{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-generative-models-of-genetic-variation","title":"Deep generative models of genetic variation capture mutation effects","arxiv_id":"1712.06527","date":"2017-12-18","proceeding":null,"authors":["Adam J. Riesselman","John B. Ingraham","Debora S. Marks"],"abstract":"The functions of proteins and RNAs are determined by a myriad of interactions\nbetween their constituent residues, but most quantitative models of how\nmolecular phenotype depends on genotype must approximate this by simple\nadditive effects. While recent models have relaxed this constraint to also\naccount for pairwise interactions, these approaches do not provide a tractable\npath towards modeling higher-order dependencies. Here, we show how latent\nvariable models with nonlinear dependencies can be applied to capture\nbeyond-pairwise constraints in biomolecules. We present a new probabilistic\nmodel for sequence families, DeepSequence, that can predict the effects of\nmutations across a variety of deep mutational scanning experiments\nsignificantly better than site independent or pairwise models that are based on\nthe same evolutionary data. The model, learned in an unsupervised manner solely\nfrom sequence information, is grounded with biologically motivated priors,\nreveals latent organization of sequence families, and can be used to\nextrapolate to new parts of sequence space","url_abs":"http://arxiv.org/abs/1712.06527v1","url_pdf":"http://arxiv.org/pdf/1712.06527v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-generative-models-of-genetic-variation","repo_url":"https://github.com/HW-work/gen-bio","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"deep-generative-models-of-genetic-variation","repo_url":"https://github.com/samsinai/VAE_protein_function","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}