Table 4.

Computational tools for the prediction of RNA-protein interactions.

Methods	Advantages	Disadvantages	Links	References
catRAPID	Outperforms other algorithms in the identification of RBPs and detection of non-classical RNA-binding regions.	Spurious binding may occur.	http://s.tartaglialab.com/page/catrapid_group	(115, 121)
lncPro	Time-saving.	Limited ability of computational prediction of RNA secondary structure for lncRNAs.	bioinfo.bjmu.edu.cn/lncpro/	(139)
RNAcontext	A more accurate elucidation of RBP-specific sequence and structural preferences.	Misleading results will be produced for those RBPs with non-trivial structural preferences.	http://www.cs.toronto.edu/~hilal/rnacontext/	(140)
RPI-Pred	A comprehensive understanding of PRIs based on the sequence features and the high-order structures of both proteins and RNAs.	Limited to prediction of ncRNA-Protein interaction.	http://ctsb.is.wfubmc.edu/projects/rpi-pred.	(141)
PRIPU	Employs SVM for predicting PRIs using only positive and unlabeled examples based on proposing a new performance measure called EPR; Outperforms existing methods and predicts unknown PRIs.	N/A	http://admis.fudan.edu.cn/projects/pripu.htm	(142)
RPISeq	Reliable prediction based on sequence.	Requirement for larger and more diverse experimental datasets.	RNA-Protein Interaction Prediction (RPISeq) (iastate.edu)	(143)

RBPs, RNA-binding proteins; SVM, biased-support vector machine; lncRNA, long noncoding RNA; PRIS, Protein-RNA interactions; EPR, explicit positive recall; N/A, not applicable.