CoChat

Stability Oracle: a structure-based graph-transformer framework for identifying stabilizing mutations

Open access
Diaz, Daniel J., Gong, Chengyue, Ouyang-Zhang, Jeffrey, Loy, James M., Wells, Jordan, Yang, David, Ellington, Andrew D., Dimakis, Alexandros G., Klivans, Adam R. · 2024 · Nature Communications
Cited by 60

The DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.

Abstract

Engineering stabilized proteins is a fundamental challenge in the development of industrial and pharmaceutical biotechnologies. We present Stability Oracle: a structure-based graph-transformer framework that achieves SOTA performance on accurately identifying thermodynamically stabilizing mutations. Our framework introduces several innovations to overcome well-known challenges in data scarcity and bias, generalization, and computation time, such as: Thermodynamic Permutations for data augmentation, structural amino acid embeddings to model a mutation with a single structure, a protein structure-specific attention-bias mechanism that makes transformers a viable alternative to graph neural networks. We provide training/test splits that mitigate data leakage and ensure proper model evaluation. Furthermore, to examine our data engineering contributions, we fine-tune ESM2 representations (Prostata-IFML) and achieve SOTA for sequence-based models. Notably, Stability Oracle outperforms Prostata-IFML even though it was pretrained on 2000X less proteins and has 548X less parameters. Our framework establishes a path for fine-tuning structure-based transformers to virtually any phenotype, a necessary task for accelerating the development of protein-based biotechnologies.

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 · 10.1038/s41467-024-49780-2

Cites

31 of 31 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: 56

  1. Wu, S., Snajdrova, R., Moore, J. C., Baldenius, K. & Bornscheuer, U. T. Biocatalysis: enzymatic synthesis for industrial applications. Angew. Chem. Int. Ed. 60, 88–119 (2021). · DOI · Paper page
  2. Bell, E. L. et al. Biocatalysis. Nat. Rev. Methods Prim. 1, 1–21 (2021). · DOI · Paper page
  3. Adams, J. P., Brown, M. J., Diaz-Rodriguez, A., Lloyd, R. C. & Roiban, G. D. Biocatalysis: a pharma perspective. Adv. Synth. Catal. 361, 2421–2432 (2019). · DOI · Paper page
  4. Jay, S. M. & Lee, R. T. Protein engineering for cardiovascular therapeutics: Untapped potential for cardiac repair. Circ. Res. 113, 933–943 (2013). · DOI
  5. Gebauer, M. & Skerra, A. Engineered protein scaffolds as next-generation therapeutics. Annu. Rev. Pharmacol. Toxicol. 60, 391–415 (2020). · DOI · Paper page
  6. Meghwanshi, G. K. et al. Enzymes for pharmaceutical and therapeutic applications. Biotechnol. Appl. Biochem. 67, 586–601 (2020). · DOI
  7. Banta, S., Dooley, K. & Shur, O. Replacing antibodies: engineering new binding proteins. Annu. Rev. Biomed. Eng. 15, 93–113 (2013). · DOI · Paper page
  8. Chen, K. & Arnold, F. H. Tuning the activity of an enzyme for unusual environments: sequential random mutagenesis of subtilisin e for catalysis in dimethylformamide. Proc. Natl Acad. Sci. USA 90, 5618–5622 (1993). · DOI
  9. Ebo, J. S., Guthertz, N., Radford, S. E. & Brockwell, D. J. Using protein engineering to understand and modulate aggregation. Curr. Opin. Struct. Biol. 60, 157–166 (2020). · DOI
  10. Arnold, F. H. Design by directed evolution. Acc. Chem. Res. 31, 125–131 (1998). · DOI · Paper page
  11. Giver, L., Gershenson, A., Freskgard, P.-O. & Arnold, F. H. Directed evolution of a thermostable esterase. Proc. Natl Acad. Sci. USA 95, 12809–12813 (1998). · DOI · Paper page
  12. Pancotti, C. et al. Predicting protein stability changes upon single-point mutation: a thorough comparison of the available tools on a new dataset. Brief. Bioinforma. 23, bbab555 (2022). · DOI · Paper page
  13. Benevenuta, S., Birolo, G., Sanavia, T., Capriotti, E. & Fariselli, P. Challenges in predicting stabilizing variations: an exploration. Front. Mol. Biosci. 9, 1–10 (2023). · DOI
  14. Pucci, F., Schwersensky, M. & Rooman, M. Artificial intelligence challenges for predicting the impact of mutations on protein stability. Curr. Opin. Struct. Biol. 72, 161–168 (2022). · DOI · Paper page
  15. Sanavia, T. et al. Limitations and challenges in protein stability prediction upon genome variations: towards future applications in precision medicine. Comput. Struct. Biotechnol. J. 18, 1968–1979 (2020). · DOI · Paper page
  16. Caldararu, O., Mehra, R., Blundell, T. L. & Kepp, K. P. Systematic investigation of the data set dependency of protein stability predictors. J. Chem. Inf. Model. 60, 4772–4784 (2020). · DOI
  17. Fedik, N. et al. Extending machine learning beyond interatomic potentials for predicting molecular properties. Nat. Rev. Chem. 6, 653–672 (2022). · DOI · Paper page
  18. Bender, A. et al. Evaluation guidelines for machine learning tools in the chemical sciences. Nat. Rev. Chem. 6, 428–442 (2022). · DOI · Paper page
  19. Diaz, D. J., Kulikova, A. V., Ellington, A. D. & Wilke, C. O. Using machine learning to predict the effects and consequences of mutations in proteins. Curr. Opin. Struct. Biol. 78, 102518 (2023). · DOI · Paper page
  20. Xu, Y. et al. Deep dive into machine learning models for protein engineering. J. Chem. Inf. Model. 60, 2773–2790 (2020). · DOI · Paper page
  21. Umerenkov, D. et al. PROSTATA: a framework for protein stability assessment using transformers. Bioinformatics 39, btad671 (2023). · DOI · Paper page
  22. Benevenuta, S., Pancotti, C., Fariselli, P., Birolo, G. & Sanavia, T. An antisymmetric neural network to predict free energy changes in protein variants. J. Phys. D Appl. Phys. 54, 245403 (2021). · DOI · Paper page
  23. Chen, T. et al. Hotprotein: a novel framework for protein thermostability prediction and editing. In: The Eleventh International Conference on Learning Representations (OpenReview.net, 2023).
  24. Hie, B. L. et al. Efficient evolution of human antibodies from general protein language models. Nat. Biotechnol. 42, 275–283 (2024). · DOI · Paper page
  25. Li, B., Yang, Y. T., Capra, J. A. & Gerstein, M. B. Predicting changes in protein thermodynamic stability upon point mutation with deep 3d convolutional neural networks. PLoS Comput. Biol. 16, e1008291 (2020). · DOI · Paper page
  26. Cao, H., Wang, J., He, L., Qi, Y. & Zhang, J. Z. Deepddg: predicting the stability change of protein point mutations using neural networks. J. Chem. Inf. Model. 59, 1508–1514 (2019). · DOI · Paper page
  27. Wang, S., Tang, H., Shan, P. & Zuo, L. Pros-GNN: predicting effects of mutations on protein stability using graph neural networks. Comput. Biol. Chem. 107, 107952 (2023). · DOI
  28. Broom, A., Trainor, K., Jacobi, Z. & Meiering, E. M. Computational modeling of protein stability: quantitative analysis reveals solutions to pervasive problems. Structure 28, 717–726.e3 (2020). · DOI · Paper page
  29. Kellogg, E. H., Leaver-Fay, A. & Baker, D. Role of conformational sampling in computing mutation-induced changes in protein structure and stability. Proteins Struct. Funct. Bioinforma. 79, 830–838 (2011). · DOI · Paper page
  30. Capriotti, E., Fariselli, P. & Casadio, R. I-mutant2. 0: predicting stability changes upon mutation from the protein sequence or structure. Nucleic Acids Res. 33, W306–W310 (2005). · DOI · Paper page
  31. Laimer, J., Hofer, H., Fritz, M., Wegenkittl, S. & Lackner, P. Maestro-multi agent stability prediction upon point mutations. BMC Bioinforma. 16, 1–13 (2015). · DOI · Paper page
  32. Dehouck, Y., Kwasigroch, J. M., Gilis, D. & Rooman, M. Popmusic 2.1: a web server for the estimation of protein stability changes upon mutation and sequence optimality. BMC Bioinforma. 12, 1–12 (2011). · DOI · Paper page
  33. Worth, C. L., Preissner, R. & Blundell, T. L. Sdm-a server for predicting effects of mutations on protein stability and malfunction. Nucleic Acids Res. 39, W215–W222 (2011). · DOI · Paper page
  34. Wainreb, G., Wolf, L., Ashkenazy, H., Dehouck, Y. & Ben-Tal, N. Protein stability: a single recorded mutation aids in predicting the effects of other mutations in the same amino acid site. Bioinformatics 27, 3286–3292 (2011). · DOI · Paper page
  35. Romero, P. A., Krause, A. & Arnold, F. H. Navigating the protein fitness landscape with Gaussian processes. Proc. Natl Acad. Sci. USA 110, E193–E201 (2013). · DOI · Paper page
  36. Cheng, J., Randall, A. & Baldi, P. Prediction of protein stability changes for single-site mutations using support vector machines. Proteins Struct. Funct. Bioinforma. 62, 1125–1132 (2006). · DOI · Paper page
  37. Nisthal, A., Wang, C. Y., Ary, M. L. & Mayo, S. L. Protein stability engineering insights revealed by domain-wide comprehensive mutagenesis. Proc. Natl Acad. Sci. USA 116, 16367–16377 (2019). · DOI · Paper page
  38. Atkins, P., Atkins, P. W. & de Paula, J. Atkins’ Physical Chemistry (Oxford University Press, 2014).
  39. Shroff, R. et al. Discovery of novel gain-of-function mutations guided by structure-based deep learning. ACS Synth. Biol. 9, 2927–2935 (2020). · DOI · Paper page
  40. Lu, H. et al. Machine learning-aided engineering of hydrolases for pet depolymerization. Nature 604, 662–667 (2022). · DOI · Paper page
  41. d’Oelsnitz, S. et al. Biosensor and machine learning-aided engineering of an amaryllidaceae enzyme. Nat. Commun. 15, 2084 (2024). · DOI · Paper page
  42. Paik, I. et al. Improved bst DNA polymerase variants derived via a machine learning approach. Biochemistry 62, 410–418 (2021). · DOI · Paper page
  43. Liu, Y. et al. Asymmetric synthesis of α-chloroamides via photoenzymatic hydroalkylation of olefins. J. Am. Chem. Soc. 146, 7191–7197 (2024). · DOI
  44. Raček, T. et al. Atomic charge calculator II: web-based tool for the calculation of partial atomic charges. Nucleic Acids Res. 48, W591–W596 (2020). · DOI
  45. Mitternacht, S. Freesasa: an open source c library for solvent accessible surface area calculations. F1000Research 5, 1–10 (2016). · DOI · Paper page
  46. Kulikova, A. V. et al. Learning the local landscape of protein structures with convolutional neural networks. J. Biol. Phys. 47, 435–454 (2021). · doi:10.1007/s10867-021-09593-6
  47. Kortemme, T., Kim, D. E. & Baker, D. Computational alanine scanning of protein-protein interfaces. Sci. STKE 2004, pl2–pl2 (2004). · DOI · Paper page
  48. Vaswani, A. et al. Attention is all you need. Adv. Neural. Inf. Process. Syst. 30, 5998–6008 (2017).
  49. Caldararu, O., Blundell, T. L. & Kepp, K. P. A base measure of precision for protein stability predictors: structural sensitivity. BMC Bioinforma. 22, 1–14 (2021). · DOI · Paper page
  50. Capriotti, E., Fariselli, P., Rossi, I. & Casadio, R. A three-state prediction of single point mutations on protein stability changes. BMC Bioinforma. 9, 1–9 (2008). · DOI · Paper page
  51. Bava, K. A., Gromiha, M. M., Uedaira, H., Kitajima, K. & Sarai, A. Protherm, version 4.0: thermodynamic database for proteins and mutants. Nucleic Acids Res. 32, D120–D121 (2004). · DOI · Paper page
  52. Meier, J. et al. Language models enable zero-shot prediction of the effects of mutations on protein function. Adv. Neural Inf. Process. Syst. 34, 29287–29303 (2021).
  53. Notin, P. M. et al. Trancepteve: Combining family-specific and family-agnostic models of protein sequences for improved fitness prediction. bioRxiv https://doi.org/10.1101/2022.12.07.519495 (2022). · DOI · Paper page
  54. Kulikova, A. V. et al. Sequence and structure based deep learning models represent different aspects of protein biochemistry. bioRxiv. https://doi.org/10.1101/2023.03.20.533508 (2023). · doi:10.1101/2023.03.20.533508
  55. Stourac, J. et al. Fireprotdb: database of manually curated protein stability data. Nucleic Acids Res. 49, D319–D324 (2021). · DOI · Paper page
  56. Rodrigues, C. H., Pires, D. E. & Ascher, D. B. Dynamut2: assessing changes in stability and flexibility upon single and multiple point missense mutations. Protein Sci. 30, 60–69 (2021). · DOI · Paper page

Cited by

See all 60

Metadata

Authors
Diaz, D. J., Gong, C., Ouyang-Zhang, J., Loy, J. M., Wells, J., Yang, D., Ellington, A. D., Dimakis, A. G., & Klivans, A. R.
Venue
Nature Communications
Published
2024-07-23
Volume
15
Issue
1
Pages
6170-6170
ISSN
2041-1723 (ISSN-L)
OpenAlex
W4400921915
Cited by
60
References
31
FWCI
6.74
Type
journal article
Language
en
Open access
gold
Licence
Funders
  • United States Department of Defense | Defense Threat Reduction Agency (HDTRA 12010001)
  • Welch Foundation (F-1654)
  • Advanced Micro Devices
  • Institute for Foundations of Machine Learning

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.