{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T01:26:37Z","timestamp":1772846797631,"version":"3.50.1"},"reference-count":30,"publisher":"Oxford University Press (OUP)","issue":"8","license":[{"start":{"date-parts":[[2023,7,27]],"date-time":"2023-07-27T00:00:00Z","timestamp":1690416000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ministry of Research"},{"name":"National Institute for Blood Transfusion"},{"DOI":"10.13039\/501100000272","name":"National Institute for Health and Medical Research","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100000272","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,8,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Alignment of protein structures is a major problem in structural biology. The first approach commonly used is to consider proteins as rigid bodies. However, alignment of protein structures can be very complex due to conformational variability, or complex evolutionary relationships between proteins such as insertions, circular permutations or repetitions. In such cases, introducing flexibility becomes useful for two reasons: (i) it can help compare two protein chains which adopted two different conformational states, such as due to proteins\/ligands interaction or post-translational modifications, and (ii) it aids in the identification of conserved regions in proteins that may have distant evolutionary relationships.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We propose ICARUS, a new approach for flexible structural alignment based on identification of Protein Units, evolutionarily preserved structural descriptors of intermediate size, between secondary structures and domains. ICARUS significantly outperforms reference methods on a dataset of very difficult structural alignments.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>Code is freely available online at https:\/\/github.com\/DSIMB\/ICARUS.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btad459","type":"journal-article","created":{"date-parts":[[2023,7,27]],"date-time":"2023-07-27T15:13:58Z","timestamp":1690470838000},"source":"Crossref","is-referenced-by-count":5,"title":["ICARUS: flexible protein structural alignment based on Protein Units"],"prefix":"10.1093","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3522-7083","authenticated-orcid":false,"given":"Gabriel","family":"Cretin","sequence":"first","affiliation":[{"name":"Universit\u00e9 Paris Cit\u00e9 and Universit\u00e9 des Antilles and Universit\u00e9 de la R\u00e9union, INSERM, BIGR , F-75015 Paris, France"},{"name":"Laboratoire d\u2019Excellence GR-Ex , 75015 Paris, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Charlotte","family":"P\u00e9rin","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Paris Cit\u00e9 and Universit\u00e9 des Antilles and Universit\u00e9 de la R\u00e9union, INSERM, BIGR , F-75015 Paris, France"},{"name":"Laboratoire d\u2019Excellence GR-Ex , 75015 Paris, France"},{"name":"TBI, Universit\u00e9 de Toulouse, CNRS, INRAE, INSA , 31077 Toulouse, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicolas","family":"Zimmermann","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Paris Cit\u00e9 and Universit\u00e9 des Antilles and Universit\u00e9 de la R\u00e9union, INSERM, BIGR , F-75015 Paris, France"},{"name":"Laboratoire d\u2019Excellence GR-Ex , 75015 Paris, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3608-5208","authenticated-orcid":false,"given":"Tatiana","family":"Galochkina","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Paris Cit\u00e9 and Universit\u00e9 des Antilles and Universit\u00e9 de la R\u00e9union, INSERM, BIGR , F-75015 Paris, France"},{"name":"Laboratoire d\u2019Excellence GR-Ex , 75015 Paris, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5138-361X","authenticated-orcid":false,"given":"Jean-Christophe","family":"Gelly","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Paris Cit\u00e9 and Universit\u00e9 des Antilles and Universit\u00e9 de la R\u00e9union, INSERM, BIGR , F-75015 Paris, France"},{"name":"Laboratoire d\u2019Excellence GR-Ex , 75015 Paris, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2023,7,27]]},"reference":[{"key":"2023080401533328100_btad459-B1","doi-asserted-by":"crossref","first-page":"D253","DOI":"10.1093\/nar\/gkl746","article-title":"SISYPHUS\u2014structural alignments for proteins with non-trivial relationships","volume":"35","author":"Andreeva","year":"2007","journal-title":"Nucleic Acids Res"},{"key":"2023080401533328100_btad459-B2","doi-asserted-by":"crossref","first-page":"D553","DOI":"10.1093\/nar\/gkab1054","article-title":"SCOPe: improvements to the structural classification of proteins \u2013 extended database to facilitate variant interpretation and machine learning","volume":"50","author":"Chandonia","year":"2022","journal-title":"Nucleic Acids Res"},{"key":"2023080401533328100_btad459-B3","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1002\/prot.10011","article-title":"A unifold, mesofold, and superfold model of protein fold use","volume":"46","author":"Coulson","year":"2002","journal-title":"Proteins"},{"key":"2023080401533328100_btad459-B4","doi-asserted-by":"crossref","first-page":"W732","DOI":"10.1093\/nar\/gkac370","article-title":"SWORD2: hierarchical analysis of protein 3D structures","volume":"50","author":"Cretin","year":"2022","journal-title":"Nucleic Acids Res"},{"key":"2023080401533328100_btad459-B5","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1186\/1471-2105-12-344","article-title":"A novel method to compare protein structures using local descriptors","volume":"12","author":"Daniluk","year":"2011","journal-title":"BMC Bioinformatics"},{"key":"2023080401533328100_btad459-B6","doi-asserted-by":"crossref","first-page":"D304","DOI":"10.1093\/nar\/gkt1240","article-title":"SCOPe: structural classification of proteins\u2014extended, integrating SCOP and ASTRAL data and classification of new structures","volume":"42","author":"Fox","year":"2014","journal-title":"Nucleic Acids Res"},{"key":"2023080401533328100_btad459-B7","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1093\/bioinformatics\/btq610","article-title":"Protein Peeling 3D: new tools for analyzing protein structures","volume":"27","author":"Gelly","year":"2011","journal-title":"Bioinformatics"},{"key":"2023080401533328100_btad459-B8","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1093\/bioinformatics\/bti773","article-title":"\u2018Protein Peeling\u2019: an approach for splitting a 3D protein structure into compact fragments","volume":"22","author":"Gelly","year":"2006","journal-title":"Bioinformatics"},{"key":"2023080401533328100_btad459-B9","doi-asserted-by":"crossref","first-page":"W75","DOI":"10.1093\/nar\/gkl292","article-title":"Protein Peeling 2: a web server to convert protein structures into series of protein units","volume":"34","author":"Gelly","year":"2006","journal-title":"Nucleic Acids Res"},{"key":"2023080401533328100_btad459-B10","doi-asserted-by":"crossref","first-page":"966","DOI":"10.1093\/gbe\/evs071","article-title":"Selective constraint on human pre-mRNA splicing by protein structural properties","volume":"4","author":"Gelly","year":"2012","journal-title":"Genome Biol Evol"},{"key":"2023080401533328100_btad459-B11","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1006\/jsbi.2001.4335","article-title":"Fold change in evolution of protein structures","volume":"134","author":"Grishin","year":"2001","journal-title":"J Struct Biol"},{"key":"2023080401533328100_btad459-B12","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1002\/pro.3749","article-title":"DALI and the persistence of protein shape","volume":"29","author":"Holm","year":"2020","journal-title":"Protein Sci"},{"key":"2023080401533328100_btad459-B13","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1002\/prot.22458","article-title":"Structure is three to ten times more conserved than sequence\u2014a study of structural response in protein cores","volume":"77","author":"Illerg\u00e5rd","year":"2009","journal-title":"Proteins"},{"key":"2023080401533328100_btad459-B14","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1038\/nature01256","article-title":"The structure of the protein universe and genome evolution","volume":"420","author":"Koonin","year":"2002","journal-title":"Nature"},{"key":"2023080401533328100_btad459-B15","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1002\/prot.10336","article-title":"Monte Carlo estimation of the number of possible protein folds: effects of sampling bias and folds distributions","volume":"51","author":"Leonov","year":"2003","journal-title":"Proteins"},{"key":"2023080401533328100_btad459-B16","doi-asserted-by":"crossref","first-page":"W60","DOI":"10.1093\/nar\/gkaa443","article-title":"FATCAT 2.0: towards a better understanding of the structural diversity of proteins","volume":"48","author":"Li","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"2023080401533328100_btad459-B17","doi-asserted-by":"crossref","first-page":"8166","DOI":"10.1038\/srep08166","article-title":"On the origin of protein superfamilies and superfolds","volume":"5","author":"Magner","year":"2015","journal-title":"Sci Rep"},{"key":"2023080401533328100_btad459-B18","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1186\/1472-6807-7-50","article-title":"Comparative analysis of protein structure alignments","volume":"7","author":"Mayr","year":"2007","journal-title":"BMC Struct Biol"},{"key":"2023080401533328100_btad459-B19","doi-asserted-by":"crossref","first-page":"e1600552","DOI":"10.1126\/sciadv.1600552","article-title":"An ambiguity principle for assigning protein structural domains","volume":"3","author":"Postic","year":"2017","journal-title":"Sci Adv"},{"key":"2023080401533328100_btad459-B20","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1042\/bj3390223","article-title":"Identification of the Mg2+-binding site in the P-type ATPase and phosphatase members of the HAD (haloacid dehalogenase) superfamily by structural similarity to the response regulator protein CheY","volume":"339","author":"Ridder","year":"1999","journal-title":"Biochem. J"},{"key":"2023080401533328100_btad459-B21","doi-asserted-by":"crossref","first-page":"2650","DOI":"10.1093\/bioinformatics\/btw300","article-title":"Calculating and scoring high quality multiple flexible protein structure alignments","volume":"32","author":"Ritchie","year":"2016","journal-title":"Bioinformatics"},{"key":"2023080401533328100_btad459-B22","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1006\/jmbi.1997.1019","article-title":"Recognition of analogous and homologous protein folds: analysis of sequence and structure conservation","volume":"269","author":"Russell","year":"1997","journal-title":"J Mol Biol"},{"key":"2023080401533328100_btad459-B23","doi-asserted-by":"crossref","first-page":"739","DOI":"10.1093\/protein\/11.9.739","article-title":"Protein structure alignment by incremental combinatorial extension (CE) of the optimal path","volume":"11","author":"Shindyalov","year":"1998","journal-title":"Protein Eng"},{"key":"2023080401533328100_btad459-B24","first-page":"2103","article-title":"D\u00e9j\u00e0 vu all over again: finding and analyzing protein structure similarities","volume":"12","author":"Sierk","year":"2004","journal-title":"Structure"},{"key":"2023080401533328100_btad459-B25","doi-asserted-by":"crossref","first-page":"2273","DOI":"10.1093\/bioinformatics\/btq420","article-title":"Towards optimal alignment of protein structure distance matrices","volume":"26","author":"Wohlers","year":"2010","journal-title":"Bioinformatics"},{"key":"2023080401533328100_btad459-B26","doi-asserted-by":"crossref","first-page":"W303","DOI":"10.1093\/nar\/gks362","article-title":"CSA: comprehensive comparison of pairwise protein structure alignments","volume":"40","author":"Wohlers","year":"2012","journal-title":"Nucleic Acids Res"},{"key":"2023080401533328100_btad459-B27","doi-asserted-by":"crossref","first-page":"897","DOI":"10.1006\/jmbi.2000.3786","article-title":"Estimating the number of protein folds and families from complete genome data","volume":"299","author":"Wolf","year":"2000","journal-title":"J Mol Biol"},{"key":"2023080401533328100_btad459-B28","doi-asserted-by":"crossref","first-page":"889","DOI":"10.1093\/bioinformatics\/btq066","article-title":"How significant is a protein structure similarity with TM-score = 0.5?","volume":"26","author":"Xu","year":"2010","journal-title":"Bioinformatics"},{"key":"2023080401533328100_btad459-B29","doi-asserted-by":"crossref","first-page":"ii246","DOI":"10.1093\/bioinformatics\/btg1086","article-title":"Flexible structure alignment by chaining aligned fragment pairs allowing twists","volume":"19","author":"Ye","year":"2003","journal-title":"Bioinformatics"},{"key":"2023080401533328100_btad459-B30","doi-asserted-by":"crossref","first-page":"2302","DOI":"10.1093\/nar\/gki524","article-title":"TM-align: a protein structure alignment algorithm based on the TM-score","volume":"33","author":"Zhang","year":"2005","journal-title":"Nucleic Acids Res"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btad459\/50975971\/btad459.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/8\/btad459\/51035790\/btad459.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/8\/btad459\/51035790\/btad459.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T01:54:02Z","timestamp":1691114042000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btad459\/7232229"}},"subtitle":[],"editor":[{"given":"Lenore","family":"Cowen","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2023,7,27]]},"references-count":30,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2023,8,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btad459","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,8,1]]},"published":{"date-parts":[[2023,7,27]]},"article-number":"btad459"}}