CoChat

A Deep SE(3)-Equivariant Model for Learning Inverse Protein Folding

Open access
McPartlon, Matt, Lai, Ben, Xu, Jinbo · 2022 · bioRxiv (Cold Spring Harbor Laboratory)
PreprintCited by 17

The DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.

Abstract

In this work, we establish a framework to tackle the inverse protein design problem; the task of predicting a protein’s primary sequence given its backbone conformation. To this end, we develop a generative SE(3)-equivariant model which significantly improves upon existing autoregressive methods. Conditioned on backbone structure, and trained with our novel partial masking scheme and side-chain conformation loss, we achieve state-of-the-art native sequence recovery on structurally independent CASP13, CASP14, CATH4.2, and TS50 test sets. On top of accurately recovering native sequences, we demonstrate that our model captures functional aspects of the underlying protein by accurately predicting the effects of point mutations through testing on Deep Mutational Scanning datasets. We further verify the efficacy of our approach by comparing with recently proposed inverse protein folding methods and by rigorous ablation studies.

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 · 10.1101/2022.04.15.488492

Cites

18 of 18 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

Research works printed but not linked: 41

  1. 2013, Predicting functional effect of human missense mutations using PolyPhen-2, In: Current protocols in human genetics, 76, 7
  2. 2020, Local rotation invariance in 3D CNNs, In: Medical Image Analysis, 65, 101756
  3. 2010, PyRosetta: a script-based interface for implementing molecular modeling algorithms using Rosetta, In: Bioinformatics, 26, 689
  4. 2020, To Improve Protein Sequence Profile Prediction through Image Captioning on Pairwise Residue Distance Map, In: Journal of Chemical Information and Modeling, 60, 391
  5. 2017, Computational protein design: a review, In: Journal of Physics: Condensed Matter, 29, 143001, 10.1088/1361-648X/aa5c76 · DOI · Paper page
  6. 2017, CATH: an expanded resource to predict protein function through structure and sequence, In: Nucleic acids research, 45, D289
  7. 2021, Protein Design with Deep Learning, In: Int J Mol Sci, 22, 136
  8. 2020, In: Advances in Neural Information Processing Systems. Ed. by, 33, 1970
  9. 2021, Structure-based protein function prediction using graph convolutional networks, In: Nature communications, 12, 1
  10. 2019, EvoEF2: accurate and fast energy function for computational protein design, In: Bioinformatics, 36, 1135
  11. 2020, FASPR: an open-source tool for fast and accurate protein side-chain packing, In: Bioinformatics, 36, 3758
  12. Ingraham, John , Vikas Garg , Regina Barzilay , and Tommi Jaakkola (2019). “Generative Models for Graph-Based Protein Design”. In: Advances in Neural Information Processing Systems. Ed. by H. Wallach et al. Vol. 32. Curran Associates, Inc.
  13. 2018, A Parametric Rosetta Energy Function Analysis with LK Peptides on SAM Surfaces, In: Langmuir, 34, 5279
  14. Jin, Wengong , Jeremy Wohlwend , Regina Barzilay , and Tommi S. Jaakkola (2022). “Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design”. In: International Conference on Learning Representations.
  15. Kingma, Diederik P. and Jimmy Ba (2015). “Adam: A Method for Stochastic Optimization”. In: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings. Ed. by Yoshua Bengio and Yann LeCun.
  16. Lai, Boqiao and Jinbo Xu (2022). “Accurate protein function prediction via graph attention networks with predicted structure information”. In: Briefings in Bioinformatics 23.1, bbab502. · DOI · Paper page
  17. 2020, Macromolecular modeling and design in Rosetta: recent methods and frameworks, In: Nat Methods, 17, 665
  18. 2022, De Novo Peptide and Protein Design Using Generative Adversarial Networks: An Update, In: Journal of Chemical Information and Modeling, 62, 761
  19. Lucas, JE. and T. Kortemme (Oct. 2020). “New Computational Protein Design Methods for De Novo Small Molecule Binding Sites”. In: PLoS Comput Biol 16.10. · DOI
  20. McPartlon, Matthew and Jinbo Xu (2022). “AttnPacker: An end-to-end deep learning method for rotamer-free protein side-chain packing”. In: bioRxiv. · DOI
  21. Meier, Joshua et al. (2021). “Language models enable zero-shot prediction of the effects of mutations on protein function”. In: Advances in Neural Information Processing Systems 34. · DOI · Paper page
  22. 2021, Fast and sensitive taxonomic assignment to metagenomic contigs, In: Bioinformatics, 37, 3029
  23. 2003, SIFT: Predicting amino acid changes that affect protein function, In: Nucleic acids research, 31, 3812
  24. 2018, SPIN2: Predicting sequence profiles from protein structures using deep neural networks, In: Proteins, 86, 629
  25. 2021, Recent advances in de novo protein design: Principles, methods, and applications, In: Journal of Biological Chemistry, 296, 100558
  26. 10.1021/acs.jctc.6b00819 · DOI · Paper page
  27. 2020, DenseCPD: Improving the Accuracy of Neural-Network-Based Computational Protein Sequence Design with DenseNet, In: Journal of Chemical Information and Modeling, 60, 1245
  28. Satorras, Victor Garcia , Emiel Hoogeboom , and Max Welling (2021). “E(n) Equivariant Graph Neural Networks”. In: CoRR abs/2102.09844. · arXiv
  29. Shroff, Raghav et al. (2019). A structure-based deep learning framework for protein engineering. · DOI
  30. 2010, Computational design of an enzyme catalyst for a stereoselective bimolecular Diels-Alder reaction, In: Science, 329, 309
  31. 2020, Fast and Flexible Protein Design Using Deep Graph Neural Networks, In: Cell Systems, 11, 402
  32. 2022, Deep generative modeling for protein design, In: Current Opinion in Structural Biology, 72, 226
  33. 2013, Computational design of ligand-binding proteins with high affinity and selectivity, In: Nature, 501, 212
  34. Wang, Jue et al. (2021). “Deep learning methods for designing proteins scaffolding functional sites”. In: bioRxiv. · DOI · Paper page
  35. 2004, Development and testing of a general amber force field, In: Journal of computational chemistry, 25, 1157
  36. Weiler, Maurice , Mario Geiger , Max Welling , Wouter Boomsma , and Taco Cohen (2018). “3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data”. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems. NIPS’18. Montréal, Canada: Curran Associates Inc., pp. 10402–10413.
  37. Xiong, Peng et al. (2014). “Protein design with a comprehensive statistical energy function and boosted by experimental selection for foldability.” In: Nature communications 5, p. 5330. · DOI
  38. 2020, Improved protein structure prediction using predicted interresidue orientations, In: Proceedings of the National Academy of Sciences, 117, 1496
  39. 2004, Accurate and efficient loop selections by the DFIRE-based all-atom statistical potential, In: Protein Sci, 13, 391
  40. 2019, ProDCoNN: Protein design using a convolutional neural network, In: Proteins: Structure, 88, 819
  41. 2020, A general-purpose protein design framework based on mining sequence-structure relationships in known protein structures, In: Proceedings of the National Academy of Sciences, 117, 1059

Cited by

See all 17

Metadata

Authors
McPartlon, M., Lai, B., & Xu, J.
Venue
bioRxiv (Cold Spring Harbor Laboratory)
Publisher
openRxiv
Published
2022-04-16
OpenAlex
W4224066120
Cited by
17
References
18
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.