CoChat

Machine Learning-Guided Protein Engineering

Open access
Kouba, Petr, Kohout, Pavel, Haddadi, Faraneh, Bushuiev, Anton, Samusevich, Raman, Sedlar, Jiri, Damborsky, Jiri, Pluskal, Tomas, Sivic, Josef, Mazurenko, Stanislav · 2023 · ACS Catalysis
Cited by 209

The DOI matches its Crossref record; 78 of the 78 references it cites were found in a registry or an index.

Abstract

Recent progress in engineering highly promising biocatalysts has increasingly involved machine learning methods. These methods leverage existing experimental and simulation data to aid in the discovery and annotation of promising enzymes, as well as in suggesting beneficial mutations for improving known targets. The field of machine learning for protein engineering is gathering steam, driven by recent success stories and notable progress in other areas. It already encompasses ambitious tasks such as understanding and predicting protein structure and function, catalytic efficiency, enantioselectivity, protein dynamics, stability, solubility, aggregation, and more. Nonetheless, the field is still evolving, with many challenges to overcome and questions to address. In this Perspective, we provide an overview of ongoing trends in this domain, highlight recent case studies, and examine the current limitations of machine learning-based methods. We emphasize the crucial importance of thorough experimental validation of emerging models before their use for rational protein design. We present our opinions on the fundamental problems and outline the potential directions for future research.

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/acscatal.3c02743

Cites

78 of 78 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 78 references

Research works printed but not linked: 292

  1. 10.1002/anie.202006648 · DOI · Paper page
  2. 10.1038/s43586-021-00044-z · DOI · Paper page
  3. 10.1016/j.jclepro.2018.09.244 · DOI · Paper page
  4. 10.1016/j.ymben.2021.12.006 · DOI
  5. 10.1111/1751-7915.13488 · DOI
  6. 10.1016/j.sbi.2021.01.010 · DOI
  7. 10.1038/s41578-023-00540-6 · doi:10.1038/s41578-023-00540-6
  8. 10.1039/D2MA00067A · DOI
  9. 10.1002/cite.202271102 · doi:10.1002/cite.202271102
  10. 10.1371/journal.pcbi.1010749 · DOI
  11. 10.1021/acscatal.9b04321 · DOI · Paper page
  12. 10.1016/j.sbi.2021.11.008 · DOI
  13. 10.1016/j.jbc.2021.100558 · DOI · Paper page
  14. 10.7554/eLife.82819 · DOI · Paper page
  15. 10.3389/fgene.2021.690049 · DOI · Paper page
  16. 10.48550/arXiv.2104.13478 · DOI · Paper page
  17. Calin O., 2020, Deep Learning Architectures, 10.1007/978-3-030-36721-3 · DOI
  18. Goodfellow I., 2016, Deep Learning
  19. 10.1093/bioinformatics/btaa1102 · DOI · Paper page
  20. 10.48550/arXiv.2210.01776 · arXiv · doi:10.48550/arxiv.2210.01776 · Paper page
  21. 10.48550/arXiv.2302.10907 · arXiv · doi:10.48550/arxiv.2302.10907
  22. 10.1021/acssynbio.0c00345 · DOI
  23. 10.48550/arXiv.2303.06275 · DOI
  24. 10.1101/2023.05.15.540857 · DOI
  25. 10.1016/j.csbj.2022.11.014 · doi:10.1016/j.csbj.2022.11.014
  26. 10.1038/s41587-022-01618-2 · DOI · Paper page
  27. Li, Y.; Rezaei, M. A.; Li, C.; Li, X. DeepAtom: A Framework for Protein-Ligand Binding Affinity Prediction. In Proceedings of the 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) , San Diego, CA, November 18–21, 2019; IEEE, 2019; pp 303–310. · DOI · Paper page
  28. 10.1021/acs.jcim.2c00306 · DOI
  29. 10.48550/arXiv.2210.13695 · DOI
  30. Igashov, I.; Stärk, H.; Vignac, C.; Satorras, V. G.; Frossard, P.; Welling, M.; Bronstein, M. M.; Correia, B. Equivariant 3D-Conditional Diffusion Models for Molecular Linker Design. OpenReview , February 1, 2023. https://openreview.net/forum?id=cnsHSSLnHVV. · DOI · Paper page
  31. Yang, A.; Nagrani, A.; Seo, P. H.; Miech, A.; Pont-Tuset, J.; Laptev, I.; Sivic, J.; Schmid, C. Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , Vancouver, Canada, June 2022, 2023; Computer Vision Foundation, 2023; pp 10714–10726. · DOI · Paper page
  32. 10.1109/TII.2021.3122801 · DOI
  33. 10.48550/arXiv.2210.02303 · DOI · Paper page
  34. Villegas, R.; Babaeizadeh, M.; Kindermans, P.J.; Moraldo, H.; Zhang, H.; Saffar, M. T.; Castro, S.; Kunze, J.; Erhan, D. Phenaki: Variable Length Video Generation from Open Domain Textual Descriptions. The Eleventh International Conference on Learning Representations , Kigali, Rwanda, May 1–5, 2023; OpenReview, 2023. https://openreview.net/pdf?id=vOEXS39nOF
  35. Singer, U.; Polyak, A.; Hayes, T.; Yin, X.; An, J.; Zhang, S.; Hu, Q.; Yang, H.; Ashual, O.; Gafni, O.; Parikh, D.; Gupta, S.; Taigman, Y. Make-A-Video: Text-to-Video Generation without Text-Video Data. The Eleventh International Conference on Learning Representations , Kigali, Rwanda, May 1–5, 2023; OpenReview, 2023. https://openreview.net/pdf?id=nJfylDvgzlq
  36. 10.2196/22590 · DOI · Paper page
  37. 10.1038/s41467-022-28865-w · doi:10.1038/s41467-022-28865-w · Paper page
  38. 10.1093/bib/bbaa257 · DOI · Paper page
  39. 10.1186/s13321-021-00488-1 · DOI · Paper page
  40. 10.1021/acs.jcim.0c01294 · DOI
  41. Hu W., 2020, Adv. Neural Inf. Process. Syst., 33, 22118
  42. 10.1093/nar/gkm998 · DOI · Paper page
  43. 10.1186/s12859-020-03546-x · DOI
  44. 10.1038/s41598-019-53324-w · DOI
  45. 10.1073/pnas.2113348119 · DOI
  46. 10.1042/ETLS20210225 · DOI
  47. Hermosilla, P.; Schäfer, M.; Lang, M.; Fackelmann, G.; Vázquez, P. P.; Kozlíková, B.; Krone, M.; Ritschel, T.; Ropinski, T. Intrinsic-Extrinsic Convolution and Pooling for Learning on 3D Protein Structures. Ninth International Conference on Learning Representations , May 3–7, 2021; OpenReview, 2021.
  48. 10.1038/s41467-022-29939-5 · DOI · Paper page
  49. 10.1038/s41467-021-23303-9 · DOI · Paper page
  50. 10.1038/s41467-023-36736-1 · DOI · Paper page
  51. Vaswani A., 2017, Adv. Neural Inf. Process. Syst., 30, 5999
  52. Fuchs F., 2020, Adv. Neural Inf. Process. Syst., 33, 1970
  53. 10.1038/s41467-022-29443-w · DOI · Paper page
  54. Meier J., 2021, Adv. Neural Inf. Process. Syst., 34, 29287
  55. 10.1126/science.ade2574 · doi:10.1126/science.ade2574 · Paper page
  56. Zhang, Z.; Xu, M.; Jamasb, A.; Chenthamarakshan, V.; Lozano, A.; Das, P.; Tang, J. Protein Representation Learning by Geometric Structure Pretraining. The Eleventh International Conference on Learning Representations , Kigali, Rwanda, May 1–5, 2023; OpenReview, 2023. https://openreview.net/pdf?id=to3qCB3tOh9
  57. 10.1039/D1CC04635G · DOI
  58. 10.1016/S1367-5931(00)00206-4 · DOI · Paper page
  59. Brown T., 2020, Adv. Neural Inf. Process. Syst., 33, 1877
  60. OpenAI. GPT-4 Technical Report. arXiv (Computer Science.Computation and Language) , March 27, 2023, 2303.08774. https://arxiv.org/abs/2303.08774. · arXiv
  61. 10.48550/arXiv.2202.08320 · DOI
  62. 10.1021/acs.jcim.1c00099 · DOI
  63. 10.1101/2022.12.27.522071 · doi:10.1101/2022.12.27.522071
  64. 10.1093/nar/28.1.235 · DOI · Paper page
  65. Brookes D., 2019, Proceedings of the 36th International Conference on Machine Learning, 97, 773
  66. 10.48550/arXiv.2010.02141 · DOI
  67. Ren Z., 2022, Proceedings of the 39th International Conference on Machine Learning, 162, 18520
  68. 10.1126/science.ade9434 · DOI · Paper page
  69. 10.1038/s41929-022-00909-w · DOI
  70. 10.1093/nar/gkaa913 · DOI · Paper page
  71. 10.1093/nar/gky1130 · DOI · Paper page
  72. 10.1093/nar/gkr1126 · DOI · Paper page
  73. 10.1093/nar/30.1.47 · DOI · Paper page
  74. 10.1093/nar/gkx1065 · DOI · Paper page
  75. 10.1093/nar/gkz861 · DOI
  76. 10.1021/acssynbio.0c00052 · doi:10.1021/acssynbio.0c00052
  77. 10.1093/bioinformatics/btt036 · DOI
  78. 10.1093/nar/28.1.304 · DOI · Paper page
  79. 10.1111/febs.16274 · DOI · Paper page
  80. 10.1038/s41467-022-28536-w · DOI
  81. 10.26434/chemrxiv-2023-jzw9w · doi:10.26434/chemrxiv-2023-jzw9w
  82. 10.1093/bioinformatics/btad029 · DOI · Paper page
  83. 10.1093/gbe/evz142 · DOI
  84. 10.1093/nar/gkg847 · DOI · Paper page
  85. 10.1016/j.bbrc.2007.09.098 · DOI · Paper page
  86. 10.1186/s12859-018-2368-y · DOI · Paper page
  87. 10.1016/j.biosystems.2006.10.004 · DOI
  88. 10.1016/j.compbiolchem.2009.09.002 · DOI
  89. 10.1186/1471-2105-13-61 · doi:10.1186/1471-2105-13-61
  90. 10.1016/j.jmb.2004.10.024 · DOI
  91. 10.1093/bioinformatics/bts510 · DOI
  92. 10.1093/bioinformatics/bts700 · DOI
  93. 10.1371/journal.pone.0155290 · DOI
  94. 10.1371/journal.pone.0084623 · DOI
  95. 10.1186/1687-4153-2012-1 · DOI
  96. 10.1186/1471-2105-14-S1-S11 · DOI
  97. 10.7717/peerj.4750 · DOI
  98. 10.1073/pnas.1821905116 · DOI · Paper page
  99. 10.7554/eLife.80942 · DOI · Paper page
  100. 10.1126/science.adf2465 · DOI · Paper page
  101. 10.1038/s41467-022-35422-y · DOI
  102. 10.1038/s41467-022-30970-9 · DOI · Paper page
  103. 10.1021/acs.jpcb.2c03287 · doi:10.1021/acs.jpcb.2c03287
  104. 10.1038/s41592-020-0801-4 · DOI · Paper page
  105. 10.3390/ijms231810798 · DOI
  106. 10.1038/s41467-022-29268-7 · DOI · Paper page
  107. 10.1016/j.sbi.2022.102518 · DOI · Paper page
  108. 10.1093/bioinformatics/btab801 · DOI
  109. 10.1021/acs.jcim.0c00591 · DOI
  110. 10.1002/cctc.202000933 · DOI
  111. 10.1016/j.csbj.2022.11.009 · DOI
  112. 10.1002/pro.4467 · DOI · Paper page
  113. 10.1093/nar/gkaa1035 · DOI · Paper page
  114. 10.1021/acs.jcim.2c00799 · DOI · Paper page
  115. 10.1093/bioinformatics/btad011 · DOI
  116. 10.3390/ijms22158027 · DOI
  117. 10.1073/pnas.2122355119 · DOI
  118. 10.1002/bit.27169 · DOI
  119. 10.1016/j.celrep.2021.110207 · DOI
  120. 10.1016/S0020-7373(87)80003-2 · DOI · Paper page
  121. 10.1101/2022.01.11.475766 · DOI
  122. 10.1021/acs.jcim.0c00489 · DOI
  123. 10.1007/s00253-020-10960-x · doi:10.1007/s00253-020-10960-x
  124. 10.1016/j.jmb.2020.11.006 · DOI
  125. 10.1371/journal.pone.0152949 · DOI
  126. 10.1080/13506129.2020.1715363 · DOI
  127. 10.1093/bioinformatics/btv027 · DOI
  128. 10.1093/nar/gkz758 · DOI
  129. 10.1093/bioinformatics/btv375 · DOI
  130. 10.1093/nar/gkaa981 · DOI · Paper page
  131. 10.1093/bib/bbab555 · DOI
  132. 10.1101/2022.11.19.517196 · doi:10.1101/2022.11.19.517196
  133. 10.15252/msb.202110305 · DOI · Paper page
  134. 10.1186/s12859-020-3439-4 · DOI · Paper page
  135. 10.1016/j.cels.2017.11.003 · DOI · Paper page
  136. Notin P., 2022, Proceedings of the 39th International Conference on Machine Learning, 162, 16990
  137. 10.1126/science.abf8761 · DOI · Paper page
  138. 10.7554/eLife.53476 · DOI
  139. 10.1021/acssynbio.9b00104 · DOI
  140. 10.1016/j.ajhg.2020.04.014 · DOI
  141. 10.1021/acs.jcim.1c00318 · DOI
  142. 10.1021/acscatal.1c02786 · DOI
  143. 10.1073/pnas.1901979116 · DOI · Paper page
  144. 10.1002/cbic.202000612 · DOI
  145. 10.1093/database/baz117 · DOI
  146. 10.1002/pro.2876 · DOI · Paper page
  147. 10.1021/acscatal.2c01426 · DOI
  148. 10.1016/j.biotechadv.2022.107926 · DOI
  149. 10.1093/nar/gky417 · DOI · Paper page
  150. 10.1016/j.molcel.2018.08.033 · DOI · Paper page
  151. 10.1021/acs.biochem.1c00757 · DOI
  152. 10.1038/s41587-023-01763-2 · DOI · Paper page
  153. 10.1101/2023.05.03.539278 · DOI
  154. 10.1016/j.cels.2023.04.006 · DOI
  155. 10.1038/s41592-019-0496-6 · DOI · Paper page
  156. 10.1016/j.cels.2021.07.008 · DOI · Paper page
  157. 10.48550/arXiv.2302.00615 · arXiv · doi:10.48550/arxiv.2302.00615
  158. Bengio E., 2021, Adv. Neural Inf. Process. Syst., 34, 27381
  159. 10.1021/acs.jcim.2c01046 · DOI
  160. 10.1038/s41587-021-01146-5 · DOI · Paper page
  161. 10.48550/arXiv.2302.01649 · arXiv · doi:10.48550/arxiv.2302.01649
  162. 10.1002/pro.4497 · DOI · Paper page
  163. 10.1101/2023.01.16.524265 · DOI · Paper page
  164. 10.1038/s41598-022-21366-2 · DOI
  165. Houlsby N., 2019, Proceedings of the 36th International Conference on Machine Learning, 97, 2790
  166. 10.1101/2023.03.22.530066 · DOI
  167. 10.48550/arXiv.2206.13517 · DOI
  168. 10.1107/S0021889809008784 · DOI · Paper page
  169. 10.1093/nar/gku947 · DOI · Paper page
  170. Rao R. M., 2021, Proceedings of the 38th International Conference on Machine Learning, 139, 8844
  171. 10.1101/2023.01.23.525232 · DOI
  172. 10.1038/s41467-021-25976-8 · DOI · Paper page
  173. 10.1126/science.abj8754 · doi:10.1126/science.abj8754 · Paper page
  174. 10.1101/2022.06.07.495081 · DOI
  175. 10.26434/chemrxiv-2023-jcds7 · DOI
  176. 10.1038/s41467-023-37958-z · DOI
  177. 10.1093/bioinformatics/btab491 · DOI · Paper page
  178. Bepler, T.; Berger, B. Learning Protein Sequence Embeddings Using Information from Structure. International Conference on Learning Representations , New Orleans, LA, May 6–9, 2019; OpenReview, 2019. https://openreview.net/forum?id=SygLehCqtm
  179. Rao R., 2019, Adv. Neural Inf. Process. Syst., 32, 9689
  180. 10.1021/jacs.0c04924 · DOI
  181. 10.1038/s41598-022-14382-9 · DOI · Paper page
  182. 10.1103/PhysRevLett.101.208101 · DOI
  183. 10.1021/acs.chemrev.0c01195 · DOI · Paper page
  184. 10.1038/s41467-017-02388-1 · DOI · Paper page
  185. 10.1101/2023.01.06.523007 · doi:10.1101/2023.01.06.523007
  186. 10.1038/s41467-021-23246-1 · DOI
  187. 10.1042/BCJ20200477 · DOI
  188. 10.1038/s41586-022-04599-z · DOI · Paper page
  189. 10.1021/acs.biochem.1c00451 · DOI · Paper page
  190. 10.1093/bioinformatics/btaa1071 · DOI
  191. 10.1093/nar/gkx285 · DOI · Paper page
  192. 10.1021/acscatal.3c02575 · DOI · Paper page
  193. 10.1371/journal.pcbi.1008736 · DOI · Paper page
  194. 10.1016/j.checat.2022.09.011 · DOI
  195. 10.1021/acscatal.2c01184 · DOI · Paper page
  196. 10.1038/s41586-023-05696-3 · DOI · Paper page
  197. 10.1038/s41467-022-27999-1 · doi:10.1038/s41467-022-27999-1
  198. 10.1021/acscatal.1c03753 · DOI
  199. 10.1038/s41467-021-25831-w · DOI
  200. 10.1038/s41467-021-23450-z · DOI

200 of 292 shown

Cited by

Metadata

Authors
Kouba, P., Kohout, P., Haddadi, F., Bushuiev, A., Samusevich, R., Sedlar, J., Damborsky, J., Pluskal, T., Sivic, J., & Mazurenko, S.
Venue
ACS Catalysis
Published
2023-10-13
Volume
13
Issue
21
Pages
13863-13895
ISSN
2155-5435 (ISSN-L)
OpenAlex
W4387601539
Cited by
209
References
78
FWCI
15.69
Type
journal article
Language
en
Open access
hybrid
Funders
  • Technology Agency of the Czech Republic (TN02000122, TN02000122/001N)
  • European Regional Development Fund (CZ.02.1.01/0.0/0.0/15_003/0000468)
  • Ministerstvo Školství, Mládeže a Telovýchovy (CZ.02.1.01/0.0/0.0/17_043/0009632, LM2023055, LX22NPO5102, RI LM2023069)
  • Grantová Agentura Ceské Republiky (21-11563M)
  • HORIZON EUROPE Marie Sklodowska-Curie Actions (891397)
  • European Cooperation in Science and Technology (CA21162)
  • Horizon 2020 Framework Programme (857560)

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.