Nucleotide transformer: building and evaluating robust foundation models for human genomics.

Last updated at 2025-08-09Posted at 2025-08-09

Nucleotide transformer: building and evaluating robust foundation models for human genomics.

H. Dalla-Torre, L. Gonzalez, J. Mendoza-Revilla, N. Lopez Carranza, A. H. Grzywaczewski, F. Oteri, C. Dallago, E. Trop, B. P. De Almeida, H. Sirelkhatim, G. Richard, M. Skwark, K. Beguir, M. Lopez, and T. Pierrot. Nucleotide transformer: building and evaluating robust foundation models for human genomics. Nature Methods, 22(2):287–297, Feb. 2025. ISSN 1548-7091, 1548-7105. doi: 10.1038/s41592-024-02523-z. URL https://www.nature.com/articles/s41592-024-02523-z.

References

Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. Bert: pre-training of deep bidirectional transformers for language understanding. Preprint at https://arxiv.org/abs/1810.04805 (2018).
Brown, T. et al. Language models are few-shot learners. Adv. Neural Inf. Process. Syst. 33, 1877–1901 (2020).
Jumper, J. et al. Highly accurate protein structure prediction with alphafold. Nature 596, 583–589 (2021).
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).
Elnaggar, A. et al. ProtTrans: towards cracking the language of life’s code through self-supervised deep learning and high performance computing. IEEE Trans. Pattern Anal. Mach. Intell. 44, 7112–7127 (2022).
Littmann, M., Heinzinger, M., Dallago, C., Olenyi, T. & Rost, B. Embeddings from deep learning transfer go annotations beyond homology. Sci. Rep. 11, 1–14 (2021).
Marquet, C. et al. Embeddings from protein language models predict conservation and variant effects. Hum. Genet. 141, 1629–1647 (2022).
Littmann, M., Heinzinger, M., Dallago, C., Weissenow, K. & Rost, B. Protein embeddings and deep learning predict binding residues for various ligand classes. Sci. Rep. 11, 23916 (2021).
Avsec, Ž. et al. Base-resolution models of transcription-factor binding reveal soft motif syntax. Nat. Genet. 53, 354–366 (2021).
Zhou, J. & Troyanskaya, O. G. Predicting effects of noncoding variants with deep learning–based sequence model. Nat. Methods 12, 931–934 (2015).
Mateo, L. J., Sinnott-Armstrong, N. & Boettiger, A. N. Tracing dna paths and rna profiles in cultured cells and tissues with orca. Nat. Protoc. 16, 1647–1713 (2021).
de Almeida, B. P., Reiter, F., Pagani, M. & Stark, A. DeepSTARR predicts enhancer activity from dna sequence and enables the de novo design of synthetic enhancers. Nat. Genet. 54, 613–624 (2022).
Eraslan, G., Avsec, Ž., Gagneur, J. & Theis, F. J. Deep learning: new computational modelling techniques for genomics. Nat. Rev. Genet. 20, 389–403 (2019).
Zhou, J. et al. Deep learning sequence-based ab initio prediction of variant effects on expression and disease risk. Nat. Genet. 50, 1171–1179 (2018).
Kelley, D. R. Cross-species regulatory sequence activity prediction. PLOS Comput. Biol. 16, e1008050 (2020).
Kelley, D. R. et al. Sequential regulatory activity prediction across chromosomes with convolutional neural networks. Genome Res. 28, 739–750 (2018).
Agarwal, V. & Shendure, J. Predicting mRNA abundance directly from genomic sequence using deep convolutional neural networks. Cell Rep. 31, 107663 (2020).
Chen, K. M., Wong, A. K., Troyanskaya, O. G. & Zhou, J. A sequence-based global map of regulatory activity for deciphering human genetics. Nat. Genet. 54, 940–949 (2022).
Avsec, Ž. et al. Effective gene expression prediction from sequence by integrating long-range interactions. Nat. Methods 18, 1196–1203 (2021).
Ji, Y., Zhou, Z., Liu, H. & Davuluri, R. V. Dnabert: pre-trained bidirectional encoder representations from transformers model for DNA-language in genome. Bioinformatics 37, 2112–2120 (2021).
Zvyagin, M. T. et al. Genslms: genome-scale language models reveal SARS-CoV-2 evolutionary dynamics. Preprint at bioRxiv https://doi.org/10.1101/2022.10.10.511571 (2022).
Outeiral, C. & Deane, C. M. Codon language embeddings provide strong signals for protein engineering. Nat. Mach. Intell. 6, 170–179 (2024).
Zhou, Z. et al. Dnabert-2: efficient foundation model and benchmark for multi-species genome. in Proceedings of the Twelfth International Conference on Learning Representations https://openreview.net/pdf?id=oMLQB4EZE1 (ICLR, 2024).
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).
Nguyen, E. et al. Hyenadna: Long-range genomic sequence modeling at single nucleotide resolution. in 37th Conference on Neural Information Processing Systems https://openreview.net/pdf?id=ubzNoJjOKj (NeurIPS, 2023).
Mendoza-Revilla, J. et al. A foundational large language model for edible plant genomes. Commun. Biol. 7, 835 (2024).
Rae, J. W. et al. Scaling language models: methods, analysis & insights from training gopher. Preprint at https://arxiv.org/abs/2112.11446 (2021).
Consortium, G. P. et al. A global reference for human genetic variation. Nature 526, 68 (2015).
Harrow, J. et al. GENCODE: the reference human genome annotation for the encode project. Genome Res. 22, 1760–1774 (2012).
Meylan, P., Dreos, R., Ambrosini, G., Groux, R. & Bucher, P. Epd in 2020: enhanced data visualization and extension to ncRNA promoters. Nucleic Acids Res. 48, D65–D69 (2020).
ENCODE. An integrated encyclopedia of dna elements in the human genome. Nature 489, 57–74 (2012).
The ENCODE Project Consortium. Expanded encyclopaedias of dna elements in the human and mouse genomes. Nature 583, 699–710 (2020).
Meuleman, W. et al. Index and biological spectrum of human DNase I hypersensitive sites. Nature 584, 244–251 (2020).
Li, F.-Z., Amini, A. P., Yang, K. K. & Lu, A. X. Pretrained protein language model transfer learning: is the final layer representation what we want? in Machine Learning for Structural Biology Workshop (NeurIPS, 2022).
Liu, H. et al. Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning. in 36th Conference on Neural Information Processing Systems (NeurIPS, 2022).
Jaganathan, K. et al. Predicting splicing from primary sequence with deep learning. Cell 176, 535–548 (2019).
Benegas, G., Batra, S. S. & Song, Y. S. DNA language models are powerful zero-shot predictors of non-coding variant effects. Proc. Natl Acad. Sci. USA 120, e2311219120 (2023).
Vig, J. et al. BERTology meets biology: interpreting attention in protein language models. in Proceedings of the International Conference on Learning Representations 2021 https://openreview.net/pdf?id=YWtLZvLmud7 (ICLR, 2021).
Braun, S. et al. Decoding a cancer-relevant splicing decision in the ron proto-oncogene using high-throughput mutagenesis. Nat. Commun. 9, 3315 (2018).
McLaren, W. et al. The Ensembl variant effect predictor. Genome Biol. 17, 1–14 (2016).
Lappalainen, T. et al. Transcriptome and genome sequencing uncovers functional variation in humans. Nature 501, 506–511 (2013).
Consortium, G. The gtex consortium atlas of genetic regulatory effects across human tissues. Science 369, 1318–1330 (2020).
Võsa, U. et al. Large-scale cis-and trans-eqtl analyses identify thousands of genetic loci and polygenic scores that regulate blood gene expression. Nat. Genetics 53, 1300–1310 (2021).
Chowdhery, A. et al. PaLM: scaling language modeling with pathways. J. Mach. Learn. Technol. 24, 11324–11436 (2021).
Hoffmann, J. et al. Training compute-optimal large language models. in 36th Conference on Neural Information Processing Systems https://proceedings.neurips.cc/paper_files/paper/2022/file/c1e2faff6f588870935f114ebe04a3e5-Paper-Conference.pdf (NeurIPS, 2022).
Rogers, A., Kovaleva, O. & Rumshisky, A. A primer in BERTology: what we know about how bert works. Trans. Assoc. Comput. Linguist. 8, 842–866 (2020).
Stärk, H., Dallago, C., Heinzinger, M. & Rost, B. Light attention predicts protein location from the language of life. Bioinform. Adv. 1, vbab035 (2021).
Zou, J. et al. A primer on deep learning in genomics. Nat. Genetics 51, 12–18 (2019).
Wang, A. et al. Superglue: a stickier benchmark for general-purpose language understanding systems. in 33rd Conference on Neural Information Processing Systems https://papers.nips.cc/paper_files/paper/2019/file/4496bf24afe7fab6f046bf4923da8de6-Paper.pdf (NeurIPS, 2019).
Hendrycks, D. & Gimpel, K. Gaussian error linear units (gelus). Preprint at https://arxiv.org/abs/1606.08415 (2016).
Su, J. et al. Roformer: enhanced transformer with rotary position embedding. Neurocomputing 568, 127063 (2024).
Kingma, D. P. & Ba, J. Adam: a method for stochastic optimization. Preprint at https://arxiv.org/abs/1412.6980v5 (2015).
Pedregosa, F. et al. Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011).
Bergstra, J., Bardenet, R., Bengio, Y. & Kégl, B. Algorithms for hyper-parameter optimization. in Advances in Neural Information Processing Systems 24 https://papers.nips.cc/paper_files/paper/2011/file/86e8f7ab32cfd12577bc2619bc635690-Paper.pdf (NeurIPS, 2011).
Byrska-Bishop, M. et al. High-coverage whole-genome sequencing of the expanded 1000 genomes project cohort including 602 trios. Cell 185, 3426–3440 (2022).
Kim, D., Paggi, J. M., Park, C., Bennett, C. & Salzberg, S. L. Graph-based genome alignment and genotyping with hisat2 and hisat-genotype. Nat. Biotechnol.37, 907–905 (2019).
Leslie, R., O’Donnell, C. J. & Johnson, A. D. GRASP: analysis of genotype–phenotype results from 1390 genome-wide association studies and corresponding open access database. Bioinformatics 30, i185–i194 (2014).
Landrum, M. J. et al. Clinvar: improving access to variant interpretations and supporting evidence. Nucleic Acids Res. 46, D1062–D1067 (2018).
Stenson, P. D. et al. The Human Gene Mutation Database (HGMD®): optimizing its use in a clinical diagnostic or research setting. Hum. Genet. 139, 1197–1207 (2020).

Nucleotide transformer: building and evaluating robust foundation models for human genomics.

Nucleotide transformer: building and evaluating robust foundation models for human genomics.

References

Related document on the Qiita