Predicting RNA-binding residues from evolutionary information and sequence conservation

RNA-binding proteins (RBPs) are designed to efficiently recognize specific RNA sequences after they are derived from the DNA sequences. Protein-RNA interactions are fundamental to cellular processes, including the assembly and function of ribonucleoprotein particles (RNPs), such as ribosomes and spliceosomes and the post-transcriptional regulation of gene products. For satisfying diverse functional requirements, RNA binding proteins are composed of multiple blocks of RNA-binding domains (RBDs) presented in various structural arrangements to provide versatile functionality [1, 2]. Although RNA structure is hierarchical, that is, the primary sequence determines the secondary structure which, in turns, determines tertiary structure, the tertiary structure of RNA is not as stable as secondary structure and is hard to predict [3]. However, sequence conservations in RNA-binding domains have been discovered in RNA-binding proteins [4, 5, 6, 7]. With the recent growth of protein-RNA complexes in the Protein Data Bank (PDB) [8] and the Nucleic Acid Database (NDB) [9], structural analysis on RNA-binding pockets [10, 11, 12, 13, 14, 15, 16, 17, 18] and the themes of RNA-protein recognition [18, 19, 20] have been investigated as well.

Most recent works on predicting RNA-binding residues used support vector machine (SVM) with protein evolutionary information from protein sequence. Wang and Brown (2006) developed the web service, BindN [21], to predict DNA and RNA binding sites using sequence features to represent structural characteristics including relative solvent accessible surface area, side chain pKa, hydrophobicity index and molecular mass of an amino acid. Tong et al. (2008) [22] proposed the hybrid RISP (RNA-Interaction Site Prediction) method by adjusting cutoff value of SVM discrimination function to improve prediction performance. Kumar et al. (2008) developed Pprint [23] by using evolutionary profiles of the position-specific scoring matrices (PSSMs) and amino acid composition while they also adjusted cutoff value of SVM discrimination function to improve prediction performance. Wang et al. (2008) developed PRINTR [24] by using additional structural information from protein-RNA complexes. Cheng et al. (2008) developed RNAProB [25] by smoothing PSSM profiles with consideration of the correlation and dependency from the neighboring residues for each amino acid in a protein. Spriggs et al. (2009) [26] developed the PiRaNhA by using support vector machine with a PSSM profile and three amino acid properties, including interface propensity (IP), predicted solvent accessibility (pA) and hydrophobicity (H) for recognizing RNA-binding residues [27]. Other machine learning approaches such as neural network and Naïve Bayes classifier have also been applied to predict RNA-binding residues. Jeong et al. (2004) [28] applied artificial neural network (ANN)-based method with amino acid sequence and predicted secondary structure information and improved the performance by using post-processing procedures such as state-shifting and filtering isolated interacting residues from prediction. Improved version by Jeong et al. (2006) [29] used evolutionary information extracted from PSI-BLAST profiles and CLUSTALW alignment. Terribilini et al. (2006) [30] applied a Naïve Bayes classifier with amino acid sequence information for predicting RNA interacting residues and presented the results through the web service RNABindR [31]. The ability to computationally predict RNA-binding residues in a RNA-binding protein can help biologists reveal site-directed mutagenesis in wet-lab experiments.

Caragea et al. [32] explored the problem of assessing the performance of classifiers trained on macromolecular sequence data, with the emphasis on cross-validation and data selection methods. In comparison of window-based k-fold cross-validation and sequence-based k-fold cross-validation, window-based cross-validation can yield overly optimistic estimates of the performance of classifier relative to the estimates obtained using sequence-based cross-validation. RNAProB, BindN, RISP, PRINTR and PiRaNhA are predictors that report performance window-based k-fold cross-validation while Pprint and RNABindR report performance with sequence-based k-fold cross-validation. The predictors evaluated with window-based k-fold cross-validation have superior performance than those with sequence-based k-fold cross-validation. The reason is that data instances in the testing fold would be predicted by data instances with sub-sequence identity higher than 25% in the training fold in window-based k-fold cross-validation. Therefore, in data with class imbalance, the metrics that measure the classification performance must be chosen carefully. Matthew's correlation coefficient (MCC), F-score and F_0.5-score are widely applied to assess the prediction performance. MCC is used to measure prediction quality with the consideration of both under- and over-predictions. F-score and F_0.5-score are used to assess balanced prediction quality on both positive class and negative class.

In this article, we proposed the prediction framework “ProteRNA” with the combination of SVM-based classifier with evolutionary profiles and conserved residues discovery by sequence conservation for identifying RNA-interacting residues in a RNA-binding protein. In the SVM-based classifier, we use features including position-specific scoring matrix computed by PSI-BLAST and secondary structure information predicted by PSIPRED as feature vectors [33]. To exploit the sequence conservation information, WildSpan [34] (http://biominer.bime.ntu.edu.tw/wildspan/), which is developed to discover functional signatures and diagnostic patterns of proteins directly from a set of unaligned protein sequences, is incorporated. The most distinguishing feature of WildSpan is that it links short motifs (local conserved regions) with large flexible gaps to deliver the most frequently observed discontinuous patterns present in related proteins. WildSpan has been embedded in many applications [35, 36, 37, 38, 39] to discover functionally important residues; therefore, we apply WildSpan to discover conserved residues as RNA-binding residues in a protein sequence to improve prediction performance on detecting more RNA-binding residues. The independent testing dataset collected for performance evaluation contains 33 testing RNA-binding proteins with less than 30% sequence identity against with training data. In the independent testing dataset, ProteRNA has been able to deliver overall accuracy of 89.78%, MCC of 0.2628, F-score of 0.3075, and F_0.5-score of 0.3546. We emphasize MCC, F-score and F_0.5-score because it provides the biochemist with a confidence level for designing an experiment to confirm whether a predicted binding residue is really involved in interaction with the RNA.

In this section, we will report the experiments conducted to evaluate the performance of our proposed approach, ProteRNA with the combination of SVM-based classifier with evolutionary profiles and conserved residues discovery by sequence conservation. In order to avoid bias, we repeated 5-fold cross-validation procedure 20 times to observe prediction performance on the training dataset RB147 (see Materials and Methods for details). For each run, we applied sequence-based 5-fold cross-validation; therefore, protein chains will be randomly divided into 5 folds: one fold for testing and remaining 4 folds for training. For this study, LIBSVM (http://www.csie.ntu.edu.tw/~cjlin/libsvm) was used for data training and classification and WildSpan was used for detecting conserved residues from homologous protein sequences. We use independent testing dataset containing 33 protein chains for comparing ProteRNA with other predictors such as PiRaNhA, Pprint, BindN, and PRIP.

Comparison with other predictors by independent testing

Only predictors that predict RNA-binding residues from protein primary sequence information were selected for performance comparison. In addition, RISP did not respond with any prediction results after submitting the jobs and PRINTR is unavailable. According to the designed framework of RNABindR, if there is an exact matched protein chain in Protein Data Bank, RNABindR will return the actual RNA-binding residues of protein-RNA complex. Therefore, it is difficult to distinguish whether the returned result is actually binding or predicted binding so RNABindR will be excluded. Finally, Table 4 shows the prediction performance of ProteRNA in comparison with PiRaNhA, Pprint, BindN, and PRIP. While ordering prediction performance in terms of MCC, ProteRNA delivers better performance than other predictors in accuracy, MCC, and F_0.5-score.

Predictor*	TP	FP	TN	FN	Sensitivity	Specificity	Precision	Accuracy	MCC	F-score	F0.5-score
ProteRNA	222	340	8563	660	25.17%	96.18%	39.50%	89.78%	0.2628	0.3075	0.3546
PiRaNhA	265	538	8365	617	30.05%	93.96%	33.00%	88.20%	0.2504	0.3145	0.3236
Pprint	447	1782	7121	435	50.68%	79.98%	20.05%	77.34%	0.2094	0.2873	0.2281
BindN	348	1613	7290	534	39.46%	81.88%	17.75%	78.06%	0.1527	0.2449	0.1994
PRIP	131	835	8068	751	14.85%	90.62%	13.56%	83.79%	0.0526	0.1418	0.1380

*Order by MCC.

Table 5 shows the Top-10 predictions by different predictors ordered by the MCC and precision among 33 independent testing samples. In terms of MCC, we can find that at least 4 predictors have predictions in 6 protein chains of Top-10 ranking. In terms of precision, we can find that at least 4 predictors have predictions in 7 protein chains of Top-10 ranking. Figure 1 (a) and (b) show the predicted RNA-binding residues in the case of E. coli SelB protein with PDB ID 2PJPA [41] by ProteRNA and PiRaNhA respectively. In this case, because WildSpan does not mine any patterns for 2PJPA, only ProteRNA_SVM gives prediction result. Figure 2 (a) and (b) show the predicted RNA-binding residues in the case of RluA [42]. In this case, ProteRNA outperforms than other predictors in terms of MCC. BindN and Pprint tend to predict more and more class label for each residue; therefore, they recommend more and more false positives and false negatives. Meanwhile, PRIP and PiRaNhA have similar performance in predicting RNA-binding residues in the case of 2I82C. These figures are rendered by PyMOL (http://www.pymol.org/).

Rank	ProteRNA	PiRaNhA	Pprint	BindN	PRIP
(a) Rank by MCC
1	2PJP_A	2QAM_Z	2QAM_Z	2QAM_Z	2PY9_C
2	2QAM_Z	2QBE_T	1VS8_O	2PY9_C	2QAM_Z
3	2PY9_C	2DER_B	2PJP_A	1VS8_O	2HYI_D
4	1VS8_O	2G4B_A	2PY9_C	2QBE_T	2NQP_B
5	2G4B_A	1VS8_O	2GYA_3	2G4B_A	2IY5_A
6	2Q66_A	2PY9_C	2DER_B	2DER_B	1VS8_O
7	2I82_C	2G8K_A	2G4B_A	2J0Q_A	2I82_C
8	2DER_B	2OZB_B	2QBE_T	2IPY_B	2V47_C
9	2QBE_T	2V47_C	2DR2_A	2HVR_A	2GJE_A
10	2DR2_A	2GJE_D	2QKK_F	2GTT_G	2JEA_B
MCC of Rank 1	0.6668	0.6415	0.6006	0.4364	0.5521
MCC of Rank 10	0.3063	0.2719	0.2390	0.1951	0.0517
(b) Rank by precision
1	2Q66_A	2GYA_3	2GYA_3	2QAM_Z	2QAM_Z
2	2PJP_A	2QBE_T	2QAM_Z	2QBE_T	2PY9_C
3	2PY9_C	2QAM_Z	2QBE_T	1VS8_O	1VS8_O
4	2QAM_Z	1VS8_O	1VS8_O	2PY9_C	2QBE_T
5	2DER_B	2OZB_B	2PY9_C	2GYA_3	2I82_C
6	1VS8_O	2PY9_C	2DER_B	2G4B_A	2V47_C
7	2GYA_3	2DER_B	2V47_C	2J0Q_A	2IY5_A
8	2I82_C	2V47_C	2I82_C	2I82_C	2GYA_3
9	2QBE_T	2G4B_A	2G4B_A	2DER_B	2G4B_A
10	2G8K_A	2Q66_A	2GJE_A	2V47_C	2GJE_A
Precision of Rank 1	100.00%	100.00%	76.92%	76.47%	75.00%
Precision of Rank 10	50.00%	35.71%	25.00%	24.00%	13.33%

Values in bold indicate listing in the top 10 by at least 5 predictors.

Values in bold and italics indicate listing in the top 10 by at least 4 predictors.

This article presents the design of a sequence based predictor aiming to identify the RNA-binding residues in a RNA-binding protein by machine learning and pattern mining approaches. RNA-binding proteins play different roles while interacting with different categories of RNAs to represent diverse functions. However, RNA-binding proteins are accommodated by the presence of multiple copies of these RNA-binding domains presented in various structural arrangements to expand the functional repertoire of RNA-binding proteins. Therefore, it is still difficult to predict RNA-binding residues in a RNA-binding protein. Furthermore, predicting RNA-binding residues in a RNA-binding protein can help biologists reveal site-directed mutagenesis in wet-lab experiments.

In the experiments reported in this article, ProteRNA used not only evolutionary profile with predicted secondary structure but also sequence conservation information. Although these conserved residues can be functional conserved residues or structural conserved residues, they also provide clues to indicate the important residues in a protein sequence. In the independent testing dataset, ProteRNA has been able to deliver overall accuracy of 89.78%, MCC of 0.2628, F-score of 0.3075, and F_0.5-score of 0.3546. It is anticipated that the prediction accuracy delivered by ProteRNA will continue to improve as the number of protein-RNA complexes deposited in the PDB continues to grow and the number of training samples that can be exploited continues to increase accordingly. Nevertheless, it is the computational biologists’ primary interest to develop more advanced prediction mechanisms. In this respect, we believe that, as the number of protein-RNA complexes deposited in the PDB increases, we can obtain more insights about the key physiochemical properties that play essential roles in protein-RNA interactions and then we will be able to develop more advanced prediction mechanisms accordingly. In addition, we will exploit the experiences learned in this study in order to design specific predictors for other families of proteins interacting with RNA. We believe that different families of proteins may have very different characteristics. Therefore, concerning a specific type of proteins, a specifically-designed predictor should be able to deliver superior performance in compared to a general-purpose predictor.