{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T22:16:05Z","timestamp":1792016165733,"version":"4.4.0"},"reference-count":66,"publisher":"National Academy of Sciences","issue":"48","license":[{"start":{"date-parts":[[2021,11,23]],"date-time":"2021-11-23T00:00:00Z","timestamp":1637625600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"HHS | National Institutes of Health","doi-asserted-by":"publisher","award":["R35GM119854"],"award-info":[{"award-number":["R35GM119854"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"HHS | National Institutes of Health","doi-asserted-by":"publisher","award":["R01GM135631"],"award-info":[{"award-number":["R01GM135631"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"HHS | National Institutes of Health","doi-asserted-by":"publisher","award":["T32HG002760"],"award-info":[{"award-number":["T32HG002760"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100001797","name":"Pharmaceutical Research and Manufacturers of America Foundation","doi-asserted-by":"publisher","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}],"id":[{"id":"10.13039\/100001797","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.pnas.org"],"crossmark-restriction":true},"short-container-title":["Proc. Natl. Acad. Sci. U.S.A."],"published-print":{"date-parts":[[2021,11,30]]},"abstract":"<jats:title>Significance<\/jats:title>\n                  <jats:p>Understanding the relationship between protein sequence and function is necessary to design new and useful proteins with applications in bioenergy, medicine, and agriculture. The mapping from sequence to function is tremendously complex because it involves thousands of molecular interactions that are coupled over multiple lengths and timescales. We show that neural networks can learn the sequence\u2013function mapping from large protein datasets. Neural networks are appealing for this task because they can learn complicated relationships from data, make few assumptions about the nature of the sequence\u2013function relationship, and can learn general rules that apply across the length of the protein sequence. We demonstrate that learned models can be applied to design new proteins with properties that exceed natural sequences.<\/jats:p>","DOI":"10.1073\/pnas.2104878118","type":"journal-article","created":{"date-parts":[[2021,11,23]],"date-time":"2021-11-23T16:40:16Z","timestamp":1637685616000},"update-policy":"https:\/\/doi.org\/10.1073\/pnas.cm10313","source":"Crossref","is-referenced-by-count":167,"title":["Neural networks to learn protein sequence\u2013function relationships from deep mutational scanning data"],"prefix":"10.1073","volume":"118","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9537-0976","authenticated-orcid":false,"given":"Sam","family":"Gelman","sequence":"first","affiliation":[{"name":"Department of Computer Sciences, University of Wisconsin\u2013Madison, Madison, WI 53706;"},{"name":"Morgridge Institute for Research, Madison, WI 53715;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sarah A.","family":"Fahlberg","sequence":"additional","affiliation":[{"name":"Department of Biochemistry, University of Wisconsin\u2013Madison, Madison, WI 53706;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5588-3731","authenticated-orcid":false,"given":"Pete","family":"Heinzelman","sequence":"additional","affiliation":[{"name":"Department of Biochemistry, University of Wisconsin\u2013Madison, Madison, WI 53706;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2586-7263","authenticated-orcid":false,"given":"Philip A.","family":"Romero","sequence":"additional","affiliation":[{"name":"Department of Biochemistry, University of Wisconsin\u2013Madison, Madison, WI 53706;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5324-9833","authenticated-orcid":false,"given":"Anthony","family":"Gitter","sequence":"additional","affiliation":[{"name":"Department of Computer Sciences, University of Wisconsin\u2013Madison, Madison, WI 53706;"},{"name":"Morgridge Institute for Research, Madison, WI 53715;"},{"name":"Department of Biostatistics and Medical Informatics, University of Wisconsin\u2013Madison, Madison, WI 53792"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"341","published-online":{"date-parts":[[2021,11,23]]},"reference":[{"key":"e_1_3_4_1_2","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.3769"},{"key":"e_1_3_4_2_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-018-0138-4"},{"key":"e_1_3_4_3_2","doi-asserted-by":"publisher","DOI":"10.1038\/nbt1286"},{"key":"e_1_3_4_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cels.2020.10.007"},{"key":"e_1_3_4_5_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1215251110"},{"key":"e_1_3_4_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cels.2017.11.003"},{"key":"e_1_3_4_7_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.0c00073"},{"key":"e_1_3_4_8_2","doi-asserted-by":"publisher","DOI":"10.1038\/nprot.2015.123"},{"key":"e_1_3_4_9_2","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth0410-248"},{"key":"e_1_3_4_10_2","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2164-16-S8-S1"},{"key":"e_1_3_4_11_2","doi-asserted-by":"crossref","unstructured":"B. Wang E. R. Gamazon Modeling mutational effects on biochemical phenotypes using convolutional neural networks: Application to SARS-CoV-2. bioRxiv [Preprint] (2021). https:\/\/doi.org\/10.1101\/2021.01.28.428521 (Accessed 8 February 2021).","DOI":"10.1101\/2021.01.28.428521"},{"key":"e_1_3_4_12_2","doi-asserted-by":"publisher","DOI":"10.1098\/rsif.2017.0387"},{"key":"e_1_3_4_13_2","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.3027"},{"key":"e_1_3_4_14_2","doi-asserted-by":"publisher","DOI":"10.1002\/pro.2897"},{"key":"e_1_3_4_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2014.09.072"},{"key":"e_1_3_4_16_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature17995"},{"key":"e_1_3_4_17_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1422285112"},{"key":"e_1_3_4_18_2","doi-asserted-by":"publisher","DOI":"10.1261\/rna.040709.113"},{"key":"e_1_3_4_19_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1303309110"},{"key":"e_1_3_4_20_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.7b00125"},{"key":"e_1_3_4_21_2","author":"Mater A. C.","year":"2020","unstructured":"A. C. Mater, M. Sandhu, C. Jackson, The NK landscape as a versatile benchmark for machine learning driven protein engineering. bioRxiv [Preprint] (2020). https:\/\/doi.org\/10.1101\/2020.09.30.319780 (Accessed 6 October 2020).","journal-title":"The NK landscape as a versatile benchmark for machine learning driven protein engineering."},{"key":"e_1_3_4_22_2","unstructured":"L. McInnes J. Healy UMAP: Uniform manifold approximation and projection for dimension reduction. arXiv [Preprint] (2020). https:\/\/arxiv.org\/abs\/1802.03426 (Accessed 18 September 2020)."},{"key":"e_1_3_4_23_2","unstructured":"M. Sundararajan A. Taly Q. Yan Axiomatic attribution for deep networks. arXiv [Preprint] (2017). https:\/\/arxiv.org\/abs\/1703.01365 (Accessed 13 June 2017)."},{"key":"e_1_3_4_24_2","doi-asserted-by":"publisher","DOI":"10.1093\/protein\/gzu005"},{"key":"e_1_3_4_25_2","doi-asserted-by":"publisher","DOI":"10.1021\/acschembio.9b00652"},{"key":"e_1_3_4_26_2","doi-asserted-by":"publisher","DOI":"10.1021\/bi00489a001"},{"key":"e_1_3_4_27_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-25371-3"},{"key":"e_1_3_4_28_2","doi-asserted-by":"crossref","unstructured":"A. Tareen . MAVE-NN: Learning genotype-phenotype maps from multiplex assays of variant effect. bioRxiv [Preprint] (2021). https:\/\/doi.org\/10.1101\/2020.07.14.201475 (Accessed 27 June 2021).","DOI":"10.1101\/2020.07.14.201475"},{"key":"e_1_3_4_29_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1804015115"},{"key":"e_1_3_4_30_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-021-01100-y"},{"key":"e_1_3_4_31_2","doi-asserted-by":"crossref","unstructured":"Y. Luo . Evolutionary context-integrated deep sequence modeling for protein engineering. bioRxiv [Preprint] (2020). https:\/\/doi.org\/10.1101\/2020.01.16.908509 (Accessed 17 January 2020).","DOI":"10.1101\/2020.01.16.908509"},{"key":"e_1_3_4_32_2","unstructured":"A. Fout J. Byrd B. Shariat A. Ben-Hur \u201cProtein interface prediction using graph convolutional networks\u201d in NIPS\u201917: Proceedings of the 31st International Conference on Neural Information Processing Systems I. Guyon . Eds. (Curran Associates Inc. Red Hook NY 2017) vol. 30 pp. 6530\u20136539."},{"key":"e_1_3_4_33_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-23303-9"},{"key":"e_1_3_4_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cels.2020.08.016"},{"key":"e_1_3_4_35_2","doi-asserted-by":"crossref","unstructured":"S. Sanyal I. Anishchenko A. Dagar D. Baker P. Talukdar ProteinGCN: Protein model quality assessment using Graph Convolutional Networks. bioRxiv [Preprint] (2020). https:\/\/doi.org\/10.1101\/2020.04.06.028266 (Accessed 7 April 2020).","DOI":"10.1101\/2020.04.06.028266"},{"key":"e_1_3_4_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"e_1_3_4_37_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-020-00793-4"},{"key":"e_1_3_4_38_2","unstructured":"C. Angermueller . Population-based black-box optimization for biological sequence design. arXiv [Preprint] (2020). https:\/\/arxiv.org\/abs\/2006.03227 (Accessed 11 July 2020)."},{"key":"e_1_3_4_39_2","unstructured":"C. Fannjiang J. Listgarten Autofocused oracles for model-based design. arXiv [Preprint] (2020). https:\/\/arxiv.org\/abs\/2006.08052 (Accessed 24 October 2020)."},{"key":"e_1_3_4_40_2","unstructured":"D. H. Brookes H. Park J. Listgarten Conditioning by adaptive sampling for robust design. arXiv [Preprint] (2021). https:\/\/arxiv.org\/abs\/1901.10060 (Accessed 12 May 2021)."},{"key":"e_1_3_4_41_2","unstructured":"J. Linder G. Seelig Fast differentiable DNA and protein sequence optimization for molecular design. arXiv [Preprint] (2020). https:\/\/arxiv.org\/abs\/2005.11275 (Accessed 20 December 2020)."},{"key":"e_1_3_4_42_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0496-6"},{"key":"e_1_3_4_43_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csbj.2019.12.011"},{"key":"e_1_3_4_44_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-019-1845-6"},{"key":"e_1_3_4_45_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1008736"},{"key":"e_1_3_4_46_2","doi-asserted-by":"crossref","unstructured":"A. Madani . ProGen: Language modeling for protein generation. bioRxiv [Preprint] (2020). https:\/\/doi.org\/10.1101\/2020.03.07.982272 (Accessed 13 March 2020).","DOI":"10.1101\/2020.03.07.982272"},{"key":"e_1_3_4_47_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0141287"},{"key":"e_1_3_4_48_2","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty178"},{"key":"e_1_3_4_49_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0598-1"},{"key":"e_1_3_4_50_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2016239118"},{"key":"e_1_3_4_51_2","doi-asserted-by":"crossref","unstructured":"S. Biswas . Toward machine-guided design of proteins. bioRxiv [Preprint] (2018). https:\/\/doi.org\/10.1101\/337154 (Accessed 2 June 2018).","DOI":"10.1101\/337154"},{"key":"e_1_3_4_52_2","doi-asserted-by":"publisher","DOI":"10.1021\/acssynbio.8b00155"},{"key":"e_1_3_4_53_2","article-title":"Machine learning-assisted directed evolution navigates a combinatorial epistatic fitness landscape with minimal screening burden","author":"Wittmann B. J.","year":"2021","unstructured":"B. J. Wittmann, Y. Yue, F. H. Arnold, Machine learning-assisted directed evolution navigates a combinatorial epistatic fitness landscape with minimal screening burden. Cell Syst., 10.1016\/j.cels.2021.07.008 (2021).","journal-title":"Cell Syst."},{"key":"e_1_3_4_54_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-017-1272-5"},{"key":"e_1_3_4_55_2","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkm998"},{"key":"e_1_3_4_56_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.str.2013.08.005"},{"key":"e_1_3_4_57_2","doi-asserted-by":"crossref","unstructured":"A. A. Hagberg D. A. Schult P. J. Swart \u201cExploring network structure dynamics and function using NetworkX\u201d in Proceedings of the 7th Python in Science Conference G. Varoquaux T. Vaught J. Millman Eds. (SciPy 2008) pp. 11\u201315.","DOI":"10.25080\/TCWV9851"},{"key":"e_1_3_4_58_2","unstructured":"M. Abadi . TensorFlow: Large-scale machine learning on heterogeneous systems (2015). https:\/\/www.tensorflow.org\/. Accessed 18 June 2019."},{"key":"e_1_3_4_59_2","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.938"},{"key":"e_1_3_4_60_2","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty862"},{"key":"e_1_3_4_61_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1002195"},{"key":"e_1_3_4_62_2","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btu739"},{"key":"e_1_3_4_63_2","unstructured":"M. Ancona E. Ceolini C. \u00d6ztireli M. Gross Towards better understanding of gradient-based attribution methods for deep neural networks. arXiv [Preprint] (2018). https:\/\/arxiv.org\/abs\/1711.06104 (Accessed 7 March 2018)."},{"key":"e_1_3_4_64_2","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-0134(1999)37:3 <171::AID-PROT21>3.0.CO;2-Z"},{"key":"e_1_3_4_65_2","unstructured":"S. Gelman S. A. Fahlberg P. A. Romero A. Gitter Neural networks for deep mutational scanning data (2020). GitHub. https:\/\/github.com\/gitter-lab\/nn4dms. Deposited 22 October 2020."},{"key":"e_1_3_4_66_2","unstructured":"S. Gelman S. A. Fahlberg P. A. Romero A. Gitter Neural networks for deep mutational scanning data (2020). Zenodo. https:\/\/doi.org\/10.5281\/zenodo.4118330. Deposited 22 October 2020."}],"container-title":["Proceedings of the National Academy of Sciences"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/www.pnas.org\/syndication\/doi\/10.1073\/pnas.2104878118","content-type":"unspecified","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pnas.org\/doi\/pdf\/10.1073\/pnas.2104878118","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,12]],"date-time":"2024-09-12T18:18:42Z","timestamp":1726165122000},"score":1,"resource":{"primary":{"URL":"https:\/\/pnas.org\/doi\/full\/10.1073\/pnas.2104878118"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,23]]},"references-count":66,"journal-issue":{"issue":"48","published-print":{"date-parts":[[2021,11,30]]}},"alternative-id":["10.1073\/pnas.2104878118"],"URL":"https:\/\/doi.org\/10.1073\/pnas.2104878118","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2020.10.25.353946","asserted-by":"object"}]},"ISSN":["0027-8424","1091-6490"],"issn-type":[{"value":"0027-8424","type":"print"},{"value":"1091-6490","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,23]]},"assertion":[{"value":"2021-10-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-11-23","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e2104878118"}}