id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_gnfj3xckrrcyhda6qgabfsjcbu	Adam C Gunning	Assessing performance of pathogenicity predictors using clinically relevant variant datasets	2020.0	9	.pdf	application/pdf	7379	1327	66	(ACGS) best practice guidelines for variant interpretation.4 Common to all guidelines is the recommendation of the use of in silico prediction tools Clinical dataset (n=1757, see figure 1B and online supplementary table S1) more accurately reflects variants that might require Table 1 Results of variant classification for individual tool, and two consensusbased combinations, for the (A) open (n=8480) and (B) clinical author benchmarking,12–14 the metapredictors REVEL, ClinPred and GAVIN were highly proficient at classifying the variants in the open dataset, achieving sensitivities of 0.87, 0.90 Figure 3 Violin plot showing variant scores for SIFT, PolyPhen-2, REVEL and ClinPred using two datasets. Within the clinically relevant dataset, the tools are either falsely concordant or discordant for ~15% of pathogenic variants but ~78% of benign Assessing performance of pathogenicity predictors using clinically relevant variant datasets Assessing performance of pathogenicity predictors using clinically relevant variant datasets	./cache/work_gnfj3xckrrcyhda6qgabfsjcbu.pdf	./txt/work_gnfj3xckrrcyhda6qgabfsjcbu.txt