RNABindRPlus: A Predictor that Combines Machine Learning and Sequence Homology-Based Methods to Improve the Reliability of Predicted RNA-Binding Residues in Proteins

Abstract

Protein-RNA interactions are central to essential cellular processes such as protein synthesis and regulation of gene expression and play roles in human infectious and genetic diseases. Reliable identification of protein-RNA interfaces is critical for understanding the structural bases and functional implications of such interactions and for developing effective approaches to rational drug design. Sequence-based computational methods offer a viable, cost-effective way to identify putative RNA-binding residues in RNA-binding proteins. Here we report two novel approaches: (i) HomPRIP, a sequence homology-based method for predicting RNA-binding sites in proteins; (ii) RNABindRPlus, a new method that combines predictions from HomPRIP with those from an optimized Support Vector Machine (SVM) classifier trained on a benchmark dataset of 198 RNA-binding proteins. Although highly reliable, HomPRIP cannot make predictions for the unaligned parts of query proteins and its coverage is limited by the availability of close sequence homologs of the query protein with experimentally determined RNA-binding sites. RNABindRPlus overcomes these limitations. We compared the performance of HomPRIP and RNABindRPlus with that of several state-of-the-art predictors on two test sets, RB44 and RB111. On a subset of proteins for which homologs with experimentally determined interfaces could be reliably identified, HomPRIP outperformed all other methods achieving an MCC of 0.63 on RB44 and 0.83 on RB111. RNABindRPlus was able to predict RNA-binding residues of all proteins in both test sets, achieving an MCC of 0.55 and 0.37, respectively, and outperforming all other methods, including those that make use of structure-derived features of proteins. More importantly, RNABindRPlus outperforms all other methods for any choice of tradeoff between precision and recall. An important advantage of both HomPRIP and RNABindRPlus is that they rely on readily available sequence and sequence-derived features of RNA-binding proteins. A webserver implementation of both methods is freely available at http://einstein.cs.iastate.edu/RNABindRPlus/.

iSEE: Interface Structure, Evolution and Energy-based machine learning predictor of binding affinity changes upon mutations

“…They capture the evolutionary conservation of a specific amino acid at the mutation position and its change after mutation, respectively. PSSM has been proven to provide crucial information in various related topics, such as binding site predictions [29] and hot-spot predictions [30]. The alignment depth does not seem to have much impact on the prediction performance ( Figure S3).…”

A boosting approach for prediction of protein-RNA binding residues

“…Based on these researches [7, 9–11, 14–24], we combined a variety of features of the amino acids to represent the specific interaction attributes of protein residues with RNA nucleotides. In this work, some of the site characteristics, such as relative accessible surface area, secondary structure and interaction propensity, can be calculated only after the protein structure information is available.…”

“…We compare PredRBR with several existing state-of-the-art RNA-binding residue prediction approaches, including BindN [9], PPRint [20], Liu-2010 [12], BindN+ [22], RNABindR2.0 [23], RNABindRPlus [14] and SNBRFinder [17] on the independent set (RBR101). In these methods, BindN [9], BindN+ [9] and PPRint [20] use SVM to build the RNA-binding site classifier; RNABindRPlus [14] utilizes a logistic regression method to integrate the homology-based method HomPRIP and optimized SVM model named SVMOpt; Liu-2010[12] is RF-based method with sequence and structural features especially the proposed interaction propensity, and SNBRFinder [17] is a hybrid method based on the sequence features.…”

“…1. A residue is defined as an RNA-binding site if there exists at least one atom in the protein with a distance cutoff < 5.0Å from an atom of the binding RNA [7, 9–11, 14–24]. RBP170 contains 6,754 (14.47%) RNA-binding sites and 39,933 (85.53%) non-binding sites.…”

“…Liu et al [12] implement a RF classifier to detect the RNA binding residues in proteins by integrating interaction propensity with other sequence and structural features. Other RNA-binding site prediction methods include PRINTR [13], RNABindRPlus [14], RBScore [15], NBench [16] and SNBRFinder [17]. …”