id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-003070-6oca1mrm	Shen, Wen-Jun	RPiRLS: Quantitative Predictions of RNA Interacting with Any Protein of Known Sequence	2018-02-28		.txt	text/plain	5476	339	56	On the non-redundant benchmark test sets extracted from the PRIDB, the RPiRLS method outperformed RPI-Pred and IPMiner in terms of accuracy, specificity and sensitivity. The computational results showed that the RPiRLS classifier outperformed the RPiRLS-7G classifier in terms of various performance measurements, indicating that the diversity of amino acids at a sequence is important for the prediction of RPIs. The performance of predicting RPIs was evaluated by using 10-fold stratified cross-validation on the RPI2662 data set. For the RPI369 data set as shown in Table 4 , the performance of the RPiRLS method was 0.85, 0.92, 0.84 and 0.86 for predictive accuracy, AUC, specificity and sensitivity, respectively. The work presented here provided a computational method, called RPiRLS, to classify RNA-protein pairs as interacting or non-interacting by integrating a sequence-based derived kernel with regularized least squares.	./cache/cord-003070-6oca1mrm.txt	./txt/cord-003070-6oca1mrm.txt