Evaluating the Advancements in Protein Language Models for Encoding Strategies in Protein Function Prediction: a Comprehensive Review

Overview

Journal Front Bioeng Biotechnol

Date 2025 Feb 5

PMID 39906415

Authors

Jia-Ying Chen

Jing-Fu Wang

Yue Hu

Xin-Hui Li

Yu-Rong Qian

Chao-Lin Song

Affiliations

Soon will be listed here.

Abstract

Protein function prediction is crucial in several key areas such as bioinformatics and drug design. With the rapid progress of deep learning technology, applying protein language models has become a research focus. These models utilize the increasing amount of large-scale protein sequence data to deeply mine its intrinsic semantic information, which can effectively improve the accuracy of protein function prediction. This review comprehensively combines the current status of applying the latest protein language models in protein function prediction. It provides an exhaustive performance comparison with traditional prediction methods. Through the in-depth analysis of experimental results, the significant advantages of protein language models in enhancing the accuracy and depth of protein function prediction tasks are fully demonstrated.

References

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

Kulmanov M, Hoehndorf R . DeepGOPlus: improved protein function prediction from sequence. Bioinformatics. 2019; 36(2):422-429. PMC: 9883727. DOI: 10.1093/bioinformatics/btz595. View

Zhang X, Guo H, Zhang F, Wang X, Wu K, Qiu S . HNetGO: protein function prediction via heterogeneous network transformer. Brief Bioinform. 2023; 24(6). PMC: 10588005. DOI: 10.1093/bib/bbab556. View

Gligorijevic V, Barot M, Bonneau R . deepNF: deep network fusion for protein function prediction. Bioinformatics. 2018; 34(22):3873-3881. PMC: 6223364. DOI: 10.1093/bioinformatics/bty440. View

Yang X, Liu G, Feng G, Bu D, Wang P, Jiang J . GeneCompass: deciphering universal gene regulatory mechanisms with a knowledge-informed cross-species foundation model. Cell Res. 2024; 34(12):830-845. PMC: 11615217. DOI: 10.1038/s41422-024-01034-y. View

Zeng X, Zhang X, Zou Q . Integrative approaches for predicting microRNA function and prioritizing disease-related microRNA using biological interaction networks. Brief Bioinform. 2015; 17(2):193-203. DOI: 10.1093/bib/bbv033. View

Pearson W . Finding Protein and Nucleotide Similarities with FASTA. Curr Protoc Bioinformatics. 2016; 53:3.9.1-3.9.25. PMC: 5072362. DOI: 10.1002/0471250953.bi0309s53. View

Toronen P, Holm L . PANNZER-A practical tool for protein function prediction. Protein Sci. 2021; 31(1):118-128. PMC: 8740830. DOI: 10.1002/pro.4193. View

Liu Y, Hsu T, Chang C, Liao W, Chang J . GODoc: high-throughput protein function prediction using novel k-nearest-neighbor and voting algorithms. BMC Bioinformatics. 2020; 21(Suppl 6):276. PMC: 7672824. DOI: 10.1186/s12859-020-03556-9. View

10.

Boutet E, Lieberherr D, Tognolli M, Schneider M, Bansal P, Bridge A . UniProtKB/Swiss-Prot, the Manually Annotated Section of the UniProt KnowledgeBase: How to Use the Entry View. Methods Mol Biol. 2015; 1374:23-54. DOI: 10.1007/978-1-4939-3167-5_2. View

11.

Berman H, Henrick K, Nakamura H . Announcing the worldwide Protein Data Bank. Nat Struct Biol. 2003; 10(12):980. DOI: 10.1038/nsb1203-980. View

12.

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

13.

Bernardes J, Pedreira C . A review of protein function prediction under machine learning perspective. Recent Pat Biotechnol. 2013; 7(2):122-41. DOI: 10.2174/18722083113079990006. View

14.

Simoni R, Hill R, Vaughan M . Urease, the first crystalline enzyme and the proof that enzymes are proteins: the work of James B. Sumner. J Biol Chem. 2002; 277(35):23e. View

15.

Hu M, Alkhairy S, Lee I, Pillich R, Fong D, Smith K . Evaluation of large language models for discovery of gene set function. Nat Methods. 2024; 22(1):82-91. PMC: 11725441. DOI: 10.1038/s41592-024-02525-x. View

16.

Jensen L, Gupta R, Blom N, Devos D, Tamames J, Kesmir C . Prediction of human protein function from post-translational modifications and localization features. J Mol Biol. 2002; 319(5):1257-65. DOI: 10.1016/S0022-2836(02)00379-0. View

17.

. UniProt: the Universal Protein Knowledgebase in 2023. Nucleic Acids Res. 2022; 51(D1):D523-D531. PMC: 9825514. DOI: 10.1093/nar/gkac1052. View

18.

Colin P, Kintses B, Gielen F, Miton C, Fischer G, Mohamed M . Ultrahigh-throughput discovery of promiscuous enzymes by picodroplet functional metagenomics. Nat Commun. 2015; 6:10008. PMC: 4686663. DOI: 10.1038/ncomms10008. View

19.

Bonetta R, Valentino G . Machine learning techniques for protein function prediction. Proteins. 2019; 88(3):397-413. DOI: 10.1002/prot.25832. View

20.

Barabasi A, Gulbahce N, Loscalzo J . Network medicine: a network-based approach to human disease. Nat Rev Genet. 2010; 12(1):56-68. PMC: 3140052. DOI: 10.1038/nrg2918. View