A dna language model based on multispecies alignment predicts the effects of genome-wide variants

Last updated at 2025-08-03Posted at 2025-08-02

A dna language model based on multispecies alignment predicts the effects of genome-wide variants Gonzalo Benegas1,2, Carlos Albors2,5, Alan J. Aw3,5, Chengzhong Ye3,5 & Yun S. Song, https://www.researchgate.net/publication/387673319_A_DNA_language_model_based_on_multispecies_alignment_predicts_the_effects_of_genome-wide_variants

References

Goldfeder, R. L., Wall, D. P., Khoury, M. J., Ioannidis, J. P. & Ashley, E. A. Human genome sequencing at the population scale: a primer on high-throughput DNA sequencing and analysis. Am. J. Epidemiol. 186, 1000–1009 (2017).
Marwaha, S., Knowles, J. W. & Ashley, E. A. A guide for the diagnosis of rare and undiagnosed disease: beyond the exome. Genome Med. 14, 23 (2022).
Lee, S., Abecasis, G. R., Boehnke, M. & Lin, X. Rare-variant association analysis: study designs and statistical tests. Am. J. Hum. Genet. 95, 5–23 (2014).
Trajanoska, K. et al. From target discovery to clinical drug development with human genetics. Nature 620, 737–745 (2023).
Meier, J. et al. Language models enable zero-shot prediction of the effects of mutations on protein function. In Proc. Advances in Neural Information Processing Systems 34 (eds Ranzato, M. et al.) 29287–29303 (Curran Associates, Inc., 2021).
Brandes, N., Goldman, G., Wang, C. H., Ye, C. J. & Ntranos, V. Genome-wide prediction of disease variant effects with a deep protein language model. Nat. Genet. 55, 1512–1522 (2023).
Jagota, M. et al. Cross-protein transfer learning substantially improves disease variant prediction. Genome Biol. 24, 182 (2023).
Benegas, G., Batra, S. S. & Song, Y. S. DNA language models are powerful predictors of genome-wide variant effects. Proc. Natl Acad. Sci. USA 120, e2311219120 (2023).
Dalla-Torre, H. et al. Nucleotide Transformer: building and evaluating robust foundation models for human genomics. Nat. Methods https://doi.org/10.1038/s41592-024-02523-z (2024).
Vaswani, A. et al. Attention is all you need. In Proc. Advances in Neural Information Processing Systems 30 (eds Guyon, S. et al.) 6000–6010 (Curran Associates, Inc., 2017).
Armstrong, J., Fiddes, I. T., Diekhans, M. & Paten, B. Wholegenome alignment and comparative annotation. Annu. Rev. Anim. Biosci. 7, 41–64 (2019).
Nguyen, E. et al. HyenaDNA: long-range genomic sequence modeling at single nucleotide resolution. In Proc. 37th International Conference on Neural Information Processing Systems (eds Oh, A. et al.) 43177–43201 (Curran Associates, Inc.,2023).
Rentzsch, P., Schubach, M., Shendure, J. & Kircher, M. CADD-Splice-improving genome-wide variant effect prediction using deep learning-derived splice scores. Genome Med. 13, 31 (2021).
Pollard, K. S., Hubisz, M. J., Rosenbloom, K. R. & Siepel, A. Detection of nonneutral substitution rates on mammalian phylogenies. Genome Res. 20, 110–121 (2010).
Sullivan, P. F. et al. Leveraging base-pair mammalian constraint to understand genetic variation and human disease. Science 380, eabn2937 (2023).
Rives, A. et al. Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. Proc. Natl Acad. Sci. USA 118, e2016239118 (2021).
Avsec, Ž. et al. Effective gene expression prediction from sequence by integrating long-range interactions. Nat. Methods 18, 1196–1203 (2021).
Jaganathan, K. et al. Predicting splicing from primary sequence with deep learning. Cell 176, 535–548.e24 (2019).
Rao, R. M. et al. MSA Transformer. In Proceedings of the 38th International Conference on Machine Learning (eds Meila, M. & Zhang, T.) (PMLR, 2021).
Paten, B. et al. Genome-wide nucleotide-level mammalian ancestor reconstruction. Genome Res. 18, 1829–1843 (2008).
Siepel, A. et al. Evolutionarily conserved elements in vertebrate, insect, worm, and yeast genomes. Genome Res. 15, 1034–1050 (2005).
Landrum, M. J. et al. ClinVar: improvements to accessing data. Nucleic Acids Res. 48, D835–D844 (2020).
Chen, S. et al. A genomic mutational constraint map using variation in 76,156 human genomes. Nature 625, 92–100 (2024).
Rentzsch, P., Witten, D., Cooper, G. M., Shendure, J. & Kircher, M. CADD: predicting the deleteriousness of variants throughout the human genome. Nucleic Acids Res. 47, D886–D894 (2019).
Tate, J. G. et al. COSMIC: the catalogue of somatic mutations in cancer. Nucleic Acids Res. 47, D941–D947 (2019).
Notin, P. et al. ProteinGym: large-scale benchmarks for protein fitness prediction and design. In Proceedings of the Advances in Neural Information Processing Systems 37 (eds Oh, A. et al.) (NeurIPS, 2023).
Smedley, D. et al. A whole-genome analysis framework for effective identification of pathogenic regulatory variants in mendelian disease. Am. J. Hum. Genet. 99, 595–606 (2016).
Albuisson, J. et al. Identification of two novel mutations in Shh long-range regulator associated with familial pre-axial polydactyly. Clin. Genet. 79, 371–377 (2011).
Kvon, E. Z. et al. Comprehensive in vivo interrogation reveals phenotypic impact of human enhancer variants. Cell 180, 1262–1271.e15 (2020).
Arbini, A. A., Pollak, E. S., Bayleran, J. K., High, K. A. & Bauer, K. A. Severe factor VII deficiency due to a mutation disrupting a hepatocyte nuclear factor 4 binding site in the factor VII promoter. Blood 89, 176–182 (1997).
Gao, H. et al. The landscape of tolerated genetic variation in humans and primates. Science 380, eabn8153 (2023).
The Dependency Map Consortium. DepMap 23Q4 public. figshare https://doi.org/10.25452/figshare.plus.24667905.v2 (2023).
Karczewski, K. J. et al. The mutational constraint spectrum quantified from variation in 141,456 humans. Nature 581, 434–443(2020).
Agarwal, I., Fuller, Z. L., Myers, S. R. & Przeworski, M. Relating pathogenic loss-of-function mutations in humans to their evolutionary fitness costs. eLife 12, e83172 (2023).
Zeng, T., Spence, J. P., Mostafavi, H. & Pritchard, J. K.Bayesian estimation of gene constraint from an evolutionary model with gene features. Nat. Genet. 56, 1632–1643 (2024).
Richards, S. et al. Standards and guidelines for the interpretation of sequence variants: a joint consensus recommendation of the American College of Medical Genetics and Genomics and the Association for Molecular Pathology. Genet. Med. 17, 405–424 (2015).
Schneider, T. D. & Stephens, R. M. Sequence logos: a new way to display consensus sequences. Nucleic Acids Res. 18, 6097–6100 (1990).
Kent, W. J. et al. The human genome browser at UCSC. Genome Res. 12, 996–1006 (2002).
Nair, S. et al. The dynseq browser track shows context-specific features at nucleotide resolution. Nat. Genet. 54, 1581–1583 (2022).
Fishman, V. et al. GENA-LM: a family of open-source foundational models for long DNA sequences. Preprint at bioRxiv https://doi.org/10.1101/2023.06.12.544594 (2023).
Borgeaud, S. et al. Improving language models by retrieving from trillions of tokens. In Proc. 39th International Conference on Machine Learning (eds Chaudhuri, K. et al.) 2206–2240 (PMLR, 2022).
Weiner, D. J. et al. Polygenic architecture of rare coding variation across 394,783 exomes. Nature 614, 492–499 (2023).
Weissbrod, O. et al. Functionally informed fine-mapping and polygenic localization of complex trait heritability. Nat. Genet. 52, 1355–1363 (2020).
Márquez-Luna, C. et al. Incorporating functional priors improves polygenic prediction accuracy in UK Biobank and 23andMe data sets. Nat. Commun. 12, 6052 (2021).
Aw, A. J., McRae, J., Rahmani, E. & Song, Y. S. Highly parameterized polygenic scores tend to overfit to population stratification via random effects. Preprint at bioRxiv https://doi.org/10.1101/2024.01.27.577589 (2024).

A dna language model based on multispecies alignment predicts the effects of genome-wide variants

References

Related document on Qiita