PRITrans: A Transformer-Based Approach for the Prediction of the Effects of Missense Mutation on Protein-RNA Interactions

Overview

Journal Int J Mol Sci

Publisher MDPI

Specialties Biochemistry
Chemistry
Molecular Biology

Date 2024 Nov 27

PMID 39596413

Authors

Fang Ge

Cui-Feng Li

Chao-Ming Zhang

Ming Zhang

Dong-Jun Yu

Affiliations

Soon will be listed here.

Abstract

Protein-RNA interactions are essential to many cellular functions, and missense mutations in RNA-binding proteins can disrupt these interactions, often leading to disease. To address this, we developed PRITrans, a specialized computational method aimed at predicting the effects of missense mutations on protein-RNA interactions, which is vital for understanding disease mechanisms and advancing molecular biology research. PRITrans is a novel deep learning model designed to predict the effects of missense mutations on protein-RNA interactions, which employs a Transformer architecture enhanced with multiscale convolution modules for comprehensive feature extraction. Its primary innovation lies in integrating protein language model embeddings with a deep feature fusion strategy, effectively handling high-dimensional feature representations. By utilizing multi-layer self-attention mechanisms, PRITrans captures nuanced, high-level sequence information, while multiscale convolutions extract features across various depths, thereby enhancing predictive accuracy. Consequently, this architecture enables significant improvements in ΔΔG prediction compared to traditional approaches. We validated PRITrans using three different cross-validation strategies on two newly reconstructed mutation datasets, S315 and S630 (containing 315 forward and 315 reverse mutations). The results consistently demonstrated PRITrans's strong performance on both datasets. PRITrans demonstrated strong predictive capability, achieving a Pearson correlation coefficient of 0.741 and a root mean square error (RMSE) of 1.168 kcal/mol on the S630 dataset. Moreover, its robust performance extended to independent test sets, achieving a Pearson correlation of 0.699 and an RMSE of 1.592 kcal/mol. These results underscore PRITrans's potential as a powerful tool for protein-RNA interaction studies. Moreover, when tested against existing prediction methods on an independent dataset, PRITrans showed improved predictive accuracy and robustness.

References

Pan Q, Nguyen T, Ascher D, Pires D . Systematic evaluation of computational tools to predict the effects of mutations on protein stability in the absence of experimental structures. Brief Bioinform. 2022; 23(2). PMC: 9155634. DOI: 10.1093/bib/bbac025. View

Yu D, Hu J, Yan H, Yang X, Yang J, Shen H . Enhancing protein-vitamin binding residues prediction by multiple heterogeneous subspace SVMs ensemble. BMC Bioinformatics. 2014; 15:297. PMC: 4261549. DOI: 10.1186/1471-2105-15-297. View

Wu J, Liu Y, Ge F, Yu D . Prediction of protein-ATP binding residues using multi-view feature learning via contextual-based co-attention network. Comput Biol Med. 2024; 172:108227. DOI: 10.1016/j.compbiomed.2024.108227. View

Hillisch A, Lorenz M, Diekmann S . Recent advances in FRET: distance determination in protein-DNA complexes. Curr Opin Struct Biol. 2001; 11(2):201-7. DOI: 10.1016/s0959-440x(00)00190-1. View

Fabian M, Sonenberg N, Filipowicz W . Regulation of mRNA translation and stability by microRNAs. Annu Rev Biochem. 2010; 79:351-79. DOI: 10.1146/annurev-biochem-060308-103103. View

Yan Z, Ge F, Liu Y, Zhang Y, Li F, Song J . TransEFVP: A Two-Stage Approach for the Prediction of Human Pathogenic Variants Based on Protein Sequence Embedding Fusion. J Chem Inf Model. 2024; 64(4):1407-1418. DOI: 10.1021/acs.jcim.3c02019. View

Iqbal S, Ge F, Li F, Akutsu T, Zheng Y, Gasser R . PROST: AlphaFold2-aware Sequence-Based Predictor to Estimate Protein Stability Changes upon Missense Mutations. J Chem Inf Model. 2022; 62(17):4270-4282. DOI: 10.1021/acs.jcim.2c00799. View

Teh H, Peh W, Su X, Thomsen J . Characterization of protein--DNA interactions using surface plasmon resonance spectroscopy with various assay schemes. Biochemistry. 2007; 46(8):2127-35. DOI: 10.1021/bi061903t. View

Maurya P, Mishra A, Yadav B, Singh S, Kumar P, Chaudhary A . Role of Y Box Protein-1 in cancer: As potential biomarker and novel therapeutic target. J Cancer. 2017; 8(10):1900-1907. PMC: 5556654. DOI: 10.7150/jca.17689. View

10.

Chen X, Li A, Sun B, Yang Y, Han Y, Yuan X . 5-methylcytosine promotes pathogenesis of bladder cancer through stabilizing mRNAs. Nat Cell Biol. 2019; 21(8):978-990. DOI: 10.1038/s41556-019-0361-y. View

11.

Lin Z, Akin H, Rao R, Hie B, Zhu Z, Lu W . Evolutionary-scale prediction of atomic-level protein structure with a language model. Science. 2023; 379(6637):1123-1130. DOI: 10.1126/science.ade2574. View

12.

Bryant P, Pozzati G, Elofsson A . Improved prediction of protein-protein interactions using AlphaFold2. Nat Commun. 2022; 13(1):1265. PMC: 8913741. DOI: 10.1038/s41467-022-28865-w. View

13.

Hu L, Wang X, Huang Y, Hu P, You Z . A survey on computational models for predicting protein-protein interactions. Brief Bioinform. 2021; 22(5). DOI: 10.1093/bib/bbab036. View

14.

Peng Y, Sun L, Jia Z, Li L, Alexov E . Predicting protein-DNA binding free energy change upon missense mutations using modified MM/PBSA approach: SAMPDI webserver. Bioinformatics. 2017; 34(5):779-786. PMC: 6048991. DOI: 10.1093/bioinformatics/btx698. View

15.

Mitchell S, Parker R . Principles and properties of eukaryotic mRNPs. Mol Cell. 2014; 54(4):547-58. DOI: 10.1016/j.molcel.2014.04.033. View

16.

Barik A, Nithin C, Karampudi N, Mukherjee S, Bahadur R . Probing binding hot spots at protein-RNA recognition sites. Nucleic Acids Res. 2015; 44(2):e9. PMC: 4737170. DOI: 10.1093/nar/gkv876. View

17.

Doyle . Characterization of binding interactions by isothermal titration calorimetry. Curr Opin Biotechnol. 1997; 8(1):31-5. DOI: 10.1016/s0958-1669(97)80154-1. View

18.

Lu H, Zhou Q, He J, Jiang Z, Peng C, Tong R . Recent advances in the development of protein-protein interactions modulators: mechanisms and clinical trials. Signal Transduct Target Ther. 2020; 5(1):213. PMC: 7511340. DOI: 10.1038/s41392-020-00315-3. View

19.

Soleymani F, Paquet E, Viktor H, Michalowski W, Spinello D . Protein-protein interaction prediction with deep learning: A comprehensive review. Comput Struct Biotechnol J. 2022; 20:5316-5341. PMC: 9520216. DOI: 10.1016/j.csbj.2022.08.070. View

20.

Jones S, Daley D, Luscombe N, Berman H, Thornton J . Protein-RNA interactions: a structural analysis. Nucleic Acids Res. 2001; 29(4):943-54. PMC: 29619. DOI: 10.1093/nar/29.4.943. View