journal article·2023-07-15Open access

A Deep Model for Species-Specific Prediction of Ribonucleic-Acid-Binding Protein with Short Motifs

Zhi-Sen Wei, Jun Rao, Yao-Jin Lin

Applied Sciences· Volume 13· Issue 14

Abstract

RNA-binding proteins (RBPs) play an important role in the synthesis and degradation of ribonucleic acid (RNA) molecules. The rapid and accurate identification of RBPs is essential for understanding the mechanisms of cell activity. Since identifying RBPs experimentally is expensive and time-consuming, computational methods have been explored to predict RBPs directly from protein sequences. In this paper, we developed an RBP prediction method named CnnRBP based on a convolution neural network. CnnRBP derived a sparse high-dimensional di- and tripeptide frequency feature vector from a protein sequence and then reduced this vector to a low-dimensional one using the Light Gradient Boosting Machine (LightGBM) algorithm. Then, the low-dimensional vectors derived from both RNA-binding proteins and non-RNA-binding proteins were fed to a multi-layer one-dimensional convolution network. Meanwhile, the SMOTE algorithm was used to alleviate the class imbalance in the training data. Extensive experiments showed that the proposed method can extract discriminative features to identify RBPs effectively. With 10-fold cross-validation on the training datasets, CnnRBP achieved AUC values of 99.98%, 99.69% and 96.72% for humans, E. coli and Salmonella, respectively. On the three independent datasets, CnnRBP achieved AUC values of 0.91, 0.96 and 0.91, outperforming the recent tripeptide-based method (i.e., TriPepSVM) by 8%, 4% and 5%, respectively. Compared with the state-of-the-art CNN-based predictor (i.e., iDRBP_MMC), CnnRBP achieved MCC values of 0.67, 0.68 and 0.73 with significant improvements by 6%, 6% and 15%, respectively. In addition, the cross-species testing shows that CnnRBP has a robust generalization performance for cross-species RBP prediction between close species.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: RNA and protein synthesis mechanisms · Machine Learning in Bioinformatics · RNA modifications and cancer

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

School of Computer Science, Minnan Normal University, Zhangzhou 363000, China

Fujian Province Universities Key Laboratory of Data Science and Intelligent Application, Minnan Normal University, Zhangzhou 363000, China

Funding

National Natural Science Foundation of China · Natural Science Foundation of Fujian · Education Department of Fujian Province

References (27)

Show source-provided references
1. RIP-seq analysis of eukaryotic Sm proteins identifies three major categories of Sm-containing ribonucleoproteins10.1186/gb-2014-15-1-r7 ↗
2. Advances in the characterization of RNA-binding proteins10.1002/wrna.1378 ↗
3. Pervasive Chromatin-RNA Binding Protein Interactions Enable RNA-Based Regulation of Transcription10.1016/j.cell.2019.06.001 ↗
4. Genome-wide CRISPR screen identifies HNRNPL as a prostate cancer dependency regulating RNA splicing10.1073/pnas.1617467114 ↗
5. A census of human RNA-binding proteins10.1038/nrg3813 ↗
6. A brave new world of RNA-binding proteins10.1038/nrm.2017.130 ↗
7. Comprehensive Identification of RNA-Binding Domains in Human Cells10.1016/j.molcel.2016.06.029 ↗
8. LightGBM: A Highly Efficient Gradient Boosting Decision Tree
9. BindUP: A web server for non-homology-based prediction of DNA and RNA binding proteins10.1093/nar/gkw454 ↗
10. SVM based prediction of RNA-binding proteins using binding residues and evolutionary information10.1002/jmr.1061 ↗
11. catRAPID signature: Identification of ribonucleoproteins and RNA-binding regions10.1093/bioinformatics/btv629 ↗
12. APRICOT: An integrated computational pipeline for the sequence-based identification and characterization of RNA-binding proteins10.1093/nar/gkx137 ↗
13. RBPPred: Predicting RNA-binding proteins from sequence using SVM10.1093/bioinformatics/btw730 ↗
14. SPOT-Seq-RNA: Predicting Protein-RNA Complex Structure and RNA-Binding Function by Fold Recognition and Binding Affinity Prediction10.1007/978-1-4939-0366-5_9 ↗
15. TriPepSVM: De novo prediction of RNA-binding proteins based on short amino acid motifs10.1093/nar/gkz203 ↗
16. A Survey on Deep Learning: Algorithms, Techniques, and Applications
17. DeepPPSite: A deep learning-based model for analysis and prediction of phosphorylation sites using efficient sequence information10.1016/j.ab.2020.113955 ↗
18. Accurate prediction of protein-ATP binding residues using position-specific frequency matrix10.1016/j.ab.2021.114241 ↗
19. Learning embedding features based on multisense-scaled attention architecture to improve the predictive performance of anticancer peptides10.1093/bioinformatics/btab560 ↗
20. DeepMC-iNABP: Deep learning for multiclass identification and classification of nucleic acid-binding proteins10.1016/j.csbj.2022.04.029 ↗
21. Deep-RBPPred: Predicting RNA binding proteins in the proteome scale based on deep learning10.1038/s41598-018-33654-x ↗
22. Du, X., Diao, Y., Yao, Y., Zhu, H., Yan, Y., and Zhang, Y. (2018, January 3–6). DeepMVF-RBP: Deep Multi-view Fusion Representation Learning for RNA-binding Proteins Prediction. Proceedings of the 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Madrid, Spain.10.1109/BIBM.2018.8621102 ↗
23. econvRBP: Improved ensemble convolutional neural networks for RNA binding protein prediction directly from sequence10.1016/j.ymeth.2019.09.008 ↗
24. iDRBP_MMC: Identifying DNA-Binding Proteins and RNA-Binding Proteins Based on Multi-Label Learning Model and Motif-Based Convolutional Neural Network10.1016/j.jmb.2020.09.008 ↗
25. Identifying RNA-binding proteins using multi-label deep learning10.1007/s11432-018-9558-2 ↗
26. rBPDL: Predicting RNA-Binding Proteins Using Deep Learning10.1109/JBHI.2021.3069259 ↗
27. SMOTE: Synthetic Minority Over-sampling Technique10.1613/jair.953 ↗