{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T02:08:32Z","timestamp":1773886112914,"version":"3.50.1"},"reference-count":20,"publisher":"Oxford University Press (OUP)","issue":"7","license":[{"start":{"date-parts":[[2019,11,28]],"date-time":"2019-11-28T00:00:00Z","timestamp":1574899200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01CA218094"],"award-info":[{"award-number":["R01CA218094"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,4,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>The precise targeting of antibodies and other protein therapeutics is required for their proper function and the elimination of deleterious off-target effects. Often the molecular structure of a therapeutic target is unknown and randomized methods are used to design antibodies without a model that relates antibody sequence to desired properties.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Here, we present Ens-Grad, a machine learning method that can design complementarity determining regions of human Immunoglobulin G antibodies with target affinities that are superior to candidates derived from phage display panning experiments. We also demonstrate that machine learning can improve target specificity by the modular composition of models from different experimental campaigns, enabling a new integrative approach to improving target specificity. Our results suggest a new path for the discovery of therapeutic molecules by demonstrating that predictive and differentiable models of antibody binding can be learned from high-throughput experimental data without the need for target structural data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>Sequencing data of the phage panning experiment are deposited at NIH\u2019s Sequence Read Archive (SRA) under the accession number SRP158510. We make our code available at https:\/\/github.com\/gifford-lab\/antibody-2019.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Supplementary information<\/jats:title>\n                    <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btz895","type":"journal-article","created":{"date-parts":[[2019,11,26]],"date-time":"2019-11-26T15:13:37Z","timestamp":1574781217000},"page":"2126-2133","source":"Crossref","is-referenced-by-count":139,"title":["Antibody complementarity determining region design using high-capacity machine learning"],"prefix":"10.1093","volume":"36","author":[{"given":"Ge","family":"Liu","sequence":"first","affiliation":[{"name":"MIT Computer Science and Artificial Intelligence Laboratory , Cambridge, MA, USA"},{"name":"Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology , Cambridge, MA, USA"}]},{"given":"Haoyang","family":"Zeng","sequence":"additional","affiliation":[{"name":"MIT Computer Science and Artificial Intelligence Laboratory , Cambridge, MA, USA"},{"name":"Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology , Cambridge, MA, USA"}]},{"given":"Jonas","family":"Mueller","sequence":"additional","affiliation":[{"name":"MIT Computer Science and Artificial Intelligence Laboratory , Cambridge, MA, USA"},{"name":"Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology , Cambridge, MA, USA"}]},{"given":"Brandon","family":"Carter","sequence":"additional","affiliation":[{"name":"MIT Computer Science and Artificial Intelligence Laboratory , Cambridge, MA, USA"},{"name":"Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology , Cambridge, MA, USA"}]},{"given":"Ziheng","family":"Wang","sequence":"additional","affiliation":[{"name":"MIT Computer Science and Artificial Intelligence Laboratory , Cambridge, MA, USA"},{"name":"Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology , Cambridge, MA, USA"}]},{"given":"Jonas","family":"Schilz","sequence":"additional","affiliation":[{"name":"Novartis Institutes for BioMedical Research , Basel, Switzerland"}]},{"given":"Geraldine","family":"Horny","sequence":"additional","affiliation":[{"name":"Novartis Institutes for BioMedical Research , Basel, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2281-3518","authenticated-orcid":false,"given":"Michael E","family":"Birnbaum","sequence":"additional","affiliation":[{"name":"Department of Biological Engineering, Massachusetts Institute of Technology , Cambridge, MA, USA"},{"name":"Koch Institute for Integrative Cancer Research at MIT , Cambridge, MA, USA"}]},{"given":"Stefan","family":"Ewert","sequence":"additional","affiliation":[{"name":"Novartis Institutes for BioMedical Research , Basel, Switzerland"}]},{"given":"David K","family":"Gifford","sequence":"additional","affiliation":[{"name":"MIT Computer Science and Artificial Intelligence Laboratory , Cambridge, MA, USA"},{"name":"Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology , Cambridge, MA, USA"},{"name":"Department of Biological Engineering, Massachusetts Institute of Technology , Cambridge, MA, USA"}]}],"member":"286","published-online":{"date-parts":[[2019,11,28]]},"reference":[{"key":"2023062312014988300_btz895-B2","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.abb.2012.03.009","article-title":"Engineering antibodies by yeast display","volume":"526","author":"Boder","year":"2012","journal-title":"Arch. Biochem. Biophys"},{"key":"2023062312014988300_btz895-B3","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1016\/0378-1119(91)90244-6","article-title":"A surface expression vector for antibody screening","volume":"104","author":"Breitling","year":"1991","journal-title":"Gene"},{"key":"2023062312014988300_btz895-B4","first-page":"1215","author":"Carney","year":"1999"},{"key":"2023062312014988300_btz895-B5","first-page":"674119","author":"Carter","year":"2019"},{"key":"2023062312014988300_btz895-B6","first-page":"567","author":"Carter","year":"2019"},{"key":"2023062312014988300_btz895-B11","author":"Erhan","year":"2009"},{"key":"2023062312014988300_btz895-B14","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1016\/j.sbi.2018.04.007","article-title":"Computational design of antibodies","volume":"51","author":"Fischman","year":"2018","journal-title":"Curr. Opin. Struct. Biol"},{"key":"2023062312014988300_btz895-B18","doi-asserted-by":"crossref","first-page":"599","DOI":"10.1093\/protein\/gzt027","article-title":"The indistinguishability of epitopes from protein surface is explained by the distinct binding preferences of each of the six antigen-binding loops","volume":"26","author":"Kunik","year":"2013","journal-title":"Protein Eng. Des. Sel"},{"key":"2023062312014988300_btz895-B19","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1093\/protein\/gzs024","article-title":"Computer-aided antibody design","volume":"25","author":"Kuroda","year":"2012","journal-title":"Protein Eng. Des. Sel"},{"key":"2023062312014988300_btz895-B20","first-page":"6402","volume-title":"Advances in The 31st Neural Information Processing Systems","author":"Lakshminarayanan","year":"2017"},{"key":"2023062312014988300_btz895-B21","doi-asserted-by":"crossref","first-page":"2944","DOI":"10.1093\/bioinformatics\/bty305","article-title":"Parapred: antibody paratope prediction using convolutional and recurrent neural networks","volume":"34","author":"Liberis","year":"2018","journal-title":"Bioinformatics"},{"key":"2023062312014988300_btz895-B22","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1186\/s12859-019-2957-4","article-title":"Visualizing complex feature interactions and feature sharing in genomic deep neural networks","volume":"20","author":"Liu","year":"2019","journal-title":"BMC Bioinformatics"},{"key":"2023062312014988300_btz895-B23","doi-asserted-by":"crossref","first-page":"552","DOI":"10.1038\/348552a0","article-title":"Phage antibodies: filamentous phage displaying antibody variable domains","volume":"348","author":"McCafferty","year":"1990","journal-title":"Nature"},{"key":"2023062312014988300_btz895-B25","doi-asserted-by":"crossref","first-page":"3002","DOI":"10.1093\/bioinformatics\/btr513","article-title":"Protein\u2013protein binding affinity prediction on a diverse set of structures","volume":"27","author":"Moal","year":"2011","journal-title":"Bioinformatics"},{"key":"2023062312014988300_btz895-B27","author":"O\u2019Brien","year":"2004"},{"key":"2023062312014988300_btz895-B29","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1093\/protein\/8.4.389","article-title":"Prediction of hypervariable CDR-H3 loop structures in antibodies","volume":"8","author":"Reczko","year":"1995","journal-title":"Protein Eng. Des. Sel"},{"key":"2023062312014988300_btz895-B31","volume-title":"Phage Display: A Laboratory Manual","author":"Scott","year":"2001"},{"key":"2023062312014988300_btz895-B33","author":"Simonyan","year":"2013"},{"key":"2023062312014988300_btz895-B34","doi-asserted-by":"crossref","first-page":"1315","DOI":"10.1126\/science.4001944","article-title":"Filamentous fusion phage: novel expression vectors that display cloned antigens on the virion surface","volume":"228","author":"Smith","year":"1985","journal-title":"Science"},{"key":"2023062312014988300_btz895-B39","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1016\/S0004-3702(02)00190-X","article-title":"Ensembling neural networks: many could be better than all","volume":"137","author":"Zhou","year":"2002","journal-title":"Artif. Intell"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btz895\/31677660\/btz895.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/7\/2126\/50670308\/bioinformatics_36_7_2126.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/7\/2126\/50670308\/bioinformatics_36_7_2126.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,24]],"date-time":"2023-06-24T17:13:51Z","timestamp":1687626831000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/36\/7\/2126\/5645171"}},"subtitle":[],"editor":[{"given":"Alfonso","family":"Valencia","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2019,11,28]]},"references-count":20,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2020,4,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btz895","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/682880","asserted-by":"object"}]},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2020,4,1]]},"published":{"date-parts":[[2019,11,28]]}}}