Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 421

The DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.

Genome-wide prediction of disease variant effects with a deep protein language model

Open access
Brandes, Nadav, Goldman, Grant, Wang, Charlotte H., Ye, Chun Jimmie, Ntranos, Vasilis·2023·Nature Genetics
DOI 10.1038/s41588-023-01465-0
Open this paper in CoChat — free account

Abstract

Predicting the effects of coding variants is a major challenge. While recent deep-learning models have improved variant effect prediction accuracy, they cannot analyze all coding variants due to dependency on close homologs or software limitations. Here we developed a workflow using ESM1b, a 650-million-parameter protein language model, to predict all ~450 million possible missense variant effects in the human genome, and made all predictions available on a web portal. ESM1b outperformed existing methods in classifying ~150,000 ClinVar/HGMD missense variants as pathogenic or benign and predicting measurements across 28 deep mutational scan datasets. We further annotated ~2 million variants as damaging only in specific protein isoforms, demonstrating the importance of considering all isoforms when predicting variant effects. Our approach also generalizes to more complex coding variants such as in-frame indels and stop-gains. Together, these results establish protein language models as an effective, accurate and general approach to predicting variant effects.

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 · 10.1038/s41588-023-01465-0

Cites

23 of 23 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 23 references

Research works printed but not linked: 47

  1. Brandes, N., Weissbrod, O. & Linial, M. Open problems in human trait genetics. Genome Biol. 23, 131 (2022). · DOI
  2. Rehm, H. L. & Fowler, D. M. Keeping up with the genomes: scaling genomic variant interpretation. Genome Med. 12, 5 (2019). · DOI
  3. Hamosh, A., Scott, A. F., Amberger, J. S., Bocchini, C. A. & McKusick, V. A. Online Mendelian Inheritance in Man (OMIM), a knowledgebase of human genes and genetic disorders. Nucleic Acids Res. 33, D514–D517 (2005). · DOI · Paper page
  4. Brandes, N., Linial, N. & Linial, M. Genetic association studies of alterations in protein function expose recessive effects on cancer predisposition. Sci. Rep. 11, 14901 (2021). · DOI
  5. Gudmundsson, S. et al. Variant interpretation using population databases: lessons from gnomAD. Hum. Mutat. 43, 1012–1030 (2021). · DOI · Paper page
  6. Esposito, D. et al. MaveDB: an open-source platform to distribute and interpret data from multiplexed assays of variant effect. Genome Biol. 20, 223 (2019). · DOI · Paper page
  7. Boucher, J. I., Bolon, D. N. & Tawfik, D. S. Quantifying and understanding the fitness effects of protein mutations: laboratory versus nature. Protein Sci. 25, 1219–1226 (2016). · DOI
  8. Ng, P. C. SIFT: predicting amino acid changes that affect protein function. Nucleic Acids Res. 31, 3812–3814 (2003). · DOI · Paper page
  9. Boutet, E. et al. UniProtKB/Swiss-Prot, the manually annotated section of the UniProt KnowledgeBase: how to use the entry view. Methods Mol. Biol. 1374, 23–54 (2016). · DOI · Paper page
  10. Ofer, D., Brandes, N. & Linial, M. The language of proteins: NLP, machine learning & protein sequences. Comput. Struct. Biotechnol. J. 19, 1750–1758 (2021). · DOI · Paper page
  11. Elnaggar, A. et al. CodeTrans: towards cracking the language of silicon’s code through self-supervised deep learning and high-performance computing. Preprint at arXiv https://doi.org/10.48550 (2021). · DOI · Paper page
  12. Strodthoff, N., Wagner, P., Wenzel, M. & Samek, W. UDSMProt: universal deep sequence models for protein classification. Bioinformatics 36, 2401–2409 (2020). · DOI · Paper page
  13. Brandes, N., Ofer, D., Peleg, Y., Rappoport, N. & Linial, M. ProteinBERT: a universal deep-learning model of protein sequence and function. Bioinformatics 38, 2102–2110 (2022). · DOI · Paper page
  14. Meier, J. et al. Language models enable zero-shot prediction of the effects of mutations on protein function. Preprint at bioRxiv https://doi.org/10.1101/2021.07.09.450648 (2021). · DOI · Paper page
  15. Stenson, P. D. et al. Human Gene Mutation Database (HGMD): 2003 update. Hum. Mutat. 21, 577–581 (2003). · DOI · Paper page
  16. Allison, R., Edgar, J. R. & Reid, E. Spastin MIT domain disease-associated mutations disrupt lysosomal function. Front. Neurosci. 13, 1179 (2019). · DOI
  17. Nava, C. et al. Hypomorphic variants of cationic amino acid transporter 3 in males with autism spectrum disorders. Amino Acids 47, 2647–2658 (2015). · DOI
  18. Shoubridge, C., Tan, M. H., Seiboth, G. & Gecz, J. ARX homeodomain mutations abolish DNA binding and lead to a loss of transcriptional repression. Hum. Mol. Genet. 21, 1639–1647 (2012). · DOI
  19. Bienvenu, T. et al. ARX, a novel Prd-class-homeobox gene highly expressed in the telencephalon, is mutated in X-linked mental retardation. Hum. Mol. Genet. 11, 981–991 (2002). · DOI · Paper page
  20. Marques, I. et al. Unraveling the pathogenesis of ARX polyalanine tract variants using a clinical and molecular interfacing approach. Mol. Genet. Genom. Med. 3, 203–214 (2015). · DOI
  21. Cho, G., Nasrallah, M. P., Lim, Y. & Golden, J. A. Hypomorphic variants of cationic amino acid transporter 3 in males with autism spectrum disorders. Amino Acids 13, 23–29 (2012).
  22. Liu, X., Li, C., Mou, C., Dong, Y. & Tu, Y. dbNSFP v4: a comprehensive database of transcript-specific functional predictions and annotations for human nonsynonymous and splice-site SNVs. Genome Med. 12, 1–8 (2020). · DOI · Paper page
  23. Eyre-Walker, A. & Keightley, P. D. High genomic deleterious mutation rates in hominids. Nature 397, 344–347 (1999). · DOI · Paper page
  24. Toledo, R. A. et al. Novel MEN1 germline mutations in Brazilian families with multiple endocrine neoplasia type 1. Clin. Endocrinol. 67, 377–384 (2007). · DOI
  25. Huang, J. et al. The same pocket in menin binds both MLL and JUND but has opposite effects on transcription. Nature 482, 542–546 (2012). · DOI · Paper page
  26. Cebrian, A. et al. Mutational and gross deletion study of the MEN1 gene and correlation with clinical features in Spanish patients. J. Med. Genet. 40, e72 (2003). · DOI
  27. Martín-Campos, J. M. et al. Molecular pathology of multiple endocrine neoplasia type I: two novel germline mutations and updated classification of mutations affecting MEN1 gene. Diagn. Mol. Pathol. 8, 195–204 (1999). · DOI
  28. Agarwal, S. K. et al. Menin interacts with the AP1 transcription factor JunD and represses JunD-activated transcription. Cell 96, 143–152 (1999). · DOI · Paper page
  29. Klein, R. D., Salih, S., Bessoni, J. & Bale, A. E. Clinical testing for multiple endocrine neoplasia type 1 in a DNA diagnostic laboratory. Genet. Med. 7, 131–138 (2005). · DOI
  30. Ehrlich, L. et al. miR-24 inhibition increases menin expression and decreases cholangiocarcinoma proliferation. Am. J. Pathol. 187, 570–580 (2017). · DOI
  31. Nagy, E. & Maquat, L. E. A rule for termination-codon position within intron-containing genes: when nonsense affects RNA abundance. Trends Biochem. Sci. 23, 198–199 (1998). · DOI · Paper page
  32. Notin, P. et al. Tranception: protein fitness prediction with autoregressive transformers and inference-time retrieval. In Proc. 39th International Conference on Machine Learning (PMLR, 2022).
  33. Notin, P. M. et al. TranceptEVE: combining family-specific and family-agnostic models of protein sequences for improved fitness prediction. Preprint at bioRxiv https://doi.org/10.1101/2022.12.07.519495 (2022). · DOI
  34. Cummings, B. B. et al. Transcript expression-aware annotation improves rare variant interpretation. Nature 581, 452–458 (2020). · DOI · Paper page
  35. Lonsdale, J. et al. The Genotype-Tissue Expression (GTEx) project. Nat. Genet. 45, 580–585 (2013). · DOI · Paper page
  36. Livesey, B. J. & Marsh, J. A. Updated benchmarking of variant effect predictors using deep mutational scanning. Mol. Syst. Biol. 19, e11474 (2023). · DOI
  37. Starita, L. M. et al. A multiplex homology-directed DNA repair assay reveals the impact of more than 1,000 BRCA1 missense substitution variants on protein function. Am. J. Hum. Genet. 103, 498–508 (2018). · DOI
  38. Nicora, G., Zucca, S., Limongelli, I., Bellazzi, R. & Magni, P. A machine learning approach based on ACMG/AMP guidelines for genomic variant classification and prioritization. Sci. Rep. 12, 2517 (2022). · DOI
  39. Tavtigian, S. V., Harrison, S. M., Boucher, K. M. & Biesecker, L. G. Fitting a naturally scaled point system to the ACMG/AMP variant classification guidelines. Hum. Mutat. 41, 1734–1737 (2020). · DOI · Paper page
  40. Hie, B. L. et al. Efficient evolution of human antibodies from general protein language models and sequence information alone. Nat. Biotechnol. https://doi.org/10.1038/s41587-023-01763-2 (2023). · DOI · Paper page
  41. Pedregosa, F. et al. Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011).
  42. Wu, Y. et al. Improved pathogenicity prediction for rare human missense variants. Am. J. Hum. Genet. 108, 1891–1906 (2021). · DOI · Paper page
  43. Kim, H. Y., Jeon, W. & Kim, D. An enhanced variant effect predictor based on a deep generative model and the born-again networks. Sci. Rep. 11, 19127 (2021). · DOI
  44. Henikoff, S. & Henikoff, J. G. Amino acid substitution matrices from protein blocks. Proc. Natl Acad. Sci. USA 89, 10915–10919 (1992). · DOI · Paper page
  45. Penn, W. D. et al. Probing biophysical sequence constraints within the transmembrane domains of rhodopsin by deep mutational scanning. Sci. Adv. 6, eaay7505 (2020). · DOI
  46. Weile, J. et al. A framework for exhaustively mapping functional missense variants. Mol. Syst. Biol. 13, 957 (2017). · DOI · Paper page
  47. Newberry, R. W., Leong, J. T., Chow, E. D., Kampmann, M. & DeGrado, W. F. Deep mutational scanning reveals the structural basis for α-synuclein activity. Nat. Chem. Biol. 16, 653–659 (2020). · DOI

Cited by

See all 421

Metadata

Authors
Brandes, N., Goldman, G., Wang, C. H., Ye, C. J., & Ntranos, V.
Venue
Nature Genetics
Publisher
Springer Science and Business Media LLC
Published
2023-08-10
Volume
55
Issue
9
Pages
1512-1522
ISSN
  • 1061-4036 (ISSN-L)
  • 1546-1718
DOI
10.1038/s41588-023-01465-0
OpenAlex
W4385737488
Cited by
421
References
23
FWCI
62.41
Type
journal article
Language
en
Open access
hybrid
Licence

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: Genome-wide prediction of disease variant effects with a deep protein language model. https://app.cochat.ai/papers/10.1038/s41588-023-01465-0
The paper
Brandes, N., Goldman, G., Wang, C. H., Ye, C. J., & Ntranos, V. (2023). Genome-wide prediction of disease variant effects with a deep protein language model. Nature Genetics. https://doi.org/10.1038/s41588-023-01465-0

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.