CoChat

Opportunities and Challenges for Machine Learning-Assisted Enzyme Engineering

Open access
Yang, Jason, Li, Francesca-Zhoufan, Arnold, Frances H. · 2024 · ACS Central Science
Cited by 246

The DOI matches its Crossref record; 240 of the 240 references it cites were found in a registry or an index.

Abstract

Enzymes can be engineered at the level of their amino acid sequences to optimize key properties such as expression, stability, substrate range, and catalytic efficiency-or even to unlock new catalytic activities not found in nature. Because the search space of possible proteins is vast, enzyme engineering usually involves discovering an enzyme starting point that has some level of the desired activity followed by directed evolution to improve its "fitness" for a desired application. Recently, machine learning (ML) has emerged as a powerful tool to complement this empirical process. ML models can contribute to (1) starting point discovery by functional annotation of known protein sequences or generating novel protein sequences with desired functions and (2) navigating protein fitness landscapes for fitness optimization by learning mappings between protein sequences and their associated fitness values. In this Outlook, we explain how ML complements enzyme engineering and discuss its future potential to unlock improved engineering outcomes.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1021/acscentsci.3c01275

Cites

240 of 240 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 240 references

Research works printed but not linked: 43

  1. 10.1101/2023.10.13.562298 · DOI
  2. 10.26434/chemrxiv-2023-jzw9w · doi:10.26434/chemrxiv-2023-jzw9w
  3. 10.1126/science.abj8754 · doi:10.1126/science.abj8754 · Paper page
  4. 10.1126/science.ade2574 · doi:10.1126/science.ade2574 · Paper page
  5. 10.1021/jacs.2c11118 · doi:10.1021/jacs.2c11118
  6. 10.1101/2023.01.23.525232 · DOI
  7. 10.1101/2023.03.14.532539 · DOI
  8. 10.1101/2022.04.14.488405 · DOI · Paper page
  9. Trippe, B. L.; Yim, J.; Tischer, D.; Baker, D.; Broderick, T.; Barzilay, R.; Jaakkola, T. Diffusion Probabilistic Modeling of Protein Backbones in 3D for the Motif-Scaffolding Problem. arXiv June 8, 2022. http://arxiv.org/abs/2206.04119. · arXiv
  10. 10.1038/s41586-021-04184-w · doi:10.1038/s41586-021-04184-w · Paper page
  11. Lin, Y.; AlQuraishi, M. Generating Novel, Designable, and Diverse Protein Structures by Equivariantly Diffusing Oriented Residue Clouds. arXiv June 6, 2023. http://arxiv.org/abs/2301.12485. · arXiv
  12. 10.1101/2023.10.03.560713 · DOI · Paper page
  13. 10.1101/2023.05.20.541582 · DOI
  14. 10.1101/2023.09.02.556057 · DOI
  15. 10.1101/2023.09.25.559319 · DOI · Paper page
  16. 10.1101/2023.10.27.564339 · doi:10.1101/2023.10.27.564339
  17. Notin, P.; Dias, M.; Frazer, J.; Marchena-Hurtado, J.; Gomez, A.; Marks, D. S.; Gal, Y. Tranception: Protein Fitness Prediction with Autoregressive Transformers and Inference-Time Retrieval. arXiv May 27, 2022. http://arxiv.org/abs/2205.13760. · arXiv
  18. 10.1101/2023.10.10.561808 · doi:10.1101/2023.10.10.561808
  19. 10.1101/2022.05.19.492714 · DOI
  20. Hesslow, D.; Zanichelli, N.; Notin, P.; Poli, I.; Marks, D. RITA: A Study on Scaling Up Generative Protein Sequence Models. arXiv May 11, 2022. http://arxiv.org/abs/2205.05789. · arXiv
  21. 10.1101/2022.05.25.493516 · DOI · Paper page
  22. Detlefsen N. S., 2022, ArXiv201202679 Cs Q-Bio
  23. 10.1101/2023.12.13.571462 · DOI · Paper page
  24. 10.1101/2023.03.27.534314 · DOI · Paper page
  25. 10.1101/2023.04.20.537698 · doi:10.1101/2023.04.20.537698
  26. 10.1101/2023.12.20.572683 · DOI
  27. Xu Z., 2022, Proceedings of the 16th Machine Learning in Computational Biology meeting, 165, 78
  28. Corso, G.; Stärk, H.; Jing, B.; Barzilay, R.; Jaakkola, T. DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking. arXiv October 4, 2022. http://arxiv.org/abs/2210.01776. · arXiv
  29. 10.1021/acssynbio.2c00136 · doi:10.1021/acssynbio.2c00136
  30. Stanton, S.; Maddox, W.; Gruver, N.; Maffettone, P.; Delaney, E.; Greenside, P.; Wilson, A. G. Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders. arXiv July 12, 2022. http://arxiv.org/abs/2203.12742. · arXiv
  31. Gruver N., 2021, ICML Workshop on Computational Biology
  32. Sinai S., 2020, ArXiv201002141 Cs Math Q-Bio
  33. Brookes, D. H.; Listgarten, J. Design by Adaptive Sampling. arXiv February 10, 2020. http://arxiv.org/abs/1810.03714. · arXiv
  34. Kirjner, A.; Yim, J.; Samusevich, R.; Jaakkola, T.; Barzilay, R.; Fiete, I. Optimizing Protein Fitness Using Gibbs Sampling with Graph-Based Smoothing. arXiv July 2, 2023. http://arxiv.org/abs/2307.00494. · arXiv
  35. 10.1101/2023.01.30.526201 · DOI · Paper page
  36. Daulton S., 2021, arXiv
  37. Amin, A. N.; Weinstein, E. N.; Marks, D. S. Biological Sequence Kernels with Guaranteed Flexibility. arXiv April 6, 2023. http://arxiv.org/abs/2304.03775. · arXiv
  38. Nisonoff, H.; Wang, Y.; Listgarten, J. Augmenting Neural Networks with Priors on Function Values. arXiv October 14, 2022. http://arxiv.org/abs/2202.04798. · arXiv
  39. 10.1101/2022.10.31.514613 · DOI · Paper page
  40. 10.1101/2022.10.31.514613 · DOI · Paper page
  41. Ren Z., 2022, Proceedings of the 39th International Conference on Machine Learning, 162, 18520
  42. Wilson, A. G.; Hu, Z.; Salakhutdinov, R.; Xing, E. P. Deep Kernel Learning. arXiv November 6, 2015. http://arxiv.org/abs/1511.02222. · arXiv
  43. Ober, S. W.; Rasmussen, C. E.; van der Wilk, M. The Promises and Pitfalls of Deep Kernel Learning. arXiv July 7, 2021. http://arxiv.org/abs/2102.12108. · arXiv

Cited by

Metadata

Authors
Yang, J., Li, F.-Z., & Arnold, F. H.
Venue
ACS Central Science
Published
2024-02-05
Volume
10
Issue
2
Pages
226-241
ISSN
  • 2374-7943 (ISSN-L)
  • 2374-7951
OpenAlex
W4391544240
Cited by
246
References
240
FWCI
28.70
Type
journal article
Language
en
Open access
diamond
Funders
  • National Science Foundation Graduate Research Fellowship Program
  • Basic Energy Sciences (DE-SC0022218)
  • Amgen
  • Division of Chemical, Bioengineering, Environmental, and Transport Systems (CBET 1937902)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.