id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-352371-t54zftal	Kumar, Ravindra	Prediction of endoplasmic reticulum resident proteins using fragmented amino acid composition and support vector machine	2017-09-04		.txt	text/plain	6606	343	54	RESULTS: In this study, we have reported a novel support vector machine based method for predicting endoplasmic reticulum resident proteins, named as ERPred. But these have some shortcomings like (i) among the above mentioned predictors, none were designed specifically to predict ERRPs; (ii) datasets used for training for prediction model were very old; (iii) subcellular locations were determined for a particular organism or groups (plant/animal/viral); (iv) many of them do not provide webserver/standalone software for scientific purpose and if some of them does so, they are not in working condition. Using standalone version of ScanProsite (Gattiker, Gasteiger & Bairoch, 2002) , out of 124 proteins of training dataset, we were able to find ER retention signal ([KRHQSA]-[DENQ]-E-L) in only 66 proteins, which shows that signal sequence is not present in all ERRPs. This shows that signal based approach may not be appropriate for complete ERRP repertoire prediction of any proteome.	./cache/cord-352371-t54zftal.txt	./txt/cord-352371-t54zftal.txt