Using machine learning to predict the effects and consequences of mutations in proteins

Review

doi: 10.1016/j.sbi.2022.102518.

Epub 2023 Jan 3.

Affiliations

¹ Department of Chemistry, The University of Texas at Austin, 105 E 24TH St., Austin, 78712, Texas, USA; Department of Molecular Biosciences, The University of Texas at Austin, 100 East 24th St., Stop A5000, Austin, 78712, Texas, USA. Electronic address: https://twitter.com/aiproteins.
² Department of Integrative Biology, The University of Texas at Austin, 2415 Speedway, Stop C0930, Austin, 78712, Texas, USA.
³ Department of Molecular Biosciences, The University of Texas at Austin, 100 East 24th St., Stop A5000, Austin, 78712, Texas, USA. Electronic address: https://twitter.com/CSSBatUT.
⁴ Department of Integrative Biology, The University of Texas at Austin, 2415 Speedway, Stop C0930, Austin, 78712, Texas, USA. Electronic address: [email protected].

Item in Clipboard

Review

Daniel J Diaz et al.

Curr Opin Struct Biol.

2023 Feb.

doi: 10.1016/j.sbi.2022.102518.

Epub 2023 Jan 3.

Affiliations

¹ Department of Chemistry, The University of Texas at Austin, 105 E 24TH St., Austin, 78712, Texas, USA; Department of Molecular Biosciences, The University of Texas at Austin, 100 East 24th St., Stop A5000, Austin, 78712, Texas, USA. Electronic address: https://twitter.com/aiproteins.
² Department of Integrative Biology, The University of Texas at Austin, 2415 Speedway, Stop C0930, Austin, 78712, Texas, USA.
³ Department of Molecular Biosciences, The University of Texas at Austin, 100 East 24th St., Stop A5000, Austin, 78712, Texas, USA. Electronic address: https://twitter.com/CSSBatUT.
⁴ Department of Integrative Biology, The University of Texas at Austin, 2415 Speedway, Stop C0930, Austin, 78712, Texas, USA. Electronic address: [email protected].

Item in Clipboard

Abstract

Machine and deep learning approaches can leverage the increasingly available massive datasets of protein sequences, structures, and mutational effects to predict variants with improved fitness. Many different approaches are being developed, but systematic benchmarking studies indicate that even though the specifics of the machine learning algorithms matter, the more important constraint comes from the data availability and quality utilized during training. In cases where little experimental data are available, unsupervised and self-supervised pre-training with generic protein datasets can still perform well after subsequent refinement via hybrid or transfer learning approaches. Overall, recent progress in this field has been staggering, and machine learning approaches will likely play a major role in future breakthroughs in protein biochemistry and engineering.

Keywords:

Convolutional neural network; Deep learning; Hybrid learning; Mutational effect; Protein engineering; Transformer.

PubMed Disclaimer

Conflict of interest statement

Declaration of competing interest D.J.D. is a cofounder of Intelligent Proteins, LLC, which uses machine learning for problems of protein engineering. A.V.K., A.D.E., and C·O.W. declare that they have no conflict of interest.

Cited by

Advances in ligand-specific biosensing for structurally similar molecules.

Xi C, Diao J, Moon TS.

Xi C, et al.
Cell Syst. 2023 Dec 20;14(12):1024-1043. doi: 10.1016/j.cels.2023.10.009.
Cell Syst. 2023.

PMID: 38128482

Review.
Semantic search using protein large language models detects class II microcins in bacterial genomes.

Kulikova AV, Parker JK, Davies BW, Wilke CO.

Kulikova AV, et al.
bioRxiv. 2023 Nov 15:2023.11.15.567263. doi: 10.1101/2023.11.15.567263. Preprint.
bioRxiv. 2023.

PMID: 38014091
Free PMC article.
Ensemble Learning with Supervised Methods Based on Large-Scale Protein Language Models for Protein Mutation Effects Prediction.

Qu Y, Niu Z, Ding Q, Zhao T, Kong T, Bai B, Ma J, Zhao Y, Zheng J.

Qu Y, et al.
Int J Mol Sci. 2023 Nov 18;24(22):16496. doi: 10.3390/ijms242216496.
Int J Mol Sci. 2023.

PMID: 38003686
Free PMC article.
Machine Learning-Guided Protein Engineering.

Kouba P, Kohout P, Haddadi F, Bushuiev A, Samusevich R, Sedlar J, Damborsky J, Pluskal T, Sivic J, Mazurenko S.

Kouba P, et al.
ACS Catal. 2023 Oct 13;13(21):13863-13895. doi: 10.1021/acscatal.3c02743. eCollection 2023 Nov 3.
ACS Catal. 2023.

PMID: 37942269
Free PMC article.

Review.
Two sequence- and two structure-based ML models have learned different aspects of protein biochemistry.

Kulikova AV, Diaz DJ, Chen T, Cole TJ, Ellington AD, Wilke CO.

Kulikova AV, et al.
Sci Rep. 2023 Aug 16;13(1):13280. doi: 10.1038/s41598-023-40247-w.
Sci Rep. 2023.

PMID: 37587128
Free PMC article.

References

1. Zuckerkandl E, Pauling L, Evolutionary divergence and convergence in proteins, in: Bryson V, Vogel HJ (Eds.), Evolving Genes and Proteins, Academic Press, 1965, pp. 97–166.
1. Shakhnovich E, Protein folding thermodynamics and dynamics: Where physics, chemistry and biology meet, Chem Rev. 106 (2006) 1559–1588.
  
  –
  
  PMC
  
  –
  
  PubMed
1. Tokuriki N, Tawfik DS, Stability effects of mutations and protein evolvability, Current Opin. Struct. Biol 19 (2009) 596–604.
  
  –
  
  PubMed
1. Serohijos AWR, Shakhnovich EI, Merging molecular mechanism and evolution: theory and computation at the interface of biophysics and evolutionary population genetics, Current Opin. Struct. Biol 26 (2014) 84–91.
  
  –
  
  PMC
  
  –
  
  PubMed
1. Araya CL, Fowler DM, Deep mutational scanning: assessing protein function on a massive scale, Trends Biotech. 29 (2011) 435–442.
  
  –
  
  PMC
  
  –
  
  PubMed