Deep Learning Approaches for the Prediction of Protein Functional Sites

Overview

Journal Molecules

Publisher MDPI

Date 2025 Jan 25

PMID 39860084

Authors

Borja Pitarch

Florencio Pazos

Affiliations

Soon will be listed here.

Abstract

Knowing which residues of a protein are important for its function is of paramount importance for understanding the molecular basis of this function and devising ways of modifying it for medical or biotechnological applications. Due to the difficulty in detecting these residues experimentally, prediction methods are essential to cope with the sequence deluge that is filling databases with uncharacterized protein sequences. Deep learning approaches are especially well suited for this task due to the large amounts of protein sequences for training them, the trivial codification of this sequence data to feed into these systems, and the intrinsic sequential nature of the data that makes them suitable for language models. As a consequence, deep learning-based approaches are being applied to the prediction of different types of functional sites and regions in proteins. This review aims to give an overview of the current landscape of methodologies so that interested users can have an idea of which kind of approaches are available for their proteins of interest. We also try to give an idea of how these systems work, as well as explain their limitations and high dependence on the training set so that users are aware of the quality of expected results.

References

Boadu F, Lee A, Cheng J . Deep learning methods for protein function prediction. Proteomics. 2024; 25(1-2):e2300471. PMC: 11735672. DOI: 10.1002/pmic.202300471. View

Bernhofer M, Rost B . TMbed: transmembrane proteins predicted through language model embeddings. BMC Bioinformatics. 2022; 23(1):326. PMC: 9358067. DOI: 10.1186/s12859-022-04873-x. View

Zhou Y, Myung Y, Rodrigues C, Ascher D . DDMut-PPI: predicting effects of mutations on protein-protein interactions using graph-based deep learning. Nucleic Acids Res. 2024; 52(W1):W207-W214. PMC: 11223791. DOI: 10.1093/nar/gkae412. View

Zhou N, Jiang Y, Bergquist T, Lee A, Kacsoh B, Crocker A . The CAFA challenge reports improved protein function prediction and new functional annotations for hundreds of genes through experimental screens. Genome Biol. 2019; 20(1):244. PMC: 6864930. DOI: 10.1186/s13059-019-1835-8. View

Sigrist C, de Castro E, Cerutti L, Cuche B, Hulo N, Bridge A . New and continuing developments at PROSITE. Nucleic Acids Res. 2012; 41(Database issue):D344-7. PMC: 3531220. DOI: 10.1093/nar/gks1067. View

Kaleel M, Zheng Y, Chen J, Feng X, Simpson J, Pollastri G . SCLpred-EMS: subcellular localization prediction of endomembrane system and secretory pathway proteins by Deep N-to-1 Convolutional Neural Networks. Bioinformatics. 2020; 36(11):3343-3349. DOI: 10.1093/bioinformatics/btaa156. View

Jumper J, Evans R, Pritzel A, Green T, Figurnov M, Ronneberger O . Highly accurate protein structure prediction with AlphaFold. Nature. 2021; 596(7873):583-589. PMC: 8371605. DOI: 10.1038/s41586-021-03819-2. View

Cagiada M, Bottaro S, Lindemose S, Schenstrom S, Stein A, Hartmann-Petersen R . Discovering functionally important sites in proteins. Nat Commun. 2023; 14(1):4175. PMC: 10345196. DOI: 10.1038/s41467-023-39909-0. View

Wilson C, Choy W, Karttunen M . AlphaFold2: A Role for Disordered Protein/Region Prediction?. Int J Mol Sci. 2022; 23(9). PMC: 9104326. DOI: 10.3390/ijms23094591. View

10.

Savojardo C, Martelli P, Casadio R . Finding functional motifs in protein sequences with deep learning and natural language models. Curr Opin Struct Biol. 2023; 81:102641. DOI: 10.1016/j.sbi.2023.102641. View

11.

Wang J, Lisanza S, Juergens D, Tischer D, Watson J, Castro K . Scaffolding protein functional sites using deep learning. Science. 2022; 377(6604):387-394. PMC: 9621694. DOI: 10.1126/science.abn2100. View

12.

Madeo G, Savojardo C, Martelli P, Casadio R . BetAware-Deep: An Accurate Web Server for Discrimination and Topology Prediction of Prokaryotic Transmembrane β-barrel Proteins. J Mol Biol. 2021; 433(11):166729. DOI: 10.1016/j.jmb.2020.166729. View

13.

Jones D . Setting the standards for machine learning in biology. Nat Rev Mol Cell Biol. 2019; 20(11):659-660. DOI: 10.1038/s41580-019-0176-5. View

14.

Brandes N, Goldman G, Wang C, Ye C, Ntranos V . Genome-wide prediction of disease variant effects with a deep protein language model. Nat Genet. 2023; 55(9):1512-1522. PMC: 10484790. DOI: 10.1038/s41588-023-01465-0. View

15.

Zou J, Huss M, Abid A, Mohammadi P, Torkamani A, Telenti A . A primer on deep learning in genomics. Nat Genet. 2018; 51(1):12-18. PMC: 11180539. DOI: 10.1038/s41588-018-0295-5. View

16.

Walsh I, Fishman D, Garcia-Gasulla D, Titma T, Pollastri G, Harrow J . DOME: recommendations for supervised machine learning validation in biology. Nat Methods. 2021; 18(10):1122-1127. DOI: 10.1038/s41592-021-01205-4. View

17.

Diaz D, Kulikova A, Ellington A, Wilke C . Using machine learning to predict the effects and consequences of mutations in proteins. Curr Opin Struct Biol. 2023; 78:102518. PMC: 9908841. DOI: 10.1016/j.sbi.2022.102518. View

18.

Derry A, Altman R . COLLAPSE: A representation learning framework for identification and characterization of protein structural sites. Protein Sci. 2022; 32(2):e4541. PMC: 9847082. DOI: 10.1002/pro.4541. View

19.

Torng W, Altman R . High precision protein functional site detection using 3D convolutional neural networks. Bioinformatics. 2019; 35(9):1503-1512. PMC: 6499237. DOI: 10.1093/bioinformatics/bty813. View

20.

Shokralla S, Spall J, Gibson J, Hajibabaei M . Next-generation sequencing technologies for environmental DNA research. Mol Ecol. 2012; 21(8):1794-805. DOI: 10.1111/j.1365-294X.2012.05538.x. View