CoChat
Sign Up
Cited by 5Genomics and Rare DiseasesGenomics and Phylogenetic StudiesProtein Structure and Dynamics

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

Proteome-wide prediction of the functional impact of missense variants with ProteoCast

Open access
Abakarova, Marina, Freiberger, Maria Inés, Liehrmann, Arnaud, Rera, Michael, Laine, Elodie·2026·Nature Communications
DOI 10.1038/s41467-026-72140-1PMC PMC13121731

Published version of a preprint

Open this paper in CoChat — free accountOpen PDF

Abstract

Abstract Background: Dissecting the functional impact of genetic mutations is essential to advancing our understanding of genotype-phenotype relationships and identifying new therapeutic targets. Despite the progress in sequencing and CRISPR technologies, proteome-wide mutation effect prediction remains challenging. Here, we introduce ProteoCast, a scalable and interpretable computational method for proteome-wide classification of genetic variants and functional protein site identification. It relies solely on evolutionary information, leveraging protein sequence data across organisms. Results: Using ProteoCast, we generated mutational landscapes for 22,169 Drosophila melanogaster protein isoforms, categorising over 293 million amino acid substitutions as functionally neutral, uncertain, or impactful. We validated our predictions with over 380 thousand natural polymorphisms observed in the Drosophila Genetic Reference Panel (DGRP) and Drosophila Evolution over Space and Time (DEST) datasets and with FlyBase's developmentally lethal mutations. About 86% of known lethal mutations were classified as impactful or uncertain, versus only 13% and 18% of DGRP and DEST mutations. Moreover, we performed ProteoCastguided genome editing experiments, providing a proof-of-concept of the validity of this strategy. Beyond variant effect prediction, ProteoCast detected evolutionary conservation signals in about one-third of 40.5K annotated post-translational modification sites and 83% of ~90 known short linear motifs. These results support its usefulness for uncovering interaction and regulatory sites in unstructured protein regions. Conclusions: Our results demonstrate ProteoCast applicability for model organisms, contributing to basic genetic research and translational studies. This work provides a publicly available dataset, userfriendly interactive web services, and a locally deployable pipeline tool for further research into gene function and mutation effects in any organism.

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/s41467-026-72140-1

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.

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

Flagged first, then by citations

Research works printed but not linked: 72

  1. Abbasi, J. DNA base editing could reverse most disease-causing point mutations. JAMA 318, 2173 (2017).
  2. Ruetz, T. J. et al. CRISPR-cas9 screens reveal regulators of ageing in neural stem cells. Nature 634, 1150–1159 (2024). · DOI
  3. Ng, P. C. & Henikoff, S. SIFT: predicting amino acid changes that affect protein function. Nucleic Acids Res. 31, 3812–3814 (2003). · DOI
  4. Figliuzzi, M., Jacquier, H., Schug, A., Tenaillon, O. & Weigt, M. Coevolutionary landscape inference and the context-dependence of mutations in beta-lactamase TEM-1. Mol. Biol. Evol. 33, 268–280 (2016). · DOI
  5. Laine, E., Karami, Y. & Carbone, A. GEMME: a simple and fast global epistatic model predicting mutational effects. Mol. Biol. Evol. 36, 2604–2619 (2019). · DOI
  6. Riesselman, A. J., Ingraham, J. B. & Marks, D. S. Deep generative models of genetic variation capture the effects of mutations. Nat. Methods 15, 816–822 (2018). · DOI · Paper page
  7. Marquet, C. et al. Embeddings from protein language models predict conservation and variant effects. Hum. Genet 141, 1629–1647 (2022). · DOI
  8. Lin, Z. et al. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science 379, 1123–1130 (2023). · DOI · Paper page
  9. Marquet, C., Schlensok, J., Abakarova, M., Rost, B. & Laine, E. Expert-guided protein language models enable accurate and blazingly fast fitness prediction. Bioinformatics 40, btae621 (2024). · DOI · Paper page
  10. Cheng, J. et al. Accurate proteome-wide missense variant effect prediction with AlphaMissense. Science 381, eadg7492 (2023). · DOI · Paper page
  11. Truong Jr, T. & Bepler, T. PoET: A generative model of protein families as sequences-of-sequences. : Adv. Neural Inf. Process. Syst. 36, 77379–77415 (2023).
  12. Su, J. et al. SaProt: protein language modeling with structure-aware vocabulary. https://doi.org/10.1101/2023.10.01.560349v5 (2024). · DOI
  13. Kircher, M. et al. A general framework for estimating the relative pathogenicity of human genetic variants. Nat. Genet 46, 310–315 (2014). · DOI · Paper page
  14. Pathak, A. K. et al. Pervasive ancestry bias in variant effect predictors. https://www.biorxiv.org/content/10.1101/2024.05.20.594987v3 (2025). · DOI
  15. Tekpinar, M., David, L., Henry, T. & Carbone, A. PRESCOTT: a population aware, epistatic, and structural model accurately predicts missense effects. Genome Biol. 26, 113 (2025). · DOI · Paper page
  16. Jagota, M. et al. Cross-protein transfer learning substantially improves disease variant prediction. Genome Biol. 24, 182 (2023). · DOI
  17. Tsishyn, M., Hermans, P., Pucci, F. & Rooman, M. Residue conservation and solvent accessibility are (almost) all you need for predicting mutational effects in proteins. https://doi.org/10.1101/2025.02.03.636212v1 (2025). · DOI
  18. Tan, Y., Wang, R., Wu, B., Hong, L. & Zhou, B. Retrieval-enhanced mutation mastery: Augmenting zero-shot prediction of protein language model. http://arxiv.org/abs/2410.21127 (2024). · arXiv
  19. Livesey, B. J. & Marsh, J. A. Variant effect predictor correlation with functional assays is reflective of clinical classification performance. https://doi.org/10.1101/2024.05.12.593741v1 (2024). · DOI
  20. Livesey, B. J. & Marsh, J. A. Updated benchmarking of variant effect predictors using deep mutational scanning. Mol. Syst. Biol. 19, e11474 (2023). · DOI
  21. Notin, P. et al. ProteinGym: large-scale benchmarks for protein fitness prediction and design. Adv. Neural Inf. Process. Syst. 36, 64331–64379 (2023).
  22. Choi, Y. & Chan, A. P. PROVEAN web server: a tool to predict the functional effect of amino acid substitutions and indels. Bioinformatics 31, 2745–2747 (2015). · DOI
  23. Abildgaard, A. B. et al. Lynch syndrome, molecular mechanisms and variant classification. Br. J. Cancer 128, 726–734 (2023). · DOI
  24. Cagiada, M. et al. Discovering functionally important sites in proteins. Nat. Commun. 14, 4175 (2023). · DOI
  25. Gersing, S. et al. A comprehensive map of human glucokinase variant activity. Genome Biol. 24, 97 (2023). · DOI · Paper page
  26. Tsuboyama, K. et al. Mega-scale experimental analysis of protein folding stability in biology and design. Nature 620, 434–444 (2023). · DOI · Paper page
  27. Abakarova, M., Marquet, C., Rera, M., Rost, B. & Laine, E. Alignment-based protein mutational landscape prediction: doing more with less. Genome Biol. Evol. 15, evad201 (2023). · DOI · Paper page
  28. Mackay, T. F. C. et al. The Drosophila melanogaster genetic reference panel. Nature 482, 173–178 (2012). · DOI
  29. Nunez, J. C. B. et al. Footprints of worldwide adaptation in structured populations of Drosophila melanogaster through the expanded DEST 2.0 genomic resource. Mol. Biol. Evol. 42, msaf132 (2025). · DOI
  30. Öztürk Çolak, A. et al. FlyBase: updates to the Drosophila genes and genomes database. Genetics 227, iyad211 (2024). · DOI
  31. Rubin, G. M. et al. Comparative genomics of the eukaryotes. Science 287, 2204–2215 (2000). · DOI · Paper page
  32. Steinegger, M. & Söding, J. MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets. Nat. Biotechnol. 35, 1026–1028 (2017). · DOI · Paper page
  33. Mirdita, M. et al. ColabFold: making protein folding accessible to all. Nat. Methods 19, 679–682 (2022). · DOI · Paper page
  34. Oh, H. & Irvine, K. D. Yorkie: the final destination of hippo signaling. Trends Cell Biol. 20, 410–417 (2010). · DOI
  35. Brogiolo, W. et al. An evolutionarily conserved function of the Drosophila insulin receptor and insulin-like peptides in growth control. Curr. Biol. 11, 213–221 (2001). · DOI · Paper page
  36. Sim, N.-L. et al. SIFT web server: predicting effects of amino acid substitutions on proteins. Nucleic Acids Res. 40, W452–457 (2012). · DOI
  37. Piovesan, D. et al. MobiDB: intrinsically disordered proteins in 2021. Nucleic Acids Res. 49, D361–D367 (2021). · DOI
  38. Hu, Y. et al. iProteinDB: an integrative database of Drosophila post-translational modifications. G3 9, 1–11 (2019). · DOI
  39. Berman, H. M. et al. The protein data bank. Nucleic Acids Res. 28, 235–242 (2000). · DOI · Paper page
  40. Mesrouze, Y. et al. Dissection of the interaction between the intrinsically disordered YAP protein and the transcription factor TEAD. Elife 6, e25068 (2017). · DOI
  41. Maidstone, R., Hocking, T., Rigaill, G. & Fearnhead, P. On optimal multiple changepoint algorithms for large data. Stat. Comput 27, 519–533 (2017). · DOI
  42. Rigaill, G. fpopw: Weighted Segmentation using Functional Pruning and Optimal Partioning. https://CRAN.R-project.org/package=fpopw (2022). · DOI
  43. Kumar, M. et al. ELM-the eukaryotic linear motif resource-2024 update. Nucleic Acids Res. 52, D442–D455 (2024). · DOI
  44. Gray, V. E. & Kumar, S. Rampant purifying selection conserves positions with posttranslational modifications in human proteins. Mol. Biol. Evol. 28, 1565–1568 (2011). · DOI
  45. Landry, C. R., Levy, E. D. & Michnick, S. W. Weak functional constraints on phosphoproteomes. Trends Genet. 25, 193–197 (2009). · DOI
  46. Kalodimou, K. et al. Separable roles for neur and ubiquitin in delta signalling in the Drosophila CNS lineages. Cells 12, 2833 (2023). · DOI
  47. Montero, L. et al. Conserved cysteine-switches for redox sensing operate in the cyclin-dependent kinase inhibitor p21(CIP/KIP) protein family. Free Radic. Biol. Med. 224, 494–505 (2024). · DOI
  48. Carroll, B. et al. Oxidation of SQSTM1/p62 mediates the link between redox state and protein homeostasis. Nat. Commun. 9, 256 (2018). · DOI
  49. Erdös, G., Mészáros, B., Reichmann, D. & Dosztányi, Z. Large-scale analysis of redox-sensitive conditionally disordered protein regions reveals their widespread nature and key roles in high-level eukaryotic processes. Proteomics 19, e1800070 (2019). · DOI
  50. Nguyen Ba, A. N. et al. Proteome-wide discovery of evolutionary conserved sequences in disordered regions. Sci. Signal. 5, rs1 (2012). · DOI
  51. Mehdiabadi, M. et al. Critical assessment of protein intrinsic disorder (caid) round 3 – predicting disorder in the era of protein language models. Proteins. https://doi.org/10.1002/prot.70045 (2025). · DOI
  52. Luo, H. et al. The Drosophila Jak kinase hopscotch is required for multiple developmental processes in the eye. Dev. Biol. 213, 432–441 (1999). · DOI
  53. Davey, N. E. et al. SLiMPrints: conservation-based discovery of functional motif fingerprints in intrinsically disordered protein regions. Nucleic Acids Res. 40, 10628–10641 (2012). · DOI
  54. Liehrmann, A. et al. DiffSegR: an RNA-seq data driven method for differential expression analysis using changepoint detection. NAR Genom. Bioinform. 5, lqad098 (2023). · DOI
  55. Liehrmann, A., Rigaill, G. & Hocking, T. D. Increased peak detection accuracy in over-dispersed ChIP-seq data with supervised segmentation models. BMC Bioinforma. 22, 323 (2021). · DOI
  56. Tricoire, H. et al. The steroid hormone receptor EcR finely modulates Drosophila lifespan during adulthood in a sex-specific manner. Mech. Ageing Dev. 130, 547–552 (2009). · DOI
  57. Rera, M., Monnier, V. & Tricoire, H. Mitochondrial electron transport chain dysfunction during development does not extend lifespan in Drosophila melanogaster. Mech. Ageing Dev. 131, 156–164 (2010). · DOI
  58. Hand, D. J. Review of mixture models: Inference and applications to clustering. J. R. Stat. Soc. C 38, 384–385 (1989). · DOI
  59. Suzek, B. E. et al. UniRef clusters: a comprehensive and scalable alternative for improving sequence similarity searches. Bioinformatics 31, 926–932 (2015). · DOI · Paper page
  60. Steinegger, M. et al. HH-suite3 for fast remote homology detection and deep protein annotation. BMC Bioinform. 20, 473 (2019). · DOI · Paper page
  61. Engelen, S., Trojan, L. A., Sacquin-Mora, S., Lavery, R. & Carbone, A. Joint evolutionary trees: a large-scale method to predict protein interfaces based on sequence sampling. PLoS Comput. Biol. 5, e1000267 (2009). · DOI
  62. Notin, P. et al. TranceptEVE: combining family-specific and family-agnostic models of protein sequences for improved fitness prediction. https://doi.org/10.1101/2022.12.07.519495v2 (2022). · DOI
  63. Dempster, A. P., Laird, N. M. & Rubin, D. B. Maximum likelihood from incomplete data via the EM algorithm. J. R. Stat. Soc. B (Methodological) 39, 1–38 (1977). · DOI · Paper page
  64. Pedregosa, F. et al. Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011).
  65. HALL, P., KAY, J. W. & TITTERINGTON, D. M. Asymptotically optimal difference-based estimation of variance in nonparametric regression. Biometrika 77, 521–528 (1990). · DOI
  66. Wojdyr, M. GEMMI: a library for structural biology. J. Open Source Softw. 7, 4200 (2022). · DOI
  67. Sehnal, D. et al. Mol* viewer: modern web app for 3d visualization and analysis of large biomolecular structures. Nucleic Acids Res. https://academic.oup.com/nar/article/49/W1/W431/6270780?login=false (2021). · DOI · Paper page
  68. Herrmann, C., Van de Sande, B., Potier, D. & Aerts, S. i-cisTarget: an integrative genomics method for the prediction of regulatory features and cis-regulatory modules. Nucleic Acids Res. 40, e114 (2012). · DOI
  69. Marletta, A. S. et al. Crystal structure of human nicotinic acid phosphoribosyltransferase. FEBS Open Bio 5, 419–428 (2015). · DOI
  70. Abakarova, M., Freiberger, M. I., Liehrmann, A., Rera, M. & Laine, E. Proteome-wide prediction of the functional impact of missense variants with ProteoCast. https://github.com/abakarovaMarina/ProteoCast. Available at https://github.com/abakarovaMarina/ProteoCast (2026). · DOI
  71. Landrum, M. J. et al. ClinVar: public archive of interpretations of clinically relevant variants. Nucleic Acids Res. 44, D862–D868 (2016). · DOI · Paper page
  72. Valanne, S., Vesala, L., Maasdorp, M. K., Salminen, T. S. & Rämet, M. The Drosophila Toll pathway in innate immunity: from the core pathway toward effector functions. J. Immunol. 209, 1817–1825 (2022). · DOI

Metadata

Authors
Abakarova, M., Freiberger, M. I., Liehrmann, A., Rera, M., & Laine, E.
Affiliations
Centre National de la Recherche Scientifique (FR)
ORCID
Venue
Nature Communications
Publisher
Springer Science and Business Media LLC
Published
2026-04-27
Volume
17
Issue
1
Pages
3813
ISSN
2041-1723 (ISSN-L)
DOI
10.1038/s41467-026-72140-1
PMC
PMC13121731
OpenAlex
W4407312172
Cited by
5
References
6
Citations by year
2026: 4
FWCI
16.01
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature Communications (publishedVersion, cc-by-nc-nd)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
  • Research Square (acceptedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
  • HAL (submittedVersion)
  • HAL (submittedVersion, cc-by-nc-nd)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
Funders
  • European Commission (101087830)
  • Agence Nationale de la Recherche (ANR-20-CE44-0010)
  • Sorbonne Université
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Genetics › Genomics and Rare Diseases
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Genomics and Phylogenetic Studies
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Structure and Dynamics
Keywords
protein sequence conservation, evolutionary conservation, lethal mutations, protein modification sites, protein binding motifs, genotype-phenotype correlation, protein annotation
MeSH terms
Gene Editing, Animals, Drosophila melanogaster, Computational Biology, Mutation, Missense, Proteome, Drosophila Proteins, Proteomics

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