TY - JOUR
T1 - BeRBP
T2 - Binding estimation for human RNA-binding proteins
AU - Yu, Hui
AU - Wang, Jing
AU - Sheng, Quanhu
AU - Liu, Qi
AU - Shyr, Yu
N1 - Funding Information:
National Cancer Institute [5U01 CA163056-05 to Y.S.]; Cancer Center Support Grant [2P30 CA068485-19 to Y.S.]; NCI SPORE in GI Cancer Career Development Award [P50 CA095103 to Q.L.]. Funding for open access charge: National Cancer Institute [5U01 CA163056-05]. Conflict of interest statement. None declared.
Publisher Copyright:
© 2019 The Author(s) 2018. Published by Oxford University Press on behalf of Nucleic Acids Research.
PY - 2019/3/18
Y1 - 2019/3/18
N2 - Identifying binding targets of RNA-binding proteins (RBPs) can greatly facilitate our understanding of their functional mechanisms. Most computational methods employ machine learning to train classifiers on either RBP-specific targets or pooled RBP-RNA interactions. The former strategy is more powerful, but it only applies to a few RBPs with a large number of known targets; conversely, the latter strategy sacrifices prediction accuracy for a wider application, since specific interaction features are inevitably obscured through pooling heterogeneous datasets. Here, we present beRBP, a dual approach to predict human RBP-RNA interaction given PWM of a RBP and one RNA sequence. Based on Random Forests, beRBP not only builds a specific model for each RBP with a decent number of known targets, but also develops a general model for RBPs with limited or null known targets. The specific and general models both compared well with existing methods on three benchmark datasets. Notably, the general model achieved a better performance than existing methods on most novel RBPs. Overall, as a composite solution overarching the RBP-specific and RBP-General strategies, beRBP is a promising tool for human RBP binding estimation with good prediction accuracy and a broad application scope.
AB - Identifying binding targets of RNA-binding proteins (RBPs) can greatly facilitate our understanding of their functional mechanisms. Most computational methods employ machine learning to train classifiers on either RBP-specific targets or pooled RBP-RNA interactions. The former strategy is more powerful, but it only applies to a few RBPs with a large number of known targets; conversely, the latter strategy sacrifices prediction accuracy for a wider application, since specific interaction features are inevitably obscured through pooling heterogeneous datasets. Here, we present beRBP, a dual approach to predict human RBP-RNA interaction given PWM of a RBP and one RNA sequence. Based on Random Forests, beRBP not only builds a specific model for each RBP with a decent number of known targets, but also develops a general model for RBPs with limited or null known targets. The specific and general models both compared well with existing methods on three benchmark datasets. Notably, the general model achieved a better performance than existing methods on most novel RBPs. Overall, as a composite solution overarching the RBP-specific and RBP-General strategies, beRBP is a promising tool for human RBP binding estimation with good prediction accuracy and a broad application scope.
UR - http://www.scopus.com/inward/record.url?scp=85062842815&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85062842815&partnerID=8YFLogxK
U2 - 10.1093/nar/gky1294
DO - 10.1093/nar/gky1294
M3 - Article
C2 - 30590704
AN - SCOPUS:85062842815
VL - 47
JO - Nucleic Acids Research
JF - Nucleic Acids Research
SN - 0305-1048
IS - 5
M1 - e26
ER -