CoChat
Sign Up
PreprintCited by 30Computational Drug Discovery Methodsvaccines and immunoinformatics approachesProtein Degradation and Inhibitors

The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.

Language Models for the Prediction of SARS-CoV-2 Inhibitors

Open access
Blanchard, Andrew E, Gounley, John, Bhowmik, Debsindhu, Shekar, Mayanka Chandra, Lyngaas, Isaac, Gao, Shang, Yin, Junqi, Tsaris, Aristeidis, Wang, Feiyi, Glaser, Jens·2021·The International Journal of High Performance Computing Applications
DOI 10.1101/2021.12.10.471928PMC PMC9548488

Preprint — published as 10.1177/10943420221121804 · Paper page

Open this paper in CoChat — free accountOpen PDF

Abstract

The COVID-19 pandemic highlights the need for computational tools to automate and accelerate drug design for novel protein targets. We leverage deep learning language models to generate and score drug candidates based on predicted protein binding affinity. We pre-trained a deep learning language model (BERT) on ∼9.6 billion molecules and achieved peak performance of 603 petaflops in mixed precision. Our work reduces pre-training time from days to hours, compared to previous efforts with this architecture, while also increasing the dataset size by nearly an order of magnitude. For scoring, we fine-tuned the language model using an assembled set of thousands of protein targets with binding affinity data and searched for inhibitors of specific protein targets, SARS-CoV-2 Mpro and PLpro. We utilized a genetic algorithm approach for finding optimal candidates using the generation and scoring capabilities of the language model. Our generalizable models accelerate the identification of inhibitors for emerging therapeutic targets.

Overview

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

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Integrity signals

Registry

Crossref · 10.1101/2021.12.10.471928

Cites

2 of 2 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.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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 2 references

Research works printed but not linked: 66

  1. 10.1177/10943420211010930 · DOI
  2. 10.1101/2020.12.23.424259 · DOI
  3. 10.1016/S1473-3099(20)30120-1 · DOI · Paper page
  4. 2017, Aids, avian flu, sars, mers, ebola, zika… what next?, Vaccine, 35, 4470, 10.1016/j.vaccine.2017.04.082 · DOI
  5. Fischer W , Eron JJ , Holman W et al. Molnupiravir, an oral antiviral treatment for COVID-19 2021; URL https://www.medrxiv.org/content/early/2021/06/17/2021.06.17.21258639.
  6. 10.1111/j.1476-5381.2010.01127.x · DOI · Paper page
  7. 10.1126/science.aat2663 · DOI
  8. 10.1021/acsmedchemlett.0c00088 · DOI · Paper page
  9. 10.1021/acs.jcim.9b01053 · DOI
  10. 1998, SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules, J Chem Inf Comput Sci, 28, 31
  11. 10.1109/TPAMI.2021.3095381 · DOI · Paper page
  12. 10.1021/acscentsci.0c00229 · DOI
  13. 10.1186/s13321-021-00494-3 · DOI
  14. De Cao N and Kipf T. MolGAN: An implicit generative model for small molecular graphs. ICML 2018 workshop on Theoretical Foundations and Applications of Deep Generative Models 2018;.
  15. 10.1186/s13321-019-0393-0 · DOI
  16. 10.1021/acscentsci.7b00512 · DOI · Paper page
  17. 10.1021/ja401184g · DOI · Paper page
  18. 10.1039/c8sc05372c · DOI
  19. 10.1021/acs.jcim.0c01010 · DOI
  20. 10.1021/ci990307l · DOI
  21. 10.1186/1758-2946-1-8 · DOI · Paper page
  22. 10.1038/nchem.1243 · DOI
  23. 10.1021/ci300124c · DOI
  24. 10.1021/acs.jcim.6b00290 · DOI
  25. 10.18653/v1/N19-1423 · DOI · Paper page
  26. Liu Y , Ott M , Goyal N et al. RoBERTa: A Robustly Optimized BERT Pretraining Approach 2019; URL http://arxiv.org/abs/1907.11692. · arXiv
  27. Gu Y , Tinn R , Cheng H et al. Domain-specific language model pretraining for biomedical natural language processing. arXiv 2020; URL https://arxiv.org/abs/2007.15779. · arXiv
  28. 10.1145/3307339.3342186 · DOI
  29. Chithrananda S , Grand G and Ramsundar B. ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction 2020; (NeurIPS). URL http://arxiv.org/abs/2010.09885.2010.09885.
  30. Honda S , Shi S and Ueda HR . Smiles transformer: Pre-trained molecular finger-print for low data drug discovery 2019; URL https://arxiv.org/abs/1911.04738. · arXiv
  31. Gurbych O , Druchok M , Yarish D et al. High throughput screening with machine learning 2020; URL http://arxiv.org/abs/2012.08275.2012.08275.
  32. 10.1093/bioinformatics/bty593 · DOI
  33. Kurth T , Treichler S , Romero J et al. Exascale deep learning for climate analytics. In SC18: International Conference for High Performance Computing, Networking, Storage and Analysis. IEEE, pp. 649–660.
  34. 2019, Exascale deep learning for scientific inverse problems, arXiv preprint
  35. Zheng S , Lin H , Zha S et al. Accelerated large batch optimization of BERT pretraining in 54 minutes 2020; URL http://arxiv.org/abs/2006.13484. · arXiv
  36. You Y , Li J , Reddi S et al. Large Batch Optimization for Deep Learning: Training BERT in 76 minutes 2019; URL http://arxiv.org/abs/1904.00962.1904.00962.
  37. Rasley J , Rajbhandari S , Ruwase O et al. Deepspeed: System optimizations enable training deep learning models with over 100 billion parameters. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. pp. 3505–3506.
  38. 2021, Efficient large-scale language model training on GPU clusters, arXiv preprint
  39. 2017, Accurate, large minibatch SGD: Training ImageNet in 1 hour, arXiv preprint
  40. Eiben AE and Smith JE . Introduction to Evolutionary Computing. 2nd ed. Springer-Verlag GmbH Germany: Springer Publishing Company, Incorporated, 2015. ISBN 3662448734.
  41. 10.1021/ci034290p · DOI
  42. 10.1162/EVCO_a_00005 · DOI
  43. 10.1145/2908812.2908916 · DOI
  44. 10.1246/cl.180665 · DOI
  45. 10.1021/acs.jcim.8b00839 · DOI · Paper page
  46. Li D , Zhang Y , Peng H et al. Contextualized perturbation for textual adversarial attack 2020; URL https://arxiv.org/abs/2009.07502.2009.07502.
  47. 10.18653/v1/2020.emnlp-main.500 · DOI
  48. 10.1109/ICASSP.2012.6289079 · DOI · Paper page
  49. 10.1021/acs.jcim.9b00943 · DOI
  50. 10.1039/c8sc02339e · DOI
  51. Lin Y , Han S , Mao H et al. Deep gradient compression: Reducing the communication bandwidth for distributed training 2017; URL https://arxiv.org/abs/1712.01887. · arXiv
  52. 10.1093/nar/gkl999 · DOI
  53. 10.1093/bioinformatics/btu626 · DOI
  54. 2005, Binding moad (mother of all databases), Proteins: Structure, Function, and Bioinformatics, 60, 333, 10.1002/prot.20512 · DOI · Paper page
  55. 2012, Biolip: a semi-manually curated database for biologically relevant ligand–protein interactions, Nucleic acids research, 41, D1096, 10.1093/nar/gks966 · DOI
  56. Oleksandr G , Maksym D , Dzvenymyra Y et al. High throughput screening with machine learning 2020; URL https://arxiv.org/abs/2012.08275. · arXiv
  57. Wolf T , Debut L , Sanh V et al. Transformers: State-of-the-art natural language processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Online: Association for Computational Linguistics, pp. 38–45. URL https://www.aclweb.org/anthology/2020.emnlp-demos.6. · DOI · Paper page
  58. Koyama K , Kamiya K and Shimada K. Cross attention dti: Drug-target interaction prediction with cross a ention module in the blind evaluation setup. 19th International Workshop on Data Mining in Bioinformatics, Aug 24, 2020, BIOKDD, San Diego ACM, New York, NY 2020;.
  59. 10.1038/nbt.1990 · DOI · Paper page
  60. Achdout H , Aimon A , Bar-David E et al. COVID moonshot: open science discovery of SARS-CoV-2 main protease inhibitors by combining crowdsourcing, high-throughput experiments, computational simulations, and machine learning. bioRxiv 2020;.
  61. 10.1101/2021.02.13.431008 · DOI
  62. Spearman C. The proof and measurement of association between two things 1961;. · DOI
  63. Wolf T , Debut L , Sanh V et al. Huggingface’s transformers: State-of-the-art natural language processing 2019; URL https://arxiv.org/abs/1910.03771. · arXiv
  64. Aizman A , Maltby G and Breuel T. High performance I/O for large scale deep learning. In 2019 IEEE International Conference on Big Data (Big Data). IEEE, pp. 5965–5967. · DOI
  65. Vazhkudai SS , De Supinski BR , Bland AS et al. The design, deployment, and evaluation of the CORAL pre-exascale systems. In SC18: International Conference for High Performance Computing, Networking, Storage and Analysis. IEEE, pp. 661–672.
  66. 10.1021/ar500432k · DOI · Paper page

Metadata

Authors
Blanchard, A. E., Gounley, J., Bhowmik, D., Shekar, M. C., Lyngaas, I., Gao, S., Yin, J., Tsaris, A., Wang, F., & Glaser, J.
Affiliations
Oak Ridge National Laboratory (US)
Corresponding author
Blanchard, Andrew E
ORCID
Venue
The International Journal of High Performance Computing Applications
Publisher
openRxiv
Published
2021-12-14
Volume
36
Issue
5-6
Pages
587-602
ISSN
0890-2720 (ISSN-L)
DOI
10.1101/2021.12.10.471928
PMC
PMC9548488
OpenAlex
W4303478269
Cited by
30
References
2
Citations by year
2026: 2 · 2025: 5 · 2024: 7 · 2023: 10 · 2022: 5 · 2021: 1
FWCI
3.65
Type
journal article
Language
en
Open access
Licence
cc-by-nc-nd
Locations
  • The International Journal of High Performance Computing Applications (publishedVersion)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
  • PubMed Central (publishedVersion)
  • PubMed (publishedVersion)
  • OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) (submittedVersion)
Funders
  • U.S. Department of Energy (17‐SC‐20‐SC, AC05-00OR22725, DE--AC05--00OR22725, DE-AC05?, under Contract DE-AC05-00OR22725, 00OR22725, 39KJ95010)
  • Office of Science (DEAC05- 00OR22725, 17-SC20-SC, AC05-00OR22725)
  • National Nuclear Security Administration (17- SC-20-SC, #DE-AC05-00OR22725)
  • Advanced Scientific Computing Research (DE-AC05-00OR22725, 17‐SC‐20‐SC, Contract DE-AC05-00OR22725)
  • Oak Ridge National Laboratory (17-SC-20-SC, AC05-00OR22725, DE-AC05-00OR22725)
Topics
  • Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › vaccines and immunoinformatics approaches
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Degradation and Inhibitors
Keywords
BERT, main protease, papain-like protease, genetic algorithm, high-performance computing

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Language Models for the Prediction of SARS-CoV-2 Inhibitors. https://app.cochat.ai/papers/10.1101/2021.12.10.471928
The paper
Blanchard, A. E., Gounley, J., Bhowmik, D., Shekar, M. C., Lyngaas, I., Gao, S., Yin, J., Tsaris, A., Wang, F., & Glaser, J. (2021). Language Models for the Prediction of SARS-CoV-2 Inhibitors. The International Journal of High Performance Computing Applications. https://doi.org/10.1101/2021.12.10.471928