al-Fatlawi, Thomas U. Berendonk, Michael Schroeder
date 2021-02-14T21:22:16Z
dc:creator Negin Malekian, Ali Al-Fatlawi, Thomas U. Berendonk, Michael Schroeder
dc:format application/pdf; version=1.5
dc:subject E Coli, Quinolone, Antibiotic Resistance, Genome-Wide Association Study (GWAS)
dc:title Mutations in bdcA and valS correlate with quinolone resistance in wastewater Escherichia Coli
dcterms:created 2021-02-12T10:09:54Z
dcterms:modified 2021-02-14T21:22:16Z
meta:author Negin Malekian, Ali Al-Fatlawi, Thomas U. Berendonk, Michael Schroeder
meta:creation-date 2021-02-12T10:09:54Z
meta:keyword E Coli, Quinolone, Antibiotic Resistance, Genome-Wide Association Study (GWAS)
meta:save-date 2021-02-14T21:22:16Z
modified 2021-02-14T21:22:16Z
pdf:PDFVersion 1.5
pdf:charsPerPage ['3702', '4965', '4466', '4704', '4734', '1542', '1200', '1401', '2846', '987', '740', '6975', '1619']
pdf:docinfo:created 2021-02-12T10:09:54Z
pdf:docinfo:creator Negin Malekian, Ali Al-Fatlawi, Thomas U. Berendonk, Michael Schroeder
pdf:docinfo:creator_tool LaTeX with hyperref
pdf:docinfo:custom:PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.20 (TeX Live 2019) kpathsea version 6.3.1
pdf:docinfo:keywords E Coli, Quinolone, Antibiotic Resistance, Genome-Wide Association Study (GWAS)
pdf:docinfo:modified 2021-02-14T21:22:16Z
pdf:docinfo:producer pdfTeX-1.40.20
pdf:docinfo:subject
pdf:docinfo:title Mutations in bdcA and valS correlate with quinolone resistance in wastewater Escherichia Coli
pdf:docinfo:trapped False
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
producer pdfTeX-1.40.20
resourceName b'10_1101-2021_02_12_430739.pdf'
subject
title Mutations in bdcA and valS correlate with quinolone resistance in wastewater Escherichia Coli
trapped False
xmp:CreatorTool LaTeX with hyperref
xmpMM:DocumentID uuid:85c69c39-1dd2-11b2-0a00-ce09271d5700
xmpTPg:NPages 13
=== file2bib.sh ===
id: 10_1101-2021_02_08_430270
author: Gerard, David
title: Scalable Bias-corrected Linkage Disequilibrium Estimation Under Genotype Uncertainty
date: 2021
pages: 22
extension: .pdf
txt: ./txt/10_1101-2021_02_08_430270.txt
cache: ./cache/10_1101-2021_02_08_430270.pdf
Author
Content-Type application/pdf
Creation-Date 2021-02-06T15:17:17Z
Keywords
Last-Modified 2021-02-14T21:22:17Z
Last-Save-Date 2021-02-14T21:22:17Z
PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.20 (TeX Live 2019/Debian) kpathsea version 6.3.1
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 140
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
cp:subject
created 2021-02-06T15:17:17Z
creator
date 2021-02-14T21:22:17Z
dc:creator
dc:format application/pdf; version=1.5
dc:subject
dc:title Scalable Bias-corrected Linkage Disequilibrium Estimation Under Genotype Uncertainty
dcterms:created 2021-02-06T15:17:17Z
dcterms:modified 2021-02-14T21:22:17Z
meta:author
meta:creation-date 2021-02-06T15:17:17Z
meta:keyword
meta:save-date 2021-02-14T21:22:17Z
modified 2021-02-14T21:22:17Z
pdf:PDFVersion 1.5
pdf:charsPerPage ['2802', '2526', '2381', '3475', '1934', '1023', '1087', '826', '1646', '807', '1100', '1292', '1510', '1328', '1406', '1480', '2341', '1019', '1098', '754', '3273', '1665']
pdf:docinfo:created 2021-02-06T15:17:17Z
pdf:docinfo:creator
pdf:docinfo:creator_tool LaTeX with hyperref
pdf:docinfo:custom:PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.20 (TeX Live 2019/Debian) kpathsea version 6.3.1
pdf:docinfo:keywords
pdf:docinfo:modified 2021-02-14T21:22:17Z
pdf:docinfo:producer pdfTeX-1.40.20
pdf:docinfo:subject
pdf:docinfo:title Scalable Bias-corrected Linkage Disequilibrium Estimation Under Genotype Uncertainty
pdf:docinfo:trapped False
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '14', '14', '2', '0', '0', '0', '0', '23', '32', '30', '28', '0', '7', '16', '10', '8', '19', '0', '0', '0', '0']
producer pdfTeX-1.40.20
resourceName b'10_1101-2021_02_08_430270.pdf'
subject
title Scalable Bias-corrected Linkage Disequilibrium Estimation Under Genotype Uncertainty
trapped False
xmp:CreatorTool LaTeX with hyperref
xmpMM:DocumentID uuid:85c73f0b-1dd2-11b2-0a00-810827edca00
xmpTPg:NPages 22
=== file2bib.sh ===
id: 10_1101-2021_02_08_430275
author: Zhang, Jianbo
title: Next-generation sequencing-based bulked segregant analysis without sequencing the parental genomes
date: 2021
pages: 6
extension: .pdf
txt: ./txt/10_1101-2021_02_08_430275.txt
cache: ./cache/10_1101-2021_02_08_430275.pdf
Author
Content-Type application/pdf
Creation-Date 2020-11-24T15:53:05Z
Keywords
Last-Modified 2021-02-14T21:22:17Z
Last-Save-Date 2021-02-14T21:22:17Z
PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.20 (TeX Live 2019/Debian) kpathsea version 6.3.1
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 456
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
cp:subject
created 2020-11-24T15:53:05Z
creator
date 2021-02-14T21:22:17Z
dc:creator
dc:format application/pdf; version=1.5
dc:subject
dc:title Next-generation sequencing-based bulked segregant analysis without sequencing the parental genomes
dcterms:created 2020-11-24T15:53:05Z
dcterms:modified 2021-02-14T21:22:17Z
meta:author
meta:creation-date 2020-11-24T15:53:05Z
meta:keyword
meta:save-date 2021-02-14T21:22:17Z
modified 2021-02-14T21:22:17Z
pdf:PDFVersion 1.5
pdf:charsPerPage ['5882', '7329', '6126', '2575', '3579', '6462']
pdf:docinfo:created 2020-11-24T15:53:05Z
pdf:docinfo:creator
pdf:docinfo:creator_tool LaTeX with hyperref
pdf:docinfo:custom:PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.20 (TeX Live 2019/Debian) kpathsea version 6.3.1
pdf:docinfo:keywords
pdf:docinfo:modified 2021-02-14T21:22:17Z
pdf:docinfo:producer pdfTeX-1.40.20
pdf:docinfo:subject
pdf:docinfo:title Next-generation sequencing-based bulked segregant analysis without sequencing the parental genomes
pdf:docinfo:trapped False
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['3', '0', '0', '0', '0', '0']
producer pdfTeX-1.40.20
resourceName b'10_1101-2021_02_08_430275.pdf'
subject
title Next-generation sequencing-based bulked segregant analysis without sequencing the parental genomes
trapped False
xmp:CreatorTool LaTeX with hyperref
xmpMM:DocumentID uuid:85c6d549-1dd2-11b2-0a00-840827bd7200
xmpTPg:NPages 6
=== file2bib.sh ===
id: 10_1101-2020_11_17_386649
author: Danciu, Daniel
title: Topology-based Sparsification of Graph Annotations
date: 2021
pages: 15
extension: .pdf
txt: ./txt/10_1101-2020_11_17_386649.txt
cache: ./cache/10_1101-2020_11_17_386649.pdf
Content-Type application/pdf
Creation-Date 2021-02-10T17:24:37Z
Last-Modified 2021-02-14T21:22:17Z
Last-Save-Date 2021-02-14T21:22:17Z
PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.21 (TeX Live 2020) kpathsea version 6.3.2
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 107
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-10T17:24:37Z
date 2021-02-14T21:22:17Z
dc:format application/pdf; version=1.5
dc:title Topology-based Sparsification of Graph Annotations
dcterms:created 2021-02-10T17:24:37Z
dcterms:modified 2021-02-14T21:22:17Z
meta:creation-date 2021-02-10T17:24:37Z
meta:save-date 2021-02-14T21:22:17Z
modified 2021-02-14T21:22:17Z
pdf:PDFVersion 1.5
pdf:charsPerPage ['3229', '3783', '3431', '3239', '3042', '2396', '2551', '2253', '3283', '3496', '2308', '1552', '3245', '2696', '2690']
pdf:docinfo:created 2021-02-10T17:24:37Z
pdf:docinfo:creator_tool TeX
pdf:docinfo:custom:PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.21 (TeX Live 2020) kpathsea version 6.3.2
pdf:docinfo:modified 2021-02-14T21:22:17Z
pdf:docinfo:producer pdfTeX-1.40.21
pdf:docinfo:title Topology-based Sparsification of Graph Annotations
pdf:docinfo:trapped False
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '2', '5', '1', '7', '0', '0', '0', '0', '0', '0', '0', '0']
producer pdfTeX-1.40.21
resourceName b'10_1101-2020_11_17_386649.pdf'
title Topology-based Sparsification of Graph Annotations
trapped False
xmp:CreatorTool TeX
xmpMM:DocumentID uuid:85c770f7-1dd2-11b2-0a00-fe08275dc400
xmpTPg:NPages 15
=== file2bib.sh ===
id: 10_1101-2021_02_11_430847
author: Pinatti, Lisa M.
title: SearcHPV: a novel approach to identify and assemble human papillomavirus-host genomic integration events in cancer
date: 2021
pages: 26
extension: .pdf
txt: ./txt/10_1101-2021_02_11_430847.txt
cache: ./cache/10_1101-2021_02_11_430847.pdf
Author Brenner, Chad
Content-Type application/pdf
Creation-Date 2021-02-11T21:58:56Z
Last-Modified 2021-02-14T21:22:17Z
Last-Save-Date 2021-02-14T21:22:17Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 250
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-11T21:58:56Z
creator Brenner, Chad
date 2021-02-14T21:22:17Z
dc:creator Brenner, Chad
dc:format application/pdf; version=1.6
dc:title SearcHPV: a novel approach to identify and assemble human papillomavirus-host genomic integration events in cancer
dcterms:created 2021-02-11T21:58:56Z
dcterms:modified 2021-02-14T21:22:17Z
meta:author Brenner, Chad
meta:creation-date 2021-02-11T21:58:56Z
meta:save-date 2021-02-14T21:22:17Z
modified 2021-02-14T21:22:17Z
pdf:PDFVersion 1.6
pdf:charsPerPage ['2756', '1833', '2101', '558', '2288', '2027', '1758', '2115', '2279', '1965', '2251', '2283', '2408', '2357', '2974', '3686', '3256', '2101', '1500', '655', '352', '537', '441', '190', '385', '30']
pdf:docinfo:created 2021-02-11T21:58:56Z
pdf:docinfo:creator Brenner, Chad
pdf:docinfo:creator_tool Acrobat PDFMaker 21 for Word
pdf:docinfo:modified 2021-02-14T21:22:17Z
pdf:docinfo:producer Adobe Acrobat Pro DC (32-bit) 21.1.20135
pdf:docinfo:title SearcHPV: a novel approach to identify and assemble human papillomavirus-host genomic integration events in cancer
pdf:encrypted false
pdf:hasMarkedContent true
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
producer Adobe Acrobat Pro DC (32-bit) 21.1.20135
resourceName b'10_1101-2021_02_11_430847.pdf'
title SearcHPV: a novel approach to identify and assemble human papillomavirus-host genomic integration events in cancer
xmp:CreatorTool Acrobat PDFMaker 21 for Word
xmpMM:DocumentID uuid:480d24e0-a20f-4afa-a462-139f117bb089
xmpTPg:NPages 26
=== file2bib.sh ===
id: 10_1101-2021_02_10_430656
author: Zakeri, Mohsen
title: A like-for-like comparison of lightweight-mapping pipelines for single-cell RNA-seq data pre-processing
date: 2021
pages: 7
extension: .pdf
txt: ./txt/10_1101-2021_02_10_430656.txt
cache: ./cache/10_1101-2021_02_10_430656.pdf
Author
Content-Type application/pdf
Creation-Date 2021-02-10T20:57:39Z
Keywords
Last-Modified 2021-02-14T21:22:17Z
Last-Save-Date 2021-02-14T21:22:17Z
PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.21 (TeX Live 2020) kpathsea version 6.3.2
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 124
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
cp:subject
created 2021-02-10T20:57:39Z
creator
date 2021-02-14T21:22:17Z
dc:creator
dc:format application/pdf; version=1.5
dc:subject
dc:title A like-for-like comparison of lightweight-mapping pipelines for single-cell RNA-seq data pre-processing
dcterms:created 2021-02-10T20:57:39Z
dcterms:modified 2021-02-14T21:22:17Z
meta:author
meta:creation-date 2021-02-10T20:57:39Z
meta:keyword
meta:save-date 2021-02-14T21:22:17Z
modified 2021-02-14T21:22:17Z
pdf:PDFVersion 1.5
pdf:charsPerPage ['5995', '6561', '3463', '792', '6766', '6861', '5533']
pdf:docinfo:created 2021-02-10T20:57:39Z
pdf:docinfo:creator
pdf:docinfo:creator_tool LaTeX with hyperref
pdf:docinfo:custom:PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.21 (TeX Live 2020) kpathsea version 6.3.2
pdf:docinfo:keywords
pdf:docinfo:modified 2021-02-14T21:22:17Z
pdf:docinfo:producer pdfTeX-1.40.21
pdf:docinfo:subject
pdf:docinfo:title A like-for-like comparison of lightweight-mapping pipelines for single-cell RNA-seq data pre-processing
pdf:docinfo:trapped False
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['1', '0', '0', '0', '0', '0', '0']
producer pdfTeX-1.40.21
resourceName b'10_1101-2021_02_10_430656.pdf'
subject
title A like-for-like comparison of lightweight-mapping pipelines for single-cell RNA-seq data pre-processing
trapped False
xmp:CreatorTool LaTeX with hyperref
xmpMM:DocumentID uuid:85c7268f-1dd2-11b2-0a00-ee08271d5700
xmpTPg:NPages 7
=== file2bib.sh ===
id: 10_1101-2021_02_08_430070
author: Zhang, Yao-zhong
title: On the application of BERT models for nanopore methylation detection
date: 2021
pages: 7
extension: .pdf
txt: ./txt/10_1101-2021_02_08_430070.txt
cache: ./cache/10_1101-2021_02_08_430070.pdf
Content-Type application/pdf
Creation-Date 2021-02-09T06:48:34Z
Last-Modified 2021-02-14T21:22:17Z
Last-Save-Date 2021-02-14T21:22:17Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 220
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-09T06:48:34Z
date 2021-02-14T21:22:17Z
dc:format application/pdf; version=1.7
dc:title On the application of BERT models for nanopore methylation detection
dcterms:created 2021-02-09T06:48:34Z
dcterms:modified 2021-02-14T21:22:17Z
meta:creation-date 2021-02-09T06:48:34Z
meta:save-date 2021-02-14T21:22:17Z
modified 2021-02-14T21:22:17Z
pdf:PDFVersion 1.7
pdf:charsPerPage ['4064', '4333', '5898', '4026', '4707', '1134', '4710']
pdf:docinfo:created 2021-02-09T06:48:34Z
pdf:docinfo:creator_tool dvips(k) 2020.1 Copyright 2020 Radical Eye Software
pdf:docinfo:modified 2021-02-14T21:22:17Z
pdf:docinfo:producer GPL Ghostscript 9.50
pdf:docinfo:title On the application of BERT models for nanopore methylation detection
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '2', '0', '0', '0', '0']
producer GPL Ghostscript 9.50
resourceName b'10_1101-2021_02_08_430070.pdf'
title On the application of BERT models for nanopore methylation detection
xmp:CreatorTool dvips(k) 2020.1 Copyright 2020 Radical Eye Software
xmpMM:DocumentID uuid:60da6715-a2bf-11f6-0000-35e12fd4d910
xmpTPg:NPages 7
=== file2bib.sh ===
id: 10_1101-2021_02_12_430923
author: Modi, Vivek
title: Kincore: a web resource for structural classification of protein kinases and their inhibitors
date: 2021
pages: 18
extension: .pdf
txt: ./txt/10_1101-2021_02_12_430923.txt
cache: ./cache/10_1101-2021_02_12_430923.pdf
Author vivekmodi
Content-Type application/pdf
Creation-Date 2021-02-12T12:59:47Z
Last-Modified 2021-02-14T21:22:17Z
Last-Save-Date 2021-02-14T21:22:17Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 121
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-12T12:59:47Z
creator vivekmodi
date 2021-02-14T21:22:17Z
dc:creator vivekmodi
dc:format application/pdf; version=1.7
dc:language en-US
dc:title Kincore: a web resource for structural classification of protein kinases and their inhibitors
dcterms:created 2021-02-12T12:59:47Z
dcterms:modified 2021-02-14T21:22:17Z
language en-US
meta:author vivekmodi
meta:creation-date 2021-02-12T12:59:47Z
meta:save-date 2021-02-14T21:22:17Z
modified 2021-02-14T21:22:17Z
pdf:PDFVersion 1.7
pdf:charsPerPage ['548', '2461', '4120', '4318', '3898', '1805', '3138', '1650', '3611', '1882', '1633', '2942', '3687', '3445', '2654', '2853', '3053', '2600']
pdf:docinfo:created 2021-02-12T12:59:47Z
pdf:docinfo:creator vivekmodi
pdf:docinfo:creator_tool Microsoft Word
pdf:docinfo:modified 2021-02-14T21:22:17Z
pdf:docinfo:title Kincore: a web resource for structural classification of protein kinases and their inhibitors
pdf:encrypted false
pdf:hasMarkedContent true
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
resourceName b'10_1101-2021_02_12_430923.pdf'
title Kincore: a web resource for structural classification of protein kinases and their inhibitors
xmp:CreatorTool Microsoft Word
xmpMM:DocumentID uuid:86B06038-C2B3-4083-8EB1-C3E7E10688FB
xmpTPg:NPages 18
=== file2bib.sh ===
id: 10_1101-2021_02_12_430989
author: Sofer, Tamar
title: Benchmarking Association Analyses of Continuous Exposures with RNA-seq in Observational Studies
date: 2021
pages: 27
extension: .pdf
txt: ./txt/10_1101-2021_02_12_430989.txt
cache: ./cache/10_1101-2021_02_12_430989.pdf
Author Administrator
Content-Type application/pdf
Creation-Date 2021-02-12T20:11:32Z
Last-Modified 2021-02-14T21:22:17Z
Last-Save-Date 2021-02-14T21:22:17Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 102
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-12T20:11:32Z
creator Administrator
date 2021-02-14T21:22:17Z
dc:creator Administrator
dc:format application/pdf; version=1.4
dc:title Benchmarking Association Analyses of Continuous Exposures with RNA-seq in Observational Studies
dcterms:created 2021-02-12T20:11:32Z
dcterms:modified 2021-02-14T21:22:17Z
meta:author Administrator
meta:creation-date 2021-02-12T20:11:32Z
meta:save-date 2021-02-14T21:22:17Z
modified 2021-02-14T21:22:17Z
pdf:PDFVersion 1.4
pdf:charsPerPage ['1793', '1826', '2384', '2072', '2125', '2065', '2176', '2085', '2167', '2092', '2248', '2203', '2202', '1934', '2013', '2319', '2363', '2242', '2021', '1882', '2977', '3460', '1111', '868', '1358', '994', '946']
pdf:docinfo:created 2021-02-12T20:11:32Z
pdf:docinfo:creator Administrator
pdf:docinfo:creator_tool PScript5.dll Version 5.2.2
pdf:docinfo:modified 2021-02-14T21:22:17Z
pdf:docinfo:producer Acrobat Distiller 8.1.0 (Windows)
pdf:docinfo:title Benchmarking Association Analyses of Continuous Exposures with RNA-seq in Observational Studies
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '44', '71', '10', '47', '0', '2', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '1', '0', '0']
producer Acrobat Distiller 8.1.0 (Windows)
resourceName b'10_1101-2021_02_12_430989.pdf'
title Benchmarking Association Analyses of Continuous Exposures with RNA-seq in Observational Studies
xmp:CreatorTool PScript5.dll Version 5.2.2
xmpMM:DocumentID uuid:85c70ff8-1dd2-11b2-0a00-b709275d6100
xmpTPg:NPages 27
=== file2bib.sh ===
id: 10_1101-2021_02_12_430963
author: Gerber, Stefan
title: Streamlining differential exon and 3' UTR usage with diffUTR
date: 2021
pages: 17
extension: .pdf
txt: ./txt/10_1101-2021_02_12_430963.txt
cache: ./cache/10_1101-2021_02_12_430963.pdf
Author
Content-Type application/pdf
Creation-Date 2021-02-12T16:44:54Z
Keywords
Last-Modified 2021-02-14T21:22:16Z
Last-Save-Date 2021-02-14T21:22:16Z
PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.21 (TeX Live 2020) kpathsea version 6.3.2
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 313
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
cp:subject
created 2021-02-12T16:44:54Z
creator
date 2021-02-14T21:22:16Z
dc:creator
dc:format application/pdf; version=1.5
dc:subject
dc:title Streamlining differential exon and 3' UTR usage with diffUTR
dcterms:created 2021-02-12T16:44:54Z
dcterms:modified 2021-02-14T21:22:16Z
meta:author
meta:creation-date 2021-02-12T16:44:54Z
meta:keyword
meta:save-date 2021-02-14T21:22:16Z
modified 2021-02-14T21:22:16Z
pdf:PDFVersion 1.5
pdf:charsPerPage ['1413', '2472', '1908', '2213', '2583', '2365', '1177', '2644', '2325', '2335', '2542', '2188', '2388', '2261', '2673', '3135', '1179']
pdf:docinfo:created 2021-02-12T16:44:54Z
pdf:docinfo:creator
pdf:docinfo:creator_tool LaTeX with hyperref
pdf:docinfo:custom:PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.21 (TeX Live 2020) kpathsea version 6.3.2
pdf:docinfo:keywords
pdf:docinfo:modified 2021-02-14T21:22:16Z
pdf:docinfo:producer pdfTeX-1.40.21
pdf:docinfo:subject
pdf:docinfo:title Streamlining differential exon and 3' UTR usage with diffUTR
pdf:docinfo:trapped False
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '6', '0', '0', '5', '1', '0']
producer pdfTeX-1.40.21
resourceName b'10_1101-2021_02_12_430963.pdf'
subject
title Streamlining differential exon and 3' UTR usage with diffUTR
trapped False
xmp:CreatorTool LaTeX with hyperref
xmpMM:DocumentID uuid:85c690de-1dd2-11b2-0a00-740827bd7200
xmpTPg:NPages 17
=== file2bib.sh ===
id: 10_1101-2021_02_11_430871
author: Vadnais, David
title: ParticleChromo3D: A Particle Swarm Optimization Algorithm for Chromosome and Genome 3D Structure Prediction from Hi-C Data
date: 2021
pages: 24
extension: .pdf
txt: ./txt/10_1101-2021_02_11_430871.txt
cache: ./cache/10_1101-2021_02_11_430871.pdf
Author David Vadnais
Content-Type application/pdf
Creation-Date 2021-02-12T05:29:17Z
Last-Modified 2021-02-14T21:22:17Z
Last-Save-Date 2021-02-14T21:22:17Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 128
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-12T05:29:17Z
creator David Vadnais
date 2021-02-14T21:22:17Z
dc:creator David Vadnais
dc:format application/pdf; version=1.7
dc:language en-US
dc:title ParticleChromo3D: A Particle Swarm Optimization Algorithm for Chromosome and Genome 3D Structure Prediction from Hi-C Data
dcterms:created 2021-02-12T05:29:17Z
dcterms:modified 2021-02-14T21:22:17Z
language en-US
meta:author David Vadnais
meta:creation-date 2021-02-12T05:29:17Z
meta:save-date 2021-02-14T21:22:17Z
modified 2021-02-14T21:22:17Z
pdf:PDFVersion 1.7
pdf:charsPerPage ['4816', '5498', '3558', '1617', '3207', '2894', '1245', '2154', '1938', '1478', '2449', '2665', '1841', '1873', '1080', '2052', '1332', '1975', '2190', '3674', '4372', '4469', '1590', '1943']
pdf:docinfo:created 2021-02-12T05:29:17Z
pdf:docinfo:creator David Vadnais
pdf:docinfo:creator_tool Microsoft Word
pdf:docinfo:modified 2021-02-14T21:22:17Z
pdf:docinfo:title ParticleChromo3D: A Particle Swarm Optimization Algorithm for Chromosome and Genome 3D Structure Prediction from Hi-C Data
pdf:encrypted false
pdf:hasMarkedContent true
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
resourceName b'10_1101-2021_02_11_430871.pdf'
title ParticleChromo3D: A Particle Swarm Optimization Algorithm for Chromosome and Genome 3D Structure Prediction from Hi-C Data
xmp:CreatorTool Microsoft Word
xmpMM:DocumentID uuid:1B1B6485-34DE-46C5-9550-0CC4C4D733CD
xmpTPg:NPages 24
=== file2bib.sh ===
id: 10_1101-2021_02_11_430695
author: Gordon-Rodriguez, Elliott
title: Learning Sparse Log-Ratios for High-Throughput Sequencing Data
date: 2021
pages: 12
extension: .pdf
txt: ./txt/10_1101-2021_02_11_430695.txt
cache: ./cache/10_1101-2021_02_11_430695.pdf
Author Elliott Gordon-Rodriguez, Thomas P. Quinn, John P. Cunningham
Content-Type application/pdf
Creation-Date 2021-02-11T17:27:55Z
Keywords Machine Learning, ICML
Last-Modified 2021-02-11T17:27:55Z
Last-Save-Date 2021-02-11T17:27:55Z
PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.20 (TeX Live 2019) kpathsea version 6.3.1
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 115
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
cp:subject Proceedings of the International Conference on Machine Learning 2021
created 2021-02-11T17:27:55Z
creator Elliott Gordon-Rodriguez, Thomas P. Quinn, John P. Cunningham
date 2021-02-11T17:27:55Z
dc:creator Elliott Gordon-Rodriguez, Thomas P. Quinn, John P. Cunningham
dc:format application/pdf; version=1.5
dc:subject Machine Learning, ICML
dc:title Learning Sparse Log-Ratios for High-Throughput Sequencing Data
dcterms:created 2021-02-11T17:27:55Z
dcterms:modified 2021-02-11T17:27:55Z
meta:author Elliott Gordon-Rodriguez, Thomas P. Quinn, John P. Cunningham
meta:creation-date 2021-02-11T17:27:55Z
meta:keyword Machine Learning, ICML
meta:save-date 2021-02-11T17:27:55Z
modified 2021-02-11T17:27:55Z
pdf:PDFVersion 1.5
pdf:charsPerPage ['4061', '4908', '4284', '3291', '3759', '3982', '4289', '3758', '3949', '3927', '4057', '230']
pdf:docinfo:created 2021-02-11T17:27:55Z
pdf:docinfo:creator Elliott Gordon-Rodriguez, Thomas P. Quinn, John P. Cunningham
pdf:docinfo:creator_tool LaTeX with hyperref
pdf:docinfo:custom:PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.20 (TeX Live 2019) kpathsea version 6.3.1
pdf:docinfo:keywords Machine Learning, ICML
pdf:docinfo:modified 2021-02-11T17:27:55Z
pdf:docinfo:producer pdfTeX-1.40.20
pdf:docinfo:subject Proceedings of the International Conference on Machine Learning 2021
pdf:docinfo:title Learning Sparse Log-Ratios for High-Throughput Sequencing Data
pdf:docinfo:trapped False
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP false
pdf:unmappedUnicodeCharsPerPage ['0', '2', '8', '14', '6', '0', '0', '0', '0', '0', '0', '0']
producer pdfTeX-1.40.20
resourceName b'10_1101-2021_02_11_430695.pdf'
subject Proceedings of the International Conference on Machine Learning 2021
title Learning Sparse Log-Ratios for High-Throughput Sequencing Data
trapped False
xmp:CreatorTool LaTeX with hyperref
xmpTPg:NPages 12
=== file2bib.sh ===
id: 10_1101-2020_09_21_305516
author: Nikolic, Ana
title: Copy-scAT: Deconvoluting single-cell chromatin accessibility of genetic subclones in cancer
date: 2021
pages: 32
extension: .pdf
txt: ./txt/10_1101-2020_09_21_305516.txt
cache: ./cache/10_1101-2020_09_21_305516.pdf
Content-Type application/pdf
Creation-Date 2021-02-12T16:20:22Z
Last-Modified 2021-02-14T21:22:18Z
Last-Save-Date 2021-02-14T21:22:18Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 126
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-12T16:20:22Z
date 2021-02-14T21:22:18Z
dc:format application/pdf; version=1.4
dc:title Copy-scAT: Deconvoluting single-cell chromatin accessibility of genetic subclones in cancer
dcterms:created 2021-02-12T16:20:22Z
dcterms:modified 2021-02-14T21:22:18Z
meta:creation-date 2021-02-12T16:20:22Z
meta:save-date 2021-02-14T21:22:18Z
modified 2021-02-14T21:22:18Z
pdf:PDFVersion 1.4
pdf:charsPerPage ['3381', '4467', '1165', '5419', '866', '4521', '1520', '4215', '669', '1345', '4158', '4270', '3473', '3942', '4230', '3824', '810', '1165', '884', '856', '689', '1095', '704', '725', '776', '807', '846', '1061', '990', '704', '703', '627']
pdf:docinfo:created 2021-02-12T16:20:22Z
pdf:docinfo:creator_tool Word
pdf:docinfo:modified 2021-02-14T21:22:18Z
pdf:docinfo:producer macOS Version 11.2.1 (Build 20D74) Quartz PDFContext
pdf:docinfo:title Copy-scAT: Deconvoluting single-cell chromatin accessibility of genetic subclones in cancer
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
producer macOS Version 11.2.1 (Build 20D74) Quartz PDFContext
resourceName b'10_1101-2020_09_21_305516.pdf'
title Copy-scAT: Deconvoluting single-cell chromatin accessibility of genetic subclones in cancer
xmp:CreatorTool Word
xmpMM:DocumentID uuid:85c8661d-1dd2-11b2-0a00-f209277d8900
xmpTPg:NPages 32
=== file2bib.sh ===
id: 10_1101-2021_02_12_430830
author: Gergely, Tibély
title: Simultaneous estimation of per cell division mutation rate and turnover rate from bulk tumor sequence data
date: 2021
pages: 19
extension: .pdf
txt: ./txt/10_1101-2021_02_12_430830.txt
cache: ./cache/10_1101-2021_02_12_430830.pdf
Author
Content-Type application/pdf
Creation-Date 2021-02-12T12:51:07Z
Keywords
Last-Modified 2021-02-14T21:22:16Z
Last-Save-Date 2021-02-14T21:22:16Z
PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.16 (TeX Live 2015) kpathsea version 6.2.1
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 300
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
cp:subject
created 2021-02-12T12:51:07Z
creator
date 2021-02-14T21:22:16Z
dc:creator
dc:format application/pdf; version=1.5
dc:subject
dc:title Simultaneous estimation of per cell division mutation rate and turnover rate from bulk tumor sequence data
dcterms:created 2021-02-12T12:51:07Z
dcterms:modified 2021-02-14T21:22:16Z
meta:author
meta:creation-date 2021-02-12T12:51:07Z
meta:keyword
meta:save-date 2021-02-14T21:22:16Z
modified 2021-02-14T21:22:16Z
pdf:PDFVersion 1.5
pdf:charsPerPage ['2344', '2892', '3313', '1197', '2366', '1948', '2587', '2787', '1337', '1536', '3109', '1199', '2709', '1289', '3331', '3112', '2139', '2457', '945']
pdf:docinfo:created 2021-02-12T12:51:07Z
pdf:docinfo:creator
pdf:docinfo:creator_tool LaTeX with hyperref package
pdf:docinfo:custom:PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.16 (TeX Live 2015) kpathsea version 6.2.1
pdf:docinfo:keywords
pdf:docinfo:modified 2021-02-14T21:22:16Z
pdf:docinfo:producer pdfTeX-1.40.16
pdf:docinfo:subject
pdf:docinfo:title Simultaneous estimation of per cell division mutation rate and turnover rate from bulk tumor sequence data
pdf:docinfo:trapped False
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '1', '0', '8', '25', '6', '3', '0', '0', '0', '0', '0', '0', '1', '0', '0', '0', '0']
producer pdfTeX-1.40.16
resourceName b'10_1101-2021_02_12_430830.pdf'
subject
title Simultaneous estimation of per cell division mutation rate and turnover rate from bulk tumor sequence data
trapped False
xmp:CreatorTool LaTeX with hyperref package
xmpMM:DocumentID uuid:85c6b3e8-1dd2-11b2-0a00-130a277d8900
xmpTPg:NPages 19
=== file2bib.sh ===
id: 10_1101-2021_02_11_430789
author: Tyagin, Ilya
title: Accelerating COVID-19 research with graph mining and transformer-based learning
date: 2021
pages: 9
extension: .pdf
txt: ./txt/10_1101-2021_02_11_430789.txt
cache: ./cache/10_1101-2021_02_11_430789.pdf
Author Ilya Tyagin, Ankit Kulshrestha, Justin Sybrandt, Krish Matta, Michael Shtutman, and Ilya Safro
Content-Type application/pdf
Creation-Date 2021-02-10T14:30:51Z
Keywords Hypothesis Generation, Literature-Based Discovery, Transformer Models, Semantic Networks, Biomedical Recommendation,
Last-Modified 2021-02-14T21:22:26Z
Last-Save-Date 2021-02-14T21:22:26Z
PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.21 (TeX Live 2020) kpathsea version 6.3.2
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 130
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
cp:subject - Applied computing -> Bioinformatics.Document management and text processing.- Computing methodologies -> Learning latent representations.Neural networks.Information extraction.Semantic networks.
created 2021-02-10T14:30:51Z
creator Ilya Tyagin, Ankit Kulshrestha, Justin Sybrandt, Krish Matta, Michael Shtutman, and Ilya Safro
date 2021-02-14T21:22:26Z
dc:creator Ilya Tyagin, Ankit Kulshrestha, Justin Sybrandt, Krish Matta, Michael Shtutman, and Ilya Safro
dc:description - Applied computing -> Bioinformatics.Document management and text processing.- Computing methodologies -> Learning latent representations.Neural networks.Information extraction.Semantic networks.
dc:format application/pdf; version=1.5
dc:language en
dc:subject Hypothesis Generation, Literature-Based Discovery, Transformer Models, Semantic Networks, Biomedical Recommendation,
dc:title Accelerating COVID-19 research with graph mining and transformer-based learning
dcterms:created 2021-02-10T14:30:51Z
dcterms:modified 2021-02-14T21:22:26Z
description - Applied computing -> Bioinformatics.Document management and text processing.- Computing methodologies -> Learning latent representations.Neural networks.Information extraction.Semantic networks.
language en
meta:author Ilya Tyagin, Ankit Kulshrestha, Justin Sybrandt, Krish Matta, Michael Shtutman, and Ilya Safro
meta:creation-date 2021-02-10T14:30:51Z
meta:keyword Hypothesis Generation, Literature-Based Discovery, Transformer Models, Semantic Networks, Biomedical Recommendation,
meta:save-date 2021-02-14T21:22:26Z
modified 2021-02-14T21:22:26Z
pdf:PDFVersion 1.5
pdf:charsPerPage ['4414', '5587', '5796', '4953', '6020', '5204', '4953', '6112', '9146']
pdf:docinfo:created 2021-02-10T14:30:51Z
pdf:docinfo:creator Ilya Tyagin, Ankit Kulshrestha, Justin Sybrandt, Krish Matta, Michael Shtutman, and Ilya Safro
pdf:docinfo:creator_tool LaTeX with acmart 2020/04/30 v1.71 Typesetting articles for the Association for Computing Machinery and hyperref 2020-05-15 v7.00e Hypertext links for LaTeX
pdf:docinfo:custom:PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.21 (TeX Live 2020) kpathsea version 6.3.2
pdf:docinfo:keywords Hypothesis Generation, Literature-Based Discovery, Transformer Models, Semantic Networks, Biomedical Recommendation,
pdf:docinfo:modified 2021-02-14T21:22:26Z
pdf:docinfo:producer pdfTeX-1.40.21
pdf:docinfo:subject - Applied computing -> Bioinformatics.Document management and text processing.- Computing methodologies -> Learning latent representations.Neural networks.Information extraction.Semantic networks.
pdf:docinfo:title Accelerating COVID-19 research with graph mining and transformer-based learning
pdf:docinfo:trapped False
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '5', '0', '0', '0', '0', '0']
producer pdfTeX-1.40.21
resourceName b'10_1101-2021_02_11_430789.pdf'
subject - Applied computing -> Bioinformatics.Document management and text processing.- Computing methodologies -> Learning latent representations.Neural networks.Information extraction.Semantic networks.
title Accelerating COVID-19 research with graph mining and transformer-based learning
trapped False
xmp:CreatorTool LaTeX with acmart 2020/04/30 v1.71 Typesetting articles for the Association for Computing Machinery and hyperref 2020-05-15 v7.00e Hypertext links for LaTeX
xmpMM:DocumentID uuid:85d60a5f-1dd2-11b2-0a00-e00927bd7700
xmpTPg:NPages 9
=== file2bib.sh ===
id: 10_1101-2021_02_12_430764
author: Ascensión, Alex M.
title: Triku: a feature selection method based on nearest neighbors for single-cell data
date: 2021
pages: 18
extension: .pdf
txt: ./txt/10_1101-2021_02_12_430764.txt
cache: ./cache/10_1101-2021_02_12_430764.pdf
Author Alex M. Ascensión, Olga Ibañez-Solé, Inaki Inza, Ander Izeta, Marcos J. Araúzo-Bravo
Content-Type application/pdf
Creation-Date 2021-02-12T10:37:24Z
Keywords scRNAseq, feature selection, bioinformatics, python
Last-Modified 2021-02-14T20:14:07Z
Last-Save-Date 2021-02-14T20:14:07Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 327
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-12T10:37:24Z
creator Alex M. Ascensión, Olga Ibañez-Solé, Inaki Inza, Ander Izeta, Marcos J. Araúzo-Bravo
date 2021-02-14T20:14:07Z
dc:creator Alex M. Ascensión, Olga Ibañez-Solé, Inaki Inza, Ander Izeta, Marcos J. Araúzo-Bravo
dc:format application/pdf; version=1.5
dc:subject scRNAseq, feature selection, bioinformatics, python
dc:title Triku: a feature selection method based on nearest neighbors for single-cell data
dcterms:created 2021-02-12T10:37:24Z
dcterms:modified 2021-02-14T20:14:07Z
meta:author Alex M. Ascensión, Olga Ibañez-Solé, Inaki Inza, Ander Izeta, Marcos J. Araúzo-Bravo
meta:creation-date 2021-02-12T10:37:24Z
meta:keyword scRNAseq, feature selection, bioinformatics, python
meta:save-date 2021-02-14T20:14:07Z
modified 2021-02-14T20:14:07Z
pdf:PDFVersion 1.5
pdf:charsPerPage ['2989', '3432', '3121', '3143', '3126', '3107', '3377', '3213', '3024', '2866', '2104', '2654', '5322', '3235', '2377', '1210', '1017', '851']
pdf:docinfo:created 2021-02-12T10:37:24Z
pdf:docinfo:creator Alex M. Ascensión, Olga Ibañez-Solé, Inaki Inza, Ander Izeta, Marcos J. Araúzo-Bravo
pdf:docinfo:creator_tool LaTeX with hyperref
pdf:docinfo:keywords scRNAseq, feature selection, bioinformatics, python
pdf:docinfo:modified 2021-02-14T20:14:07Z
pdf:docinfo:producer xdvipdfmx (20190225)
pdf:docinfo:title Triku: a feature selection method based on nearest neighbors for single-cell data
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '396', '0', '0', '0']
producer xdvipdfmx (20190225)
resourceName b'10_1101-2021_02_12_430764.pdf'
subject scRNAseq, feature selection, bioinformatics, python
title Triku: a feature selection method based on nearest neighbors for single-cell data
xmp:CreatorTool LaTeX with hyperref
xmpMM:DocumentID uuid:6d664b1d-1dd2-11b2-0a00-8208278d5b00
xmpTPg:NPages 18
=== file2bib.sh ===
id: 10_1101-2020_02_04_934216
author: Kirchoff, Kathryn E.
title: EMBER: Multi-label prediction of kinase-substrate phosphorylation events through deep learning
date: 2021
pages: 13
extension: .pdf
txt: ./txt/10_1101-2020_02_04_934216.txt
cache: ./cache/10_1101-2020_02_04_934216.pdf
Content-Type application/pdf
Creation-Date 2021-02-10T16:35:43Z
Last-Modified 2021-02-14T21:22:17Z
Last-Save-Date 2021-02-14T21:22:17Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 276
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-10T16:35:43Z
date 2021-02-14T21:22:17Z
dc:format application/pdf; version=1.4
dc:title EMBER: Multi-label prediction of kinase-substrate phosphorylation events through deep learning
dcterms:created 2021-02-10T16:35:43Z
dcterms:modified 2021-02-14T21:22:17Z
meta:creation-date 2021-02-10T16:35:43Z
meta:save-date 2021-02-14T21:22:17Z
modified 2021-02-14T21:22:17Z
pdf:PDFVersion 1.4
pdf:charsPerPage ['5129', '5413', '4261', '3539', '4285', '3469', '4716', '3179', '7747', '530', '1564', '978', '677']
pdf:docinfo:created 2021-02-10T16:35:43Z
pdf:docinfo:creator_tool LaTeX with hyperref
pdf:docinfo:modified 2021-02-14T21:22:17Z
pdf:docinfo:producer macOS Version 10.15.7 (Build 19H2) Quartz PDFContext
pdf:docinfo:title EMBER: Multi-label prediction of kinase-substrate phosphorylation events through deep learning
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '18', '29', '4']
producer macOS Version 10.15.7 (Build 19H2) Quartz PDFContext
resourceName b'10_1101-2020_02_04_934216.pdf'
title EMBER: Multi-label prediction of kinase-substrate phosphorylation events through deep learning
xmp:CreatorTool LaTeX with hyperref
xmpMM:DocumentID uuid:85c76a22-1dd2-11b2-0a00-000927fd5800
xmpTPg:NPages 13
=== file2bib.sh ===
id: 10_1101-2021_02_08_428881
author: Lu, Yang Young
title: ACE: Explaining cluster from an adversarial perspective
date: 2021
pages: 12
extension: .pdf
txt: ./txt/10_1101-2021_02_08_428881.txt
cache: ./cache/10_1101-2021_02_08_428881.pdf
Author Yang Young Lu, Timothy C. Yu, Giancarlo Bonora, William Stafford Noble
Content-Type application/pdf
Creation-Date 2021-02-09T13:00:55Z
Keywords Machine Learning, ICML
Last-Modified 2021-02-14T21:22:17Z
Last-Save-Date 2021-02-14T21:22:17Z
PTEX.Fullbanner This is MiKTeX-pdfTeX 2.9.4307 (1.40.12)
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 1420
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
cp:subject Proceedings of the International Conference on Machine Learning 2021
created 2021-02-09T13:00:55Z
creator Yang Young Lu, Timothy C. Yu, Giancarlo Bonora, William Stafford Noble
date 2021-02-14T21:22:17Z
dc:creator Yang Young Lu, Timothy C. Yu, Giancarlo Bonora, William Stafford Noble
dc:description Proceedings of the International Conference on Machine Learning 2021
dc:format application/pdf; version=1.5
dc:subject Machine Learning, ICML
dc:title ACE: Explaining cluster from an adversarial perspective
dcterms:created 2021-02-09T13:00:55Z
dcterms:modified 2021-02-14T21:22:17Z
description Proceedings of the International Conference on Machine Learning 2021
meta:author Yang Young Lu, Timothy C. Yu, Giancarlo Bonora, William Stafford Noble
meta:creation-date 2021-02-09T13:00:55Z
meta:keyword Machine Learning, ICML
meta:save-date 2021-02-14T21:22:17Z
modified 2021-02-14T21:22:17Z
pdf:PDFVersion 1.5
pdf:charsPerPage ['4324', '4945', '3406', '4075', '4894', '3533', '4631', '3844', '4142', '3413', '561', '665']
pdf:docinfo:created 2021-02-09T13:00:55Z
pdf:docinfo:creator Yang Young Lu, Timothy C. Yu, Giancarlo Bonora, William Stafford Noble
pdf:docinfo:creator_tool LaTeX with hyperref package
pdf:docinfo:custom:PTEX.Fullbanner This is MiKTeX-pdfTeX 2.9.4307 (1.40.12)
pdf:docinfo:keywords Machine Learning, ICML
pdf:docinfo:modified 2021-02-14T21:22:17Z
pdf:docinfo:producer pdfTeX-1.40.12
pdf:docinfo:subject Proceedings of the International Conference on Machine Learning 2021
pdf:docinfo:title ACE: Explaining cluster from an adversarial perspective
pdf:docinfo:trapped False
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '10', '27', '0', '0', '0', '0', '0', '0', '0', '0']
producer pdfTeX-1.40.12
resourceName b'10_1101-2021_02_08_428881.pdf'
subject Proceedings of the International Conference on Machine Learning 2021
title ACE: Explaining cluster from an adversarial perspective
trapped False
xmp:CreatorTool LaTeX with hyperref package
xmpMM:DocumentID uuid:85c6f0fe-1dd2-11b2-0a00-1a0927edca00
xmpTPg:NPages 12
=== file2bib.sh ===
id: 10_1101-2021_02_10_430649
author: Wen, Zi-Hang
title: Bfimpute: A Bayesian factorization method to recover single-cell RNA sequencing data
date: 2021
pages: 11
extension: .pdf
txt: ./txt/10_1101-2021_02_10_430649.txt
cache: ./cache/10_1101-2021_02_10_430649.pdf
Author
Content-Type application/pdf
Creation-Date 2021-02-12T16:42:36Z
Keywords
Last-Modified 2021-02-14T21:22:16Z
Last-Save-Date 2021-02-14T21:22:16Z
PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.21 (TeX Live 2020) kpathsea version 6.3.2
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 1286
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
cp:subject
created 2021-02-12T16:42:36Z
creator
date 2021-02-14T21:22:16Z
dc:creator
dc:format application/pdf; version=1.5
dc:subject
dc:title Bfimpute: A Bayesian factorization method to recover single-cell RNA sequencing data
dcterms:created 2021-02-12T16:42:36Z
dcterms:modified 2021-02-14T21:22:16Z
meta:author
meta:creation-date 2021-02-12T16:42:36Z
meta:keyword
meta:save-date 2021-02-14T21:22:16Z
modified 2021-02-14T21:22:16Z
pdf:PDFVersion 1.5
pdf:charsPerPage ['4396', '3587', '3999', '3258', '3868', '3519', '6427', '2602', '3216', '5326', '3921']
pdf:docinfo:created 2021-02-12T16:42:36Z
pdf:docinfo:creator
pdf:docinfo:creator_tool LaTeX with hyperref
pdf:docinfo:custom:PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.21 (TeX Live 2020) kpathsea version 6.3.2
pdf:docinfo:keywords
pdf:docinfo:modified 2021-02-14T21:22:16Z
pdf:docinfo:producer pdfTeX-1.40.21
pdf:docinfo:subject
pdf:docinfo:title Bfimpute: A Bayesian factorization method to recover single-cell RNA sequencing data
pdf:docinfo:trapped False
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '57', '14', '0', '0', '0', '0', '0', '0', '0']
producer pdfTeX-1.40.21
resourceName b'10_1101-2021_02_10_430649.pdf'
subject
title Bfimpute: A Bayesian factorization method to recover single-cell RNA sequencing data
trapped False
xmp:CreatorTool LaTeX with hyperref
xmpMM:DocumentID uuid:85c66f59-1dd2-11b2-0a00-f508278d5b00
xmpTPg:NPages 11
=== file2bib.sh ===
id: 10_1101-2021_02_12_430979
author: Da Silva, Kévin
title: StrainFLAIR: Strain-level profiling of metagenomic samples using variation graphs
date: 2021
pages: 20
extension: .pdf
txt: ./txt/10_1101-2021_02_12_430979.txt
cache: ./cache/10_1101-2021_02_12_430979.pdf
Content-Type application/pdf
Creation-Date 2021-02-12T17:18:42Z
Last-Modified 2021-02-14T19:23:11Z
Last-Save-Date 2021-02-14T19:23:11Z
PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.21 (TeX Live 2020) kpathsea version 6.3.2
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 94
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-12T17:18:42Z
date 2021-02-14T19:23:11Z
dc:format application/pdf; version=1.5
dc:title StrainFLAIR: Strain-level profiling of metagenomic samples using variation graphs
dcterms:created 2021-02-12T17:18:42Z
dcterms:modified 2021-02-14T19:23:11Z
meta:creation-date 2021-02-12T17:18:42Z
meta:save-date 2021-02-14T19:23:11Z
modified 2021-02-14T19:23:11Z
pdf:PDFVersion 1.5
pdf:charsPerPage ['3449', '4370', '2071', '4378', '2438', '4050', '3798', '3720', '2144', '2109', '4338', '4305', '4821', '3388', '3022', '1456', '1895', '1533', '1522', '541']
pdf:docinfo:created 2021-02-12T17:18:42Z
pdf:docinfo:creator_tool TeX
pdf:docinfo:custom:PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.21 (TeX Live 2020) kpathsea version 6.3.2
pdf:docinfo:modified 2021-02-14T19:23:11Z
pdf:docinfo:producer pdfTeX-1.40.21
pdf:docinfo:title StrainFLAIR: Strain-level profiling of metagenomic samples using variation graphs
pdf:docinfo:trapped False
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
producer pdfTeX-1.40.21
resourceName b'10_1101-2021_02_12_430979.pdf'
title StrainFLAIR: Strain-level profiling of metagenomic samples using variation graphs
trapped False
xmp:CreatorTool TeX
xmpMM:DocumentID uuid:5b2f399e-1dd2-11b2-0a00-d30827bd3700
xmpTPg:NPages 20
=== file2bib.sh ===
id: 10_1101-2021_02_13_429885
author: Househam, Jacob
title: A fully automated approach for quality control of cancer mutations in the era of high-resolution whole genome sequencing
date: 2021
pages: 36
extension: .pdf
txt: ./txt/10_1101-2021_02_13_429885.txt
cache: ./cache/10_1101-2021_02_13_429885.pdf
Content-Type application/pdf
Creation-Date 2021-02-13T13:37:27Z
Last-Modified 2021-02-14T21:22:17Z
Last-Save-Date 2021-02-14T21:22:17Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 216
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-13T13:37:27Z
date 2021-02-14T21:22:17Z
dc:format application/pdf; version=1.5
dc:title A fully automated approach for quality control of cancer mutations in the era of high-resolution whole genome sequencing
dcterms:created 2021-02-13T13:37:27Z
dcterms:modified 2021-02-14T21:22:17Z
meta:creation-date 2021-02-13T13:37:27Z
meta:save-date 2021-02-14T21:22:17Z
modified 2021-02-14T21:22:17Z
pdf:PDFVersion 1.5
pdf:charsPerPage ['2646', '3593', '3421', '2574', '2758', '3251', '2949', '3250', '4228', '4125', '2811', '2417', '2788', '2811', '2908', '729', '1969', '1259', '1715', '1413', '932', '646', '1253', '862', '744', '744', '745', '710', '711', '711', '711', '711', '712', '1331', '1098', '484']
pdf:docinfo:created 2021-02-13T13:37:27Z
pdf:docinfo:modified 2021-02-14T21:22:17Z
pdf:docinfo:producer Skia/PDF m90
pdf:docinfo:title A fully automated approach for quality control of cancer mutations in the era of high-resolution whole genome sequencing
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
producer Skia/PDF m90
resourceName b'10_1101-2021_02_13_429885.pdf'
title A fully automated approach for quality control of cancer mutations in the era of high-resolution whole genome sequencing
xmpMM:DocumentID uuid:a5aab842-f0f5-5f42-b83c-1d098c720a7a
xmpTPg:NPages 36
=== file2bib.sh ===
id: 10_1101-2021_02_10_430623
author: Aberasturi, Dillon
title: “Single-subject studies”-derived analyses unveil altered biomechanisms between very small cohorts: implications for rare diseases
date: 2021
pages: 9
extension: .pdf
txt: ./txt/10_1101-2021_02_10_430623.txt
cache: ./cache/10_1101-2021_02_10_430623.pdf
Author Nima Pouladi
Content-Type application/pdf
Creation-Date 2021-02-10T16:03:33Z
Last-Modified 2021-02-14T21:22:17Z
Last-Save-Date 2021-02-14T21:22:17Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 388
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-10T16:03:33Z
creator Nima Pouladi
date 2021-02-14T21:22:17Z
dc:creator Nima Pouladi
dc:format application/pdf; version=1.4
dc:title “Single-subject studies”-derived analyses unveil altered biomechanisms between very small cohorts: implications for rare diseases
dcterms:created 2021-02-10T16:03:33Z
dcterms:modified 2021-02-14T21:22:17Z
meta:author Nima Pouladi
meta:creation-date 2021-02-10T16:03:33Z
meta:save-date 2021-02-14T21:22:17Z
modified 2021-02-14T21:22:17Z
pdf:PDFVersion 1.4
pdf:charsPerPage ['4080', '6240', '7703', '4913', '7277', '7679', '7670', '7920', '8386']
pdf:docinfo:created 2021-02-10T16:03:33Z
pdf:docinfo:creator Nima Pouladi
pdf:docinfo:creator_tool Word
pdf:docinfo:modified 2021-02-14T21:22:17Z
pdf:docinfo:producer macOS Version 10.15.7 (Build 19H2) Quartz PDFContext
pdf:docinfo:title “Single-subject studies”-derived analyses unveil altered biomechanisms between very small cohorts: implications for rare diseases
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '43', '145', '4', '0', '2', '0', '0']
producer macOS Version 10.15.7 (Build 19H2) Quartz PDFContext
resourceName b'10_1101-2021_02_10_430623.pdf'
title “Single-subject studies”-derived analyses unveil altered biomechanisms between very small cohorts: implications for rare diseases
xmp:CreatorTool Word
xmpMM:DocumentID uuid:85c83ffc-1dd2-11b2-0a00-1509278d5b00
xmpTPg:NPages 9
=== file2bib.sh ===
id: 10_1101-2020_09_02_279521
author: Abi Nader, Clément
title: Simulating the outcome of amyloid treatments in Alzheimer’s disease from imaging and clinical data
date: 2021
pages: 32
extension: .pdf
txt: ./txt/10_1101-2020_09_02_279521.txt
cache: ./cache/10_1101-2020_09_02_279521.pdf
Author Luigi
Content-Type application/pdf
Creation-Date 2021-02-10T15:18:40Z
Last-Modified 2021-02-14T21:22:17Z
Last-Save-Date 2021-02-14T21:22:17Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 151
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-10T15:18:40Z
creator Luigi
date 2021-02-14T21:22:17Z
dc:creator Luigi
dc:format application/pdf; version=1.7
dc:language en-US
dc:title Simulating the outcome of amyloid treatments in Alzheimer’s disease from imaging and clinical data
dcterms:created 2021-02-10T15:18:40Z
dcterms:modified 2021-02-14T21:22:17Z
language en-US
meta:author Luigi
meta:creation-date 2021-02-10T15:18:40Z
meta:save-date 2021-02-14T21:22:17Z
modified 2021-02-14T21:22:17Z
pdf:PDFVersion 1.7
pdf:charsPerPage ['2434', '2713', '3212', '3195', '2791', '3085', '3958', '1263', '1767', '2315', '1805', '2788', '2584', '1738', '1346', '2581', '2596', '658', '3084', '3005', '3258', '3194', '2934', '2319', '2637', '2729', '2500', '2660', '2549', '2716', '2848', '509']
pdf:docinfo:created 2021-02-10T15:18:40Z
pdf:docinfo:creator Luigi
pdf:docinfo:creator_tool Microsoft® Word for Microsoft 365
pdf:docinfo:modified 2021-02-14T21:22:17Z
pdf:docinfo:producer Microsoft® Word for Microsoft 365
pdf:docinfo:title Simulating the outcome of amyloid treatments in Alzheimer’s disease from imaging and clinical data
pdf:encrypted false
pdf:hasMarkedContent true
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
producer Microsoft® Word for Microsoft 365
resourceName b'10_1101-2020_09_02_279521.pdf'
title Simulating the outcome of amyloid treatments in Alzheimer’s disease from imaging and clinical data
xmp:CreatorTool Microsoft® Word for Microsoft 365
xmpMM:DocumentID uuid:06032D44-3EB9-44B9-86B0-2BD226EEB074
xmpTPg:NPages 32
=== file2bib.sh ===
id: 10_1101-2021_02_10_430512
author: Kim, Catherine
title: Prediction of adverse drug reactions associated with drug-drug interactions using hierarchical classification
date: 2021
pages: 41
extension: .pdf
txt: ./txt/10_1101-2021_02_10_430512.txt
cache: ./cache/10_1101-2021_02_10_430512.pdf
Author Administrator
Content-Type application/pdf
Creation-Date 2021-02-10T16:35:24Z
Last-Modified 2021-02-14T21:22:17Z
Last-Save-Date 2021-02-14T21:22:17Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 138
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-10T16:35:24Z
creator Administrator
date 2021-02-14T21:22:17Z
dc:creator Administrator
dc:format application/pdf; version=1.4
dc:title Prediction of adverse drug reactions associated with drug-drug interactions using hierarchical classification
dcterms:created 2021-02-10T16:35:24Z
dcterms:modified 2021-02-14T21:22:17Z
meta:author Administrator
meta:creation-date 2021-02-10T16:35:24Z
meta:save-date 2021-02-14T21:22:17Z
modified 2021-02-14T21:22:17Z
pdf:PDFVersion 1.4
pdf:charsPerPage ['799', '1424', '3057', '1322', '2396', '2821', '838', '2839', '2649', '2927', '3046', '2894', '2854', '3091', '2975', '2901', '1457', '2391', '2551', '2648', '2590', '2505', '2444', '2515', '2623', '2360', '2741', '519', '572', '2642', '2718', '1974', '358', '358', '359', '361', '359', '358', '358', '358', '520']
pdf:docinfo:created 2021-02-10T16:35:24Z
pdf:docinfo:creator Administrator
pdf:docinfo:creator_tool PScript5.dll Version 5.2.2
pdf:docinfo:modified 2021-02-14T21:22:17Z
pdf:docinfo:producer Acrobat Distiller 8.1.0 (Windows)
pdf:docinfo:title Prediction of adverse drug reactions associated with drug-drug interactions using hierarchical classification
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '16', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
producer Acrobat Distiller 8.1.0 (Windows)
resourceName b'10_1101-2021_02_10_430512.pdf'
title Prediction of adverse drug reactions associated with drug-drug interactions using hierarchical classification
xmp:CreatorTool PScript5.dll Version 5.2.2
xmpMM:DocumentID uuid:85c74254-1dd2-11b2-0a00-a108275dc400
xmpTPg:NPages 41
=== file2bib.sh ===
id: 10_1101-2021_02_08_430343
author: Gibbs, David L
title: Patient-specific cell communication networks associate with disease progression in cancer
date: 2021
pages: 29
extension: .pdf
txt: ./txt/10_1101-2021_02_08_430343.txt
cache: ./cache/10_1101-2021_02_08_430343.pdf
Appligent AppendPDF Pro 5.5 Linux Kernel 2.6 64bit Oct 2 2014 Library 10.1.0
Author Dave
Content-Type application/pdf
Creation-Date 2021-02-09T04:01:31Z
Last-Modified 2021-02-14T21:22:17Z
Last-Save-Date 2021-02-14T21:22:17Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 334
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-09T04:01:31Z
creator Dave
date 2021-02-14T21:22:17Z
dc:creator Dave
dc:format application/pdf; version=1.7
dc:language en-US
dc:title 96291204
dcterms:created 2021-02-09T04:01:31Z
dcterms:modified 2021-02-14T21:22:17Z
language en-US
meta:author Dave
meta:creation-date 2021-02-09T04:01:31Z
meta:save-date 2021-02-14T21:22:17Z
modified 2021-02-14T21:22:17Z
pdf:PDFVersion 1.7
pdf:charsPerPage ['2561', '4352', '3379', '3527', '3566', '3828', '4402', '4535', '4228', '4333', '4207', '3279', '1677', '2262', '2297', '2203', '3241', '3317', '2921', '2659', '338', '338', '338', '338', '338', '338', '338', '338', '338']
pdf:docinfo:created 2021-02-09T04:01:31Z
pdf:docinfo:creator Dave
pdf:docinfo:creator_tool Appligent AppendPDF Pro 5.5
pdf:docinfo:custom:Appligent AppendPDF Pro 5.5 Linux Kernel 2.6 64bit Oct 2 2014 Library 10.1.0
pdf:docinfo:modified 2021-02-14T21:22:17Z
pdf:docinfo:producer Microsoft® Word for Microsoft 365
pdf:docinfo:title 96291204
pdf:encrypted false
pdf:hasMarkedContent true
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
producer Microsoft® Word for Microsoft 365
resourceName b'10_1101-2021_02_08_430343.pdf'
title 96291204
xmp:CreatorTool Appligent AppendPDF Pro 5.5
xmpMM:DocumentID uuid:02a690eb-b082-11b2-0a00-782dad000000
xmpTPg:NPages 29
=== file2bib.sh ===
id: 10_1101-2021_02_09_430550
author: Song, Dongyuan
title: scPNMF: sparse gene encoding of single cells to facilitate gene selection for targeted gene profiling
date: 2021
pages: 37
extension: .pdf
txt: ./txt/10_1101-2021_02_09_430550.txt
cache: ./cache/10_1101-2021_02_09_430550.pdf
Author
Content-Type application/pdf
Creation-Date 2021-02-10T07:08:44Z
Keywords
Last-Modified 2021-02-14T21:22:17Z
Last-Save-Date 2021-02-14T21:22:17Z
PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.21 (TeX Live 2020) kpathsea version 6.3.2
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 153
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
cp:subject
created 2021-02-10T07:08:44Z
creator
date 2021-02-14T21:22:17Z
dc:creator
dc:format application/pdf; version=1.5
dc:subject
dc:title scPNMF: sparse gene encoding of single cells to facilitate gene selection for targeted gene profiling
dcterms:created 2021-02-10T07:08:44Z
dcterms:modified 2021-02-14T21:22:17Z
meta:author
meta:creation-date 2021-02-10T07:08:44Z
meta:keyword
meta:save-date 2021-02-14T21:22:17Z
modified 2021-02-14T21:22:17Z
pdf:PDFVersion 1.5
pdf:charsPerPage ['2602', '3331', '3092', '1969', '2476', '2626', '2136', '2674', '2221', '2436', '1603', '2850', '2182', '2921', '3297', '1944', '2318', '2544', '2453', '2588', '860', '2144', '2326', '2412', '896', '970', '1053', '767', '438', '525', '435', '529', '2318', '2544', '2453', '2588', '860']
pdf:docinfo:created 2021-02-10T07:08:44Z
pdf:docinfo:creator
pdf:docinfo:creator_tool LaTeX with hyperref
pdf:docinfo:custom:PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.21 (TeX Live 2020) kpathsea version 6.3.2
pdf:docinfo:keywords
pdf:docinfo:modified 2021-02-14T21:22:17Z
pdf:docinfo:producer pdfTeX-1.40.21
pdf:docinfo:subject
pdf:docinfo:title scPNMF: sparse gene encoding of single cells to facilitate gene selection for targeted gene profiling
pdf:docinfo:trapped False
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '69', '6', '8', '4', '0', '0', '6', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '4', '2', '34', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
producer pdfTeX-1.40.21
resourceName b'10_1101-2021_02_09_430550.pdf'
subject
title scPNMF: sparse gene encoding of single cells to facilitate gene selection for targeted gene profiling
trapped False
xmp:CreatorTool LaTeX with hyperref
xmpMM:DocumentID uuid:85c7129e-1dd2-11b2-0a00-4808278d5b00
xmpTPg:NPages 37
=== file2bib.sh ===
id: 10_1101-2021_02_10_430606
author: Wei, Zheng
title: NeuronMotif: Deciphering transcriptional cis-regulatory codes from deep neural networks
date: 2021
pages: 31
extension: .pdf
txt: ./txt/10_1101-2021_02_10_430606.txt
cache: ./cache/10_1101-2021_02_10_430606.pdf
Content-Type application/pdf
Creation-Date 2021-02-11T07:26:25Z
Keywords
Last-Modified 2021-02-14T21:22:17Z
Last-Save-Date 2021-02-14T21:22:17Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 161
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-11T07:26:25Z
date 2021-02-14T21:22:17Z
dc:format application/pdf; version=1.4
dc:subject
dc:title NeuronMotif: Deciphering transcriptional cis-regulatory codes from deep neural networks
dcterms:created 2021-02-11T07:26:25Z
dcterms:modified 2021-02-14T21:22:17Z
meta:creation-date 2021-02-11T07:26:25Z
meta:keyword
meta:save-date 2021-02-14T21:22:17Z
modified 2021-02-14T21:22:17Z
pdf:PDFVersion 1.4
pdf:charsPerPage ['1957', '1927', '1871', '1344', '1768', '265', '1654', '1374', '3237', '1483', '3133', '3345', '3309', '2950', '3308', '3422', '2952', '1097', '2527', '2241', '2894', '2551', '2511', '2949', '3107', '3322', '2890', '1419', '2894', '3279', '1145']
pdf:docinfo:created 2021-02-11T07:26:25Z
pdf:docinfo:creator_tool Word
pdf:docinfo:keywords
pdf:docinfo:modified 2021-02-14T21:22:17Z
pdf:docinfo:producer macOS 版本 10.14.6（版号 18G8012） Quartz PDFContext
pdf:docinfo:title NeuronMotif: Deciphering transcriptional cis-regulatory codes from deep neural networks
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '32', '4', '0', '12', '0', '0', '0', '0', '0', '1', '20', '0', '0', '0', '0', '0', '0', '55', '132', '27', '119', '88', '8', '0', '0', '5', '0', '0', '0', '0']
producer macOS 版本 10.14.6（版号 18G8012） Quartz PDFContext
resourceName b'10_1101-2021_02_10_430606.pdf'
subject
title NeuronMotif: Deciphering transcriptional cis-regulatory codes from deep neural networks
xmp:CreatorTool Word
xmpMM:DocumentID uuid:85c819d0-1dd2-11b2-0a00-9708277d8900
xmpTPg:NPages 31
=== file2bib.sh ===
id: 10_1101-2020_10_08_327718
author: Jambor, Helena
title: Creating Clear and Informative Image-based Figures for Scientific Publications
date: 2021
pages: 36
extension: .pdf
txt: ./txt/10_1101-2020_10_08_327718.txt
cache: ./cache/10_1101-2020_10_08_327718.pdf
Author Tracey Weissgerber
Comments
Company
Content-Type application/pdf
Creation-Date 2021-02-11T08:45:34Z
Keywords
Last-Modified 2021-02-14T21:22:17Z
Last-Save-Date 2021-02-14T21:22:17Z
SourceModified D:20210211084452
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 166
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
cp:subject
created 2021-02-11T08:45:34Z
creator Tracey Weissgerber
date 2021-02-14T21:22:17Z
dc:creator Tracey Weissgerber
dc:format application/pdf; version=1.6
dc:language EN-US
dc:subject
dc:title
dcterms:created 2021-02-11T08:45:34Z
dcterms:modified 2021-02-14T21:22:17Z
language EN-US
meta:author Tracey Weissgerber
meta:creation-date 2021-02-11T08:45:34Z
meta:keyword
meta:save-date 2021-02-14T21:22:17Z
modified 2021-02-14T21:22:17Z
pdf:PDFVersion 1.6
pdf:charsPerPage ['3190', '1904', '3819', '3897', '910', '2670', '754', '2640', '1136', '3780', '2209', '2046', '2394', '2062', '1692', '1524', '1280', '2079', '2312', '2250', '2370', '3715', '3836', '2374', '3859', '4070', '3003', '1054', '1685', '1658', '1475', '890', '412', '3866', '3908', '2364']
pdf:docinfo:created 2021-02-11T08:45:34Z
pdf:docinfo:creator Tracey Weissgerber
pdf:docinfo:creator_tool Acrobat PDFMaker 20 for Word
pdf:docinfo:custom:Comments
pdf:docinfo:custom:Company
pdf:docinfo:custom:SourceModified D:20210211084452
pdf:docinfo:keywords
pdf:docinfo:modified 2021-02-14T21:22:17Z
pdf:docinfo:producer Adobe PDF Library 20.13.96
pdf:docinfo:subject
pdf:docinfo:title
pdf:encrypted false
pdf:hasMarkedContent true
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
producer Adobe PDF Library 20.13.96
resourceName b'10_1101-2020_10_08_327718.pdf'
subject
title
xmp:CreatorTool Acrobat PDFMaker 20 for Word
xmpMM:DocumentID uuid:5d3787c4-53fe-422c-847f-b8011720723d
xmpTPg:NPages 36
=== file2bib.sh ===
id: 10_1101-698605
author: Sarantopoulou, Dimitra
title: Comparative evaluation of full-length isoform quantification from RNA-Seq
date: 2021
pages: 37
extension: .pdf
txt: ./txt/10_1101-698605.txt
cache: ./cache/10_1101-698605.pdf
Author Thomas Brooks
Content-Type application/pdf
Creation-Date 2021-02-11T17:18:36Z
Last-Modified 2021-02-14T21:22:17Z
Last-Save-Date 2021-02-14T21:22:17Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 315
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-11T17:18:36Z
creator Thomas Brooks
date 2021-02-14T21:22:17Z
dc:creator Thomas Brooks
dc:format application/pdf; version=1.7
dc:title Comparative evaluation of full-length isoform quantification from RNA-Seq
dcterms:created 2021-02-11T17:18:36Z
dcterms:modified 2021-02-14T21:22:17Z
meta:author Thomas Brooks
meta:creation-date 2021-02-11T17:18:36Z
meta:save-date 2021-02-14T21:22:17Z
modified 2021-02-14T21:22:17Z
pdf:PDFVersion 1.7
pdf:charsPerPage ['2300', '2678', '3181', '3316', '2068', '3156', '2759', '1252', '2934', '2853', '1939', '1704', '2616', '1349', '1899', '2026', '1841', '2304', '2390', '2985', '1795', '2952', '3087', '3064', '2972', '2970', '2485', '1728', '2104', '2438', '2468', '2365', '613', '1062', '771', '951', '697']
pdf:docinfo:created 2021-02-11T17:18:36Z
pdf:docinfo:creator Thomas Brooks
pdf:docinfo:creator_tool Microsoft® Word for Microsoft 365
pdf:docinfo:modified 2021-02-14T21:22:17Z
pdf:docinfo:producer Microsoft® Word for Microsoft 365
pdf:docinfo:title Comparative evaluation of full-length isoform quantification from RNA-Seq
pdf:encrypted false
pdf:hasMarkedContent true
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
producer Microsoft® Word for Microsoft 365
resourceName b'10_1101-698605.pdf'
title Comparative evaluation of full-length isoform quantification from RNA-Seq
xmp:CreatorTool Microsoft® Word for Microsoft 365
xmpMM:DocumentID uuid:c591608c-c000-4b6e-931d-a5352ac54f59
xmpTPg:NPages 37
=== file2bib.sh ===
id: 10_1101-2021_02_10_430563
author: Bandrowski, Anita
title: SPARC Data Structure: Rationale and Design of a FAIR Standard for Biomedical Research Data
date: 2021
pages: 16
extension: .pdf
txt: ./txt/10_1101-2021_02_10_430563.txt
cache: ./cache/10_1101-2021_02_10_430563.pdf
Author Calmi2
Content-Type application/pdf
Creation-Date 2021-02-10T08:53:11Z
Last-Modified 2021-02-14T21:22:18Z
Last-Save-Date 2021-02-14T21:22:18Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 530
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-10T08:53:11Z
creator Calmi2
date 2021-02-14T21:22:18Z
dc:creator Calmi2
dc:format application/pdf; version=1.7
dc:language en-US
dc:title SPARC Data Structure: Rationale and Design of a FAIR Standard for Biomedical Research Data
dcterms:created 2021-02-10T08:53:11Z
dcterms:modified 2021-02-14T21:22:18Z
language en-US
meta:author Calmi2
meta:creation-date 2021-02-10T08:53:11Z
meta:save-date 2021-02-14T21:22:18Z
modified 2021-02-14T21:22:18Z
pdf:PDFVersion 1.7
pdf:charsPerPage ['2645', '6469', '5580', '4241', '6477', '4383', '4414', '5014', '3391', '4754', '3775', '6024', '3764', '3020', '2517', '3837']
pdf:docinfo:created 2021-02-10T08:53:11Z
pdf:docinfo:creator Calmi2
pdf:docinfo:creator_tool Microsoft® Word for Microsoft 365
pdf:docinfo:modified 2021-02-14T21:22:18Z
pdf:docinfo:producer Microsoft® Word for Microsoft 365
pdf:docinfo:title SPARC Data Structure: Rationale and Design of a FAIR Standard for Biomedical Research Data
pdf:encrypted false
pdf:hasMarkedContent true
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
producer Microsoft® Word for Microsoft 365
resourceName b'10_1101-2021_02_10_430563.pdf'
title SPARC Data Structure: Rationale and Design of a FAIR Standard for Biomedical Research Data
xmp:CreatorTool Microsoft® Word for Microsoft 365
xmpMM:DocumentID uuid:F3D69740-A838-49AB-AADD-0C81C78493F2
xmpTPg:NPages 16
=== file2bib.sh ===
id: 10_1101-2021_02_01_429246
author: Zheng, Hongyu
title: Sequence-specific minimizers via polar sets
date: 2021
pages: 24
extension: .pdf
txt: ./txt/10_1101-2021_02_01_429246.txt
cache: ./cache/10_1101-2021_02_01_429246.pdf
Author
Content-Type application/pdf
Creation-Date 2021-02-10T23:12:39Z
Keywords
Last-Modified 2021-02-14T21:22:17Z
Last-Save-Date 2021-02-14T21:22:17Z
PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.17 (TeX Live 2016) kpathsea version 6.2.2
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 202
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
cp:subject
created 2021-02-10T23:12:39Z
creator
date 2021-02-14T21:22:17Z
dc:creator
dc:format application/pdf; version=1.5
dc:subject
dc:title Sequence-specific minimizers via polar sets
dcterms:created 2021-02-10T23:12:39Z
dcterms:modified 2021-02-14T21:22:17Z
meta:author
meta:creation-date 2021-02-10T23:12:39Z
meta:keyword
meta:save-date 2021-02-14T21:22:17Z
modified 2021-02-14T21:22:17Z
pdf:PDFVersion 1.5
pdf:charsPerPage ['3341', '4822', '3505', '2808', '3432', '3527', '3426', '3056', '2923', '3266', '3567', '3791', '3419', '4322', '3187', '3142', '1097', '3740', '2460', '3254', '3286', '1064', '1574', '785']
pdf:docinfo:created 2021-02-10T23:12:39Z
pdf:docinfo:creator
pdf:docinfo:creator_tool LaTeX with hyperref package
pdf:docinfo:custom:PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.17 (TeX Live 2016) kpathsea version 6.2.2
pdf:docinfo:keywords
pdf:docinfo:modified 2021-02-14T21:22:17Z
pdf:docinfo:producer pdfTeX-1.40.17
pdf:docinfo:subject
pdf:docinfo:title Sequence-specific minimizers via polar sets
pdf:docinfo:trapped False
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '1', '0', '7', '4', '10', '13', '12', '0', '2', '3', '0', '0', '0', '0', '0', '0', '13', '2', '2', '0', '0', '0']
producer pdfTeX-1.40.17
resourceName b'10_1101-2021_02_01_429246.pdf'
subject
title Sequence-specific minimizers via polar sets
trapped False
xmp:CreatorTool LaTeX with hyperref package
xmpMM:DocumentID uuid:85c73a57-1dd2-11b2-0a00-6f09275d6100
xmpTPg:NPages 24
=== file2bib.sh ===
id: 10_1101-2021_02_08_430280
author: Kasukurthi, Mohan V
title: SALTS – SURFR (sncRNA) And LAGOOn (lncRNA) Transcriptomics Suite
date: 2021
pages: 23
extension: .pdf
txt: ./txt/10_1101-2021_02_08_430280.txt
cache: ./cache/10_1101-2021_02_08_430280.pdf
Author glen borchert
Content-Type application/pdf
Creation-Date 2021-02-08T17:59:42Z
Last-Modified 2021-02-14T21:22:17Z
Last-Save-Date 2021-02-14T21:22:17Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 332
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-08T17:59:42Z
creator glen borchert
date 2021-02-14T21:22:17Z
dc:creator glen borchert
dc:format application/pdf; version=1.5
dc:language en-US
dc:title SALTS – SURFR (sncRNA) And LAGOOn (lncRNA) Transcriptomics Suite
dcterms:created 2021-02-08T17:59:42Z
dcterms:modified 2021-02-14T21:22:17Z
language en-US
meta:author glen borchert
meta:creation-date 2021-02-08T17:59:42Z
meta:save-date 2021-02-14T21:22:17Z
modified 2021-02-14T21:22:17Z
pdf:PDFVersion 1.5
pdf:charsPerPage ['1572', '3069', '4757', '4428', '2929', '2020', '5103', '3677', '2141', '4289', '4322', '3554', '3166', '6567', '2370', '4458', '4580', '4205', '3674', '4080', '3597', '3637', '1271']
pdf:docinfo:created 2021-02-08T17:59:42Z
pdf:docinfo:creator glen borchert
pdf:docinfo:creator_tool Microsoft® Word 2016
pdf:docinfo:modified 2021-02-14T21:22:17Z
pdf:docinfo:producer Microsoft® Word 2016
pdf:docinfo:title SALTS – SURFR (sncRNA) And LAGOOn (lncRNA) Transcriptomics Suite
pdf:encrypted false
pdf:hasMarkedContent true
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
producer Microsoft® Word 2016
resourceName b'10_1101-2021_02_08_430280.pdf'
title SALTS – SURFR (sncRNA) And LAGOOn (lncRNA) Transcriptomics Suite
xmp:CreatorTool Microsoft® Word 2016
xmpMM:DocumentID uuid:85c75b5e-1dd2-11b2-0a00-c70827bd7200
xmpTPg:NPages 23
=== file2bib.sh ===
id: 10_1101-2021_02_10_430705
author: Stassen, Shobana V.
title: VIA: Generalized and scalable trajectory inference in single-cell omics data
date: 2021
pages: 24
extension: .pdf
txt: ./txt/10_1101-2021_02_10_430705.txt
cache: ./cache/10_1101-2021_02_10_430705.pdf
Content-Type application/pdf
Creation-Date 2021-02-10T05:27:48Z
Last-Modified 2021-02-14T18:00:57Z
Last-Save-Date 2021-02-14T18:00:57Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 391
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-10T05:27:48Z
date 2021-02-14T18:00:57Z
dc:format application/pdf; version=1.4
dc:title VIA: Generalized and scalable trajectory inference in single-cell omics data
dcterms:created 2021-02-10T05:27:48Z
dcterms:modified 2021-02-14T18:00:57Z
meta:creation-date 2021-02-10T05:27:48Z
meta:save-date 2021-02-14T18:00:57Z
modified 2021-02-14T18:00:57Z
pdf:PDFVersion 1.4
pdf:charsPerPage ['5373', '2864', '5483', '5526', '5130', '345', '6236', '5474', '2917', '4605', '4025', '3650', '5031', '4563', '5222', '5654', '5634', '4294', '3842', '3498', '4377', '4589', '4431', '1921']
pdf:docinfo:created 2021-02-10T05:27:48Z
pdf:docinfo:creator_tool Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.75 Safari/537.36
pdf:docinfo:modified 2021-02-14T18:00:57Z
pdf:docinfo:producer Skia/PDF m77
pdf:docinfo:title VIA: Generalized and scalable trajectory inference in single-cell omics data
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
producer Skia/PDF m77
resourceName b'10_1101-2021_02_10_430705.pdf'
title VIA: Generalized and scalable trajectory inference in single-cell omics data
xmp:CreatorTool Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.75 Safari/537.36
xmpMM:DocumentID uuid:3dc71ea7-1dd2-11b2-0a00-7a08275dc400
xmpTPg:NPages 24
=== file2bib.sh ===
id: 10_1101-2021_02_09_430363
author: Bayer, Johanna M. M.
title: Accommodating site variation in neuroimaging data using hierarchical and Bayesian models
date: 2021
pages: 20
extension: .pdf
txt: ./txt/10_1101-2021_02_09_430363.txt
cache: ./cache/10_1101-2021_02_09_430363.pdf
Author
Content-Type application/pdf
Creation-Date 2021-02-09T06:02:04Z
Keywords
Last-Modified 2021-02-14T21:22:27Z
Last-Save-Date 2021-02-14T21:22:27Z
PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.19 (TeX Live 2018) kpathsea version 6.3.0
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 165
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
cp:subject
created 2021-02-09T06:02:04Z
creator
date 2021-02-14T21:22:27Z
dc:creator
dc:format application/pdf; version=1.5
dc:subject
dc:title Accommodating site variation in neuroimaging data using hierarchical and Bayesian models
dcterms:created 2021-02-09T06:02:04Z
dcterms:modified 2021-02-14T21:22:27Z
meta:author
meta:creation-date 2021-02-09T06:02:04Z
meta:keyword
meta:save-date 2021-02-14T21:22:27Z
modified 2021-02-14T21:22:27Z
pdf:PDFVersion 1.5
pdf:charsPerPage ['1502', '4844', '5626', '4771', '2956', '3003', '1660', '2526', '3391', '4243', '1765', '3323', '2090', '3826', '5707', '3101', '4217', '4665', '4787', '959']
pdf:docinfo:created 2021-02-09T06:02:04Z
pdf:docinfo:creator
pdf:docinfo:creator_tool LaTeX with hyperref
pdf:docinfo:custom:PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.19 (TeX Live 2018) kpathsea version 6.3.0
pdf:docinfo:keywords
pdf:docinfo:modified 2021-02-14T21:22:27Z
pdf:docinfo:producer pdfTeX-1.40.19
pdf:docinfo:subject
pdf:docinfo:title Accommodating site variation in neuroimaging data using hierarchical and Bayesian models
pdf:docinfo:trapped False
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '10', '9', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
producer pdfTeX-1.40.19
resourceName b'10_1101-2021_02_09_430363.pdf'
subject
title Accommodating site variation in neuroimaging data using hierarchical and Bayesian models
trapped False
xmp:CreatorTool LaTeX with hyperref
xmpMM:DocumentID uuid:85d672f8-1dd2-11b2-0a00-b309275d6100
xmpTPg:NPages 20
=== file2bib.sh ===
id: 10_1101-2021_02_11_430762
author: Schäffer, Alejandro A.
title: Ribovore: ribosomal RNA sequence analysis for GenBank submissions and database curation
date: 2021
pages: 28
extension: .pdf
txt: ./txt/10_1101-2021_02_11_430762.txt
cache: ./cache/10_1101-2021_02_11_430762.pdf
Content-Type application/pdf
Creation-Date 2021-02-11T12:21:20Z
Last-Modified 2021-02-14T21:22:17Z
Last-Save-Date 2021-02-14T21:22:17Z
PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.20 (TeX Live 2019/MacPorts 2019.50896_2) kpathsea version 6.3.1
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 186
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-11T12:21:20Z
date 2021-02-14T21:22:17Z
dc:format application/pdf; version=1.5
dc:title Ribovore: ribosomal RNA sequence analysis for GenBank submissions and database curation
dcterms:created 2021-02-11T12:21:20Z
dcterms:modified 2021-02-14T21:22:17Z
meta:creation-date 2021-02-11T12:21:20Z
meta:save-date 2021-02-14T21:22:17Z
modified 2021-02-14T21:22:17Z
pdf:PDFVersion 1.5
pdf:charsPerPage ['3536', '3441', '3231', '3411', '3332', '2676', '3013', '3264', '3585', '3505', '3340', '3147', '3237', '2993', '3597', '3360', '3849', '3022', '3179', '3559', '3323', '3293', '3281', '3253', '3263', '5532', '1767', '692']
pdf:docinfo:created 2021-02-11T12:21:20Z
pdf:docinfo:creator_tool TeX
pdf:docinfo:custom:PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.20 (TeX Live 2019/MacPorts 2019.50896_2) kpathsea version 6.3.1
pdf:docinfo:modified 2021-02-14T21:22:17Z
pdf:docinfo:producer pdfTeX-1.40.20
pdf:docinfo:title Ribovore: ribosomal RNA sequence analysis for GenBank submissions and database curation
pdf:docinfo:trapped False
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '17', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
producer pdfTeX-1.40.20
resourceName b'10_1101-2021_02_11_430762.pdf'
title Ribovore: ribosomal RNA sequence analysis for GenBank submissions and database curation
trapped False
xmp:CreatorTool TeX
xmpMM:DocumentID uuid:85c6efdd-1dd2-11b2-0a00-d909278d5b00
xmpTPg:NPages 28
=== file2bib.sh ===
id: 10_1101-2020_09_23_308239
author: Schultz, Bruce T
title: The COVID-19 PHARMACOME: A method for the rational selection of drug repurposing candidates from multimodal knowledge harmonization
date: 2021
pages: 31
extension: .pdf
txt: ./txt/10_1101-2020_09_23_308239.txt
cache: ./cache/10_1101-2020_09_23_308239.pdf
Appligent AppendPDF Pro 5.5 Linux Kernel 2.6 64bit Oct 2 2014 Library 10.1.0
Content-Type application/pdf
Creation-Date 2021-02-11T08:22:35Z
Last-Modified 2021-02-14T21:22:20Z
Last-Save-Date 2021-02-14T21:22:20Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 5558
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-11T08:22:35Z
date 2021-02-14T21:22:20Z
dc:format application/pdf; version=1.7
dc:language en-US
dc:title 2599906
dcterms:created 2021-02-11T08:22:35Z
dcterms:modified 2021-02-14T21:22:20Z
language en-US
meta:creation-date 2021-02-11T08:22:35Z
meta:save-date 2021-02-14T21:22:20Z
modified 2021-02-14T21:22:20Z
pdf:PDFVersion 1.7
pdf:charsPerPage ['2584', '1515', '2194', '2218', '491', '2118', '1934', '1624', '2074', '2074', '1754', '1826', '2154', '1228', '1624', '1173', '1263', '2086', '2088', '508', '2314', '1363', '534', '4487', '5088', '348', '344', '347', '349', '344', '7141']
pdf:docinfo:created 2021-02-11T08:22:35Z
pdf:docinfo:creator_tool Appligent AppendPDF Pro 5.5
pdf:docinfo:custom:Appligent AppendPDF Pro 5.5 Linux Kernel 2.6 64bit Oct 2 2014 Library 10.1.0
pdf:docinfo:modified 2021-02-14T21:22:20Z
pdf:docinfo:producer Microsoft® Word for Microsoft 365
pdf:docinfo:title 2599906
pdf:encrypted false
pdf:hasMarkedContent true
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
producer Microsoft® Word for Microsoft 365
resourceName b'10_1101-2020_09_23_308239.pdf'
title 2599906
xmp:CreatorTool Appligent AppendPDF Pro 5.5
xmpMM:DocumentID uuid:65fc1ff4-b086-11b2-0a00-782dad000000
xmpTPg:NPages 31
=== file2bib.sh ===
id: 10_1101-2020_01_28_923532
author: Ahmadi, Saba
title: The Landscape of Precision Cancer Combination Therapy: A Single-Cell Perspective
date: 2021
pages: 46
extension: .pdf
txt: ./txt/10_1101-2020_01_28_923532.txt
cache: ./cache/10_1101-2020_01_28_923532.pdf
Author Schaffer, Alejandro (NIH/NLM/NCBI) [E]
Content-Type application/pdf
Creation-Date 2021-02-12T10:57:20Z
Last-Modified 2021-02-14T20:40:41Z
Last-Save-Date 2021-02-14T20:40:41Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 310
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-12T10:57:20Z
creator Schaffer, Alejandro (NIH/NLM/NCBI) [E]
date 2021-02-14T20:40:41Z
dc:creator Schaffer, Alejandro (NIH/NLM/NCBI) [E]
dc:format application/pdf; version=1.7
dc:language en-US
dc:title The Landscape of Precision Cancer Combination Therapy: A Single-Cell Perspective
dcterms:created 2021-02-12T10:57:20Z
dcterms:modified 2021-02-14T20:40:41Z
language en-US
meta:author Schaffer, Alejandro (NIH/NLM/NCBI) [E]
meta:creation-date 2021-02-12T10:57:20Z
meta:save-date 2021-02-14T20:40:41Z
modified 2021-02-14T20:40:41Z
pdf:PDFVersion 1.7
pdf:charsPerPage ['1785', '909', '2031', '2819', '3037', '2594', '1347', '1985', '2038', '3076', '2477', '1952', '1872', '1658', '1185', '2016', '2878', '1058', '1201', '2930', '2007', '1643', '2801', '3005', '2714', '3060', '2616', '3072', '1293', '2812', '2597', '2058', '1247', '856', '1289', '2511', '2560', '2403', '2051', '1906', '2272', '3658', '3506', '3579', '3509', '1722']
pdf:docinfo:created 2021-02-12T10:57:20Z
pdf:docinfo:creator Schaffer, Alejandro (NIH/NLM/NCBI) [E]
pdf:docinfo:creator_tool Microsoft® Word for Office 365
pdf:docinfo:modified 2021-02-14T20:40:41Z
pdf:docinfo:producer Microsoft® Word for Office 365
pdf:docinfo:title The Landscape of Precision Cancer Combination Therapy: A Single-Cell Perspective
pdf:encrypted false
pdf:hasMarkedContent true
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
producer Microsoft® Word for Office 365
resourceName b'10_1101-2020_01_28_923532.pdf'
title The Landscape of Precision Cancer Combination Therapy: A Single-Cell Perspective
xmp:CreatorTool Microsoft® Word for Office 365
xmpMM:DocumentID uuid:647F7B6F-D5FD-4AA7-A927-7A5C48053B39
xmpTPg:NPages 46
=== file2bib.sh ===
id: 10_1101-2021_02_09_430460
author: Banerjee, Shayantan
title: Sequence neighborhoods enable reliable prediction of pathogenic mutations in cancer genomes
date: 2021
pages: 39
extension: .pdf
txt: ./txt/10_1101-2021_02_09_430460.txt
cache: ./cache/10_1101-2021_02_09_430460.pdf
Appligent AppendPDF Pro 5.5 Linux Kernel 2.6 64bit Oct 2 2014 Library 10.1.0
Content-Type application/pdf
Creation-Date 2021-02-09T18:13:05Z
Last-Modified 2021-02-14T21:22:18Z
Last-Save-Date 2021-02-14T21:22:18Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 501
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-09T18:13:05Z
date 2021-02-14T21:22:18Z
dc:format application/pdf; version=1.5
dc:title 99120235
dcterms:created 2021-02-09T18:13:05Z
dcterms:modified 2021-02-14T21:22:18Z
meta:creation-date 2021-02-09T18:13:05Z
meta:save-date 2021-02-14T21:22:18Z
modified 2021-02-14T21:22:18Z
pdf:PDFVersion 1.5
pdf:charsPerPage ['2933', '3586', '3699', '3184', '3141', '3534', '3190', '3343', '3362', '3202', '3398', '3616', '3061', '3423', '3333', '3280', '3702', '3698', '2901', '3903', '3853', '3930', '3937', '1941', '1445', '809', '880', '1975', '3658', '3874', '1427', '341', '341', '341', '341', '341', '341', '341', '341']
pdf:docinfo:created 2021-02-09T18:13:05Z
pdf:docinfo:creator_tool Appligent AppendPDF Pro 5.5
pdf:docinfo:custom:Appligent AppendPDF Pro 5.5 Linux Kernel 2.6 64bit Oct 2 2014 Library 10.1.0
pdf:docinfo:modified 2021-02-14T21:22:18Z
pdf:docinfo:producer Skia/PDF m90
pdf:docinfo:title 99120235
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
producer Skia/PDF m90
resourceName b'10_1101-2021_02_09_430460.pdf'
title 99120235
xmp:CreatorTool Appligent AppendPDF Pro 5.5
xmpMM:DocumentID uuid:3332bc21-b083-11b2-0a00-782dad000000
xmpTPg:NPages 39
=== file2bib.sh ===
id: 10_1101-2021_02_09_430536
author: Lin, Cui-Xiang
title: Genome-wide prediction and integrative functional characterization of Alzheimer’s disease-associated genes
date: 2021
pages: 47
extension: .pdf
txt: ./txt/10_1101-2021_02_09_430536.txt
cache: ./cache/10_1101-2021_02_09_430536.pdf
Content-Type application/pdf
Creation-Date 2021-02-08T13:33:39Z
Last-Modified 2021-02-14T21:22:18Z
Last-Save-Date 2021-02-14T21:22:18Z
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 509
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
created 2021-02-08T13:33:39Z
date 2021-02-14T21:22:18Z
dc:format application/pdf; version=1.4
dc:title Genome-wide prediction and integrative functional characterization of Alzheimer’s disease-associated genes
dcterms:created 2021-02-08T13:33:39Z
dcterms:modified 2021-02-14T21:22:18Z
meta:creation-date 2021-02-08T13:33:39Z
meta:save-date 2021-02-14T21:22:18Z
modified 2021-02-14T21:22:18Z
pdf:PDFVersion 1.4
pdf:charsPerPage ['1664', '2073', '2208', '2343', '2100', '2396', '2229', '2243', '2075', '2132', '2088', '2141', '2348', '2222', '2377', '2256', '2313', '2108', '2317', '2344', '2180', '2187', '2176', '2145', '2140', '2082', '2090', '2146', '2191', '2089', '3111', '2933', '2995', '3073', '2378', '1830', '1583', '1697', '2746', '2631', '1348', '1962', '1975', '681', '7158', '1185', '1009']
pdf:docinfo:created 2021-02-08T13:33:39Z
pdf:docinfo:creator_tool Word
pdf:docinfo:modified 2021-02-14T21:22:18Z
pdf:docinfo:producer macOS Version 10.15.7 (Build 19H114) Quartz PDFContext
pdf:docinfo:title Genome-wide prediction and integrative functional characterization of Alzheimer’s disease-associated genes
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '9', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
producer macOS Version 10.15.7 (Build 19H114) Quartz PDFContext
resourceName b'10_1101-2021_02_09_430536.pdf'
title Genome-wide prediction and integrative functional characterization of Alzheimer’s disease-associated genes
xmp:CreatorTool Word
xmpMM:DocumentID uuid:85c859ad-1dd2-11b2-0a00-5408271d5700
xmpTPg:NPages 47
=== file2bib.sh ===
id: 10_1101-727867
author: Tangherloni, Andrea
title: scAEspy: a tool for autoencoder-based analysis of single-cell RNA sequencing data
date: 2021
pages: 28
extension: .pdf
txt: ./txt/10_1101-727867.txt
cache: ./cache/10_1101-727867.pdf
Author Andrea Tangherloni, Federico Ricciuti, Daniela Besozzi, Pietro Liò, Ana Cvejic
Content-Type application/pdf
Creation-Date 2021-02-12T16:25:04Z
Keywords Autoencoders, scRNA-Seq, Dimensionality reduction, Clustering, Batch correction, Data integration
Last-Modified 2021-02-14T21:11:17Z
Last-Save-Date 2021-02-14T21:11:17Z
PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.20 (TeX Live 2019) kpathsea version 6.3.1
X-Parsed-By ['org.apache.tika.parser.DefaultParser', 'org.apache.tika.parser.pdf.PDFParser']
X-TIKA:content_handler ToTextContentHandler
X-TIKA:embedded_depth 0
X-TIKA:parse_time_millis 3963
access_permission:assemble_document true
access_permission:can_modify true
access_permission:can_print true
access_permission:can_print_degraded true
access_permission:extract_content true
access_permission:extract_for_accessibility true
access_permission:fill_in_form true
access_permission:modify_annotations true
cp:subject
created 2021-02-12T16:25:04Z
creator Andrea Tangherloni, Federico Ricciuti, Daniela Besozzi, Pietro Liò, Ana Cvejic
date 2021-02-14T21:11:17Z
dc:creator Andrea Tangherloni, Federico Ricciuti, Daniela Besozzi, Pietro Liò, Ana Cvejic
dc:format application/pdf; version=1.5
dc:subject Autoencoders, scRNA-Seq, Dimensionality reduction, Clustering, Batch correction, Data integration
dc:title scAEspy: a tool for autoencoder-based analysis of single-cell RNA sequencing data
dcterms:created 2021-02-12T16:25:04Z
dcterms:modified 2021-02-14T21:11:17Z
meta:author Andrea Tangherloni, Federico Ricciuti, Daniela Besozzi, Pietro Liò, Ana Cvejic
meta:creation-date 2021-02-12T16:25:04Z
meta:keyword Autoencoders, scRNA-Seq, Dimensionality reduction, Clustering, Batch correction, Data integration
meta:save-date 2021-02-14T21:11:17Z
modified 2021-02-14T21:11:17Z
pdf:PDFVersion 1.5
pdf:charsPerPage ['1552', '2911', '3437', '3290', '3172', '2974', '2835', '2923', '3313', '3204', '3158', '3151', '3207', '3309', '3262', '2383', '4689', '5805', '6016', '2696', '1341', '1788', '1428', '1745', '1871', '1746', '1423', '1664']
pdf:docinfo:created 2021-02-12T16:25:04Z
pdf:docinfo:creator Andrea Tangherloni, Federico Ricciuti, Daniela Besozzi, Pietro Liò, Ana Cvejic
pdf:docinfo:creator_tool LaTeX with hyperref
pdf:docinfo:custom:PTEX.Fullbanner This is pdfTeX, Version 3.14159265-2.6-1.40.20 (TeX Live 2019) kpathsea version 6.3.1
pdf:docinfo:keywords Autoencoders, scRNA-Seq, Dimensionality reduction, Clustering, Batch correction, Data integration
pdf:docinfo:modified 2021-02-14T21:11:17Z
pdf:docinfo:producer pdfTeX-1.40.20
pdf:docinfo:subject
pdf:docinfo:title scAEspy: a tool for autoencoder-based analysis of single-cell RNA sequencing data
pdf:docinfo:trapped False
pdf:encrypted false
pdf:hasMarkedContent false
pdf:hasXFA false
pdf:hasXMP true
pdf:unmappedUnicodeCharsPerPage ['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '2', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '0']
producer pdfTeX-1.40.20
resourceName b'10_1101-727867.pdf'
subject
title scAEspy: a tool for autoencoder-based analysis of single-cell RNA sequencing data
trapped False
xmp:CreatorTool LaTeX with hyperref
xmpMM:DocumentID uuid:81d7d1e9-1dd2-11b2-0a00-030a276d7200
xmpTPg:NPages 28
10_1101-2021_02_10_430604 txt/../ent/10_1101-2021_02_10_430604.ent
10_1101-2020_05_15_090266 txt/../ent/10_1101-2020_05_15_090266.ent
10_1101-2021_02_11_430806 txt/../ent/10_1101-2021_02_11_430806.ent
10_1101-2021_02_09_430036 txt/../ent/10_1101-2021_02_09_430036.ent
10_1101-2021_02_10_430367 txt/../ent/10_1101-2021_02_10_430367.ent
10_1101-2021_02_08_430070 txt/../ent/10_1101-2021_02_08_430070.ent
10_1101-2021_02_10_430619 txt/../ent/10_1101-2021_02_10_430619.ent
10_1101-2021_02_12_431018 txt/../ent/10_1101-2021_02_12_431018.ent
10_1101-2021_02_08_430275 txt/../ent/10_1101-2021_02_08_430275.ent
10_1101-2021_02_10_430656 txt/../ent/10_1101-2021_02_10_430656.ent
10_1101-2020_12_24_424317 txt/../ent/10_1101-2020_12_24_424317.ent
10_1101-2020_09_23_308239 txt/../ent/10_1101-2020_09_23_308239.ent
10_1101-2021_02_08_430270 txt/../ent/10_1101-2021_02_08_430270.ent
10_1101-2021_02_12_430963 txt/../ent/10_1101-2021_02_12_430963.ent
10_1101-2021_02_09_430405 txt/../ent/10_1101-2021_02_09_430405.ent
10_1101-2021_02_12_430923 txt/../ent/10_1101-2021_02_12_430923.ent
10_1101-2021_02_12_430989 txt/../ent/10_1101-2021_02_12_430989.ent
10_1101-2020_09_23_310276 txt/../ent/10_1101-2020_09_23_310276.ent
10_1101-2020_11_17_386649 txt/../ent/10_1101-2020_11_17_386649.ent
10_1101-2021_02_12_430979 txt/../ent/10_1101-2021_02_12_430979.ent
10_1101-2021_02_08_428881 txt/../ent/10_1101-2021_02_08_428881.ent
10_1101-2021_02_12_430739 txt/../ent/10_1101-2021_02_12_430739.ent
10_1101-2021_02_11_430695 txt/../ent/10_1101-2021_02_11_430695.ent
10_1101-2020_02_04_934216 txt/../ent/10_1101-2020_02_04_934216.ent
10_1101-2021_02_12_430830 txt/../ent/10_1101-2021_02_12_430830.ent
10_1101-2021_02_10_430623 txt/../ent/10_1101-2021_02_10_430623.ent
10_1101-2021_02_11_430847 txt/../ent/10_1101-2021_02_11_430847.ent
10_1101-2021_02_10_430649 txt/../ent/10_1101-2021_02_10_430649.ent
10_1101-2021_02_11_430789 txt/../ent/10_1101-2021_02_11_430789.ent
10_1101-2021_02_12_430764 txt/../ent/10_1101-2021_02_12_430764.ent
10_1101-2020_09_21_305516 txt/../ent/10_1101-2020_09_21_305516.ent
10_1101-2021_02_10_430563 txt/../ent/10_1101-2021_02_10_430563.ent
10_1101-2021_02_08_430343 txt/../ent/10_1101-2021_02_08_430343.ent
10_1101-2021_02_09_430550 txt/../ent/10_1101-2021_02_09_430550.ent
10_1101-2021_02_09_430363 txt/../ent/10_1101-2021_02_09_430363.ent
10_1101-2020_09_02_279521 txt/../ent/10_1101-2020_09_02_279521.ent
10_1101-2021_02_11_430871 txt/../ent/10_1101-2021_02_11_430871.ent
10_1101-2020_10_08_327718 txt/../ent/10_1101-2020_10_08_327718.ent
10_1101-2021_02_13_429885 txt/../ent/10_1101-2021_02_13_429885.ent
10_1101-698605 txt/../ent/10_1101-698605.ent
10_1101-2021_02_08_430280 txt/../ent/10_1101-2021_02_08_430280.ent
10_1101-2021_02_01_429246 txt/../ent/10_1101-2021_02_01_429246.ent
10_1101-2021_02_10_430705 txt/../ent/10_1101-2021_02_10_430705.ent
10_1101-2021_02_10_430606 txt/../ent/10_1101-2021_02_10_430606.ent
10_1101-2021_02_10_430512 txt/../ent/10_1101-2021_02_10_430512.ent
10_1101-2021_02_11_430762 txt/../ent/10_1101-2021_02_11_430762.ent
10_1101-2021_02_09_430460 txt/../ent/10_1101-2021_02_09_430460.ent
10_1101-727867 txt/../ent/10_1101-727867.ent
10_1101-2020_01_28_923532 txt/../ent/10_1101-2020_01_28_923532.ent
10_1101-2021_02_09_430536 txt/../ent/10_1101-2021_02_09_430536.ent
10_1101-2021_02_10_430604 txt/../pos/10_1101-2021_02_10_430604.pos
10_1101-2021_02_11_430806 txt/../pos/10_1101-2021_02_11_430806.pos
10_1101-2021_02_12_431018 txt/../pos/10_1101-2021_02_12_431018.pos
10_1101-2020_05_15_090266 txt/../pos/10_1101-2020_05_15_090266.pos
10_1101-2021_02_10_430619 txt/../pos/10_1101-2021_02_10_430619.pos
10_1101-2020_12_24_424317 txt/../pos/10_1101-2020_12_24_424317.pos
10_1101-2021_02_09_430036 txt/../pos/10_1101-2021_02_09_430036.pos
10_1101-2021_02_08_430070 txt/../pos/10_1101-2021_02_08_430070.pos
10_1101-2020_09_23_310276 txt/../pos/10_1101-2020_09_23_310276.pos
10_1101-2021_02_09_430405 txt/../pos/10_1101-2021_02_09_430405.pos
10_1101-2021_02_08_430275 txt/../pos/10_1101-2021_02_08_430275.pos
10_1101-2021_02_12_430963 txt/../pos/10_1101-2021_02_12_430963.pos
10_1101-2021_02_10_430367 txt/../pos/10_1101-2021_02_10_430367.pos
10_1101-2021_02_10_430656 txt/../pos/10_1101-2021_02_10_430656.pos
10_1101-2021_02_08_430270 txt/../pos/10_1101-2021_02_08_430270.pos
10_1101-2021_02_11_430847 txt/../pos/10_1101-2021_02_11_430847.pos
10_1101-2020_09_23_308239 txt/../pos/10_1101-2020_09_23_308239.pos
10_1101-2021_02_12_430739 txt/../pos/10_1101-2021_02_12_430739.pos
10_1101-2021_02_12_430923 txt/../pos/10_1101-2021_02_12_430923.pos
10_1101-2021_02_12_430989 txt/../pos/10_1101-2021_02_12_430989.pos
10_1101-2021_02_08_428881 txt/../pos/10_1101-2021_02_08_428881.pos
10_1101-2021_02_12_430830 txt/../pos/10_1101-2021_02_12_430830.pos
10_1101-2021_02_10_430623 txt/../pos/10_1101-2021_02_10_430623.pos
10_1101-2020_11_17_386649 txt/../pos/10_1101-2020_11_17_386649.pos
10_1101-2021_02_12_430764 txt/../pos/10_1101-2021_02_12_430764.pos
10_1101-2020_02_04_934216 txt/../pos/10_1101-2020_02_04_934216.pos
10_1101-2021_02_11_430695 txt/../pos/10_1101-2021_02_11_430695.pos
10_1101-2021_02_11_430871 txt/../pos/10_1101-2021_02_11_430871.pos
10_1101-2021_02_12_430979 txt/../pos/10_1101-2021_02_12_430979.pos
10_1101-2021_02_13_429885 txt/../pos/10_1101-2021_02_13_429885.pos
10_1101-2021_02_11_430789 txt/../pos/10_1101-2021_02_11_430789.pos
10_1101-2021_02_10_430563 txt/../pos/10_1101-2021_02_10_430563.pos
10_1101-2021_02_10_430649 txt/../pos/10_1101-2021_02_10_430649.pos
10_1101-2020_09_21_305516 txt/../pos/10_1101-2020_09_21_305516.pos
10_1101-2021_02_09_430550 txt/../pos/10_1101-2021_02_09_430550.pos
10_1101-2021_02_08_430343 txt/../pos/10_1101-2021_02_08_430343.pos
10_1101-698605 txt/../pos/10_1101-698605.pos
10_1101-2021_02_01_429246 txt/../pos/10_1101-2021_02_01_429246.pos
10_1101-2021_02_10_430606 txt/../pos/10_1101-2021_02_10_430606.pos
10_1101-2021_02_08_430280 txt/../pos/10_1101-2021_02_08_430280.pos
10_1101-2020_09_02_279521 txt/../pos/10_1101-2020_09_02_279521.pos
10_1101-2021_02_10_430512 txt/../pos/10_1101-2021_02_10_430512.pos
10_1101-2020_10_08_327718 txt/../pos/10_1101-2020_10_08_327718.pos
10_1101-2021_02_09_430363 txt/../pos/10_1101-2021_02_09_430363.pos
10_1101-2021_02_10_430705 txt/../pos/10_1101-2021_02_10_430705.pos
10_1101-727867 txt/../pos/10_1101-727867.pos
10_1101-2020_01_28_923532 txt/../pos/10_1101-2020_01_28_923532.pos
10_1101-2021_02_09_430460 txt/../pos/10_1101-2021_02_09_430460.pos
10_1101-2021_02_11_430762 txt/../pos/10_1101-2021_02_11_430762.pos
10_1101-2021_02_09_430536 txt/../pos/10_1101-2021_02_09_430536.pos
10_1101-2021_02_10_430604 txt/../wrd/10_1101-2021_02_10_430604.wrd
10_1101-2020_05_15_090266 txt/../wrd/10_1101-2020_05_15_090266.wrd
10_1101-2021_02_09_430036 txt/../wrd/10_1101-2021_02_09_430036.wrd
10_1101-2021_02_12_431018 txt/../wrd/10_1101-2021_02_12_431018.wrd
10_1101-2021_02_11_430806 txt/../wrd/10_1101-2021_02_11_430806.wrd
10_1101-2020_12_24_424317 txt/../wrd/10_1101-2020_12_24_424317.wrd
10_1101-2021_02_08_430070 txt/../wrd/10_1101-2021_02_08_430070.wrd
10_1101-2021_02_10_430367 txt/../wrd/10_1101-2021_02_10_430367.wrd
10_1101-2021_02_10_430619 txt/../wrd/10_1101-2021_02_10_430619.wrd
10_1101-2021_02_11_430847 txt/../wrd/10_1101-2021_02_11_430847.wrd
10_1101-2021_02_10_430656 txt/../wrd/10_1101-2021_02_10_430656.wrd
10_1101-2020_09_23_310276 txt/../wrd/10_1101-2020_09_23_310276.wrd
10_1101-2021_02_12_430830 txt/../wrd/10_1101-2021_02_12_430830.wrd
10_1101-2021_02_12_430989 txt/../wrd/10_1101-2021_02_12_430989.wrd
10_1101-2021_02_08_430275 txt/../wrd/10_1101-2021_02_08_430275.wrd
10_1101-2021_02_12_430739 txt/../wrd/10_1101-2021_02_12_430739.wrd
10_1101-2021_02_11_430695 txt/../wrd/10_1101-2021_02_11_430695.wrd
10_1101-2021_02_12_430923 txt/../wrd/10_1101-2021_02_12_430923.wrd
10_1101-2021_02_12_430963 txt/../wrd/10_1101-2021_02_12_430963.wrd
10_1101-2021_02_09_430405 txt/../wrd/10_1101-2021_02_09_430405.wrd
10_1101-2021_02_08_430270 txt/../wrd/10_1101-2021_02_08_430270.wrd
10_1101-2020_02_04_934216 txt/../wrd/10_1101-2020_02_04_934216.wrd
10_1101-2021_02_10_430649 txt/../wrd/10_1101-2021_02_10_430649.wrd
10_1101-2021_02_12_430764 txt/../wrd/10_1101-2021_02_12_430764.wrd
10_1101-2020_11_17_386649 txt/../wrd/10_1101-2020_11_17_386649.wrd
10_1101-2021_02_11_430789 txt/../wrd/10_1101-2021_02_11_430789.wrd
10_1101-2020_09_23_308239 txt/../wrd/10_1101-2020_09_23_308239.wrd
10_1101-2021_02_12_430979 txt/../wrd/10_1101-2021_02_12_430979.wrd
10_1101-2021_02_10_430623 txt/../wrd/10_1101-2021_02_10_430623.wrd
10_1101-2021_02_11_430871 txt/../wrd/10_1101-2021_02_11_430871.wrd
10_1101-2021_02_08_428881 txt/../wrd/10_1101-2021_02_08_428881.wrd
10_1101-2021_02_10_430563 txt/../wrd/10_1101-2021_02_10_430563.wrd
10_1101-2021_02_13_429885 txt/../wrd/10_1101-2021_02_13_429885.wrd
10_1101-2021_02_08_430343 txt/../wrd/10_1101-2021_02_08_430343.wrd
10_1101-2021_02_10_430606 txt/../wrd/10_1101-2021_02_10_430606.wrd
10_1101-2020_09_02_279521 txt/../wrd/10_1101-2020_09_02_279521.wrd
10_1101-2021_02_10_430512 txt/../wrd/10_1101-2021_02_10_430512.wrd
10_1101-2020_09_21_305516 txt/../wrd/10_1101-2020_09_21_305516.wrd
10_1101-698605 txt/../wrd/10_1101-698605.wrd
10_1101-2020_10_08_327718 txt/../wrd/10_1101-2020_10_08_327718.wrd
10_1101-2021_02_08_430280 txt/../wrd/10_1101-2021_02_08_430280.wrd
10_1101-2021_02_10_430705 txt/../wrd/10_1101-2021_02_10_430705.wrd
10_1101-2021_02_09_430363 txt/../wrd/10_1101-2021_02_09_430363.wrd
10_1101-2021_02_09_430550 txt/../wrd/10_1101-2021_02_09_430550.wrd
10_1101-2021_02_01_429246 txt/../wrd/10_1101-2021_02_01_429246.wrd
10_1101-2021_02_11_430762 txt/../wrd/10_1101-2021_02_11_430762.wrd
10_1101-2021_02_09_430460 txt/../wrd/10_1101-2021_02_09_430460.wrd
10_1101-2020_01_28_923532 txt/../wrd/10_1101-2020_01_28_923532.wrd
10_1101-727867 txt/../wrd/10_1101-727867.wrd
10_1101-2021_02_09_430536 txt/../wrd/10_1101-2021_02_09_430536.wrd
Done mapping.
Reducing neuroscience-from-bioarxiv
=== reduce.pl bib ===
id = 10_1101-2020_09_21_305516
author = Nikolic, Ana
title = Copy-scAT: Deconvoluting single-cell chromatin accessibility of genetic subclones in cancer
date = 2021
pages = 32
extension = .pdf
mime = application/pdf
words = 10376
sentences = 1280
flesch = 67
summary = Copy-scAT: Deconvoluting single-cell chromatin accessibility of genetic subclones in cancer 1 Copy-scAT: Deconvoluting single-cell chromatin accessibility of genetic subclones in cancer 1 uses single-cell epigenomic data to infer copy number variants (CNVs) that define cancer cells. We have tested the ability of Copy-scAT to use scATAC data to call CNVs with three different approaches 100 genome sequencing (WGS) data for adult GBM (aGBM) surgical resections (n = 4 samples, 3,647 cells). adult GBM samples identified using both methods, versus total numbers of gains detected by scATAC or 160 Number of chromosome-arm level gains detected in adult GBM samples identified using both methods, 163 (c) Multiple myeloma samples were profiled by both scATAC and the single-cell CNV assay. chromosome-arm level gains detected in adult GBM samples identified using both methods, versus total 166 CNVs are detected in scATAC clusters with Copy-scAT in pediatric GBM samples.
cache = ./cache/10_1101-2020_09_21_305516.pdf
txt = ./txt/10_1101-2020_09_21_305516.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_10_430649
author = Wen, Zi-Hang
title = Bfimpute: A Bayesian factorization method to recover single-cell RNA sequencing data
date = 2021
pages = 11
extension = .pdf
mime = application/pdf
words = 8418
sentences = 1302
flesch = 71
summary = Bfimpute: A Bayesian factorization method to recover single-cell RNA sequencing data Recovering dropout events in a sparse gene expression matrix for scRNA-seq data is a long-standing matrix completion We introduce Bfimpute, a Bayesian factorization imputation algorithm that reconstructs two latent gene and cell matrices to impute final gene expression matrix within each cell group, with or without the aid of cell type labels or bulk Bfimpute achieves better accuracy than other six publicly notable scRNA-seq imputation methods on simulated Key words: single cell; RNA-seq; imputation; Bayesian factorization impute dropout events by adopting the bulk RNA-seq data imputation of single cell RNA-seq data could be applied by Bfimpute recovers dropout values and improves cell type identification in the simulated data. and the imputed data by Bfimpute, scImpute, and DrImpute for the human embryonic stem cell differentiation study. imputation method scimpute for single-cell rna-seq data.
cache = ./cache/10_1101-2021_02_10_430649.pdf
txt = ./txt/10_1101-2021_02_10_430649.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_12_431018
author = Truong Nguyen, Phuoc
title = HaVoC, a bioinformatic pipeline for reference-based consensus assembly and lineage assignment for SARS-CoV-2 sequences.
date = 2021
pages = 14
extension = .pdf
mime = application/pdf
words = 3786
sentences = 502
flesch = 61
summary = HaVoC, a bioinformatic pipeline for reference-based consensus assembly and lineage assignment for SARS-CoV-2 sequences. HaVoC, a bioinformatic pipeline for reference-based consensus assembly and lineage 2 Several new variants of SARS-CoV-2 have emerged globally, of which the 18 based assemblies on raw SARS-CoV-2 sequences in addition to identifying lineages to detect 26 variants of concern, we have developed an open source bioinformatic pipeline called HaVoC 27 monitor the spread of SARS-CoV-2 variants of concern during local outbreaks. currently being used in Finland for monitoring the spread of SARS-CoV-2 variants. SARS-CoV2, variant detection, reference assembly, lineage identification, coronavirus, 40 surveillance of virus variants by sequencing the SARS-CoV-2 genomes would provide a fast 80 to query SARS-CoV-2 fastq sequence libraries and assigns lineages to them individually in 92 processing and a reference genome of SARS-CoV-2 in a separate FASTA file. The likelihood of emergence of novel SARS-CoV-2 variants of concern is increased and 209 Emerging SARS-CoV-2 Variants.
cache = ./cache/10_1101-2021_02_12_431018.pdf
txt = ./txt/10_1101-2021_02_12_431018.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_11_430847
author = Pinatti, Lisa M.
title = SearcHPV: a novel approach to identify and assemble human papillomavirus-host genomic integration events in cancer
date = 2021
pages = 26
extension = .pdf
mime = application/pdf
words = 6849
sentences = 788
flesch = 57
summary = SearcHPV: a novel approach to identify and assemble human papillomavirus-host genomic integration events in cancer squamous cell carcinomas; however, the impact of HPV integration into the host human genome SearcHPV uncovered HPV integration sites adjacent to known cancer-related detection of HPV-human integration sites from targeted capture DNA sequencing data. developed a novel HPV integration detection tool for targeted capture sequencing data, which we SearcHPV showed a high frequency of HPV16 integration with a total of six events in UM-SCCIn this study, SearcHPV also called HPV integration sites within TP63. HPV integration sites have been associated with structural variations in the human genome3, 8, 37, which supports an additional genetic mechanism as to why HPV integration sites Genome-wide analysis of HPV integration in human and their integration sites in host genomes through next generation sequencing data. identify viruses and their integration sites using next-generation sequencing of human cancer
cache = ./cache/10_1101-2021_02_11_430847.pdf
txt = ./txt/10_1101-2021_02_11_430847.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_12_430963
author = Gerber, Stefan
title = Streamlining differential exon and 3' UTR usage with diffUTR
date = 2021
pages = 17
extension = .pdf
mime = application/pdf
words = 6710
sentences = 896
flesch = 62
summary = adenylation site databases to enable differential 3' UTR usage analysis. Conclusions: diffUTR enables differential 3' UTR analysis and more generally facilitates DEU9 Popular bin-based DEU methods are provided by the limma [25,24], edgeR [23] and DEXSeq [22]41 Bins are prepared from various types of gene annotations as well as, optionally, additional APA-driven segmentation and extension, then read counts among statistically-significant genes, especially for bins with a higher expression (Figure 3A).78 diffUTR provides three main plot types to explore differential bin usage analyses, each with a88 Plotted are the UTR bins found statistically significant (binand gene-level FDR deuBinPlot (Figure 4B) provides bin-level statistic plots for a given gene, similar to those99 than CDS bins, including counts of 3' UTR when calculating overall gene expression could under-121 diffUTR streamlines DEU analysis and outperforms alternative methods in inferring UTR changes,127 For differential UTR analysis, gene-level results are ob-206
cache = ./cache/10_1101-2021_02_12_430963.pdf
txt = ./txt/10_1101-2021_02_12_430963.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_11_430871
author = Vadnais, David
title = ParticleChromo3D: A Particle Swarm Optimization Algorithm for Chromosome and Genome 3D Structure Prediction from Hi-C Data
date = 2021
pages = 24
extension = .pdf
mime = application/pdf
words = 10071
sentences = 1053
flesch = 63
summary = ParticleChromo3D: A Particle Swarm Optimization Algorithm for Chromosome and Genome 3D Structure Prediction from Hi-C Data chromosome and genome structure reconstruction from Hi-C data using Particle Swarm Optimization approach chromosome bin, according to the particle swarm algorithm, and then iterates its position towards a global best This paper presents ParticleChromo3D, a new distance-based algorithm for chromosome 3D structure The structures generated by ParticleChromo3D also shows that the result at swarm size Structures generated by ParticleChromo3D at different swarm size values. obtained by comparing the ParticleChromo3D algorithm's output structure to the simulated dataset's true plot of ParticleChromo3D SCC performance on 500KB GM12878 cell Hi-C data for chromosome 1 to 23. plot of ParticleChromo3D SCC performance on 500KB GM12878 cell Hi-C data for chromosome 1 to 23. chromosome 3D structure reconstruction algorithms on the GM12878 data set at both the 1MB and 500KB chromosome and genome structures reconstructed from Hi-C data.
cache = ./cache/10_1101-2021_02_11_430871.pdf
txt = ./txt/10_1101-2021_02_11_430871.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_13_429885
author = Househam, Jacob
title = A fully automated approach for quality control of cancer mutations in the era of high-resolution whole genome sequencing
date = 2021
pages = 36
extension = .pdf
mime = application/pdf
words = 10584
sentences = 1257
flesch = 49
summary = know tumour purity and the ploidy of a CNA segment, then the VAF mutations mapped A fully automated approach for quality control of cancer mutations in the era of high-resolution whole genome sequencing. A fully automated approach for quality control of cancer mutations in the era of high-resolution whole genome sequencing. A fully automated approach for quality control of cancer mutations in the era of high-resolution whole genome sequencing. A fully automated approach for quality control of cancer mutations in the era of high-resolution whole genome sequencing. A fully automated approach for quality control of cancer mutations in the era of high-resolution whole genome sequencing. A fully automated approach for quality control of cancer mutations in the era of high-resolution whole genome sequencing. A fully automated approach for quality control of cancer mutations in the era of high-resolution whole genome sequencing. A fully automated approach for quality control of cancer mutations in the era of high-resolution whole genome sequencing.
cache = ./cache/10_1101-2021_02_13_429885.pdf
txt = ./txt/10_1101-2021_02_13_429885.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_12_430830
author = Gergely, Tibély
title = Simultaneous estimation of per cell division mutation rate and turnover rate from bulk tumor sequence data
date = 2021
pages = 19
extension = .pdf
mime = application/pdf
words = 8181
sentences = 793
flesch = 68
summary = Simultaneous estimation of per cell division mutation rate and turnover rate from bulk tumor sequence data widely available bulk sequencing data where mutations from individual cells are and genomic mutation rate from bulk sequencing data. based on the maximum likelihood estimation of the parameters of a generative model of tumor growth and mutations. human hepatocellular carcinoma sample reveals an elevated per cell division mutation rate and high cell turnover. Due to the limitations of bulk sequencing, which only essays mutation frequencies for a population of cells from each tumor sample and does not The estimation is based on a maximum likelihood fit of the parameters of a birth-death model to the measured mutant and be estimated from readcount data, to separate the effects of the mutation rate We use pre-generated division trees from the ELynx suite at predetermined turnover rate values. Using the turnover rate, we also estimated the number of cell
cache = ./cache/10_1101-2021_02_12_430830.pdf
txt = ./txt/10_1101-2021_02_12_430830.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_12_430739
author = Malekian, Negin
title = Mutations in bdcA and valS correlate with quinolone resistance in wastewater Escherichia Coli
date = 2021
pages = 13
extension = .pdf
mime = application/pdf
words = 7516
sentences = 1093
flesch = 70
summary = Mutations in bdcA and valS correlate with quinolone resistance in wastewater Escherichia Coli Here, we systematically screen for candidate quinolone resistance-conferring mutations. coli and performed a genome-wide association study (GWAS) correlating over 200,000 mutations against quinolone resistance phenotypes. significant mutations including one located at the active site of the biofilm dispersal genes bdcA and six silent In summary, we demonstrate that GWAS effectively and comprehensively identifies resistance mutations Keywords: E Coli; Quinolone; Antibiotic Resistance; Genome-Wide Association Study (GWAS) direct route to resistance is mutations in the drug targets gyrA and parC. In summary, we aim to show that a bacterial genomewide association study can effectively and comprehensively identify targets relevant to antibiotic resistance. Based on representative resistance phenotypes, the authors selected 103 isolates for sequencing with Illumina MiSeq, 92 of which are available from coli bdcA may act indirectly on antibiotic resistance.
cache = ./cache/10_1101-2021_02_12_430739.pdf
txt = ./txt/10_1101-2021_02_12_430739.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_12_430764
author = Ascensión, Alex M.
title = Triku: a feature selection method based on nearest neighbors for single-cell data
date = 2021
pages = 18
extension = .pdf
mime = application/pdf
words = 9518
sentences = 1135
flesch = 64
summary = Triku: a feature selection method based on nearest neighbors for single-cell data Triku is a feature selection method that favours genes defining the main Single-cell RNA sequencing (scRNA-seq) is a powerful technology to study the biological heterogeneity of tissues at the individual cell level, allowing the characterization of new cell populations and cell states–i.e. cell types responding to different scRNA-seq datasets are multidimensional, i.e. the expression profile per cell consists of multiple genes. feature selection method: 1) the ability to recover basic dataset structure (main cell low, meaning that features selected with the different methods yielded clustering solutions that were quite similar to the manually-labeled cell types, although there are We first studied the expression pattern of genes selected by triku and other methods, To evaluate the cluster expression of selected genes in benchmarking datasets, for proteins within the genes selected by different FS methods in the two sets of benchmarking datasets.
cache = ./cache/10_1101-2021_02_12_430764.pdf
txt = ./txt/10_1101-2021_02_12_430764.txt
=== reduce.pl bib ===
id = 10_1101-2020_01_28_923532
author = Ahmadi, Saba
title = The Landscape of Precision Cancer Combination Therapy: A Single-Cell Perspective
date = 2021
pages = 46
extension = .pdf
mime = application/pdf
words = 16705
sentences = 1572
flesch = 66
summary = We focus our analysis on genes encoding protein targets that encode receptors on the cell all "modular", including one part that specifically targets the tumor cell via one gene/protein and MadHitter and each patient receives an optimal personalized combination of targeted therapies from a prespecified set (pill bottle). Cohort and Individual Target Set Sizes as Functions of Tumor Killing and Given the single-cell tumor data sets and the ILP optimization framework described above, we filtering as this threshold is decreased), decreases the size of the target cell surface receptor gene heterogeneity of the cancer, number of patients within the data set, size of target gene set, lack of used for filtering the gene set to avoid targeting non-cancerous tissues. the genes in the optimal target set, the expression of that gene in that non-tumor cell exceeds the set of genes which is known to be targetable to cell 𝐶.
cache = ./cache/10_1101-2020_01_28_923532.pdf
txt = ./txt/10_1101-2020_01_28_923532.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_11_430762
author = Schäffer, Alejandro A.
title = Ribovore: ribosomal RNA sequence analysis for GenBank submissions and database curation
date = 2021
pages = 28
extension = .pdf
mime = application/pdf
words = 16496
sentences = 1489
flesch = 65
summary = Ribovore: ribosomal RNA sequence analysis for GenBank submissions and database curation alignments of SSU, LSU and 5S rRNA from all three domains as well as from organelles, along with secondary structure predictions for selected sequences. Ribovore software package for the analysis of SSU rRNA and LSU rRNA sequences 18S SSU rRNA database of 1091 sequences was updated most recently on September 27, 2018 by running version 0.28 of the Ribovore program ribodbmaker on an input set of 579,279 GenBank sequences returned from the eukaryotic SSU rRNA The results of ribotyper and rRNA sensor are combined and each sequence is separated into one of four outcome classes depending on whether it passed or failed each input a set of candidate sequences and a specified rRNA model (e.g. SSU.Bacteria) two blastn databases: one of 1267 bacterial and archaeal 16S SSU rRNA sequences
cache = ./cache/10_1101-2021_02_11_430762.pdf
txt = ./txt/10_1101-2021_02_11_430762.txt
=== reduce.pl bib ===
id = 10_1101-2020_09_23_308239
author = Schultz, Bruce T
title = The COVID-19 PHARMACOME: A method for the rational selection of drug repurposing candidates from multimodal knowledge harmonization
date = 2021
pages = 31
extension = .pdf
mime = application/pdf
words = 8797
sentences = 1318
flesch = 57
summary = The COVID-19 PHARMACOME: A method for the rational selection of drug repurposing COVID-19 PHARMACOME, a comprehensive drug-target-mechanism graph generated from a initial version of the COVID-19 PHARMACOME, a comprehensive drug-target-mechanism graph representing COVID-19 pathophysiology mechanisms that includes both drug targets Figure 3: Overlap of compound hits between different drug repurposing screening experiments. space overlap between different COVID-19 drug repurposing screenings. The COVID-19 PHARMACOME associates pathways derived from drug repurposing targets Figure 4 shows the distribution of repurposing drugs in the COVID-19 cause-and-effect graph, overlap analysis allows for the identification of repurposing drugs targeting mechanisms that Virus-response mechanisms are targets for repurposing drugs Figure 5: Visualization of drug repurposing candidates (and their targets) used in combination treatment as our own drug repurposing screening results, we were able to identify mechanisms targeted COVID-19 PHARMACOME, we are now able to link repurposing drugs, their targets and the SARS-CoV-2 protein interaction map reveals targets for drug repurposing.
cache = ./cache/10_1101-2020_09_23_308239.pdf
txt = ./txt/10_1101-2020_09_23_308239.txt
=== reduce.pl bib ===
id = 10_1101-2020_09_23_310276
author = Greenfest-Allen, Emily
title = NIAGADS Alzheimer's GenomicsDB: A resource for exploring Alzheimer's Disease genetic and genomic knowledge
date = 2021
pages = 19
extension = .pdf
mime = application/pdf
words = 5987
sentences = 592
flesch = 52
summary = The NIAGADS Alzheimer's Genomics Database (GenomicsDB) is an interactive knowledgebase for Alzheimer's disease (AD) genetics that provides access to GWAS summary statistics datasets The website makes available >70 genome-wide summary statistics datasets from GWAS and efficient real-time data analysis and variant or gene report generation. Gene reports provide summaries of co-located ADRD risk-associated variants and have pages linking summary statistics to variant and gene annotations, this resource makes these summary statistics available for browsing (on dataset, gene, and variant reports and as genome NIAGADS GenomicsDB variant reports and a track is available on the genome browser. The NIAGADS GenomicsDB includes allele frequency data from 1000 Genomes (phase 3, version visualizations for summarizing search results and annotations in gene and variant reports. compare NIAGADS GWAS summary statistics tracks to each other, against annotated gene or A detailed report is provided for each of the GWAS summary statistics and ADSP meta-analysis
cache = ./cache/10_1101-2020_09_23_310276.pdf
txt = ./txt/10_1101-2020_09_23_310276.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_11_430806
author = Badaczewska-Dawid, Aleksandra
title = BIAPSS - BioInformatic Analysis of liquid-liquid Phase-Separating protein Sequences
date = 2021
pages = 3
extension = .pdf
mime = application/pdf
words = 2698
sentences = 301
flesch = 53
summary = BIAPSS BioInformatic Analysis of liquid-liquid Phase-Separating protein Sequences web platform named BIAPSS (BioInformatic Analysis of liquidliquid Phase-Separating protein Sequences) which offers the users interactive data analytic tools for facilitating the discovery of statistically significant sequence signals for proteins with Phase-Separating protein Sequences. The objective of BIAPSS is to enable a rapid and on-the-fly deep statistical analysis of LLPS-driver proteins using the pool of sequences with The comparison to benchmarks of various protein groups enables statistical inference of specific phase-separating affinities. Furthermore, the residue-resolution biophysical regularities inferred from BIAPSS will help not only to accurately identify regions prone to phase separation but also to design sequence modifications targeting various biomedical applications. for comprehensive sequence-based analysis of LLPS proteins. the driving forces for phase separation of prion-like RNA binding proteins. disordered protein regions encode a driving force for liquid-liquid phase separation? of proteins driving liquid-liquid phase separation.
cache = ./cache/10_1101-2021_02_11_430806.pdf
txt = ./txt/10_1101-2021_02_11_430806.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_11_430695
author = Gordon-Rodriguez, Elliott
title = Learning Sparse Log-Ratios for High-Throughput Sequencing Data
date = 2021
pages = 12
extension = .pdf
mime = application/pdf
words = 7973
sentences = 817
flesch = 60
summary = Log-ratios are an important class of features for analyzing high-throughput sequencing (HTS) metagenomic data for HTS data, and more generally, high-dimensional CoDa. Unlike existing methods, CoDaCoRe is simultaneously scalable, interpretable, sparse, and accurate. unlabelled datasets, {xi}ni=1, as a method for identiLearning Sparse Log-Ratios for High-Throughput Sequencing Data CoDaCoRe variable selection for the first (most explanatory) log-ratio on the Crohn disease data (Rivera-Pinto et al., 2018). more generally, in the field of CoDa. Learning Sparse Log-Ratios for High-Throughput Sequencing Data Learning Sparse Log-Ratios for High-Throughput Sequencing Data Learning Sparse Log-Ratios for High-Throughput Sequencing Data Learning Sparse Log-Ratios for High-Throughput Sequencing Data Learning Sparse Log-Ratios for High-Throughput Sequencing Data Learning Sparse Log-Ratios for High-Throughput Sequencing Data Learning Sparse Log-Ratios for High-Throughput Sequencing Data Learning Sparse Log-Ratios for High-Throughput Sequencing Data Learning Sparse Log-Ratios for High-Throughput Sequencing Data Learning Sparse Log-Ratios for High-Throughput Sequencing Data Learning Sparse Log-Ratios for High-Throughput Sequencing Data Learning Sparse Log-Ratios for High-Throughput Sequencing Data
cache = ./cache/10_1101-2021_02_11_430695.pdf
txt = ./txt/10_1101-2021_02_11_430695.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_12_430979
author = Da Silva, Kévin
title = StrainFLAIR: Strain-level profiling of metagenomic samples using variation graphs
date = 2021
pages = 20
extension = .pdf
mime = application/pdf
words = 10624
sentences = 992
flesch = 66
summary = StrainFLAIR: Strain-level profiling of metagenomic samples using variation graphs results show that StrainFLAIR was able to distinguish and estimate the abundances of close strains, as approaches to handle multiple similar genomes as with strains use gene clustering and then select the64 StrainFLAIR assigns and estimates species and strain abundances of a bacterial metagenomic sample graph, called the "node abundance", is computed, first focusing on unique mapped reads (first step). Strain-level abundances are then obtained by exploiting the specific genes of each reference genome188 from the reference variation graph thus simulating a new strain to be identified and quantified.231 strains from a sequenced sample, mapped onto this graph.343 Reference strains relative abundances expected and computed by StrainFLAIR or Reference strains relative abundances expected and computed by StrainFLAIR or Reference strains relative abundances expected and computed by StrainFLAIR or Reference strains relative abundances expected and computed by StrainFLAIR or
cache = ./cache/10_1101-2021_02_12_430979.pdf
txt = ./txt/10_1101-2021_02_12_430979.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_12_430989
author = Sofer, Tamar
title = Benchmarking Association Analyses of Continuous Exposures with RNA-seq in Observational Studies
date = 2021
pages = 27
extension = .pdf
mime = application/pdf
words = 8136
sentences = 626
flesch = 48
summary = Benchmarking Association Analyses of Continuous Exposures with RNA-seq in Observational Studies as well as linear regression-based analyses for studying the association of continuous exposures generation of empirical null distribution of association p-values, and we apply the pipeline to Many studies of phenotypes associated with gene expression from RNA-seq consist of small Residual permutation approach for simulations and for empirical p-value computation covariates, and outcome distributions; and (b) their relationships, aside from the exposureoutcome association, are the same as in the real data, we used a residual permutation approach. association studies applied to residual permutations were included to compute empirical papproach to study the distribution of p-values under the null of no association between the phenotypes and RNA-seq, and used this approach to further study power, and to compute approaches for transcriptome-wide analysis of RNA-seq in population-based studies, including more comprehensive study of statistical permutation approaches for RNA-seq association
cache = ./cache/10_1101-2021_02_12_430989.pdf
txt = ./txt/10_1101-2021_02_12_430989.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_12_430923
author = Modi, Vivek
title = Kincore: a web resource for structural classification of protein kinases and their inhibitors
date = 2021
pages = 18
extension = .pdf
mime = application/pdf
words = 7913
sentences = 666
flesch = 62
summary = Kincore: a web resource for structural classification of protein kinases and their inhibitors result, among the DFGin structures, we distinguished between the catalytically active kinase conformation pages for kinase phylogenetic groups, genes, conformational labels, PDBids, ligands and ligand types. options to download data – database tables as a tab separated files; the kinase structures as PyMOL Kincore provides conformational assignments and ligand type labels to protein kinase structures from Figure 1: Representative protein kinase structure (3ETA_A) displaying the residues used to define inhibitor The distribution of different ligand types across kinase conformations is provided in Table 1. Table 1: Distribution of ligand types across protein kinase conformations (Number of chains). including conformational and ligand type labels and C-helix position, kinase family, gene name, Uniprot provides the number of kinase chains in the group across different conformations with their Database table provides the list of all the PDB chains with conformational labels and ligand
cache = ./cache/10_1101-2021_02_12_430923.pdf
txt = ./txt/10_1101-2021_02_12_430923.txt
=== reduce.pl bib ===
id = 10_1101-727867
author = Tangherloni, Andrea
title = scAEspy: a tool for autoencoder-based analysis of single-cell RNA sequencing data
date = 2021
pages = 28
extension = .pdf
mime = application/pdf
words = 15281
sentences = 2865
flesch = 72
summary = scAEspy: a tool for autoencoder-based analysis of single-cell RNA sequencing data This computational tool allows for coupling low-dimensional probabilistic representation of gene expression data with the downstream analysis to consider the Finally, the currently available AEs cannot be directly exploited to obtain the latent space or to generate synthetic cells. to show the cells in this embedded space or as a starting point for other dimensionality reduction approaches (e.g., t-SNE and UMAP) as well as downstream analyses Non-linear approaches for dimensionality reduction can be effectively used to capture the non-linearities among the gene interactions that may exist in the highdimensional expression space of scRNA-Seq data [16]. be effectively applied to analyse disparate types of single-cell data from different flexible method developed to cluster single-cell data; (ii) a centroid is calculated batch-effect correction methods for single-cell rna sequencing data. Wang, D., Gu, J.: VASC: dimension reduction and visualization of single-cell RNA-seq data by deep
cache = ./cache/10_1101-727867.pdf
txt = ./txt/10_1101-727867.txt
=== reduce.pl bib ===
id = 10_1101-2020_12_24_424317
author = Muazzam, Fariha
title = Multi-class Cancer Classification and Biomarker Identification using Deep Learning
date = 2021
pages = 12
extension = .pdf
mime = application/pdf
words = 4252
sentences = 426
flesch = 57
summary = classification, feature extraction and relevant gene identification through deep learning methods for 12 This research picks up from detection of different types of cancer RNA-Seq expressions using deep neural classification of gene expression profiles for different kinds of cancers. Hence, the effectiveness of deep learning models for feature extraction and relevant gene identification is performed revealing substantial results and they produced five high-ranked gene sets and reduced feature This study was aimed at classifying 12 types of cancer and identifying relevant genes and the results show were able to identify cancer-relevant pathways and genes for the sets, that different experiments generated, A deep learning approach for cancer detection and relevant gene Tumor gene expression data classification via sample expansionbased deep learning. Identification of a multi-cancer gene expression Multi-class Cancer Classification and Biomarker Identification using Deep Learning Multi-class Cancer Classification and Biomarker Identification using Deep Learning
cache = ./cache/10_1101-2020_12_24_424317.pdf
txt = ./txt/10_1101-2020_12_24_424317.txt
=== reduce.pl bib ===
id = 10_1101-2020_10_08_327718
author = Jambor, Helena
title = Creating Clear and Informative Image-based Figures for Scientific Publications
date = 2021
pages = 36
extension = .pdf
mime = application/pdf
words = 12824
sentences = 1189
flesch = 56
summary = journals in three fields; plant sciences, cell biology and physiology (n=580 papers). figures were uncommon (physiology 16%, cell biology 12%, plant sciences 2%). among papers published in top journals in plant sciences, cell biology and physiology. contained images (plant science: 68%, cell biology: 72%, physiology: 55%). in physiology (49%) and cell biology (55%), and 28% of plant science papers provided and 29% of plant sciences papers contained no scale information on any image. Some publications use insets to show the same image at two different scales (cell Figure 1: Image types and reporting of scale information and insets physiology and plant science papers contained some images that were inaccessible to B: Most papers explain colors in image-based figures, however, explanations are less Figure 4: Using scale bars to annotate image size Creating clear and informative image-based figures for scientific publications. Creating clear and informative image-based figures for scientific publications.
cache = ./cache/10_1101-2020_10_08_327718.pdf
txt = ./txt/10_1101-2020_10_08_327718.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_09_430550
author = Song, Dongyuan
title = scPNMF: sparse gene encoding of single cells to facilitate gene selection for targeted gene profiling
date = 2021
pages = 37
extension = .pdf
mime = application/pdf
words = 13512
sentences = 1548
flesch = 64
summary = (scPNMF) method to select informative genes from scRNA-seq data in an unsupervised way. Therefore, for scRNA-seq data analysis, informative gene selection Besides scRNA-seq data analysis, informative gene selection is also crucial for designing number and a scRNA-seq dataset, scPNMF selects informative genes based on its weight matrix; First, the informative genes selected by scPNMF lead to the most accurate cell clustering. the informative genes and weight matrix of scPNMF lead to the best cell type prediction accuracy Figure 3: Benchmarking scPNMF against 11 informative gene selection methods on seven scRNA-seq (b) UMAP visualization of cells in the Zheng4 dataset based on 100 informative genes selected by We benchmark scPNMF against the 11 gene selection methods in terms of cell type prediction We propose scPNMF, an unsupervised gene selection and data projection method for scRNA-seq For cell type prediction, we project every targeted gene profiling dataset and its scRNA-seq
cache = ./cache/10_1101-2021_02_09_430550.pdf
txt = ./txt/10_1101-2021_02_09_430550.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_10_430656
author = Zakeri, Mohsen
title = A like-for-like comparison of lightweight-mapping pipelines for single-cell RNA-seq data pre-processing
date = 2021
pages = 7
extension = .pdf
mime = application/pdf
words = 6557
sentences = 568
flesch = 64
summary = A like-for-like comparison of lightweight-mapping pipelines for single-cell RNA-seq data pre-processing benchmark comparing the kallisto-bustools pipeline (2) for single-cell demonstrate that, when configured to match the computational complexity of kallisto-bustools as closely as possible, alevin-fry processes Alevin-fry (3) is a new pipeline for single-cell RNA-seq benchmarking STARsolo (9), kallisto-bustools (2) and alevin-fry (3), out new tools like alevin-fry for the pre-processing of single-cell data, (1), we have now created a simple-to-follow tutorial for speedoptimized single-cell pre-processing using alevin-fry (https:// by Booeshaghi and Pachter (1) change when a like-for-like comparison between alevin-fry and kallisto-bustools is carried out, we The time and memory used by the relevant steps of the alevin-fry and kallisto-bustools pipelines for pre-processing the 20 diverse tagged-end single-cell RNA-seq datasets used in (1). A comparison of the resulting count matrices obtained from alevin-fry and kallisto-bustools, as run in this manuscript, for the pbmc_10k_v3 dataset. peak memory than alevin-fry, with the kallisto-bustools pipeline using
cache = ./cache/10_1101-2021_02_10_430656.pdf
txt = ./txt/10_1101-2021_02_10_430656.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_10_430619
author = Schutz, Sacha
title = Cutevariant: a GUI-based desktop application to explore genetics variations
date = 2021
pages = 8
extension = .pdf
mime = application/pdf
words = 4932
sentences = 632
flesch = 66
summary = Cutevariant: a GUI-based desktop application to explore genetics variations Cutevariant is a user-friendly GUI based desktop application for genomic research designed to search for variations in DNA samples collected in annotated files and encoded in the Variant Calling Format. application imports data into a local relational database wherefrom complex filter-queries can be built either Key words: genomics, DNA variant, desktop application, Domain Specific Language, Graphic User Interface applications import the data from VCF files into an indexed Cutevariant imports data from VCF files into a normalized Fig. 2: The Cutevariant main view showing the variants list sub-window (middle), different controllers sub-windows but not all are Just like Variant Tools, Cutevariant supports operations Features Cutevariant BrowseVCF VCF-Miner VCF-Explorer VCF-Server VCF-Filters GEMINI Variant Tools SnpSift Comparaison of time performance between cutevariant and VCF-miner for importation and query execution. 3. Pablo Cingolani, Adrian Platts, Le Lily Wang, Melissa VCF-Miner: GUI-based application for mining variants
cache = ./cache/10_1101-2021_02_10_430619.pdf
txt = ./txt/10_1101-2021_02_10_430619.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_11_430789
author = Tyagin, Ilya
title = Accelerating COVID-19 research with graph mining and transformer-based learning
date = 2021
pages = 9
extension = .pdf
mime = application/pdf
words = 9408
sentences = 807
flesch = 58
summary = Accelerating COVID-19 research with graph mining and transformer-based learning develop text mining techniques that can help the science community answer high-priority scientific questions related to COVID-19. is currently customized and available in the open domain to massively process COVID-19 related queries. Both systems are the next generation of the AGATHA knowledge network mining transformer model [37]. (1) Most of the existing HG systems are domain-specific (e.g., genedisease interactions) that is usually expressed in limiting the processed information (e.g., significant filtering vocabulary and papers a trained deep bi-LSTM model for extracting predicates from unstructured text. For instance, the node representing the entity "COVID-19" is connected to every sentence and predicate that The prior AGATHA semantic network only includes UMLS terms that appear in SemMedDB predicates [18] which is a major limitation. obtain embeddings per node in the semantic graph, we train AGATHA system ranking model.
cache = ./cache/10_1101-2021_02_11_430789.pdf
txt = ./txt/10_1101-2021_02_11_430789.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_10_430512
author = Kim, Catherine
title = Prediction of adverse drug reactions associated with drug-drug interactions using hierarchical classification
date = 2021
pages = 41
extension = .pdf
mime = application/pdf
words = 11859
sentences = 1137
flesch = 56
summary = into DDIs. In this study, a hierarchical machine learning model was created to predict DDIassociated ADRs and pharmacological insight thereof for any drug pair. drugs' chemical structures as inputs to predict their target, enzyme, and transporter (TET) Development of RFCs for Prediction of Target, Enzyme, and Transporter Profiles of Drugs Development of a Model for Prediction of DDI-associated ADRs from TET Profiles of Drugs ADR prediction from Target, Enzyme, and Transporter Profiles of Drug Pairs To predict ADRs of a drug pair from its TET profiles, Random Forest Classifier (RFC), Application of the SVM model for DDI-associated ADRs Involving Three Major Drugs through predicted PRR changes of drug pairs upon removal of each of the targets, enzymes, and changes of drug pairs were predicted by the model upon removal of each of the targets, enzymes, Target, enzyme, and transporter (TET) profiles of atorvastatin and concomitant drugs,
cache = ./cache/10_1101-2021_02_10_430512.pdf
txt = ./txt/10_1101-2021_02_10_430512.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_10_430705
author = Stassen, Shobana V.
title = VIA: Generalized and scalable trajectory inference in single-cell omics data
date = 2021
pages = 24
extension = .pdf
mime = application/pdf
words = 13590
sentences = 1383
flesch = 53
summary = 1 VIA: Generalized and scalable trajectory inference in single-cell omics data 1 VIA: Generalized and scalable trajectory inference in single-cell omics data 35 strategy to compute pseudotime, and reconstruct cell lineages based on lazy-teleporting random walks Step 1: Single-cell level graph is clustered such that each node 50 user defined start cell) is first computed by the expected hitting time for a lazy-teleporting random walk along an 57 network topology and single-cell level pseudotime/lineage probability properties onto an embedding using GAMs, as The cell fates and their lineage pathways are then computed by a two-stage probabilistic method, 94 graph-traversal allows it to infer cell fates when the underlying data spans combinations of multifurcating 201 detected cell fates annotated (o) lineage pathway and gene-pseudotime trend shown for the CD41 Megakaryocytic 259 Figure 3 VIA infers trajectories in single-cell multi-omic and image datasets (a) Major lineages of human Single cells are represented by graph nodes that are connected based on
cache = ./cache/10_1101-2021_02_10_430705.pdf
txt = ./txt/10_1101-2021_02_10_430705.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_10_430606
author = Wei, Zheng
title = NeuronMotif: Deciphering transcriptional cis-regulatory codes from deep neural networks
date = 2021
pages = 31
extension = .pdf
mime = application/pdf
words = 12013
sentences = 1107
flesch = 63
summary = Each point is a decoupled motif generate by a sample set of sequence. Only the max activation value of the decoupled motifs in Fig. 3b are significantly higher than the decoupled motifs of other neurons in layer 3 of Basset-3 model. discovered (q-value < 0.001) from the neuron in convolutional output layer of Basset, BD-5 and BD-10 model. c, The number of motif discovered (q-value < 0.01) from the neuron in layer 3 of Basset model using different sub-patterns in the input feature map of the max pooling layer to split the sequences set of which are DNA-sequence based DCNN models with 3 general convolutional layers for stacking sequences of different synonymous motifs with the maximum activation value In summary, we presented NeuronMotif as an effective algorithm to reveal the cisregulatory motif grammar learned by DCNN model that use DNA sequence to annotate sequences indicate more synonymous motif mixture in this DCNN model.
cache = ./cache/10_1101-2021_02_10_430606.pdf
txt = ./txt/10_1101-2021_02_10_430606.txt
=== reduce.pl bib ===
id = 10_1101-698605
author = Sarantopoulou, Dimitra
title = Comparative evaluation of full-length isoform quantification from RNA-Seq
date = 2021
pages = 37
extension = .pdf
mime = application/pdf
words = 12853
sentences = 1332
flesch = 55
summary = Comparative evaluation of full-length isoform quantification from RNA-Seq Full-length isoform quantification from RNA-Seq is a key goal in transcriptomics analyses benchmarking, isoform quantification, simulated data, pseudo-alignment, RNA-Seq, short Given the difficulty in full-length isoform quantification, many RNA-Seq studies simply analysis performed on the known true isoform quantifications of the simulated data to the For the simulated data we started with 11 real RNA-Seq samples: six liver and six the isoform expression level using idealized and realistic simulated data, with full and true counts), for the set of expressed isoforms in sample 1 in C) idealized and D) realistic data. Method effect on differential expression analysis, using realistic data. Method effect on differential expression analysis, using realistic data. RSEM is a gene/isoform abundance tool for RNA-Seq data which uses a generative model S1 Fig. Method effect on full-length isoform quantification using simulated data. Method effect on full-length isoform quantification using simulated data.
cache = ./cache/10_1101-698605.pdf
txt = ./txt/10_1101-698605.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_10_430563
author = Bandrowski, Anita
title = SPARC Data Structure: Rationale and Design of a FAIR Standard for Biomedical Research Data
date = 2021
pages = 16
extension = .pdf
mime = application/pdf
words = 10901
sentences = 1026
flesch = 48
summary = investigators across the SPARC consortium that provide key details about organ-specific circuitry, including structural (BIDS), the SDS has been designed to capture the large variety of data generated by SPARC investigators who are description of the SPARC curation process and the automated tools for complying with the SDS, including the SDS validator and Software to Organize Data Automatically (SODA) for SPARC. required to organize their data files and metadata organized according to the SPARC Data Structure data according to the SPARC Dataset Structure. is the preferred file format for tabular data in SPARC, the Data files are organized into 3 different top-level folders, The organization structure of the files and folders for a SPARC dataset. https://github.com/SciCrunch/sparc-curation/releases/tag/dataset-template-1.2.3 https://github.com/SciCrunch/sparc-curation/releases/tag/dataset-template-1.2.3 investigators include folders that organize data along a from these subjects, data files are organized within fields, the curation team developed a SPARC Dataset files/folders, and share datasets with the SPARC
cache = ./cache/10_1101-2021_02_10_430563.pdf
txt = ./txt/10_1101-2021_02_10_430563.txt
=== reduce.pl bib ===
id = 10_1101-2020_11_17_386649
author = Danciu, Daniel
title = Topology-based Sparsification of Graph Annotations
date = 2021
pages = 15
extension = .pdf
mime = application/pdf
words = 8205
sentences = 774
flesch = 67
summary = Experiments on 10,000 RNA-seq datasets show that RowDiff combined with MultiBRWT results in a 30% reduction in annotation footprint over Mantis-MST, the previously known most a binary matrix, where the k-mer set indexes the rows and each annotation label specifies a column. Starting from any vertex in the de Bruijn graph, Algorithm 1 defines a traversal leading to an anchor Each row in a RowDiff-transformed annotation matrix has the same or fewer set bits than A naı̈ve implementation of the RowDiff construction would be to load the matrix A in memory, and gradually replace its rows with their sparsified counterpart, while traversing the graph. We now note that, when querying annotations for paths in the graph, or sets of rows corresponding to vertices We constructed annotated de Bruijn graphs from the RNA-Seq data set in the same We now compare the representation size for RowDiff and other state-of-the-art graph annotation compression methods.
cache = ./cache/10_1101-2020_11_17_386649.pdf
txt = ./txt/10_1101-2020_11_17_386649.txt
=== reduce.pl bib ===
id = 10_1101-2020_05_15_090266
author = Zhang, R.
title = SpacePHARER: Sensitive identification of phages from CRISPR spacers in prokaryotic hosts
date = 2021
pages = 6
extension = .pdf
mime = application/pdf
words = 2191
sentences = 283
flesch = 64
summary = Summary: SpacePHARER (CRISPR Spacer Phage-Host Pair Finder) is a sensitive and fast tool for de novo prediction of phage-host relationships via identifying phage genomes that match CRISPR spacers in genomic or metagenomic data. SpacePHARER gains sensitivity by comparing spacers and phages at the protein level, optimizing its scores for matching SpacePHARER by searching a comprehensive spacer list against all complete phage genomes. methods compare individual CRISPR spacers with phage To increase sensitivity, (1) we compare protein coding sequences because phage genomes are mostly coding, and, (0) Preprocess input: scan the phage genome and CRISPR spacers in six ORFs q of CRISPR spacers extracted from one prokaryotic genome, and each target set T comprises the putative protein sequences t from a single phage. The performance of SpacePHARER was evaluated on the spacer test set against a target database predicted the correct host for more phages than BLASTN BLASTN in detecting phage-host pairs, due to searching
cache = ./cache/10_1101-2020_05_15_090266.pdf
txt = ./txt/10_1101-2020_05_15_090266.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_01_429246
author = Zheng, Hongyu
title = Sequence-specific minimizers via polar sets
date = 2021
pages = 24
extension = .pdf
mime = application/pdf
words = 15440
sentences = 1407
flesch = 71
summary = minimizers focus on sampling fewer k-mers on a random sequence and use universal hitting sets (sets suggests, a UHS is a set of k-mers that "hits" every w-long window of every possible sequence (hence the the elements of the polar sets are in the sequence: the higher the energy, the more spread apart the k-mers have densities upper bounded by |U|/σk, because only k-mers from the universal hitting set can be selected. Section 2.2 gives a formal definition of the link energy of a polar set and Theorem 1 gives upper and lower bounds using this link energy for the density of a minimizer compatible with a polar set. form a link, which in turn is the number of k-mer pairs in the polar set that are exactly w bases away on S. A context is charged if the minimizer selects a different k-mer in the first window than in the second
cache = ./cache/10_1101-2021_02_01_429246.pdf
txt = ./txt/10_1101-2021_02_01_429246.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_10_430623
author = Aberasturi, Dillon
title = “Single-subject studies”-derived analyses unveil altered biomechanisms between very small cohorts: implications for rare diseases
date = 2021
pages = 9
extension = .pdf
mime = application/pdf
words = 9478
sentences = 748
flesch = 58
summary = published S3-type N-of-1-pathways MixEnrich to two paired samples (e.g., diseased vs unaffected tissues) for determining patient-specific enriched genes sets: Odds Ratios (S3-OR) and S3-variance using these models to derive effect sizes and statistical significance in singlesubject studies of transcriptomes, these samples are isogenic or quasi-isogenic, and thus do not necessarily generalize to a group of subjects (cohort-level signal). The novel bioinformatic method identifies meaningful biomechanism differences between very small cohorts by using single-subject-study-derived effect sizes for gene sets. (B) For the generalized linear model-based analyses, we applied a different filtering process to the raw data where we eliminated all the transcripts with 0 counts for each subject and then calculated the coefficient 2.3 Description of the Generalized Linear Models and application of Inter-N-of-1 methods for small cohort comparison and their evaluation in the Breast Cancer Data the analysis of subsets of the TCGA Breast Cancer data, genes were declared differentially expressed if their abs(log2FC) > log2(1.2) and their FDR-adjusted p-value <
cache = ./cache/10_1101-2021_02_10_430623.pdf
txt = ./txt/10_1101-2021_02_10_430623.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_09_430405
author = Quazi, Sameer
title = In-silico Structural and Molecular Docking-Based Drug Discovery Against Viral Protein (VP35) of Marburg Virus: A potent Agent of MAVD
date = 2021
pages = 23
extension = .pdf
mime = application/pdf
words = 5941
sentences = 1038
flesch = 64
summary = In-silico Structural and Molecular Docking-Based Drug Discovery Against Viral Protein (VP35) of Marburg Virus: A potent Agent of MAVD including structure-based drug-like compounds screening from online databases, molecular The final small molecules of drug-like compounds would have more effective and selected for the molecular docking with FGI-103 antiviral drug-using AutoDock 4.2 software. After that, FGI-103 was set and screen other drug-like compounds from PubChem databases. The finally selected drug-like compounds were docked with the P1 site of VP35 of based on ap1 site for ligand in every dock for VP35 MARV utilizing a grid chart of 50 × 50 × 50 The ADMET properties of finally selected drug-like compounds were checked to utilize 2D molecules structure of selected drug-like compounds (A) represents the 2D The molecule structure of three drug-like compounds is shown in Figure 6. "In-Silico Structural and Molecular Docking-Based Drug Discovery "In-Silico Structural and Molecular Docking-Based Drug Discovery
cache = ./cache/10_1101-2021_02_09_430405.pdf
txt = ./txt/10_1101-2021_02_09_430405.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_10_430367
author = Chen, Meili
title = Genome Warehouse: A Public Repository Housing Genome-scale Data
date = 2021
pages = 18
extension = .pdf
mime = application/pdf
words = 4875
sentences = 656
flesch = 66
summary = Running title: Chen M et al / Genome Assembly Data Repository 21 Genomics Data Center (NGDC), part of the China National Center for Bioinformation 40 archive high-quality genome sequences and annotations, GWH is equipped with a 46 Collectively, GWH serves as an important resource for genome-scale data 51 https://bigd.big.ac.cn/) [13], the aim of GWH is to accept data submissions worldwide 78 GWH is a centralized resource housing genome-scale data, with the purpose to 105 GWH not only accepts genome assembly associated data through an on-line 111 GWH will assign a unique accession number to the submitted genome assembly upon 149 GWH provides data visualization for both genome 163 Collectively, GWH is a user-friendly portal for genome data submission, release, and 209 Database resources of the National Genomics Data 302 Genome assembly accession number is prefixed with "GWH", followed by four 334 Genome assembly accession number is prefixed with "GWH", followed by four 334
cache = ./cache/10_1101-2021_02_10_430367.pdf
txt = ./txt/10_1101-2021_02_10_430367.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_09_430536
author = Lin, Cui-Xiang
title = Genome-wide prediction and integrative functional characterization of Alzheimer’s disease-associated genes
date = 2021
pages = 47
extension = .pdf
mime = application/pdf
words = 20656
sentences = 4864
flesch = 79
summary = Genome-wide prediction and integrative functional characterization of Alzheimer's disease-associated genes example, a module-trait network approach was proposed and applied to identify gene 63 functional enrichment-based approach to identify negative genes that are not likely 94 associated genes through an optimal selection of networks and machine learning 98 FGN, and prediction of AD-associated genes using machine learning models (Fig. 1). addition, we tested their enrichment in three AD-related gene sets associated with 122 The top-ranked genes are enriched in AD-associated functions and phenotypes 154 These results provide additional evidence that our predicted genes are associated with 194 The top-ranked genes are associated with AD based on miRNA-target networks 227 We investigated whether top-ranked genes were functionally related to AD-associated 229 We tested whether the top-ranked k genes were more likely to interact with AD-associated 576 related to AD-associated genes or miRNAs based on miRNA-target interaction networks.
cache = ./cache/10_1101-2021_02_09_430536.pdf
txt = ./txt/10_1101-2021_02_09_430536.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_09_430363
author = Bayer, Johanna M. M.
title = Accommodating site variation in neuroimaging data using hierarchical and Bayesian models
date = 2021
pages = 20
extension = .pdf
mime = application/pdf
words = 13439
sentences = 1891
flesch = 70
summary = Accommodating site variation in neuroimaging data using hierarchical and Bayesian models The potential of normative modeling to make individualized predictions has led to structural neuroimaging results that go beyond the case-control approach. in a similar way for multi-site modeling in a pooled neuroimaging data set, which contained 7499 participants that org/abide/) data set to compare a non-linear, Gaussian version of the model, to a linear hierarchical Bayesian version and mathematical description of our approach to include site as predictor in a normative hierarchical Bayesian model. With the aim to create reliable normative models in multi-site neuroimaging data, we developed and compared two model is also able to capture non-linear effects between age and thickness of the cortical region ("Hierarchical Bayesian Gaussian Process term, which allows to model non-linear association between age and cortical thickness measures. The only models that perform better for most regions than the mean of the training data set are the Hierarchical Bayesian
cache = ./cache/10_1101-2021_02_09_430363.pdf
txt = ./txt/10_1101-2021_02_09_430363.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_09_430460
author = Banerjee, Shayantan
title = Sequence neighborhoods enable reliable prediction of pathogenic mutations in cancer genomes
date = 2021
pages = 39
extension = .pdf
mime = application/pdf
words = 15659
sentences = 1731
flesch = 40
summary = experimentally validated cancer mutation data in this study, we explored various string-based evolutionary features resulted in the development of a pan-cancer mutation effect prediction Distinguishing between driver and passenger mutations from sequenced cancer genomes is a Recent studies have identified specific signatures or patterns of mutations in different cancer than passenger mutations and built probabilistic models to identify driver genes that had this study, missense mutations from 58 genes that were pan-cancer-based were combined from We used the same datasets to judge our model's ability to predict rare driver mutations based Driver and Passenger Mutations' Features Used to Train NBDriver are Significantly Although our method's focus was to identify missense driver mutations from sequenced cancer surrounding driver and passenger mutations obtained from sequenced cancer genomes. computational prediction of driver missense mutations," Cancer Res., vol. functionally validated cancer-related missense mutations," Genome Biology, vol. Figure 7: Differences in the distribution of features between driver and passenger mutations
cache = ./cache/10_1101-2021_02_09_430460.pdf
txt = ./txt/10_1101-2021_02_09_430460.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_08_430070
author = Zhang, Yao-zhong
title = On the application of BERT models for nanopore methylation detection
date = 2021
pages = 7
extension = .pdf
mime = application/pdf
words = 5183
sentences = 586
flesch = 60
summary = On the application of BERT models for nanopore methylation detection with deep learning models, have achieved significant performance improvements on nanopore methylation recurrent patterns of positional-signal-shift in the context window surrounding target 5-methylcytosine that the refined BERT model can achieve competitive or even better results than the state-of-the-art biRNN of datasets from the different research groups, BERT models demonstrate a good generalization Fig. 1: Basic BERT's and refined BERT's model structure used for methylation detection. a refined BERT model to take account of signal-shift patterns in the proposed refined BERT model achieves a competitive or even better result explore applying the BERT model for the nanopore methylation detection 2.2 Applying BERT models for nanopore methylation For the cross-sample evaluation, we train models on one dataset and test a BERT model to pay more attention to center positions. In-sample evaluation of different deep learning models on 5mC datasets.
cache = ./cache/10_1101-2021_02_08_430070.pdf
txt = ./txt/10_1101-2021_02_08_430070.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_09_430036
author = Goldsborough, Thibaut
title = A comparative study of genomic adaptations to low nitrogen availability in Genlisea aurea
date = 2021
pages = 7
extension = .pdf
mime = application/pdf
words = 3128
sentences = 477
flesch = 70
summary = A comparative study of genomic adaptations to low nitrogen availability in Genlisea aurea A comparative study of genomic adaptations to low nitrogen availability in Genlisea aurea is a carnivorous plant that grows on nitrogen-poor waterlogged sandstone aurea's genome, CDS and non-coding DNA 2) Determination of transcriptomic nitrogen content and codon usage bias associated with higher nitrogen content tRNAs (among codons that are coding for the same amino a considerably lower number of nitrogen atoms in its genome than the two other plant species. has higher nitrogen counts per molecular unit in genomic DNA, CDS, Non-Coding DNA, protein, aurea has a higher nitrogen usage in its DNA, RNA and proteins Figure 2: Average number of nitrogen atoms per molecular unit in genomic DNA, CDS, Non-Coding DNA, aurea had lower nitrogen content in tRNA sequences but not in other Figure 3: Bar graph representing the codon usage bias and tRNA nitrogen content in G.
cache = ./cache/10_1101-2021_02_09_430036.pdf
txt = ./txt/10_1101-2021_02_09_430036.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_08_428881
author = Lu, Yang Young
title = ACE: Explaining cluster from an adversarial perspective
date = 2021
pages = 12
extension = .pdf
mime = application/pdf
words = 7909
sentences = 790
flesch = 66
summary = A common workflow in single-cell RNA-seq analysis is to project the data to a latent space, cluster the cells in that space, and identify sets of marker genes that explain the differences among the nonlinear embedding model which maps the gene expression to the low-dimensional representation where the groups A notable feature of ACE's approach is that, by identifying genes jointly, the method moves away from the notion Input: gene expression matrix Deep autoencoder learns low-dimensional representation Embedding clustering Clustering is neuralized and concatenated with the encoder Differentiation analysis by ACE Output: gene relevance ACE takes as input a single-cell gene expression matrix and learns a low-dimensional representation for each Next, a neuralized version of the k-means algorithm is applied to the learned representation to identify cell groups. input gene expression profile that lead the neuralized clustering model to alter the assignment from one group to the other.
cache = ./cache/10_1101-2021_02_08_428881.pdf
txt = ./txt/10_1101-2021_02_08_428881.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_08_430343
author = Gibbs, David L
title = Patient-specific cell communication networks associate with disease progression in cancer
date = 2021
pages = 29
extension = .pdf
mime = application/pdf
words = 11335
sentences = 1445
flesch = 58
summary = tumor microenvironment, the method identified ligands, receptors and cells meeting certain criteria of 56 9,234 samples in The Cancer Genome Atlas (TCGA), starting from a network of 64 cell types and 1,894 62 Data sources including TCGA and cell-sorted gene expression, bulk tumor expression, cell type scores, 78 ligands and receptors for each of the 64 cell types in xCell, using the source gene expression data. With this procedure, a network scaffold is induced, where cells produce ligands that bind to receptors on 113 (PFI) and tumor stage for each sample, a matrix of patient-specific edge weights was constructed 206 number of high weight edges in each tumor type did not associate with the number of samples, as might 254 in the tumor stage contrast, a majority of ligand-producing cells include GMP cells, Osteoblasts, MSC 283 In the PFI results, Th1 cells appeared in 13 high scoring edges in SKCM, all with 394
cache = ./cache/10_1101-2021_02_08_430343.pdf
txt = ./txt/10_1101-2021_02_08_430343.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_08_430275
author = Zhang, Jianbo
title = Next-generation sequencing-based bulked segregant analysis without sequencing the parental genomes
date = 2021
pages = 6
extension = .pdf
mime = application/pdf
words = 6404
sentences = 694
flesch = 68
summary = Next-generation sequencing-based bulked segregant analysis without sequencing the parental genomes identified using BSA-Seq, a technology in which next-generation sequencing (NGS) is applied to bulked segregant analysis (BSA). recently developed the significant structural variant method for BSASeq data analysis that exhibits higher detection power than standard to analyze BSA-Seq data in which genome sequences of one parent served as the reference sequences in genotype calling, and thus We analyzed a public BSA-Seq dataset using our modified method and the standard allele frequency and Gmethod allows the detection of such associations without sequencing the parental genomes, leading to further lower the the BSA-Seq data with the genome sequences of both the parents101 when the parental genome sequences are used to aid BSA-Seq data 193 The allele frequency method: The ΔAF value of each SNP in 267 BSA-Seq data analysis using the genome sequences of both the parents and the bulks. BSA-Seq data analysis using only the bulk genome sequences.
cache = ./cache/10_1101-2021_02_08_430275.pdf
txt = ./txt/10_1101-2021_02_08_430275.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_08_430270
author = Gerard, David
title = Scalable Bias-corrected Linkage Disequilibrium Estimation Under Genotype Uncertainty
date = 2021
pages = 22
extension = .pdf
mime = application/pdf
words = 7219
sentences = 1582
flesch = 69
summary = Scalable Bias-corrected Linkage Disequilibrium Estimation Under Genotype Uncertainty Keywords and phrases: attenuation bias, genotype likelihood, linkage disequilibrium, polyploidy, reliability ratio. Let XiA and XiB be the posterior means at loci A and B for individual Equations (5)–(7) take the naive estimators most researchers use in practice (the sample covariance/correlation of posterior means) and inflate these by a multiplicative effect. Gerard and Ferrão, 2019] to obtain the posterior moments for each individual's genotype at each SNP reliability ratios of most SNPs only increase their correlation estimates by less than 10%. To evaluate the LD estimates of high reliability ratio SNPs, we calculated the MLEs for ρ2 applied to simple linear regression with an additive effects model (where the SNP effect is proportional to the dosage), result in the standard ordinary least squares estimates when using the extreme reliability ratio of PotVar0080327, the genotype-error adjusted correlation estimate is -1.
cache = ./cache/10_1101-2021_02_08_430270.pdf
txt = ./txt/10_1101-2021_02_08_430270.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_10_430604
author = Youngblut, Nicholas D.
title = Struo2: efficient metagenome profiling database construction for ever-expanding microbial genome datasets
date = 2021
pages = 4
extension = .pdf
mime = application/pdf
words = 1409
sentences = 157
flesch = 56
summary = Struo2: efficient metagenome profiling database construction for ever-expanding microbial genome datasets 1 Struo2: efficient metagenome profiling database construction for ever-expanding 10 Mapping metagenome reads to reference databases is the standard approach for 12 reference databases often lack recently generated genomic data such as 15 method for constructing custom databases; however, the pipeline does not scale well with the 17 not allow for efficient database updating as new data are generated. 20 HUMAnN3 databases that can be easily updated with new genomes and/or individual gene Struo2 enables feasible database generation for continually increasing large-scale 25 ● Pre-built databases: http://ftp.tue.mpg.de/ebio/projects/struo2/ 26 ● Utility tools: https://github.com/nick-youngblut/gtdb_to_taxdump 28 Metagenome profiling involves mapping reads to reference sequence databases and is 39 computational resources, which led us to create Struo for straight-forward custom metagenome 54 CPU hours per genome versus ~2.4 for Struo (Figure 1B). 67 taxonomy (available at https://github.com/nick-youngblut/gtdb_to_taxdump ). (2020) Struo: a pipeline for building custom databases for
cache = ./cache/10_1101-2021_02_10_430604.pdf
txt = ./txt/10_1101-2021_02_10_430604.txt
=== reduce.pl bib ===
id = 10_1101-2021_02_08_430280
author = Kasukurthi, Mohan V
title = SALTS – SURFR (sncRNA) And LAGOOn (lncRNA) Transcriptomics Suite
date = 2021
pages = 23
extension = .pdf
mime = application/pdf
words = 12363
sentences = 1218
flesch = 58
summary = given transcriptome provided as either a raw user-generated RNA-Seq dataset or NCBI SRR file identifier. SURFR identifies all ncRNA fragments (both annotated and novel) and their expressions in up to ten datasets per comprehensively compare all fragment expressions identified in up to 30 individual datasets by entering multiple SURFR session IDs window detailing each fragment identified in the individual, selected small RNA-Seq dataset. of the results page redirects the user to a SURFR window detailing the expressions of all full length sncRNAs in the provided datasets. Fragments" window (Figure 2D) for each fragment identified in the individual, selected small RNA-Seq dataset within its host gene along with the fragment's expression (RPM) in each individual small RNA-Seq dataset, and lncRNAs expressed in a given human transcriptome from either a user-provided RNA-Seq dataset or publically More importantly, however, LAGOOn identified MALAT1 as the most highly expressed lncRNA in MDAMB-231 breast cancer cells (Figure 9).
cache = ./cache/10_1101-2021_02_08_430280.pdf
txt = ./txt/10_1101-2021_02_08_430280.txt
=== reduce.pl bib ===
id = 10_1101-2020_02_04_934216
author = Kirchoff, Kathryn E.
title = EMBER: Multi-label prediction of kinase-substrate phosphorylation events through deep learning
date = 2021
pages = 13
extension = .pdf
mime = application/pdf
words = 8121
sentences = 726
flesch = 59
summary = EMBER: Multi-label prediction of kinase-substrate phosphorylation events through deep learning task of kinase-motif phosphorylation prediction as a multi-label kinase or substrate, as well as protein scaffolds that facilitate structural orientation and downstream catalysis of the reaction, modify the efficacy of motif phosphorylation. prediction of phosphorylation events), a deep learning approach for predicting multi-label kinase-motif phosphorylation relationships. example, the TLK kinase family only has nine positive labels (verified TLK-motif interactions) and more than 10,000 resulting data set is comprised of 7302 phosphorylatable motifs and their reaction-associated kinase families (Table 1). The final output is a vector, k, of length eight, where each value corresponds to the probability that the motif a was phosphorylated by one of the kinase families indicated in We sought to illuminate the relationship between kinase-family dissimilarity and phosphorylated motif-group dissimilarity described results provide motivation to incorporate both motif dissimilarity and kinase relatedness into the predictive model, as of kinase-motif prediction compared to the single-label approaches.
cache = ./cache/10_1101-2020_02_04_934216.pdf
txt = ./txt/10_1101-2020_02_04_934216.txt
=== reduce.pl bib ===
id = 10_1101-2020_09_02_279521
author = Abi Nader, Clément
title = Simulating the outcome of amyloid treatments in Alzheimer’s disease from imaging and clinical data
date = 2021
pages = 32
extension = .pdf
mime = application/pdf
words = 12164
sentences = 1038
flesch = 56
summary = Simulating the outcome of amyloid treatments in Alzheimer's disease from imaging and clinical data When applied to multimodal imaging and clinical data from the Alzheimer's Disease Neuroimaging Initiative our * Data used in preparation of this article were obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database Keywords : Alzheimer's Disease ; Clinical trials ; Disease progression; Amyloid hypothesis; of large datasets of different data modalities, such as clinical scores, or brain imaging measures to model Alzheimer's disease progression based on specific assumptions on the biochemical combining traditional DPMs with dynamical models of Alzheimer's disease progression. In this work we present a novel computational model of Alzheimer's disease progression to multi-modal imaging and clinical data from the Alzheimer's Disease Neuroimaging To simulate the long-term progression of Alzheimer's disease we first project the AD subjects Figure 3 Model-based progression of Alzheimer's disease. clinical data, based on the estimation of latent biomarkers' relationships governing Alzheimer's
cache = ./cache/10_1101-2020_09_02_279521.pdf
txt = ./txt/10_1101-2020_09_02_279521.txt
Building ./etc/reader.txt
10_1101-2021_02_09_430460
10_1101-727867
10_1101-2021_02_13_429885
10_1101-2021_02_09_430363
10_1101-2021_02_13_429885
10_1101-2021_02_09_430460
number of items: 50
sum of words: 466,439
average size in words: 9,328
average readability score: 61
nouns: preprint; data; cell; genes; version; gene; copyright; review; author; holder; funder; peer; license; %; cells; preprintthis; analysis; methods; perpetuity; model; licenseavailable; number; set; sequence; expression; sequences; results; datasets; cancer; values; seq; method; dataset; figure; models; mutations; value; p; information; ad; sample; time; types; structure; sets; approach; k; samples; size; drug
verbs: is; are; was; be; has; using; were; posted; certified; made; display; granted; used; based; biorxiv; have; https://www.zotero.org/google-docs/?hsltkm; associated; �; been; selected; set; given; found; compared; shown; obtained; identified; including; use; generated; show; see; performed; identify; shows; provided; do; known; related; developed; described; defined; applied; following; calculated; provide; expected; expressed; proposed
adjectives: -; single; different; available; other; high; such; specific; non; same; genome; human; new; more; multiple; similar; large; first; small; many; low; random; clinical; best; individual; significant; average; linear; functional; higher; most; genomic; original; biological; international; polar; wide; relative; possible; subject; additional; computational; total; multi; standard; real; full; top; various; dimensional
adverbs: not; also; only; more; then; however; e.g.; well; thus; most; as; here; first; very; respectively; highly; therefore; out; often; finally; further; even; significantly; so; hence; previously; top; still; fully; up; instead; much; currently; at; less; specifically; recently; now; randomly; least; directly; similarly; rather; next; already; easily; better; usually; generally; moreover
pronouns: we; it; our; their; its; they; i; them; us; one; itself; https://doi.org/10.1101/2020.09.21.305516; you; themselves; your; https://doi.org/10.1101/2020.11.17.386649; https://doi.org/10.1101/2020.01.28.923532; he; 𝒙; sample; u; s; https://doi.org/10.1101/2021.02.10.430705; ∆̂′; ours; m′; https://doi.org/10.1101/2021.02.12.430830; his; 𝑙𝑎; λ; ourselves; n; my; il-; https://doi.org/10.1101/2021.02.08.430280; http://paperpile.com/b/5tes3g/x5omi; 𝜟; 𝑒𝑖; 𝑆∗of; ’s; τ2; α; ʻʻuniprotdom_postmodenzʼ; y∗; yij; yes; whole-644; when398; uw; us-
proper nouns: al; february; et; international; j.; m.; .; nc; rna; s.; d.; c.; a.; nd; k; m; r.; c; l.; p.; s; j; b.; e.; g.; figure; fig; t.; a; k.; t; by; supplementary; n; h.; µm; r; seq; n.; e; d; http://creativecommons.org/licenses/by-nc/4.0/; data; f.; alzheimer; b; genome; li; y.; y
keywords: february; international; rna; cell; gene; seq; figure; supplementary; mutation; fig; data; alzheimer; set; sequence; sars; pca; motif; method; gwas; covid-19; cancer; δaf; vql; vp35; vcf; vaf; utr; usc; umls; type; tet; target; swarm; surfr; subject; struo; strain; stad; ssu; sparc; snp; skcm; single; siamese; sds; sda; scc; rrna; ribovore; remdesivir
one topic; one dimension: 10
file(s): ./cache/10_1101-2020_09_21_305516.pdf
titles(s): Copy-scAT: Deconvoluting single-cell chromatin accessibility of genetic subclones in cancer
three topics; one dimension: 10; org; 10
file(s): ./cache/10_1101-2021_02_09_430536.pdf, ./cache/10_1101-2021_02_09_430460.pdf, ./cache/10_1101-2021_02_11_430762.pdf
titles(s): Genome-wide prediction and integrative functional characterization of Alzheimer’s disease-associated genes | Sequence neighborhoods enable reliable prediction of pathogenic mutations in cancer genomes | Ribovore: ribosomal RNA sequence analysis for GenBank submissions and database curation
five topics; three dimensions: 10 org doi; 10 org 2021; org https google; http com https; 10 sequences org
file(s): ./cache/10_1101-727867.pdf, ./cache/10_1101-2021_02_09_430536.pdf, ./cache/10_1101-2021_02_09_430460.pdf, ./cache/10_1101-2021_02_08_430343.pdf, ./cache/10_1101-2021_02_11_430762.pdf
titles(s): scAEspy: a tool for autoencoder-based analysis of single-cell RNA sequencing data | Genome-wide prediction and integrative functional characterization of Alzheimer’s disease-associated genes | Sequence neighborhoods enable reliable prediction of pathogenic mutations in cancer genomes | Patient-specific cell communication networks associate with disease progression in cancer | Ribovore: ribosomal RNA sequence analysis for GenBank submissions and database curation
Type: biorxiv
title: neuroscience-from-bioarxiv
date: 2021-02-14
time: 21:20
username: emorgan
patron: Eric Morgan
email: emorgan@nd.edu
input: eMBISSE4cL.xml
==== make-pages.sh htm files
==== make-pages.sh complex files
==== make-pages.sh named enities
==== making bibliographics
id: 10_1101-2021_02_10_430623
author: Aberasturi, Dillon
title: “Single-subject studies”-derived analyses unveil altered biomechanisms between very small cohorts: implications for rare diseases
date: 2021
words: 9478
sentences: 748
pages: 9
flesch: 58
cache: ./cache/10_1101-2021_02_10_430623.pdf
txt: ./txt/10_1101-2021_02_10_430623.txt
summary: published S3-type N-of-1-pathways MixEnrich to two paired samples (e.g., diseased vs unaffected tissues) for determining patient-specific enriched genes sets: Odds Ratios (S3-OR) and S3-variance using these models to derive effect sizes and statistical significance in singlesubject studies of transcriptomes, these samples are isogenic or quasi-isogenic, and thus do not necessarily generalize to a group of subjects (cohort-level signal). The novel bioinformatic method identifies meaningful biomechanism differences between very small cohorts by using single-subject-study-derived effect sizes for gene sets. (B) For the generalized linear model-based analyses, we applied a different filtering process to the raw data where we eliminated all the transcripts with 0 counts for each subject and then calculated the coefficient 2.3 Description of the Generalized Linear Models and application of Inter-N-of-1 methods for small cohort comparison and their evaluation in the Breast Cancer Data the analysis of subsets of the TCGA Breast Cancer data, genes were declared differentially expressed if their abs(log2FC) > log2(1.2) and their FDR-adjusted p-value <
id: 10_1101-2020_09_02_279521
author: Abi Nader, Clément
title: Simulating the outcome of amyloid treatments in Alzheimer’s disease from imaging and clinical data
date: 2021
words: 12164
sentences: 1038
pages: 32
flesch: 56
cache: ./cache/10_1101-2020_09_02_279521.pdf
txt: ./txt/10_1101-2020_09_02_279521.txt
summary: Simulating the outcome of amyloid treatments in Alzheimer''s disease from imaging and clinical data When applied to multimodal imaging and clinical data from the Alzheimer''s Disease Neuroimaging Initiative our * Data used in preparation of this article were obtained from the Alzheimer''s Disease Neuroimaging Initiative (ADNI) database Keywords : Alzheimer''s Disease ; Clinical trials ; Disease progression; Amyloid hypothesis; of large datasets of different data modalities, such as clinical scores, or brain imaging measures to model Alzheimer''s disease progression based on specific assumptions on the biochemical combining traditional DPMs with dynamical models of Alzheimer''s disease progression. In this work we present a novel computational model of Alzheimer''s disease progression to multi-modal imaging and clinical data from the Alzheimer''s Disease Neuroimaging To simulate the long-term progression of Alzheimer''s disease we first project the AD subjects Figure 3 Model-based progression of Alzheimer''s disease. clinical data, based on the estimation of latent biomarkers'' relationships governing Alzheimer''s
id: 10_1101-2020_01_28_923532
author: Ahmadi, Saba
title: The Landscape of Precision Cancer Combination Therapy: A Single-Cell Perspective
date: 2021
words: 16705
sentences: 1572
pages: 46
flesch: 66
cache: ./cache/10_1101-2020_01_28_923532.pdf
txt: ./txt/10_1101-2020_01_28_923532.txt
summary: We focus our analysis on genes encoding protein targets that encode receptors on the cell all "modular", including one part that specifically targets the tumor cell via one gene/protein and MadHitter and each patient receives an optimal personalized combination of targeted therapies from a prespecified set (pill bottle). Cohort and Individual Target Set Sizes as Functions of Tumor Killing and Given the single-cell tumor data sets and the ILP optimization framework described above, we filtering as this threshold is decreased), decreases the size of the target cell surface receptor gene heterogeneity of the cancer, number of patients within the data set, size of target gene set, lack of used for filtering the gene set to avoid targeting non-cancerous tissues. the genes in the optimal target set, the expression of that gene in that non-tumor cell exceeds the set of genes which is known to be targetable to cell 𝐶.
id: 10_1101-2021_02_12_430764
author: Ascensión, Alex M.
title: Triku: a feature selection method based on nearest neighbors for single-cell data
date: 2021
words: 9518
sentences: 1135
pages: 18
flesch: 64
cache: ./cache/10_1101-2021_02_12_430764.pdf
txt: ./txt/10_1101-2021_02_12_430764.txt
summary: Triku: a feature selection method based on nearest neighbors for single-cell data Triku is a feature selection method that favours genes defining the main Single-cell RNA sequencing (scRNA-seq) is a powerful technology to study the biological heterogeneity of tissues at the individual cell level, allowing the characterization of new cell populations and cell states–i.e. cell types responding to different scRNA-seq datasets are multidimensional, i.e. the expression profile per cell consists of multiple genes. feature selection method: 1) the ability to recover basic dataset structure (main cell low, meaning that features selected with the different methods yielded clustering solutions that were quite similar to the manually-labeled cell types, although there are We first studied the expression pattern of genes selected by triku and other methods, To evaluate the cluster expression of selected genes in benchmarking datasets, for proteins within the genes selected by different FS methods in the two sets of benchmarking datasets.
id: 10_1101-2021_02_11_430806
author: Badaczewska-Dawid, Aleksandra
title: BIAPSS - BioInformatic Analysis of liquid-liquid Phase-Separating protein Sequences
date: 2021
words: 2698
sentences: 301
pages: 3
flesch: 53
cache: ./cache/10_1101-2021_02_11_430806.pdf
txt: ./txt/10_1101-2021_02_11_430806.txt
summary: BIAPSS BioInformatic Analysis of liquid-liquid Phase-Separating protein Sequences web platform named BIAPSS (BioInformatic Analysis of liquidliquid Phase-Separating protein Sequences) which offers the users interactive data analytic tools for facilitating the discovery of statistically significant sequence signals for proteins with Phase-Separating protein Sequences. The objective of BIAPSS is to enable a rapid and on-the-fly deep statistical analysis of LLPS-driver proteins using the pool of sequences with The comparison to benchmarks of various protein groups enables statistical inference of specific phase-separating affinities. Furthermore, the residue-resolution biophysical regularities inferred from BIAPSS will help not only to accurately identify regions prone to phase separation but also to design sequence modifications targeting various biomedical applications. for comprehensive sequence-based analysis of LLPS proteins. the driving forces for phase separation of prion-like RNA binding proteins. disordered protein regions encode a driving force for liquid-liquid phase separation? of proteins driving liquid-liquid phase separation.
id: 10_1101-2021_02_10_430563
author: Bandrowski, Anita
title: SPARC Data Structure: Rationale and Design of a FAIR Standard for Biomedical Research Data
date: 2021
words: 10901
sentences: 1026
pages: 16
flesch: 48
cache: ./cache/10_1101-2021_02_10_430563.pdf
txt: ./txt/10_1101-2021_02_10_430563.txt
summary: investigators across the SPARC consortium that provide key details about organ-specific circuitry, including structural (BIDS), the SDS has been designed to capture the large variety of data generated by SPARC investigators who are description of the SPARC curation process and the automated tools for complying with the SDS, including the SDS validator and Software to Organize Data Automatically (SODA) for SPARC. required to organize their data files and metadata organized according to the SPARC Data Structure data according to the SPARC Dataset Structure. is the preferred file format for tabular data in SPARC, the Data files are organized into 3 different top-level folders, The organization structure of the files and folders for a SPARC dataset. https://github.com/SciCrunch/sparc-curation/releases/tag/dataset-template-1.2.3 https://github.com/SciCrunch/sparc-curation/releases/tag/dataset-template-1.2.3 investigators include folders that organize data along a from these subjects, data files are organized within fields, the curation team developed a SPARC Dataset files/folders, and share datasets with the SPARC
id: 10_1101-2021_02_09_430460
author: Banerjee, Shayantan
title: Sequence neighborhoods enable reliable prediction of pathogenic mutations in cancer genomes
date: 2021
words: 15659
sentences: 1731
pages: 39
flesch: 40
cache: ./cache/10_1101-2021_02_09_430460.pdf
txt: ./txt/10_1101-2021_02_09_430460.txt
summary: experimentally validated cancer mutation data in this study, we explored various string-based evolutionary features resulted in the development of a pan-cancer mutation effect prediction Distinguishing between driver and passenger mutations from sequenced cancer genomes is a Recent studies have identified specific signatures or patterns of mutations in different cancer than passenger mutations and built probabilistic models to identify driver genes that had this study, missense mutations from 58 genes that were pan-cancer-based were combined from We used the same datasets to judge our model''s ability to predict rare driver mutations based Driver and Passenger Mutations'' Features Used to Train NBDriver are Significantly Although our method''s focus was to identify missense driver mutations from sequenced cancer surrounding driver and passenger mutations obtained from sequenced cancer genomes. computational prediction of driver missense mutations," Cancer Res., vol. functionally validated cancer-related missense mutations," Genome Biology, vol. Figure 7: Differences in the distribution of features between driver and passenger mutations
id: 10_1101-2021_02_09_430363
author: Bayer, Johanna M. M.
title: Accommodating site variation in neuroimaging data using hierarchical and Bayesian models
date: 2021
words: 13439
sentences: 1891
pages: 20
flesch: 70
cache: ./cache/10_1101-2021_02_09_430363.pdf
txt: ./txt/10_1101-2021_02_09_430363.txt
summary: Accommodating site variation in neuroimaging data using hierarchical and Bayesian models The potential of normative modeling to make individualized predictions has led to structural neuroimaging results that go beyond the case-control approach. in a similar way for multi-site modeling in a pooled neuroimaging data set, which contained 7499 participants that org/abide/) data set to compare a non-linear, Gaussian version of the model, to a linear hierarchical Bayesian version and mathematical description of our approach to include site as predictor in a normative hierarchical Bayesian model. With the aim to create reliable normative models in multi-site neuroimaging data, we developed and compared two model is also able to capture non-linear effects between age and thickness of the cortical region ("Hierarchical Bayesian Gaussian Process term, which allows to model non-linear association between age and cortical thickness measures. The only models that perform better for most regions than the mean of the training data set are the Hierarchical Bayesian
id: 10_1101-2021_02_10_430367
author: Chen, Meili
title: Genome Warehouse: A Public Repository Housing Genome-scale Data
date: 2021
words: 4875
sentences: 656
pages: 18
flesch: 66
cache: ./cache/10_1101-2021_02_10_430367.pdf
txt: ./txt/10_1101-2021_02_10_430367.txt
summary: Running title: Chen M et al / Genome Assembly Data Repository 21 Genomics Data Center (NGDC), part of the China National Center for Bioinformation 40 archive high-quality genome sequences and annotations, GWH is equipped with a 46 Collectively, GWH serves as an important resource for genome-scale data 51 https://bigd.big.ac.cn/) [13], the aim of GWH is to accept data submissions worldwide 78 GWH is a centralized resource housing genome-scale data, with the purpose to 105 GWH not only accepts genome assembly associated data through an on-line 111 GWH will assign a unique accession number to the submitted genome assembly upon 149 GWH provides data visualization for both genome 163 Collectively, GWH is a user-friendly portal for genome data submission, release, and 209 Database resources of the National Genomics Data 302 Genome assembly accession number is prefixed with "GWH", followed by four 334 Genome assembly accession number is prefixed with "GWH", followed by four 334
id: 10_1101-2021_02_12_430979
author: Da Silva, Kévin
title: StrainFLAIR: Strain-level profiling of metagenomic samples using variation graphs
date: 2021
words: 10624
sentences: 992
pages: 20
flesch: 66
cache: ./cache/10_1101-2021_02_12_430979.pdf
txt: ./txt/10_1101-2021_02_12_430979.txt
summary: StrainFLAIR: Strain-level profiling of metagenomic samples using variation graphs results show that StrainFLAIR was able to distinguish and estimate the abundances of close strains, as approaches to handle multiple similar genomes as with strains use gene clustering and then select the64 StrainFLAIR assigns and estimates species and strain abundances of a bacterial metagenomic sample graph, called the "node abundance", is computed, first focusing on unique mapped reads (first step). Strain-level abundances are then obtained by exploiting the specific genes of each reference genome188 from the reference variation graph thus simulating a new strain to be identified and quantified.231 strains from a sequenced sample, mapped onto this graph.343 Reference strains relative abundances expected and computed by StrainFLAIR or Reference strains relative abundances expected and computed by StrainFLAIR or Reference strains relative abundances expected and computed by StrainFLAIR or Reference strains relative abundances expected and computed by StrainFLAIR or
id: 10_1101-2020_11_17_386649
author: Danciu, Daniel
title: Topology-based Sparsification of Graph Annotations
date: 2021
words: 8205
sentences: 774
pages: 15
flesch: 67
cache: ./cache/10_1101-2020_11_17_386649.pdf
txt: ./txt/10_1101-2020_11_17_386649.txt
summary: Experiments on 10,000 RNA-seq datasets show that RowDiff combined with MultiBRWT results in a 30% reduction in annotation footprint over Mantis-MST, the previously known most a binary matrix, where the k-mer set indexes the rows and each annotation label specifies a column. Starting from any vertex in the de Bruijn graph, Algorithm 1 defines a traversal leading to an anchor Each row in a RowDiff-transformed annotation matrix has the same or fewer set bits than A naı̈ve implementation of the RowDiff construction would be to load the matrix A in memory, and gradually replace its rows with their sparsified counterpart, while traversing the graph. We now note that, when querying annotations for paths in the graph, or sets of rows corresponding to vertices We constructed annotated de Bruijn graphs from the RNA-Seq data set in the same We now compare the representation size for RowDiff and other state-of-the-art graph annotation compression methods.
id: 10_1101-2021_02_08_430270
author: Gerard, David
title: Scalable Bias-corrected Linkage Disequilibrium Estimation Under Genotype Uncertainty
date: 2021
words: 7219
sentences: 1582
pages: 22
flesch: 69
cache: ./cache/10_1101-2021_02_08_430270.pdf
txt: ./txt/10_1101-2021_02_08_430270.txt
summary: Scalable Bias-corrected Linkage Disequilibrium Estimation Under Genotype Uncertainty Keywords and phrases: attenuation bias, genotype likelihood, linkage disequilibrium, polyploidy, reliability ratio. Let XiA and XiB be the posterior means at loci A and B for individual Equations (5)–(7) take the naive estimators most researchers use in practice (the sample covariance/correlation of posterior means) and inflate these by a multiplicative effect. Gerard and Ferrão, 2019] to obtain the posterior moments for each individual''s genotype at each SNP reliability ratios of most SNPs only increase their correlation estimates by less than 10%. To evaluate the LD estimates of high reliability ratio SNPs, we calculated the MLEs for ρ2 applied to simple linear regression with an additive effects model (where the SNP effect is proportional to the dosage), result in the standard ordinary least squares estimates when using the extreme reliability ratio of PotVar0080327, the genotype-error adjusted correlation estimate is -1.
id: 10_1101-2021_02_12_430963
author: Gerber, Stefan
title: Streamlining differential exon and 3'' UTR usage with diffUTR
date: 2021
words: 6710
sentences: 896
pages: 17
flesch: 62
cache: ./cache/10_1101-2021_02_12_430963.pdf
txt: ./txt/10_1101-2021_02_12_430963.txt
summary: adenylation site databases to enable differential 3'' UTR usage analysis. Conclusions: diffUTR enables differential 3'' UTR analysis and more generally facilitates DEU9 Popular bin-based DEU methods are provided by the limma [25,24], edgeR [23] and DEXSeq [22]41 Bins are prepared from various types of gene annotations as well as, optionally, additional APA-driven segmentation and extension, then read counts among statistically-significant genes, especially for bins with a higher expression (Figure 3A).78 diffUTR provides three main plot types to explore differential bin usage analyses, each with a88 Plotted are the UTR bins found statistically significant (binand gene-level FDR deuBinPlot (Figure 4B) provides bin-level statistic plots for a given gene, similar to those99 than CDS bins, including counts of 3'' UTR when calculating overall gene expression could under-121 diffUTR streamlines DEU analysis and outperforms alternative methods in inferring UTR changes,127 For differential UTR analysis, gene-level results are ob-206
id: 10_1101-2021_02_12_430830
author: Gergely, Tibély
title: Simultaneous estimation of per cell division mutation rate and turnover rate from bulk tumor sequence data
date: 2021
words: 8181
sentences: 793
pages: 19
flesch: 68
cache: ./cache/10_1101-2021_02_12_430830.pdf
txt: ./txt/10_1101-2021_02_12_430830.txt
summary: Simultaneous estimation of per cell division mutation rate and turnover rate from bulk tumor sequence data widely available bulk sequencing data where mutations from individual cells are and genomic mutation rate from bulk sequencing data. based on the maximum likelihood estimation of the parameters of a generative model of tumor growth and mutations. human hepatocellular carcinoma sample reveals an elevated per cell division mutation rate and high cell turnover. Due to the limitations of bulk sequencing, which only essays mutation frequencies for a population of cells from each tumor sample and does not The estimation is based on a maximum likelihood fit of the parameters of a birth-death model to the measured mutant and be estimated from readcount data, to separate the effects of the mutation rate We use pre-generated division trees from the ELynx suite at predetermined turnover rate values. Using the turnover rate, we also estimated the number of cell
id: 10_1101-2021_02_08_430343
author: Gibbs, David L
title: Patient-specific cell communication networks associate with disease progression in cancer
date: 2021
words: 11335
sentences: 1445
pages: 29
flesch: 58
cache: ./cache/10_1101-2021_02_08_430343.pdf
txt: ./txt/10_1101-2021_02_08_430343.txt
summary: tumor microenvironment, the method identified ligands, receptors and cells meeting certain criteria of 56 9,234 samples in The Cancer Genome Atlas (TCGA), starting from a network of 64 cell types and 1,894 62 Data sources including TCGA and cell-sorted gene expression, bulk tumor expression, cell type scores, 78 ligands and receptors for each of the 64 cell types in xCell, using the source gene expression data. With this procedure, a network scaffold is induced, where cells produce ligands that bind to receptors on 113 (PFI) and tumor stage for each sample, a matrix of patient-specific edge weights was constructed 206 number of high weight edges in each tumor type did not associate with the number of samples, as might 254 in the tumor stage contrast, a majority of ligand-producing cells include GMP cells, Osteoblasts, MSC 283 In the PFI results, Th1 cells appeared in 13 high scoring edges in SKCM, all with 394
id: 10_1101-2021_02_09_430036
author: Goldsborough, Thibaut
title: A comparative study of genomic adaptations to low nitrogen availability in Genlisea aurea
date: 2021
words: 3128
sentences: 477
pages: 7
flesch: 70
cache: ./cache/10_1101-2021_02_09_430036.pdf
txt: ./txt/10_1101-2021_02_09_430036.txt
summary: A comparative study of genomic adaptations to low nitrogen availability in Genlisea aurea A comparative study of genomic adaptations to low nitrogen availability in Genlisea aurea is a carnivorous plant that grows on nitrogen-poor waterlogged sandstone aurea''s genome, CDS and non-coding DNA 2) Determination of transcriptomic nitrogen content and codon usage bias associated with higher nitrogen content tRNAs (among codons that are coding for the same amino a considerably lower number of nitrogen atoms in its genome than the two other plant species. has higher nitrogen counts per molecular unit in genomic DNA, CDS, Non-Coding DNA, protein, aurea has a higher nitrogen usage in its DNA, RNA and proteins Figure 2: Average number of nitrogen atoms per molecular unit in genomic DNA, CDS, Non-Coding DNA, aurea had lower nitrogen content in tRNA sequences but not in other Figure 3: Bar graph representing the codon usage bias and tRNA nitrogen content in G.
id: 10_1101-2021_02_11_430695
author: Gordon-Rodriguez, Elliott
title: Learning Sparse Log-Ratios for High-Throughput Sequencing Data
date: 2021
words: 7973
sentences: 817
pages: 12
flesch: 60
cache: ./cache/10_1101-2021_02_11_430695.pdf
txt: ./txt/10_1101-2021_02_11_430695.txt
summary: Log-ratios are an important class of features for analyzing high-throughput sequencing (HTS) metagenomic data for HTS data, and more generally, high-dimensional CoDa. Unlike existing methods, CoDaCoRe is simultaneously scalable, interpretable, sparse, and accurate. unlabelled datasets, {xi}ni=1, as a method for identiLearning Sparse Log-Ratios for High-Throughput Sequencing Data CoDaCoRe variable selection for the first (most explanatory) log-ratio on the Crohn disease data (Rivera-Pinto et al., 2018). more generally, in the field of CoDa. Learning Sparse Log-Ratios for High-Throughput Sequencing Data Learning Sparse Log-Ratios for High-Throughput Sequencing Data Learning Sparse Log-Ratios for High-Throughput Sequencing Data Learning Sparse Log-Ratios for High-Throughput Sequencing Data Learning Sparse Log-Ratios for High-Throughput Sequencing Data Learning Sparse Log-Ratios for High-Throughput Sequencing Data Learning Sparse Log-Ratios for High-Throughput Sequencing Data Learning Sparse Log-Ratios for High-Throughput Sequencing Data Learning Sparse Log-Ratios for High-Throughput Sequencing Data Learning Sparse Log-Ratios for High-Throughput Sequencing Data Learning Sparse Log-Ratios for High-Throughput Sequencing Data Learning Sparse Log-Ratios for High-Throughput Sequencing Data
id: 10_1101-2020_09_23_310276
author: Greenfest-Allen, Emily
title: NIAGADS Alzheimer''s GenomicsDB: A resource for exploring Alzheimer''s Disease genetic and genomic knowledge
date: 2021
words: 5987
sentences: 592
pages: 19
flesch: 52
cache: ./cache/10_1101-2020_09_23_310276.pdf
txt: ./txt/10_1101-2020_09_23_310276.txt
summary: The NIAGADS Alzheimer''s Genomics Database (GenomicsDB) is an interactive knowledgebase for Alzheimer''s disease (AD) genetics that provides access to GWAS summary statistics datasets The website makes available >70 genome-wide summary statistics datasets from GWAS and efficient real-time data analysis and variant or gene report generation. Gene reports provide summaries of co-located ADRD risk-associated variants and have pages linking summary statistics to variant and gene annotations, this resource makes these summary statistics available for browsing (on dataset, gene, and variant reports and as genome NIAGADS GenomicsDB variant reports and a track is available on the genome browser. The NIAGADS GenomicsDB includes allele frequency data from 1000 Genomes (phase 3, version visualizations for summarizing search results and annotations in gene and variant reports. compare NIAGADS GWAS summary statistics tracks to each other, against annotated gene or A detailed report is provided for each of the GWAS summary statistics and ADSP meta-analysis
id: 10_1101-2021_02_13_429885
author: Househam, Jacob
title: A fully automated approach for quality control of cancer mutations in the era of high-resolution whole genome sequencing
date: 2021
words: 10584
sentences: 1257
pages: 36
flesch: 49
cache: ./cache/10_1101-2021_02_13_429885.pdf
txt: ./txt/10_1101-2021_02_13_429885.txt
summary: know tumour purity and the ploidy of a CNA segment, then the VAF mutations mapped A fully automated approach for quality control of cancer mutations in the era of high-resolution whole genome sequencing. A fully automated approach for quality control of cancer mutations in the era of high-resolution whole genome sequencing. A fully automated approach for quality control of cancer mutations in the era of high-resolution whole genome sequencing. A fully automated approach for quality control of cancer mutations in the era of high-resolution whole genome sequencing. A fully automated approach for quality control of cancer mutations in the era of high-resolution whole genome sequencing. A fully automated approach for quality control of cancer mutations in the era of high-resolution whole genome sequencing. A fully automated approach for quality control of cancer mutations in the era of high-resolution whole genome sequencing. A fully automated approach for quality control of cancer mutations in the era of high-resolution whole genome sequencing.
id: 10_1101-2020_10_08_327718
author: Jambor, Helena
title: Creating Clear and Informative Image-based Figures for Scientific Publications
date: 2021
words: 12824
sentences: 1189
pages: 36
flesch: 56
cache: ./cache/10_1101-2020_10_08_327718.pdf
txt: ./txt/10_1101-2020_10_08_327718.txt
summary: journals in three fields; plant sciences, cell biology and physiology (n=580 papers). figures were uncommon (physiology 16%, cell biology 12%, plant sciences 2%). among papers published in top journals in plant sciences, cell biology and physiology. contained images (plant science: 68%, cell biology: 72%, physiology: 55%). in physiology (49%) and cell biology (55%), and 28% of plant science papers provided and 29% of plant sciences papers contained no scale information on any image. Some publications use insets to show the same image at two different scales (cell Figure 1: Image types and reporting of scale information and insets physiology and plant science papers contained some images that were inaccessible to B: Most papers explain colors in image-based figures, however, explanations are less Figure 4: Using scale bars to annotate image size Creating clear and informative image-based figures for scientific publications. Creating clear and informative image-based figures for scientific publications.
id: 10_1101-2021_02_08_430280
author: Kasukurthi, Mohan V
title: SALTS – SURFR (sncRNA) And LAGOOn (lncRNA) Transcriptomics Suite
date: 2021
words: 12363
sentences: 1218
pages: 23
flesch: 58
cache: ./cache/10_1101-2021_02_08_430280.pdf
txt: ./txt/10_1101-2021_02_08_430280.txt
summary: given transcriptome provided as either a raw user-generated RNA-Seq dataset or NCBI SRR file identifier. SURFR identifies all ncRNA fragments (both annotated and novel) and their expressions in up to ten datasets per comprehensively compare all fragment expressions identified in up to 30 individual datasets by entering multiple SURFR session IDs window detailing each fragment identified in the individual, selected small RNA-Seq dataset. of the results page redirects the user to a SURFR window detailing the expressions of all full length sncRNAs in the provided datasets. Fragments" window (Figure 2D) for each fragment identified in the individual, selected small RNA-Seq dataset within its host gene along with the fragment''s expression (RPM) in each individual small RNA-Seq dataset, and lncRNAs expressed in a given human transcriptome from either a user-provided RNA-Seq dataset or publically More importantly, however, LAGOOn identified MALAT1 as the most highly expressed lncRNA in MDAMB-231 breast cancer cells (Figure 9).
id: 10_1101-2021_02_10_430512
author: Kim, Catherine
title: Prediction of adverse drug reactions associated with drug-drug interactions using hierarchical classification
date: 2021
words: 11859
sentences: 1137
pages: 41
flesch: 56
cache: ./cache/10_1101-2021_02_10_430512.pdf
txt: ./txt/10_1101-2021_02_10_430512.txt
summary: into DDIs. In this study, a hierarchical machine learning model was created to predict DDIassociated ADRs and pharmacological insight thereof for any drug pair. drugs'' chemical structures as inputs to predict their target, enzyme, and transporter (TET) Development of RFCs for Prediction of Target, Enzyme, and Transporter Profiles of Drugs Development of a Model for Prediction of DDI-associated ADRs from TET Profiles of Drugs ADR prediction from Target, Enzyme, and Transporter Profiles of Drug Pairs To predict ADRs of a drug pair from its TET profiles, Random Forest Classifier (RFC), Application of the SVM model for DDI-associated ADRs Involving Three Major Drugs through predicted PRR changes of drug pairs upon removal of each of the targets, enzymes, and changes of drug pairs were predicted by the model upon removal of each of the targets, enzymes, Target, enzyme, and transporter (TET) profiles of atorvastatin and concomitant drugs,
id: 10_1101-2020_02_04_934216
author: Kirchoff, Kathryn E.
title: EMBER: Multi-label prediction of kinase-substrate phosphorylation events through deep learning
date: 2021
words: 8121
sentences: 726
pages: 13
flesch: 59
cache: ./cache/10_1101-2020_02_04_934216.pdf
txt: ./txt/10_1101-2020_02_04_934216.txt
summary: EMBER: Multi-label prediction of kinase-substrate phosphorylation events through deep learning task of kinase-motif phosphorylation prediction as a multi-label kinase or substrate, as well as protein scaffolds that facilitate structural orientation and downstream catalysis of the reaction, modify the efficacy of motif phosphorylation. prediction of phosphorylation events), a deep learning approach for predicting multi-label kinase-motif phosphorylation relationships. example, the TLK kinase family only has nine positive labels (verified TLK-motif interactions) and more than 10,000 resulting data set is comprised of 7302 phosphorylatable motifs and their reaction-associated kinase families (Table 1). The final output is a vector, k, of length eight, where each value corresponds to the probability that the motif a was phosphorylated by one of the kinase families indicated in We sought to illuminate the relationship between kinase-family dissimilarity and phosphorylated motif-group dissimilarity described results provide motivation to incorporate both motif dissimilarity and kinase relatedness into the predictive model, as of kinase-motif prediction compared to the single-label approaches.
id: 10_1101-2021_02_09_430536
author: Lin, Cui-Xiang
title: Genome-wide prediction and integrative functional characterization of Alzheimer’s disease-associated genes
date: 2021
words: 20656
sentences: 4864
pages: 47
flesch: 79
cache: ./cache/10_1101-2021_02_09_430536.pdf
txt: ./txt/10_1101-2021_02_09_430536.txt
summary: Genome-wide prediction and integrative functional characterization of Alzheimer''s disease-associated genes example, a module-trait network approach was proposed and applied to identify gene 63 functional enrichment-based approach to identify negative genes that are not likely 94 associated genes through an optimal selection of networks and machine learning 98 FGN, and prediction of AD-associated genes using machine learning models (Fig. 1). addition, we tested their enrichment in three AD-related gene sets associated with 122 The top-ranked genes are enriched in AD-associated functions and phenotypes 154 These results provide additional evidence that our predicted genes are associated with 194 The top-ranked genes are associated with AD based on miRNA-target networks 227 We investigated whether top-ranked genes were functionally related to AD-associated 229 We tested whether the top-ranked k genes were more likely to interact with AD-associated 576 related to AD-associated genes or miRNAs based on miRNA-target interaction networks.
id: 10_1101-2021_02_08_428881
author: Lu, Yang Young
title: ACE: Explaining cluster from an adversarial perspective
date: 2021
words: 7909
sentences: 790
pages: 12
flesch: 66
cache: ./cache/10_1101-2021_02_08_428881.pdf
txt: ./txt/10_1101-2021_02_08_428881.txt
summary: A common workflow in single-cell RNA-seq analysis is to project the data to a latent space, cluster the cells in that space, and identify sets of marker genes that explain the differences among the nonlinear embedding model which maps the gene expression to the low-dimensional representation where the groups A notable feature of ACE''s approach is that, by identifying genes jointly, the method moves away from the notion Input: gene expression matrix Deep autoencoder learns low-dimensional representation Embedding clustering Clustering is neuralized and concatenated with the encoder Differentiation analysis by ACE Output: gene relevance ACE takes as input a single-cell gene expression matrix and learns a low-dimensional representation for each Next, a neuralized version of the k-means algorithm is applied to the learned representation to identify cell groups. input gene expression profile that lead the neuralized clustering model to alter the assignment from one group to the other.
id: 10_1101-2021_02_12_430739
author: Malekian, Negin
title: Mutations in bdcA and valS correlate with quinolone resistance in wastewater Escherichia Coli
date: 2021
words: 7516
sentences: 1093
pages: 13
flesch: 70
cache: ./cache/10_1101-2021_02_12_430739.pdf
txt: ./txt/10_1101-2021_02_12_430739.txt
summary: Mutations in bdcA and valS correlate with quinolone resistance in wastewater Escherichia Coli Here, we systematically screen for candidate quinolone resistance-conferring mutations. coli and performed a genome-wide association study (GWAS) correlating over 200,000 mutations against quinolone resistance phenotypes. significant mutations including one located at the active site of the biofilm dispersal genes bdcA and six silent In summary, we demonstrate that GWAS effectively and comprehensively identifies resistance mutations Keywords: E Coli; Quinolone; Antibiotic Resistance; Genome-Wide Association Study (GWAS) direct route to resistance is mutations in the drug targets gyrA and parC. In summary, we aim to show that a bacterial genomewide association study can effectively and comprehensively identify targets relevant to antibiotic resistance. Based on representative resistance phenotypes, the authors selected 103 isolates for sequencing with Illumina MiSeq, 92 of which are available from coli bdcA may act indirectly on antibiotic resistance.
id: 10_1101-2021_02_12_430923
author: Modi, Vivek
title: Kincore: a web resource for structural classification of protein kinases and their inhibitors
date: 2021
words: 7913
sentences: 666
pages: 18
flesch: 62
cache: ./cache/10_1101-2021_02_12_430923.pdf
txt: ./txt/10_1101-2021_02_12_430923.txt
summary: Kincore: a web resource for structural classification of protein kinases and their inhibitors result, among the DFGin structures, we distinguished between the catalytically active kinase conformation pages for kinase phylogenetic groups, genes, conformational labels, PDBids, ligands and ligand types. options to download data – database tables as a tab separated files; the kinase structures as PyMOL Kincore provides conformational assignments and ligand type labels to protein kinase structures from Figure 1: Representative protein kinase structure (3ETA_A) displaying the residues used to define inhibitor The distribution of different ligand types across kinase conformations is provided in Table 1. Table 1: Distribution of ligand types across protein kinase conformations (Number of chains). including conformational and ligand type labels and C-helix position, kinase family, gene name, Uniprot provides the number of kinase chains in the group across different conformations with their Database table provides the list of all the PDB chains with conformational labels and ligand
id: 10_1101-2020_12_24_424317
author: Muazzam, Fariha
title: Multi-class Cancer Classification and Biomarker Identification using Deep Learning
date: 2021
words: 4252
sentences: 426
pages: 12
flesch: 57
cache: ./cache/10_1101-2020_12_24_424317.pdf
txt: ./txt/10_1101-2020_12_24_424317.txt
summary: classification, feature extraction and relevant gene identification through deep learning methods for 12 This research picks up from detection of different types of cancer RNA-Seq expressions using deep neural classification of gene expression profiles for different kinds of cancers. Hence, the effectiveness of deep learning models for feature extraction and relevant gene identification is performed revealing substantial results and they produced five high-ranked gene sets and reduced feature This study was aimed at classifying 12 types of cancer and identifying relevant genes and the results show were able to identify cancer-relevant pathways and genes for the sets, that different experiments generated, A deep learning approach for cancer detection and relevant gene Tumor gene expression data classification via sample expansionbased deep learning. Identification of a multi-cancer gene expression Multi-class Cancer Classification and Biomarker Identification using Deep Learning Multi-class Cancer Classification and Biomarker Identification using Deep Learning
id: 10_1101-2020_09_21_305516
author: Nikolic, Ana
title: Copy-scAT: Deconvoluting single-cell chromatin accessibility of genetic subclones in cancer
date: 2021
words: 10376
sentences: 1280
pages: 32
flesch: 67
cache: ./cache/10_1101-2020_09_21_305516.pdf
txt: ./txt/10_1101-2020_09_21_305516.txt
summary: Copy-scAT: Deconvoluting single-cell chromatin accessibility of genetic subclones in cancer 1 Copy-scAT: Deconvoluting single-cell chromatin accessibility of genetic subclones in cancer 1 uses single-cell epigenomic data to infer copy number variants (CNVs) that define cancer cells. We have tested the ability of Copy-scAT to use scATAC data to call CNVs with three different approaches 100 genome sequencing (WGS) data for adult GBM (aGBM) surgical resections (n = 4 samples, 3,647 cells). adult GBM samples identified using both methods, versus total numbers of gains detected by scATAC or 160 Number of chromosome-arm level gains detected in adult GBM samples identified using both methods, 163 (c) Multiple myeloma samples were profiled by both scATAC and the single-cell CNV assay. chromosome-arm level gains detected in adult GBM samples identified using both methods, versus total 166 CNVs are detected in scATAC clusters with Copy-scAT in pediatric GBM samples.
id: 10_1101-2021_02_11_430847
author: Pinatti, Lisa M.
title: SearcHPV: a novel approach to identify and assemble human papillomavirus-host genomic integration events in cancer
date: 2021
words: 6849
sentences: 788
pages: 26
flesch: 57
cache: ./cache/10_1101-2021_02_11_430847.pdf
txt: ./txt/10_1101-2021_02_11_430847.txt
summary: SearcHPV: a novel approach to identify and assemble human papillomavirus-host genomic integration events in cancer squamous cell carcinomas; however, the impact of HPV integration into the host human genome SearcHPV uncovered HPV integration sites adjacent to known cancer-related detection of HPV-human integration sites from targeted capture DNA sequencing data. developed a novel HPV integration detection tool for targeted capture sequencing data, which we SearcHPV showed a high frequency of HPV16 integration with a total of six events in UM-SCCIn this study, SearcHPV also called HPV integration sites within TP63. HPV integration sites have been associated with structural variations in the human genome3, 8, 37, which supports an additional genetic mechanism as to why HPV integration sites Genome-wide analysis of HPV integration in human and their integration sites in host genomes through next generation sequencing data. identify viruses and their integration sites using next-generation sequencing of human cancer
id: 10_1101-2021_02_09_430405
author: Quazi, Sameer
title: In-silico Structural and Molecular Docking-Based Drug Discovery Against Viral Protein (VP35) of Marburg Virus: A potent Agent of MAVD
date: 2021
words: 5941
sentences: 1038
pages: 23
flesch: 64
cache: ./cache/10_1101-2021_02_09_430405.pdf
txt: ./txt/10_1101-2021_02_09_430405.txt
summary: In-silico Structural and Molecular Docking-Based Drug Discovery Against Viral Protein (VP35) of Marburg Virus: A potent Agent of MAVD including structure-based drug-like compounds screening from online databases, molecular The final small molecules of drug-like compounds would have more effective and selected for the molecular docking with FGI-103 antiviral drug-using AutoDock 4.2 software. After that, FGI-103 was set and screen other drug-like compounds from PubChem databases. The finally selected drug-like compounds were docked with the P1 site of VP35 of based on ap1 site for ligand in every dock for VP35 MARV utilizing a grid chart of 50 × 50 × 50 The ADMET properties of finally selected drug-like compounds were checked to utilize 2D molecules structure of selected drug-like compounds (A) represents the 2D The molecule structure of three drug-like compounds is shown in Figure 6. "In-Silico Structural and Molecular Docking-Based Drug Discovery "In-Silico Structural and Molecular Docking-Based Drug Discovery
id: 10_1101-698605
author: Sarantopoulou, Dimitra
title: Comparative evaluation of full-length isoform quantification from RNA-Seq
date: 2021
words: 12853
sentences: 1332
pages: 37
flesch: 55
cache: ./cache/10_1101-698605.pdf
txt: ./txt/10_1101-698605.txt
summary: Comparative evaluation of full-length isoform quantification from RNA-Seq Full-length isoform quantification from RNA-Seq is a key goal in transcriptomics analyses benchmarking, isoform quantification, simulated data, pseudo-alignment, RNA-Seq, short Given the difficulty in full-length isoform quantification, many RNA-Seq studies simply analysis performed on the known true isoform quantifications of the simulated data to the For the simulated data we started with 11 real RNA-Seq samples: six liver and six the isoform expression level using idealized and realistic simulated data, with full and true counts), for the set of expressed isoforms in sample 1 in C) idealized and D) realistic data. Method effect on differential expression analysis, using realistic data. Method effect on differential expression analysis, using realistic data. RSEM is a gene/isoform abundance tool for RNA-Seq data which uses a generative model S1 Fig. Method effect on full-length isoform quantification using simulated data. Method effect on full-length isoform quantification using simulated data.
id: 10_1101-2020_09_23_308239
author: Schultz, Bruce T
title: The COVID-19 PHARMACOME: A method for the rational selection of drug repurposing candidates from multimodal knowledge harmonization
date: 2021
words: 8797
sentences: 1318
pages: 31
flesch: 57
cache: ./cache/10_1101-2020_09_23_308239.pdf
txt: ./txt/10_1101-2020_09_23_308239.txt
summary: The COVID-19 PHARMACOME: A method for the rational selection of drug repurposing COVID-19 PHARMACOME, a comprehensive drug-target-mechanism graph generated from a initial version of the COVID-19 PHARMACOME, a comprehensive drug-target-mechanism graph representing COVID-19 pathophysiology mechanisms that includes both drug targets Figure 3: Overlap of compound hits between different drug repurposing screening experiments. space overlap between different COVID-19 drug repurposing screenings. The COVID-19 PHARMACOME associates pathways derived from drug repurposing targets Figure 4 shows the distribution of repurposing drugs in the COVID-19 cause-and-effect graph, overlap analysis allows for the identification of repurposing drugs targeting mechanisms that Virus-response mechanisms are targets for repurposing drugs Figure 5: Visualization of drug repurposing candidates (and their targets) used in combination treatment as our own drug repurposing screening results, we were able to identify mechanisms targeted COVID-19 PHARMACOME, we are now able to link repurposing drugs, their targets and the SARS-CoV-2 protein interaction map reveals targets for drug repurposing.
id: 10_1101-2021_02_10_430619
author: Schutz, Sacha
title: Cutevariant: a GUI-based desktop application to explore genetics variations
date: 2021
words: 4932
sentences: 632
pages: 8
flesch: 66
cache: ./cache/10_1101-2021_02_10_430619.pdf
txt: ./txt/10_1101-2021_02_10_430619.txt
summary: Cutevariant: a GUI-based desktop application to explore genetics variations Cutevariant is a user-friendly GUI based desktop application for genomic research designed to search for variations in DNA samples collected in annotated files and encoded in the Variant Calling Format. application imports data into a local relational database wherefrom complex filter-queries can be built either Key words: genomics, DNA variant, desktop application, Domain Specific Language, Graphic User Interface applications import the data from VCF files into an indexed Cutevariant imports data from VCF files into a normalized Fig. 2: The Cutevariant main view showing the variants list sub-window (middle), different controllers sub-windows but not all are Just like Variant Tools, Cutevariant supports operations Features Cutevariant BrowseVCF VCF-Miner VCF-Explorer VCF-Server VCF-Filters GEMINI Variant Tools SnpSift Comparaison of time performance between cutevariant and VCF-miner for importation and query execution. 3. Pablo Cingolani, Adrian Platts, Le Lily Wang, Melissa VCF-Miner: GUI-based application for mining variants
id: 10_1101-2021_02_11_430762
author: Schäffer, Alejandro A.
title: Ribovore: ribosomal RNA sequence analysis for GenBank submissions and database curation
date: 2021
words: 16496
sentences: 1489
pages: 28
flesch: 65
cache: ./cache/10_1101-2021_02_11_430762.pdf
txt: ./txt/10_1101-2021_02_11_430762.txt
summary: Ribovore: ribosomal RNA sequence analysis for GenBank submissions and database curation alignments of SSU, LSU and 5S rRNA from all three domains as well as from organelles, along with secondary structure predictions for selected sequences. Ribovore software package for the analysis of SSU rRNA and LSU rRNA sequences 18S SSU rRNA database of 1091 sequences was updated most recently on September 27, 2018 by running version 0.28 of the Ribovore program ribodbmaker on an input set of 579,279 GenBank sequences returned from the eukaryotic SSU rRNA The results of ribotyper and rRNA sensor are combined and each sequence is separated into one of four outcome classes depending on whether it passed or failed each input a set of candidate sequences and a specified rRNA model (e.g. SSU.Bacteria) two blastn databases: one of 1267 bacterial and archaeal 16S SSU rRNA sequences
id: 10_1101-2021_02_12_430989
author: Sofer, Tamar
title: Benchmarking Association Analyses of Continuous Exposures with RNA-seq in Observational Studies
date: 2021
words: 8136
sentences: 626
pages: 27
flesch: 48
cache: ./cache/10_1101-2021_02_12_430989.pdf
txt: ./txt/10_1101-2021_02_12_430989.txt
summary: Benchmarking Association Analyses of Continuous Exposures with RNA-seq in Observational Studies as well as linear regression-based analyses for studying the association of continuous exposures generation of empirical null distribution of association p-values, and we apply the pipeline to Many studies of phenotypes associated with gene expression from RNA-seq consist of small Residual permutation approach for simulations and for empirical p-value computation covariates, and outcome distributions; and (b) their relationships, aside from the exposureoutcome association, are the same as in the real data, we used a residual permutation approach. association studies applied to residual permutations were included to compute empirical papproach to study the distribution of p-values under the null of no association between the phenotypes and RNA-seq, and used this approach to further study power, and to compute approaches for transcriptome-wide analysis of RNA-seq in population-based studies, including more comprehensive study of statistical permutation approaches for RNA-seq association
id: 10_1101-2021_02_09_430550
author: Song, Dongyuan
title: scPNMF: sparse gene encoding of single cells to facilitate gene selection for targeted gene profiling
date: 2021
words: 13512
sentences: 1548
pages: 37
flesch: 64
cache: ./cache/10_1101-2021_02_09_430550.pdf
txt: ./txt/10_1101-2021_02_09_430550.txt
summary: (scPNMF) method to select informative genes from scRNA-seq data in an unsupervised way. Therefore, for scRNA-seq data analysis, informative gene selection Besides scRNA-seq data analysis, informative gene selection is also crucial for designing number and a scRNA-seq dataset, scPNMF selects informative genes based on its weight matrix; First, the informative genes selected by scPNMF lead to the most accurate cell clustering. the informative genes and weight matrix of scPNMF lead to the best cell type prediction accuracy Figure 3: Benchmarking scPNMF against 11 informative gene selection methods on seven scRNA-seq (b) UMAP visualization of cells in the Zheng4 dataset based on 100 informative genes selected by We benchmark scPNMF against the 11 gene selection methods in terms of cell type prediction We propose scPNMF, an unsupervised gene selection and data projection method for scRNA-seq For cell type prediction, we project every targeted gene profiling dataset and its scRNA-seq
id: 10_1101-2021_02_10_430705
author: Stassen, Shobana V.
title: VIA: Generalized and scalable trajectory inference in single-cell omics data
date: 2021
words: 13590
sentences: 1383
pages: 24
flesch: 53
cache: ./cache/10_1101-2021_02_10_430705.pdf
txt: ./txt/10_1101-2021_02_10_430705.txt
summary: 1 VIA: Generalized and scalable trajectory inference in single-cell omics data 1 VIA: Generalized and scalable trajectory inference in single-cell omics data 35 strategy to compute pseudotime, and reconstruct cell lineages based on lazy-teleporting random walks Step 1: Single-cell level graph is clustered such that each node 50 user defined start cell) is first computed by the expected hitting time for a lazy-teleporting random walk along an 57 network topology and single-cell level pseudotime/lineage probability properties onto an embedding using GAMs, as The cell fates and their lineage pathways are then computed by a two-stage probabilistic method, 94 graph-traversal allows it to infer cell fates when the underlying data spans combinations of multifurcating 201 detected cell fates annotated (o) lineage pathway and gene-pseudotime trend shown for the CD41 Megakaryocytic 259 Figure 3 VIA infers trajectories in single-cell multi-omic and image datasets (a) Major lineages of human Single cells are represented by graph nodes that are connected based on
id: 10_1101-727867
author: Tangherloni, Andrea
title: scAEspy: a tool for autoencoder-based analysis of single-cell RNA sequencing data
date: 2021
words: 15281
sentences: 2865
pages: 28
flesch: 72
cache: ./cache/10_1101-727867.pdf
txt: ./txt/10_1101-727867.txt
summary: scAEspy: a tool for autoencoder-based analysis of single-cell RNA sequencing data This computational tool allows for coupling low-dimensional probabilistic representation of gene expression data with the downstream analysis to consider the Finally, the currently available AEs cannot be directly exploited to obtain the latent space or to generate synthetic cells. to show the cells in this embedded space or as a starting point for other dimensionality reduction approaches (e.g., t-SNE and UMAP) as well as downstream analyses Non-linear approaches for dimensionality reduction can be effectively used to capture the non-linearities among the gene interactions that may exist in the highdimensional expression space of scRNA-Seq data [16]. be effectively applied to analyse disparate types of single-cell data from different flexible method developed to cluster single-cell data; (ii) a centroid is calculated batch-effect correction methods for single-cell rna sequencing data. Wang, D., Gu, J.: VASC: dimension reduction and visualization of single-cell RNA-seq data by deep
id: 10_1101-2021_02_12_431018
author: Truong Nguyen, Phuoc
title: HaVoC, a bioinformatic pipeline for reference-based consensus assembly and lineage assignment for SARS-CoV-2 sequences.
date: 2021
words: 3786
sentences: 502
pages: 14
flesch: 61
cache: ./cache/10_1101-2021_02_12_431018.pdf
txt: ./txt/10_1101-2021_02_12_431018.txt
summary: HaVoC, a bioinformatic pipeline for reference-based consensus assembly and lineage assignment for SARS-CoV-2 sequences. HaVoC, a bioinformatic pipeline for reference-based consensus assembly and lineage 2 Several new variants of SARS-CoV-2 have emerged globally, of which the 18 based assemblies on raw SARS-CoV-2 sequences in addition to identifying lineages to detect 26 variants of concern, we have developed an open source bioinformatic pipeline called HaVoC 27 monitor the spread of SARS-CoV-2 variants of concern during local outbreaks. currently being used in Finland for monitoring the spread of SARS-CoV-2 variants. SARS-CoV2, variant detection, reference assembly, lineage identification, coronavirus, 40 surveillance of virus variants by sequencing the SARS-CoV-2 genomes would provide a fast 80 to query SARS-CoV-2 fastq sequence libraries and assigns lineages to them individually in 92 processing and a reference genome of SARS-CoV-2 in a separate FASTA file. The likelihood of emergence of novel SARS-CoV-2 variants of concern is increased and 209 Emerging SARS-CoV-2 Variants.
id: 10_1101-2021_02_11_430789
author: Tyagin, Ilya
title: Accelerating COVID-19 research with graph mining and transformer-based learning
date: 2021
words: 9408
sentences: 807
pages: 9
flesch: 58
cache: ./cache/10_1101-2021_02_11_430789.pdf
txt: ./txt/10_1101-2021_02_11_430789.txt
summary: Accelerating COVID-19 research with graph mining and transformer-based learning develop text mining techniques that can help the science community answer high-priority scientific questions related to COVID-19. is currently customized and available in the open domain to massively process COVID-19 related queries. Both systems are the next generation of the AGATHA knowledge network mining transformer model [37]. (1) Most of the existing HG systems are domain-specific (e.g., genedisease interactions) that is usually expressed in limiting the processed information (e.g., significant filtering vocabulary and papers a trained deep bi-LSTM model for extracting predicates from unstructured text. For instance, the node representing the entity "COVID-19" is connected to every sentence and predicate that The prior AGATHA semantic network only includes UMLS terms that appear in SemMedDB predicates [18] which is a major limitation. obtain embeddings per node in the semantic graph, we train AGATHA system ranking model.
id: 10_1101-2021_02_11_430871
author: Vadnais, David
title: ParticleChromo3D: A Particle Swarm Optimization Algorithm for Chromosome and Genome 3D Structure Prediction from Hi-C Data
date: 2021
words: 10071
sentences: 1053
pages: 24
flesch: 63
cache: ./cache/10_1101-2021_02_11_430871.pdf
txt: ./txt/10_1101-2021_02_11_430871.txt
summary: ParticleChromo3D: A Particle Swarm Optimization Algorithm for Chromosome and Genome 3D Structure Prediction from Hi-C Data chromosome and genome structure reconstruction from Hi-C data using Particle Swarm Optimization approach chromosome bin, according to the particle swarm algorithm, and then iterates its position towards a global best This paper presents ParticleChromo3D, a new distance-based algorithm for chromosome 3D structure The structures generated by ParticleChromo3D also shows that the result at swarm size Structures generated by ParticleChromo3D at different swarm size values. obtained by comparing the ParticleChromo3D algorithm''s output structure to the simulated dataset''s true plot of ParticleChromo3D SCC performance on 500KB GM12878 cell Hi-C data for chromosome 1 to 23. plot of ParticleChromo3D SCC performance on 500KB GM12878 cell Hi-C data for chromosome 1 to 23. chromosome 3D structure reconstruction algorithms on the GM12878 data set at both the 1MB and 500KB chromosome and genome structures reconstructed from Hi-C data.
id: 10_1101-2021_02_10_430606
author: Wei, Zheng
title: NeuronMotif: Deciphering transcriptional cis-regulatory codes from deep neural networks
date: 2021
words: 12013
sentences: 1107
pages: 31
flesch: 63
cache: ./cache/10_1101-2021_02_10_430606.pdf
txt: ./txt/10_1101-2021_02_10_430606.txt
summary: Each point is a decoupled motif generate by a sample set of sequence. Only the max activation value of the decoupled motifs in Fig. 3b are significantly higher than the decoupled motifs of other neurons in layer 3 of Basset-3 model. discovered (q-value < 0.001) from the neuron in convolutional output layer of Basset, BD-5 and BD-10 model. c, The number of motif discovered (q-value < 0.01) from the neuron in layer 3 of Basset model using different sub-patterns in the input feature map of the max pooling layer to split the sequences set of which are DNA-sequence based DCNN models with 3 general convolutional layers for stacking sequences of different synonymous motifs with the maximum activation value In summary, we presented NeuronMotif as an effective algorithm to reveal the cisregulatory motif grammar learned by DCNN model that use DNA sequence to annotate sequences indicate more synonymous motif mixture in this DCNN model.
id: 10_1101-2021_02_10_430649
author: Wen, Zi-Hang
title: Bfimpute: A Bayesian factorization method to recover single-cell RNA sequencing data
date: 2021
words: 8418
sentences: 1302
pages: 11
flesch: 71
cache: ./cache/10_1101-2021_02_10_430649.pdf
txt: ./txt/10_1101-2021_02_10_430649.txt
summary: Bfimpute: A Bayesian factorization method to recover single-cell RNA sequencing data Recovering dropout events in a sparse gene expression matrix for scRNA-seq data is a long-standing matrix completion We introduce Bfimpute, a Bayesian factorization imputation algorithm that reconstructs two latent gene and cell matrices to impute final gene expression matrix within each cell group, with or without the aid of cell type labels or bulk Bfimpute achieves better accuracy than other six publicly notable scRNA-seq imputation methods on simulated Key words: single cell; RNA-seq; imputation; Bayesian factorization impute dropout events by adopting the bulk RNA-seq data imputation of single cell RNA-seq data could be applied by Bfimpute recovers dropout values and improves cell type identification in the simulated data. and the imputed data by Bfimpute, scImpute, and DrImpute for the human embryonic stem cell differentiation study. imputation method scimpute for single-cell rna-seq data.
id: 10_1101-2021_02_10_430604
author: Youngblut, Nicholas D.
title: Struo2: efficient metagenome profiling database construction for ever-expanding microbial genome datasets
date: 2021
words: 1409
sentences: 157
pages: 4
flesch: 56
cache: ./cache/10_1101-2021_02_10_430604.pdf
txt: ./txt/10_1101-2021_02_10_430604.txt
summary: Struo2: efficient metagenome profiling database construction for ever-expanding microbial genome datasets 1 Struo2: efficient metagenome profiling database construction for ever-expanding 10 Mapping metagenome reads to reference databases is the standard approach for 12 reference databases often lack recently generated genomic data such as 15 method for constructing custom databases; however, the pipeline does not scale well with the 17 not allow for efficient database updating as new data are generated. 20 HUMAnN3 databases that can be easily updated with new genomes and/or individual gene Struo2 enables feasible database generation for continually increasing large-scale 25 ● Pre-built databases: http://ftp.tue.mpg.de/ebio/projects/struo2/ 26 ● Utility tools: https://github.com/nick-youngblut/gtdb_to_taxdump 28 Metagenome profiling involves mapping reads to reference sequence databases and is 39 computational resources, which led us to create Struo for straight-forward custom metagenome 54 CPU hours per genome versus ~2.4 for Struo (Figure 1B). 67 taxonomy (available at https://github.com/nick-youngblut/gtdb_to_taxdump ). (2020) Struo: a pipeline for building custom databases for
id: 10_1101-2021_02_10_430656
author: Zakeri, Mohsen
title: A like-for-like comparison of lightweight-mapping pipelines for single-cell RNA-seq data pre-processing
date: 2021
words: 6557
sentences: 568
pages: 7
flesch: 64
cache: ./cache/10_1101-2021_02_10_430656.pdf
txt: ./txt/10_1101-2021_02_10_430656.txt
summary: A like-for-like comparison of lightweight-mapping pipelines for single-cell RNA-seq data pre-processing benchmark comparing the kallisto-bustools pipeline (2) for single-cell demonstrate that, when configured to match the computational complexity of kallisto-bustools as closely as possible, alevin-fry processes Alevin-fry (3) is a new pipeline for single-cell RNA-seq benchmarking STARsolo (9), kallisto-bustools (2) and alevin-fry (3), out new tools like alevin-fry for the pre-processing of single-cell data, (1), we have now created a simple-to-follow tutorial for speedoptimized single-cell pre-processing using alevin-fry (https:// by Booeshaghi and Pachter (1) change when a like-for-like comparison between alevin-fry and kallisto-bustools is carried out, we The time and memory used by the relevant steps of the alevin-fry and kallisto-bustools pipelines for pre-processing the 20 diverse tagged-end single-cell RNA-seq datasets used in (1). A comparison of the resulting count matrices obtained from alevin-fry and kallisto-bustools, as run in this manuscript, for the pbmc_10k_v3 dataset. peak memory than alevin-fry, with the kallisto-bustools pipeline using
id: 10_1101-2021_02_08_430275
author: Zhang, Jianbo
title: Next-generation sequencing-based bulked segregant analysis without sequencing the parental genomes
date: 2021
words: 6404
sentences: 694
pages: 6
flesch: 68
cache: ./cache/10_1101-2021_02_08_430275.pdf
txt: ./txt/10_1101-2021_02_08_430275.txt
summary: Next-generation sequencing-based bulked segregant analysis without sequencing the parental genomes identified using BSA-Seq, a technology in which next-generation sequencing (NGS) is applied to bulked segregant analysis (BSA). recently developed the significant structural variant method for BSASeq data analysis that exhibits higher detection power than standard to analyze BSA-Seq data in which genome sequences of one parent served as the reference sequences in genotype calling, and thus We analyzed a public BSA-Seq dataset using our modified method and the standard allele frequency and Gmethod allows the detection of such associations without sequencing the parental genomes, leading to further lower the the BSA-Seq data with the genome sequences of both the parents101 when the parental genome sequences are used to aid BSA-Seq data 193 The allele frequency method: The ΔAF value of each SNP in 267 BSA-Seq data analysis using the genome sequences of both the parents and the bulks. BSA-Seq data analysis using only the bulk genome sequences.
id: 10_1101-2020_05_15_090266
author: Zhang, R.
title: SpacePHARER: Sensitive identification of phages from CRISPR spacers in prokaryotic hosts
date: 2021
words: 2191
sentences: 283
pages: 6
flesch: 64
cache: ./cache/10_1101-2020_05_15_090266.pdf
txt: ./txt/10_1101-2020_05_15_090266.txt
summary: Summary: SpacePHARER (CRISPR Spacer Phage-Host Pair Finder) is a sensitive and fast tool for de novo prediction of phage-host relationships via identifying phage genomes that match CRISPR spacers in genomic or metagenomic data. SpacePHARER gains sensitivity by comparing spacers and phages at the protein level, optimizing its scores for matching SpacePHARER by searching a comprehensive spacer list against all complete phage genomes. methods compare individual CRISPR spacers with phage To increase sensitivity, (1) we compare protein coding sequences because phage genomes are mostly coding, and, (0) Preprocess input: scan the phage genome and CRISPR spacers in six ORFs q of CRISPR spacers extracted from one prokaryotic genome, and each target set T comprises the putative protein sequences t from a single phage. The performance of SpacePHARER was evaluated on the spacer test set against a target database predicted the correct host for more phages than BLASTN BLASTN in detecting phage-host pairs, due to searching
id: 10_1101-2021_02_08_430070
author: Zhang, Yao-zhong
title: On the application of BERT models for nanopore methylation detection
date: 2021
words: 5183
sentences: 586
pages: 7
flesch: 60
cache: ./cache/10_1101-2021_02_08_430070.pdf
txt: ./txt/10_1101-2021_02_08_430070.txt
summary: On the application of BERT models for nanopore methylation detection with deep learning models, have achieved significant performance improvements on nanopore methylation recurrent patterns of positional-signal-shift in the context window surrounding target 5-methylcytosine that the refined BERT model can achieve competitive or even better results than the state-of-the-art biRNN of datasets from the different research groups, BERT models demonstrate a good generalization Fig. 1: Basic BERT''s and refined BERT''s model structure used for methylation detection. a refined BERT model to take account of signal-shift patterns in the proposed refined BERT model achieves a competitive or even better result explore applying the BERT model for the nanopore methylation detection 2.2 Applying BERT models for nanopore methylation For the cross-sample evaluation, we train models on one dataset and test a BERT model to pay more attention to center positions. In-sample evaluation of different deep learning models on 5mC datasets.
id: 10_1101-2021_02_01_429246
author: Zheng, Hongyu
title: Sequence-specific minimizers via polar sets
date: 2021
words: 15440
sentences: 1407
pages: 24
flesch: 71
cache: ./cache/10_1101-2021_02_01_429246.pdf
txt: ./txt/10_1101-2021_02_01_429246.txt
summary: minimizers focus on sampling fewer k-mers on a random sequence and use universal hitting sets (sets suggests, a UHS is a set of k-mers that "hits" every w-long window of every possible sequence (hence the the elements of the polar sets are in the sequence: the higher the energy, the more spread apart the k-mers have densities upper bounded by |U|/σk, because only k-mers from the universal hitting set can be selected. Section 2.2 gives a formal definition of the link energy of a polar set and Theorem 1 gives upper and lower bounds using this link energy for the density of a minimizer compatible with a polar set. form a link, which in turn is the number of k-mer pairs in the polar set that are exactly w bases away on S. A context is charged if the minimizer selects a different k-mer in the first window than in the second
==== make-pages.sh questions
==== make-pages.sh search
==== make-pages.sh topic modeling corpus
Zipping study carrel