Abstract
At the end of 2021, there were more than 200 million proteins in which their molecular functions were still unknown. As the empirical determination of these functions is slow and expensive, several research groups around the world have applied machine learning to perform the prediction of protein functions. In this work, we evaluate the use of Transformer architectures to classify protein molecular functions. Our classifier uses the embeddings resulting from two Transformer-based architectures as input to a Multi-Layer Perceptron classifier. This model got \(F_{\max }\) of 0.562 in our database and, when we applied this model to the same database used by DeepGOPlus, we reached the value of 0.617, surpassing the best result available in the literature.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Altschul, S.F., et al.: Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. Nucleic Acids Res. 25(17), 3389–3402 (1997)
Ashburner, M., et al.: Gene Ontology: tool for the unification of biology. Nat. Genet. 25(1), 25–29 (2000)
Bonetta, R., Valentino, G.: Machine learning techniques for protein function prediction. Proteins: Struct. Funct. Bioinform. 88(3), 397–413 (2020)
Brown, T.B., et al.: Language models are few-shot learners. arXiv:2005.14165 (2020)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805 (2018)
Elnaggar, A., et al.: ProtTrans: Towards Cracking the Language of Life’s Code Through Self-Supervised Deep Learning and High Performance Computing. arXiv:2007.06225 (2021)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Kingma, D.P., Ba, J.: Adam: A Method for Stochastic Optimization. arXiv:1412.6980 (2014)
Kulmanov, M., Hoehndorf, R.: DeepGOPlus: improved protein function prediction from sequence. Bioinformatics 36(2), 422–429 (2019)
Kulmanov, M., Khan, M.A., Hoehndorf, R.: DeepGO: predicting protein functions from sequence and interactions using a deep ontology-aware classifier. Bioinformatics 34(4), 660–668 (2018)
Liu, Y., et al.: RoBERTa: a robustly optimized bert pretraining approach. arXiv:1907.11692 (2019)
Maiya, A.S.: ktrain: A Low-Code Library for Augmented Machine Learning. arXiv:2004.10703 (2020)
Ranjan, A., Fernandez-Baca, D., Tripathi, S., Deepak, A.: An ensemble Tf-Idf based approach to protein function prediction via sequence segmentation. IEEE/ACM Trans. Comput. Biol. Bioinf. 14(8), 1–12 (2021)
Strodthoff, N., Wagner, P., Wenzel, M., Samek, W.: UDSMProt: universal deep sequence models for protein classification. Bioinformatics 36(8), 2401–2409 (2020)
UniProt: UniProt Database (2021). https://www.uniprot.org/
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (NIPS), pp. 5998–6008 (2017)
Weaver, R.F.: Molecular Biology, 5th edn. McGraw-Hill, New York (2012)
Wolf, T., et al.: Huggingface’s transformers: state-of-the-art natural language processing. arXiv:1910.03771 (2019)
You, R., Huang, X., Zhu, S.: DeepText2GO: improving large-scale protein function prediction with deep semantic text representation. Methods 145(1), 82–90 (2018)
You, R., Zhang, Z., Xiong, Y., Sun, F., Mamitsuka, H., Zhu, S.: GOLabeler: improving sequence-based large-scale protein function prediction by learning to rank. Bioinformatics 34(14), 2465–2473 (2018)
Zhao, Y., Wang, J., Chen, J., Zhang, X., Guo, M., Yu, G.: A literature review of gene function prediction by modeling gene ontology. Front. Genet. 11, 400 (2020)
Zhou, N., et al.: The CAFA challenge reports improved protein function prediction and new functional annotations for hundreds of genes through experimental screens. Genome Biol. 20(1), 244 (2019)
Acknowledgements
This research was supported by São Paulo Research Foundation (FAPESP) [grant numbers 2015/11937-9, 2017/12646-3, 2017/16246-0, 2017/12646-3 and 2019/20875-8], the National Council for Scientific and Technological Development (CNPq) [grant numbers 161015/2021-2, 304380/2018-0 and 309330/2018-1], and Coordination for the Improvement of Higher Education Personnel (CAPES).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
de Mello, F.L., de Oliveira, G.B., Pedrini, H., Dias, Z. (2023). Prediction of Protein Molecular Functions Using Transformers. In: Rutkowski, L., Scherer, R., Korytkowski, M., Pedrycz, W., Tadeusiewicz, R., Zurada, J.M. (eds) Artificial Intelligence and Soft Computing. ICAISC 2022. Lecture Notes in Computer Science(), vol 13589. Springer, Cham. https://doi.org/10.1007/978-3-031-23480-4_32
Download citation
DOI: https://doi.org/10.1007/978-3-031-23480-4_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-23479-8
Online ISBN: 978-3-031-23480-4
eBook Packages: Computer ScienceComputer Science (R0)