{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T02:32:31Z","timestamp":1790735551444,"version":"4.1.0"},"reference-count":56,"publisher":"Oxford University Press (OUP)","issue":"7","license":[{"start":{"date-parts":[[2022,1,31]],"date-time":"2022-01-31T00:00:00Z","timestamp":1643587200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000266","name":"UK's Engineering and Physical Sciences Research Council","doi-asserted-by":"crossref","award":["EP\/M013243\/1"],"award-info":[{"award-number":["EP\/M013243\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,3,28]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Summary<\/jats:title>\n                  <jats:p>Motivation. Predicting the native state of a protein has long been considered a gateway problem for understanding protein folding. Recent advances in structural modeling driven by deep learning have achieved unprecedented success at predicting a protein\u2019s crystal structure, but it is not clear if these models are learning the physics of how proteins dynamically fold into their equilibrium structure or are just accurate knowledge-based predictors of the final state.<\/jats:p>\n                  <jats:p>Results. In this work, we compare the pathways generated by state-of-the-art protein structure prediction methods to experimental data about protein folding pathways. The methods considered were AlphaFold 2, RoseTTAFold, trRosetta, RaptorX, DMPfold, EVfold, SAINT2 and Rosetta. We find evidence that their simulated dynamics capture some information about the folding pathway, but their predictive ability is worse than a trivial classifier using sequence-agnostic features like chain length. The folding trajectories produced are also uncorrelated with experimental observables such as intermediate structures and the folding rate constant. These results suggest that recent advances in structure prediction do not yet provide an enhanced understanding of protein folding.<\/jats:p>\n                  <jats:p>Availability. The data underlying this article are available in GitHub at https:\/\/github.com\/oxpig\/structure-vs-folding\/<\/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\/btab881","type":"journal-article","created":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T20:15:04Z","timestamp":1643314504000},"page":"1881-1887","source":"Crossref","is-referenced-by-count":90,"title":["Current structure predictors are not learning the physics of protein folding"],"prefix":"10.1093","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1408-5554","authenticated-orcid":false,"given":"Carlos","family":"Outeiral","sequence":"first","affiliation":[{"name":"Department of Statistics, University of Oxford , Oxford OX1 3PB, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0550-9394","authenticated-orcid":false,"given":"Daniel A","family":"Nissley","sequence":"additional","affiliation":[{"name":"Department of Statistics, University of Oxford , Oxford OX1 3PB, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1388-2252","authenticated-orcid":false,"given":"Charlotte M","family":"Deane","sequence":"additional","affiliation":[{"name":"Department of Statistics, University of Oxford , Oxford OX1 3PB, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2022,1,31]]},"reference":[{"key":"2023020109001173100_btab881-B1","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1107\/S0907444909052925","article-title":"Phenix: a comprehensive python-based system for macromolecular structure solution","volume":"66","author":"Adams","year":"2010","journal-title":"Acta Crystallogr. Sect. D Biol. Crystallogr"},{"key":"2023020109001173100_btab881-B2","doi-asserted-by":"crossref","first-page":"3031","DOI":"10.1021\/acs.jctc.7b00125","article-title":"The Rosetta all-atom energy function for macromolecular modeling and design","volume":"13","author":"Alford","year":"2017","journal-title":"J. Chem. Theory Comput"},{"key":"2023020109001173100_btab881-B3","article-title":"Accurate prediction of protein structures and interactions using a three-track network","author":"Baek","year":"2021","journal-title":"Science, 373, 6557, 871\u2013876"},{"key":"2023020109001173100_btab881-B4","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1093\/nar\/28.1.235","article-title":"The protein data bank","volume":"28","author":"Berman","year":"2000","journal-title":"Nucleic Acids Res"},{"key":"2023020109001173100_btab881-B5","doi-asserted-by":"crossref","first-page":"17874","DOI":"10.1073\/pnas.1311599110","article-title":"Native contacts determine protein folding mechanisms in atomistic simulations","volume":"110","author":"Best","year":"2013","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023020109001173100_btab881-B6","doi-asserted-by":"crossref","first-page":"905","DOI":"10.1107\/S0907444998003254","article-title":"Crystallography & NMR system: a new software suite for macromolecular structure determination","volume":"54","author":"Br\u00fcnger","year":"1998","journal-title":"Acta Crystallogr. Sect. D Biol. Crystallogr"},{"key":"2023020109001173100_btab881-B7","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1146\/annurev-biophys-052118-115517","article-title":"The role of conformational dynamics and allostery in modulating protein evolution","volume":"49","author":"Campitelli","year":"2020","journal-title":"Annu. Rev. Biophys"},{"key":"2023020109001173100_btab881-B8","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1016\/S1359-0278(96)00038-7","article-title":"An evaluation of the use of hydrogen exchange at equilibrium to probe intermediates on the protein folding pathway","volume":"1","author":"Clarke","year":"1996","journal-title":"Folding Des"},{"key":"2023020109001173100_btab881-B9","doi-asserted-by":"crossref","first-page":"W615","DOI":"10.1093\/nar\/gkh398","article-title":"Molprobity: structure validation and all-atom contact analysis for nucleic acids and their complexes","volume":"32","author":"Davis","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"2023020109001173100_btab881-B10","doi-asserted-by":"crossref","first-page":"1132","DOI":"10.1093\/bioinformatics\/btx722","article-title":"Sequential search leads to faster, more efficient fragment-based de novo protein structure prediction","volume":"34","author":"de Oliveira","year":"2018","journal-title":"Bioinformatics"},{"key":"2023020109001173100_btab881-B11","doi-asserted-by":"crossref","first-page":"1226","DOI":"10.1002\/prot.26138","article-title":"Alphafold2 predicts the inward-facing conformation of the multidrug transporter LMRP","volume":"89","author":"Del Alamo","year":"2021","journal-title":"Proteins Struct. Funct. Bioinf"},{"key":"2023020109001173100_btab881-B12","doi-asserted-by":"crossref","first-page":"8646","DOI":"10.1021\/bi101126f","article-title":"Rapid collapse into a molten globule is followed by simple two-state kinetics in the folding of lysozyme from bacteriophage \u03bb","volume":"49","author":"Di Paolo","year":"2010","journal-title":"Biochemistry"},{"key":"2023020109001173100_btab881-B13","doi-asserted-by":"crossref","first-page":"1042","DOI":"10.1126\/science.1219021","article-title":"The protein-folding problem, 50 years on","volume":"338","author":"Dill","year":"2012","journal-title":"Science"},{"key":"2023020109001173100_btab881-B14","doi-asserted-by":"crossref","first-page":"8253","DOI":"10.1073\/pnas.1706196114","article-title":"The case for defined protein folding pathways","volume":"114","author":"Englander","year":"2017","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023020109001173100_btab881-B15","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1080\/00401706.1989.10488470","article-title":"Flexible parsimonious smoothing and additive modeling","volume":"31","author":"Friedman","year":"1989","journal-title":"Technometrics"},{"key":"2023020109001173100_btab881-B16","doi-asserted-by":"crossref","first-page":"566","DOI":"10.1002\/prot.340230412","article-title":"Knowledge-based protein secondary structure assignment","volume":"23","author":"Frishman","year":"1995","journal-title":"Proteins Struct. Funct. Bioinf"},{"key":"2023020109001173100_btab881-B17","doi-asserted-by":"crossref","first-page":"1149","DOI":"10.1016\/S0022-2836(03)00211-0","article-title":"Local secondary structure content predicts folding rates for simple, two-state proteins","volume":"327","author":"Gong","year":"2003","journal-title":"J. Mol. Biol"},{"key":"2023020109001173100_btab881-B18","author":"Gowers","year":"2019"},{"key":"2023020109001173100_btab881-B19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-019-11994-0","article-title":"Deep learning extends de novo protein modelling coverage of genomes using iteratively predicted structural constraints","volume":"10","author":"Greener","year":"2019","journal-title":"Nat. Commun"},{"key":"2023020109001173100_btab881-B20","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1016\/j.cell.2012.04.012","article-title":"Three-dimensional structures of membrane proteins from genomic sequencing","volume":"149","author":"Hopf","year":"2012","journal-title":"Cell"},{"key":"2023020109001173100_btab881-B21","doi-asserted-by":"crossref","first-page":"1582","DOI":"10.1093\/bioinformatics\/bty862","article-title":"The evcouplings python framework for coevolutionary sequence analysis","volume":"35","author":"Hopf","year":"2019","journal-title":"Bioinformatics"},{"key":"2023020109001173100_btab881-B22","doi-asserted-by":"crossref","first-page":"1845","DOI":"10.1039\/b600829c","article-title":"Ubiquitin: a small protein folding paradigm","volume":"4","author":"Jackson","year":"2006","journal-title":"Organic Biomol. Chem"},{"key":"2023020109001173100_btab881-B23","doi-asserted-by":"crossref","first-page":"1711","DOI":"10.1002\/prot.26257","article-title":"Applying and improving alphafold at casp14","volume":"89","author":"Jumper","year":"2021","journal-title":"Proteins Struct. Funct. Bioinf"},{"key":"2023020109001173100_btab881-B24","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"},{"key":"2023020109001173100_btab881-B25","doi-asserted-by":"crossref","first-page":"896","DOI":"10.1016\/S0140-6736(14)61393-3","article-title":"Parkinson\u2019s disease","volume":"386","author":"Kalia","year":"2015","journal-title":"The Lancet"},{"key":"2023020109001173100_btab881-B26","doi-asserted-by":"crossref","first-page":"1511","DOI":"10.1038\/nprot.2012.085","article-title":"Template-based protein structure modeling using the raptorx web server","volume":"7","author":"K\u00e4llberg","year":"2012","journal-title":"Nat. Protoc"},{"key":"2023020109001173100_btab881-B27","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1002\/prot.24987","article-title":"Toward a detailed understanding of search trajectories in fragment assembly approaches to protein structure prediction","volume":"84","author":"Kandathil","year":"2016","journal-title":"Proteins Struct. Funct. Bioinf"},{"key":"2023020109001173100_btab881-B28","doi-asserted-by":"crossref","first-page":"881","DOI":"10.1016\/j.jmb.2006.10.048","article-title":"The folding pathway of t4 lysozyme: an on-pathway hidden folding intermediate","volume":"365","author":"Kato","year":"2007","journal-title":"J. Mol. Biol"},{"key":"2023020109001173100_btab881-B29","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1146\/annurev.bi.51.070182.002331","article-title":"Specific intermediates in the folding reactions of small proteins and the mechanism of protein folding","volume":"51","author":"Kim","year":"1982","journal-title":"Annu. Rev. Biochem"},{"key":"2023020109001173100_btab881-B30","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1146\/annurev.bi.59.070190.003215","article-title":"Intermediates in the folding reactions of small proteins","volume":"59","author":"Kim","year":"1990","journal-title":"Annu. Rev. Biochem"},{"key":"2023020109001173100_btab881-B31","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1002\/prot.24448","article-title":"Casp10 results compared to those of previous CASP experiments","volume":"82","author":"Kryshtafovych","year":"2014","journal-title":"Proteins Struct. Funct. Bioinf"},{"key":"2023020109001173100_btab881-B32","doi-asserted-by":"crossref","first-page":"1011","DOI":"10.1002\/prot.25823","article-title":"Critical assessment of methods of protein structure prediction (CASP)-round xiii","volume":"87","author":"Kryshtafovych","year":"2019","journal-title":"Proteins Struct. Funct. Bioinf"},{"key":"2023020109001173100_btab881-B33","doi-asserted-by":"crossref","first-page":"1072","DOI":"10.1038\/14956","article-title":"The energetics of t4 lysozyme reveal a hierarchy of conformations","volume":"6","author":"Llin\u00e1s","year":"1999","journal-title":"Nat. Struct. Biol"},{"key":"2023020109001173100_btab881-B34","doi-asserted-by":"crossref","first-page":"4749","DOI":"10.1021\/bi00135a002","article-title":"Detection and characterization of an early folding intermediate of t4 lysozyme using pulsed hydrogen exchange and two-dimensional NMR","volume":"31","author":"Lu","year":"1992","journal-title":"Biochemistry"},{"key":"2023020109001173100_btab881-B35","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-018-36992-y","article-title":"Pfdb: a standardized protein folding database with temperature correction","volume":"9","author":"Manavalan","year":"2019","journal-title":"Sci. Rep"},{"key":"2023020109001173100_btab881-B36","doi-asserted-by":"crossref","first-page":"2319","DOI":"10.1002\/jcc.21787","article-title":"Mdanalysis: a toolkit for the analysis of molecular dynamics simulations","volume":"32","author":"Michaud-Agrawal","year":"2011","journal-title":"J. Comput. Chem"},{"key":"2023020109001173100_btab881-B37","doi-asserted-by":"crossref","first-page":"1554","DOI":"10.1002\/1873-3468.13046","article-title":"Codon harmonization\u2014going beyond the speed limit for protein expression","volume":"592","author":"Mignon","year":"2018","journal-title":"FEBS Lett"},{"key":"2023020109001173100_btab881-B38","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1016\/S0958-1669(96)80118-2","article-title":"The current state of the art in protein structure prediction","volume":"7","author":"Moult","year":"1996","journal-title":"Curr. Opin. Biotechnol"},{"key":"2023020109001173100_btab881-B39","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1016\/j.sbi.2005.05.011","article-title":"A decade of CASP: progress, bottlenecks and prognosis in protein structure prediction","volume":"15","author":"Moult","year":"2005","journal-title":"Curr. Opin. Struct. Biol"},{"key":"2023020109001173100_btab881-B40","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1002\/prot.25415","article-title":"Critical assessment of methods of protein structure prediction (CASP)-round xii","volume":"86","author":"Moult","year":"2018","journal-title":"Proteins Struct. Funct. Bioinf"},{"key":"2023020109001173100_btab881-B41","doi-asserted-by":"crossref","first-page":"9927","DOI":"10.1021\/acs.jpcb.8b07726","article-title":"Structural origins of fret-observed nascent chain compaction on the ribosome","volume":"122","author":"Nissley","year":"2018","journal-title":"J. Phys. Chem. B"},{"key":"2023020109001173100_btab881-B42","doi-asserted-by":"crossref","first-page":"553","DOI":"10.1146\/annurev-biochem-072711-164947","article-title":"Intrinsically disordered proteins and intrinsically disordered protein regions","volume":"83","author":"Oldfield","year":"2014","journal-title":"Annu. Rev. Biochem"},{"key":"2023020109001173100_btab881-B43","doi-asserted-by":"crossref","first-page":"103030","DOI":"10.1088\/1367-2630\/ac29ff","article-title":"Investigating the potential for a limited quantum speedup on protein lattice problems","volume":"23","author":"Outeiral","year":"2021","journal-title":"N. J. Phys"},{"key":"2023020109001173100_btab881-B44","doi-asserted-by":"crossref","first-page":"D429","DOI":"10.1093\/nar\/gkv1185","article-title":"Start2fold: a database of hydrogen\/deuterium exchange data on protein folding and stability","volume":"44","author":"Pancsa","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2023020109001173100_btab881-B45","doi-asserted-by":"crossref","first-page":"1781","DOI":"10.1002\/jcc.20289","article-title":"Scalable molecular dynamics with NAMD","volume":"26","author":"Phillips","year":"2005","journal-title":"J. Comput. Chem"},{"key":"2023020109001173100_btab881-B46","doi-asserted-by":"crossref","first-page":"985","DOI":"10.1006\/jmbi.1998.1645","article-title":"Contact order, transition state placement and the refolding rates of single domain proteins","volume":"277","author":"Plaxco","year":"1998","journal-title":"J. Mol. Biol"},{"key":"2023020109001173100_btab881-B47","doi-asserted-by":"crossref","first-page":"5968","DOI":"10.1073\/pnas.1800168115","article-title":"Extant fold-switching proteins are widespread","volume":"115","author":"Porter","year":"2018","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023020109001173100_btab881-B48","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1016\/j.jmb.2005.02.068","article-title":"Protein folding rates estimated from contact predictions","volume":"348","author":"Punta","year":"2005","journal-title":"J. Mol. Biol"},{"key":"2023020109001173100_btab881-B49","volume-title":"R: A Language and Environment for Statistical Computing","year":"2013"},{"key":"2023020109001173100_btab881-B50","doi-asserted-by":"crossref","first-page":"1460","DOI":"10.1002\/jcc.20906","article-title":"Fast procedure for reconstruction of full-atom protein models from reduced representations","volume":"29","author":"Rotkiewicz","year":"2008","journal-title":"J. Comput. Chem"},{"key":"2023020109001173100_btab881-B51","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1016\/S0022-1694(01)00466-8","article-title":"Rosetta: a computer program for estimating soil hydraulic parameters with hierarchical pedotransfer functions","volume":"251","author":"Schaap","year":"2001","journal-title":"J. Hydrol"},{"key":"2023020109001173100_btab881-B52","article-title":"Co-evolutionary distance predictions contain flexibility information","author":"Schwarz","year":"2020","journal-title":"Bioinformatics, 38(1), 65\u201372"},{"key":"2023020109001173100_btab881-B53","doi-asserted-by":"crossref","first-page":"595","DOI":"10.15252\/emmm.201606210","article-title":"The amyloid hypothesis of Alzheimer\u2019s disease at 25 years","volume":"8","author":"Selkoe","year":"2016","journal-title":"EMBO Mol. Med"},{"key":"2023020109001173100_btab881-B54","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"Scipy 1.0: fundamental algorithms for scientific computing in python","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nat. Methods"},{"key":"2023020109001173100_btab881-B55","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1002\/cpbi.3","article-title":"Comparative protein structure modeling using modeller","volume":"54","author":"Webb","year":"2016","journal-title":"Curr. Protoc. Bioinf"},{"key":"2023020109001173100_btab881-B56","doi-asserted-by":"crossref","first-page":"1496","DOI":"10.1073\/pnas.1914677117","article-title":"Improved protein structure prediction using predicted interresidue orientations","volume":"117","author":"Yang","year":"2020","journal-title":"Proc. Natl. Acad. Sci"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btab881\/42377860\/btab881.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/7\/1881\/49009618\/btab881.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/7\/1881\/49009618\/btab881.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T20:42:36Z","timestamp":1675284156000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/38\/7\/1881\/6517779"}},"subtitle":[],"editor":[{"given":"Lenore","family":"Cowen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,1,31]]},"references-count":56,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2022,3,28]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btab881","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,4,1]]},"published":{"date-parts":[[2022,1,31]]}}}