CoChat

Protein Sequence Design with a Learned Potential

Open access
Anand-Achim, Namrata, Eguchi, Raphael R., Mathews, Irimpan I., Perez, Carla P., Derry, Alexander, Altman, Russ B., Huang, Po-Ssu · 2020 · bioRxiv (Cold Spring Harbor Laboratory)
PreprintCited by 40

The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.

Abstract

A bstract: The task of protein sequence design is central to nearly all rational protein engineering problems, and enormous effort has gone into the development of energy functions to guide design. We investigate the capability of a deep neural network model to automate design of sequences onto protein backbones, having learned directly from crystal structure data and without any human-specified priors. The model generalizes to native topologies not seen during training, producing experimentally stable designs. We evaluate the generalizability of our method to a de novo TIM-barrel scaffold. The model produces novel sequences, and high-resolution crystal structures of two designs show excellent agreement with the in silico models. Our findings demonstrate the tractability of an entirely learned method for protein sequence design.

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 · 10.1101/2020.01.06.895466

Cites

6 of 6 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 6 references

Research works printed but not linked: 71

  1. 10.1038/nbt.2214 · DOI · Paper page
  2. 10.1038/s41586-018-0830-7 · DOI · Paper page
  3. 10.1038/nature12443 · DOI · Paper page
  4. Anum A Glasgow , Yao-Ming Huang , Daniel J Mandell , Michael Thompson , Ryan Ritterson , Amanda L Losh-baugh , Jenna Pellegrino , Cody Krivacic , Roland A Pache , Kyle A Barlow , et al. Computational design of a modular protein sense/response system. bioRxiv, page 648485, 2019. · DOI · Paper page
  5. 10.7554/eLife.28909 · DOI · Paper page
  6. 10.1038/nature06879 · DOI · Paper page
  7. 10.1126/science.1190239 · DOI · Paper page
  8. 10.1126/science.aad8865 · DOI · Paper page
  9. 10.1126/science.1261172 · DOI · Paper page
  10. 10.1126/science.1198841 · DOI · Paper page
  11. 10.1093/protein/15.10.779 · DOI · Paper page
  12. 1992, Fast and simple monte carlo algorithm for side chain optimization in proteins: application to model building by homology, Proteins: Structure, Function, and Bioinformatics, 14, 213, 10.1002/prot.340140208 · DOI · Paper page
  13. 10.1073/pnas.97.19.10383 · DOI · Paper page
  14. 10.1016/S0076-6879(04)83004-0 · DOI · Paper page
  15. 2017, The rosetta allatom energy function for macromolecular modeling and design, Journal of chemical theory and computation, 13, 3031, 10.1021/acs.jctc.7b00125 · DOI · Paper page
  16. 2016, Simultaneous optimization of biomolecular energy functions on features from small molecules and macromolecules, Journal of chemical theory and computation, 12, 6201, 10.1021/acs.jctc.6b00819 · DOI · Paper page
  17. Namrata Anand and Possu Huang . Generative modeling for protein structures. In Advances in Neural Information Processing Systems, pages 7494–7505, 2018.
  18. Ivan Anishchenko , Tamuka Martin Chidyausiku , Sergey Ovchinnikov , Samuel J Pellock , and David Baker . De novo protein design by deep network hallucination. bioRxiv, 2020. · DOI · Paper page
  19. Andrew W Senior , Richard Evans , John Jumper , James Kirkpatrick , Laurent Sifre , Tim Green , Chongli Qin , Augustin Žídek , Alexander WR Nelson , Alex Bridgland , et al. Protein structure prediction using multiple deep neural networks in casp13. Proteins: Structure, Function, and Bioinformatics, 2019. · DOI · Paper page
  20. 10.1073/pnas.1914677117 · DOI · Paper page
  21. Surojit Biswas , Grigory Khimulya , Ethan C Alley , Kevin M Esvelt , and George M Church . Low-n protein engineering with data-efficient deep learning. BioRxiv, 2020. · DOI
  22. Julian Besag . Efficiency of pseudolikelihood estimation for simple gaussian fields. Biometrika, pages 616–618, 1977. · DOI · Paper page
  23. 10.1006/jmbi.1999.3091 · DOI · Paper page
  24. 10.1111/j.1742-4658.2005.04945.x · DOI · Paper page
  25. 10.1093/nar/29.14.2994 · DOI · Paper page
  26. 10.1093/nar/25.17.3389 · DOI · Paper page
  27. 1983, Dictionary of protein secondary structure: pattern recognition of hydrogen-bonded and geometrical features, Biopolymers: Original Research on Biomolecules, 22, 2577, 10.1002/bip.360221211 · DOI · Paper page
  28. 2000, Hm and westbrook, z. feng, g. gilliland, tn bhat, h. weissig, in shindyalov, and pe bourne. the protein databank, Nucleic Acids Research, 106, 16972
  29. 2017, Gene3d: extensive prediction of globular domains in proteins, Nucleic acids research, 46, D435
  30. 2016, Cath: an expanded resource to predict protein function through structure and sequence, Nucleic acids research, 45, D289
  31. Wouter Boomsma and Jes Frellsen . Spherical convolutions and their application in molecular modelling. In Advances in Neural Information Processing Systems, pages 3433–3443, 2017.
  32. Maurice Weiler , Mario Geiger , Max Welling , Wouter Boomsma , and Taco Cohen . 3d steerable cnns: Learning rotationally equivariant features in volumetric data. In Advances in Neural Information Processing Systems, pages 10381–10392, 2018.
  33. 2020, Discovery of novel gain-of-function mutations guided by structure-based deep learning, ACS Synthetic Biology, 9, 2927, 10.1021/acssynbio.0c00345 · DOI · Paper page
  34. 10.1016/B978-0-12-394292-0.00006-0 · DOI · Paper page
  35. Yilun Du Du , Joshua Meier , Jerry Ma , Rob Fergus , and Alexander Rives . Energy-based models for atomic-resolution protein conformations. International Conference on Learning Representations 2020, 2020.
  36. 2016, De novo design of a four-fold symmetric tim-barrel protein with atomic-level accuracy, Nature chemical biology, 12, 29, 10.1038/nchembio.1966 · DOI · Paper page
  37. 10.1038/s41586-018-0509-0 · DOI · Paper page
  38. 10.1073/pnas.1412768111 · DOI · Paper page
  39. 10.1006/jmbi.2000.4152 · DOI · Paper page
  40. 10.1073/pnas.2008535117 · DOI · Paper page
  41. Sergio Romero-Romero , Miguel Costas , Daniel-Adriano Silva , Sina Kordes , Erendira Rojas-Ortega , Yasel Guerra , Cinthya Tapia , Sooruban Shanmugaratnam , Adela Rodríguez-Romero , David Baker , et al. Epistasis on the stability landscape of de novo tim barrels explored by a modular design approach. bioRxiv, 2020. · DOI
  42. 10.1021/acs.jctc.8b00033 · DOI · Paper page
  43. 2015, Batch normalization: Accelerating deep network training by reducing internal covariate shift, arXiv preprint
  44. 10.1093/nar/gkq1105 · DOI · Paper page
  45. Andrew Leaver-Fay , Michael Tyka , Steven M. Lewis , Oliver F. Lange , James Thompson , Ron Jacak , Kristian W. Kaufman , P. Douglas Renfrew , Colin A. Smith , Will Sheffler , Ian W. Davis , Seth Cooper , Adrien Treuille , Daniel J. Mandell , Florian Richter , Yih-En Andrew Ban , Sarel J. Fleishman , Jacob E. Corn , David E. Kim , Sergey Lyskov , Monica Berrondo , Stuart Mentzer , Zoran Popovic , James J. Havranek , John Karanicolas , Rhiju Das , Jens Meiler , Tanja Kortemme , Jeffrey J. Gray , Brian Kuhlman , David Baker , and Philip Bradley . Chapter nineteen -rosetta3: An object-oriented software suite for the simulation and design of macromolecules. In Michael L. Johnson and Ludwig Brand , editors, Computer Methods, Part C, volume 487 of Methods in Enzymology, pages 545–574. Academic Press, 2011. · doi:10.1016/b978-0-12-381270-4.00019-6
  46. 10.1093/nar/gkl163 · DOI · Paper page
  47. 10.1371/journal.pone.0024109 · DOI · Paper page
  48. 2016, Simultaneous optimization of biomolecular energy functions on features from small molecules and macromolecules, Journal of chemical theory and computation, 12, 6201, 10.1021/acs.jctc.6b00819 · DOI · Paper page
  49. 10.1002/pro.8 · DOI · Paper page
  50. 10.1002/jcc.540140309 · DOI · Paper page
  51. 10.1371/journal.pone.0059004 · DOI · Paper page
  52. 10.1002/pro.2389 · DOI · Paper page
  53. 10.1073/pnas.1115898108 · DOI · Paper page
  54. 10.1016/j.jmb.2010.11.008 · DOI · Paper page
  55. UniProt Consortium, 2014, Uniref clusters: a comprehensive and scalable alternative for improving sequence similarity searches, Bioinformatics, 31, 926
  56. 10.1371/journal.pone.0023294 · DOI · Paper page
  57. 10.1107/S0907444909047337 · DOI · Paper page
  58. 10.1107/S0021889807021206 · DOI · Paper page
  59. 10.1107/S0907444906022116 · DOI · Paper page
  60. 10.1107/S0907444910007493 · DOI · Paper page
  61. 10.1107/S0907444911001314 · DOI · Paper page
  62. 2020, Predicting changes in protein thermodynamic stability upon point mutation with deep 3d convolutional neural networks, PLoS computational biology, 16, e1008291, 10.1371/journal.pcbi.1008291 · DOI · Paper page
  63. 2017, Prediction of amino acid side chain conformation using a deep neural network, arXiv preprint
  64. 10.1016/j.jmb.2007.05.078 · DOI · Paper page
  65. 10.1074/jbc.272.2.701 · DOI · Paper page
  66. 10.1021/bi00437a058 · DOI · Paper page
  67. 10.1126/science.1553543 · DOI · Paper page
  68. 10.1038/355371a0 · DOI · Paper page
  69. 10.1016/S0065-3233(08)60608-7 · DOI · Paper page
  70. 10.1038/319199a0 · DOI · Paper page
  71. 10.1110/ps.051454805 · DOI · Paper page

Cited by

Metadata

Authors
Anand-Achim, N., Eguchi, R. R., Mathews, I. I., Perez, C. P., Derry, A., Altman, R. B., & Huang, P.-S.
Venue
bioRxiv (Cold Spring Harbor Laboratory)
Publisher
openRxiv
Published
2020-01-07
OpenAlex
W2998116736
Cited by
40
References
6
Type
posted content
Language
en
Open access
green

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.