{"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/learning-protein-constitutive-motifs-from","title":"Learning protein constitutive motifs from sequence data","arxiv_id":"1803.08718","date":"2018-03-23","proceeding":null,"authors":["Jérôme Tubiana","Simona Cocco","Rémi Monasson"],"abstract":"Statistical analysis of evolutionary-related protein sequences provides\ninsights about their structure, function, and history. We show that Restricted\nBoltzmann Machines (RBM), designed to learn complex high-dimensional data and\ntheir statistical features, can efficiently model protein families from\nsequence information. We apply RBM to two protein domains, Kunitz and WW, and\nto synthetic lattice proteins for benchmarking. The features inferred by the\nRBM can be biologically interpreted in terms of structural modes, including\nresidue-residue tertiary contacts and extended secondary motifs ($\\alpha$-helix\nand $\\beta$-sheet), of functional modes controlling activity and ligand\nspecificity, or of phylogenetic identity. In addition, we use RBM to design new\nprotein sequences with putative properties by composing and turning up or down\nthe different modes at will. Our work therefore shows that RBM are a versatile\nand practical tool to unveil and exploit the genotype-phenotype relationship\nfor protein families.","url_abs":"http://arxiv.org/abs/1803.08718v2","url_pdf":"http://arxiv.org/pdf/1803.08718v2.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":"learning-protein-constitutive-motifs-from","repo_url":"https://github.com/jertubiana/ProteinMotifRBM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"specificity","task_name":"Specificity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.08718","atlas_url":"https://app.syntology.ai/?focus=1803.08718","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}