{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T11:43:51Z","timestamp":1753875831366,"version":"3.41.2"},"reference-count":8,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2022,12,10]],"date-time":"2022-12-10T00:00:00Z","timestamp":1670630400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"TPUs from Google\u2019s TPU Research Cloud"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,1,1]]},"abstract":"Abstract<\/jats:title>\n \n Summary<\/jats:title>\n ManyFold is a flexible library for protein structure prediction with deep learning that (i) supports models that use both multiple sequence alignments (MSAs) and protein language model (pLM) embedding as inputs, (ii) allows inference of existing models (AlphaFold and OpenFold), (iii) is fully trainable, allowing for both fine-tuning and the training of new models from scratch and (iv) is written in Jax to support efficient batched operation in distributed settings. A proof-of-concept pLM-based model, pLMFold, is trained from scratch to obtain reasonable results with reduced computational overheads in comparison to AlphaFold.<\/jats:p>\n <\/jats:sec>\n \n Availability and implementation<\/jats:title>\n The source code for ManyFold, the validation dataset and a small sample of training data are available at https:\/\/github.com\/instadeepai\/manyfold.<\/jats:p>\n <\/jats:sec>\n \n Supplementary information<\/jats:title>\n Supplementary data are available at Bioinformatics online.<\/jats:p>\n <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btac773","type":"journal-article","created":{"date-parts":[[2022,12,10]],"date-time":"2022-12-10T12:24:22Z","timestamp":1670675062000},"source":"Crossref","is-referenced-by-count":6,"title":["ManyFold: an efficient and flexible library for training and validating protein folding models"],"prefix":"10.1093","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3286-049X","authenticated-orcid":false,"given":"Amelia","family":"Villegas-Morcillo","sequence":"first","affiliation":[{"name":"InstaDeep , London W2 1AY, UK"},{"name":"Department of Signal Theory, Telematics and Communications, University of Granada , Granada 18071, Spain"}]},{"given":"Louis","family":"Robinson","sequence":"additional","affiliation":[{"name":"InstaDeep , London W2 1AY, UK"}]},{"given":"Arthur","family":"Flajolet","sequence":"additional","affiliation":[{"name":"InstaDeep , London W2 1AY, UK"}]},{"given":"Thomas D","family":"Barrett","sequence":"additional","affiliation":[{"name":"InstaDeep , London W2 1AY, UK"}]}],"member":"286","published-online":{"date-parts":[[2022,12,10]]},"reference":[{"year":"2022","author":"Ahdritz","key":"2023010805361756500_btac773-B1"},{"key":"2023010805361756500_btac773-B2","first-page":"7112","article-title":"ProtTrans: towards cracking the language of life\u2019s code through self-supervised deep learning and high performance computing","author":"Elnaggar","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"year":"2022","author":"Fang","key":"2023010805361756500_btac773-B3"},{"key":"2023010805361756500_btac773-B4","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction with AlphaFold","volume":"596","author":"Jumper","year":"2021","journal-title":"Nature"},{"year":"2022","author":"Lin","key":"2023010805361756500_btac773-B5"},{"key":"2023010805361756500_btac773-B6","doi-asserted-by":"crossref","first-page":"2722","DOI":"10.1093\/bioinformatics\/btt473","article-title":"lDDT: a local superposition-free score for comparing protein structures and models using distance difference tests","volume":"29","author":"Mariani","year":"2013","journal-title":"Bioinformatics"},{"key":"2023010805361756500_btac773-B7","doi-asserted-by":"crossref","first-page":"e2016239118","DOI":"10.1073\/pnas.2016239118","article-title":"Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences","volume":"118","author":"Rives","year":"2021","journal-title":"Proc. Natl. Acad. Sci. USA"},{"year":"2022","author":"Wu","key":"2023010805361756500_btac773-B8"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btac773\/47842047\/btac773.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/1\/btac773\/48520729\/btac773.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/1\/btac773\/48520729\/btac773.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,8]],"date-time":"2023-01-08T05:36:41Z","timestamp":1673156201000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btac773\/6887136"}},"subtitle":[],"editor":[{"given":"Pier Luigi","family":"Martelli","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2022,12,10]]},"references-count":8,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btac773","relation":{},"ISSN":["1367-4811"],"issn-type":[{"type":"electronic","value":"1367-4811"}],"subject":[],"published-other":{"date-parts":[[2023,1,1]]},"published":{"date-parts":[[2022,12,10]]},"article-number":"btac773"}}