{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T12:47:38Z","timestamp":1762865258712},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2007,3,1]],"date-time":"2007-03-01T00:00:00Z","timestamp":1172707200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/2.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2007,12]]},"DOI":"10.1186\/1471-2105-8-68","type":"journal-article","created":{"date-parts":[[2007,3,1]],"date-time":"2007-03-01T19:52:08Z","timestamp":1172778728000},"source":"Crossref","is-referenced-by-count":6,"title":["False occurrences of functional motifs in protein sequences highlight evolutionary constraints"],"prefix":"10.1186","volume":"8","author":[{"given":"Allegra","family":"Via","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pier Federico","family":"Gherardini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enrico","family":"Ferraro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gabriele","family":"Ausiello","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gianpaolo","family":"Scalia Tomba","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manuela","family":"Helmer-Citterich","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2007,3,1]]},"reference":[{"key":"1440_CR1","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1093\/nar\/30.1.235","volume":"30","author":"L Falquet","year":"2002","unstructured":"Falquet L, Pagni M, Bucher P, Hulo N, Sigrist CJ, Hofmann K, Bairoch A: The PROSITE database, its status in 2002. Nucleic Acids Res 2002, 30: 235\u2013238. 10.1093\/nar\/30.1.235","journal-title":"Nucleic Acids Res"},{"key":"1440_CR2","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1038\/349111a0","volume":"349","author":"MJE Sternberg","year":"1991","unstructured":"Sternberg MJE: Library of common protein motifs. Nature 1991, 349: 111. 10.1038\/349111a0","journal-title":"Nature"},{"key":"1440_CR3","doi-asserted-by":"publisher","first-page":"5865","DOI":"10.1073\/pnas.95.11.5865","volume":"95","author":"CG Nevill-Manning","year":"1998","unstructured":"Nevill-Manning CG, Wu TD, Brutlag DL: Highly specific protein sequence motifs for genome analysis. Proc Nat Acad Sci USA 1998, 95: 5865\u20135871. 10.1073\/pnas.95.11.5865","journal-title":"Proc Nat Acad Sci USA"},{"key":"1440_CR4","doi-asserted-by":"publisher","first-page":"D134","DOI":"10.1093\/nar\/gkh044","volume":"32","author":"N Hulo","year":"2004","unstructured":"Hulo N, Sigrist CJ, Le Saux V, Langendijk-Genevaux PS, Bordoli L, Gattiker A, De Castro E, Bucher P, Bairoch A: Recent improvements to the PROSITE database. Nucleic Acids Res 2004, 32: D134-D137. 10.1093\/nar\/gkh044","journal-title":"Nucleic Acids Res"},{"key":"1440_CR5","doi-asserted-by":"publisher","first-page":"D154","DOI":"10.1093\/nar\/gki070","volume":"33","author":"A Bairoch","year":"2005","unstructured":"Bairoch A, Apweiler R, Wu CH, Barker WC, Boeckmann B, Ferro S, Gasteiger E, Huang H, Lopez R, Magrane M, Martin MJ, Natale DA, O'Donovan C, Redaschi N, Yeh LS: The Universal Protein Resource (UniProt). Nucleic Acids Res 2005, 33: D154-D159. 10.1093\/nar\/gki070","journal-title":"Nucleic Acids Res"},{"key":"1440_CR6","doi-asserted-by":"publisher","first-page":"S161","DOI":"10.1093\/bioinformatics\/18.suppl_2.S161","volume":"18","author":"P Nicod\u00e8me","year":"2002","unstructured":"Nicod\u00e8me P, Doerks T, Vingron M: Proteome analysis based on motif statistics. Bioinformatics 2002, 18: S161-S171.","journal-title":"Bioinformatics"},{"key":"1440_CR7","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1089\/106652700750050952","volume":"7","author":"RK Hart","year":"2000","unstructured":"Hart RK, Royyuru AK, Stolovitzky G, Califano A: Systematic and fully automated identification of protein sequence patterns. J Comput Biol 2000, 7: 585\u2013600. 10.1089\/106652700750050952","journal-title":"J Comput Biol"},{"key":"1440_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1089\/10665270050081360","volume":"7","author":"G Reinert","year":"2000","unstructured":"Reinert G, Schbath S, Waterman MS: Probabilistic and statistical properties of words: an overview. J Comput Biol 2000, 7: 1\u201346. 10.1089\/10665270050081360","journal-title":"J Comput Biol"},{"key":"1440_CR9","first-page":"194","volume-title":"ESA'99 volume 1643 of Lecture Notes in Computer Science. Proc European Symposium on Algorithms-ESA'99, Prague","author":"P Nicod\u00e8me","year":"1999","unstructured":"Nicod\u00e8me P, Salvy B, Flajolet P: Motif Statistics. ESA'99 volume 1643 of Lecture Notes in Computer Science. Proc European Symposium on Algorithms-ESA'99, Prague Springer-Verlag; 1999, 194\u2013211. [\n                    http:\/\/citeseer.ist.psu.edu\/eme99motif.html\n                    \n                  ]"},{"key":"1440_CR10","first-page":"71","volume":"56","author":"P Nicod\u00e8me","year":"2003","unstructured":"Nicod\u00e8me P: Regexpcount, a symbolic package for counting problems on regular expressions and words. Fundamenta Informaticae 2003, 56: 71\u201387.","journal-title":"Fundamenta Informaticae"},{"key":"1440_CR11","doi-asserted-by":"publisher","first-page":"761","DOI":"10.1089\/10665270260518254","volume":"9","author":"S Robin","year":"2002","unstructured":"Robin S, Daudin J-J, Richard H, Sagot M-F, Schbath S: Occurrence probability of structured motifs in random sequences. J Comp Biol 2002, 9: 761\u2013773. 10.1089\/10665270260518254","journal-title":"J Comp Biol"},{"key":"1440_CR12","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1093\/bib\/3.3.246","volume":"3","author":"F Servant","year":"2002","unstructured":"Servant F, Bru C, Carrere S, Courcelle E, Gouzy J, Peyruc D, Kahn D: ProDom: Automated clustering of homologous domains. Brief Bioinform 2002, 3: 246\u2013251. 10.1093\/bib\/3.3.246","journal-title":"Brief Bioinform"},{"key":"1440_CR13","doi-asserted-by":"publisher","first-page":"D247","DOI":"10.1093\/nar\/gkj149","volume":"34","author":"RD Finn","year":"2006","unstructured":"Finn RD, Mistry J, Schuster-B\u00f6ckler B, Griffiths-Jones S, Hollich V, Lassmann T, Moxon S, Marshall M, Khanna A, Durbin R, Eddy SR, Sonnhammer ELL, Bateman A: Pfam: clans, webtools and services. Nucleic Acids Res 2006, 34: D247-D251. 10.1093\/nar\/gkj149","journal-title":"Nucleic Acids Res"},{"key":"1440_CR14","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1006\/jmbi.2000.4211","volume":"304","author":"I Jonassen","year":"2000","unstructured":"Jonassen I, Eidhammer I, Grindhaug SH, Taylor WR: Searching the protein structure databank with weak sequence patterns and structural constraints. J Mol Biol 2000, 304: 599\u2013619. 10.1006\/jmbi.2000.4211","journal-title":"J Mol Biol"},{"key":"1440_CR15","doi-asserted-by":"publisher","first-page":"D138","DOI":"10.1093\/nar\/gkh121","volume":"32","author":"A Bateman","year":"2004","unstructured":"Bateman A, Coin L, Durbin R, Finn RD, Hollich V, Griffiths-Jones S, Khanna A, Marshall M, Moxon S, Sonnhammer ELL, Studholme DJ, Yeats C, R Eddy SR: The Pfam protein families database. Nucleic Acids Res 2004, 32: D138-D141. 10.1093\/nar\/gkh121","journal-title":"Nucleic Acids Res"},{"key":"1440_CR16","doi-asserted-by":"publisher","first-page":"2281","DOI":"10.1093\/nar\/19.9.2281","volume":"19","author":"S Austin","year":"1991","unstructured":"Austin S, Kundrot C, Dixon R: Influence of a mutation in the putative nucleotide binding site of the nitrogen regulatory protein NTRC on its positive control function. Nucleic Acids Res 1991, 19: 2281\u20132287. 10.1093\/nar\/19.9.2281","journal-title":"Nucleic Acids Res"},{"key":"1440_CR17","doi-asserted-by":"crossref","first-page":"6067","DOI":"10.1128\/jb.175.19.6067-6074.1993","volume":"175","author":"E Morett","year":"1993","unstructured":"Morett E, Segovia L: The sigma 54 bacterial enhancer-binding protein family: mechanism of action and phylogenetic relationship of their functional domains. J Bacteriol 1993, 175: 6067\u201374.","journal-title":"J Bacteriol"},{"key":"1440_CR18","doi-asserted-by":"publisher","first-page":"3625","DOI":"10.1093\/nar\/gkg545","volume":"31","author":"P Puntervoll","year":"2003","unstructured":"Puntervoll P, Linding R, Gem\u00fcnd C, Chabanis-Davidson S, Mattingsdal M, Cameron S, Martin DMA, Ausiello G, Brannetti B, Costantini A, Ferre F, Maselli V, Via A, Cesareni G, Diella F, Superti-Furga G, Wyrwicz L, Ramu C, McGuigan C, Gudavalli R, Letunic I, Bork P, Rychlewski L, Kuster B, Helmer-Citterich M, Hunter WN, Aasland R, Gibson TJ: ELM server: a new resource for revealing short functional sites in modular eukaryotic proteins. Nucleic Acids Res 2003, 31: 3625\u20133630. 10.1093\/nar\/gkg545","journal-title":"Nucleic Acids Res"},{"key":"1440_CR19","unstructured":"ELM \u2013 Functional Sites in Proteins[\n                    http:\/\/elm.eu.org\/\n                    \n                  ]"},{"key":"1440_CR20","doi-asserted-by":"publisher","first-page":"3701","DOI":"10.1093\/nar\/gkg519","volume":"31","author":"R Linding","year":"2003","unstructured":"Linding R, Russell RB, Neduva V, Gibson TJ: GlobPlot: exploring protein sequences for globularity and disorder. Nucleic Acids Res 2003, 31: 3701\u20133708. 10.1093\/nar\/gkg519","journal-title":"Nucleic Acids Res"},{"key":"1440_CR21","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1016\/0022-2836(86)90165-8","volume":"188","author":"TD Schneider","year":"1986","unstructured":"Schneider TD, Stormo GD, Ehrenfeucht A: Information content of binding sites on nucleotide sequences. J Mol Biol 1986, 188: 415\u2013431. 10.1016\/0022-2836(86)90165-8","journal-title":"J Mol Biol"},{"key":"1440_CR22","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1038\/nri1085","volume":"3","author":"E Palmer","year":"2003","unstructured":"Palmer E: Negative selection \u2013 clearing out the bad apples from the T-cell repertoire. Nat Rev Immunol 2003, 3: 383\u201391. Review Review 10.1038\/nri1085","journal-title":"Nat Rev Immunol"},{"key":"1440_CR23","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1038\/86737","volume":"19","author":"MB Yaffe","year":"2001","unstructured":"Yaffe MB, Leparc GG, Lai J, Obata T, Volinia S, Cantley LC: A motif-based profile scanning approach for genome-wide prediction of signaling pathways. Nat Biotechnol 2001, 19: 348\u2013353. 10.1038\/86737","journal-title":"Nat Biotechnol"},{"key":"1440_CR24","doi-asserted-by":"publisher","first-page":"2097","DOI":"10.1126\/science.1084648","volume":"300","author":"JR Newman","year":"2003","unstructured":"Newman JR, Keating AE: Comprehensive identification of human bZIP interactions with coiled-coil arrays. Science 2003, 300: 2097\u20132101. 10.1126\/science.1084648","journal-title":"Science"},{"key":"1440_CR25","doi-asserted-by":"publisher","first-page":"676","DOI":"10.1038\/nature02178","volume":"426","author":"A Zarrinpar","year":"2003","unstructured":"Zarrinpar A, Park SH, Lim WA: Optimization of specificity in a cellular protein network by negative selection. Nature 2003, 426: 676\u2013680. 10.1038\/nature02178","journal-title":"Nature"},{"key":"1440_CR26","unstructured":"Integr8 \u2013 Access to complete genomes and proteomes[\n                    http:\/\/www.ebi.ac.uk\/integr8\/\n                    \n                  ]"},{"key":"1440_CR27","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1016\/0022-2836(83)90002-5","volume":"163","author":"WM Fitch","year":"1983","unstructured":"Fitch WM: Random sequences. J Mol Biol 1983, 163: 171\u2013176. 10.1016\/0022-2836(83)90002-5","journal-title":"J Mol Biol"},{"key":"1440_CR28","unstructured":"Galassi M, Davies J, Theiler J, Gough B, Jungman G, Booth M, Rossi F:GNU Scientific Library Reference Manual. 2nd edition. ISBN 0954161734 [\n                    http:\/\/www.gnu.org\/software\/gsl\/\n                    \n                  ] ISBN 0954161734"},{"key":"1440_CR29","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1089\/10665270152530836","volume":"8","author":"P Nicod\u00e8me","year":"2001","unstructured":"Nicod\u00e8me P: Fast approximate motif statistics. J Comput Biol 2001, 8: 235\u201348. 10.1089\/10665270152530836","journal-title":"J Comput Biol"},{"key":"1440_CR30","volume-title":"R: A language and environment for statistical computing","author":"R Development Core Team","year":"2004","unstructured":"R Development Core Team: R: A language and environment for statistical computing.R Foundation for Statistical Computing, Vienna, Austria; 2004. [\n                    http:\/\/www.R-project.org\n                    \n                  ] ISBN 3-900051-07-0"},{"key":"1440_CR31","doi-asserted-by":"publisher","first-page":"1587","DOI":"10.1002\/pro.5560040817","volume":"4","author":"I Jonassen","year":"1995","unstructured":"Jonassen I, Collins JF, Higgins DG: Finding flexible patterns in unaligned protein sequences. Protein Sci 1995, 4: 1587\u201395.","journal-title":"Protein Sci"},{"key":"1440_CR32","volume-title":"Bell System Technical Journal","author":"CE Shannon","year":"1948","unstructured":"Shannon CE: A mathematical theory of communication. Bell System Technical Journal 1948., 27: 379\u2013423 and 623\u2013656 379\u2013423 and 623\u2013656"},{"key":"1440_CR33","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1006\/jmbi.1999.3110","volume":"293","author":"P Wright","year":"1999","unstructured":"Wright P, Dyson H: Intrinsically unstructured proteins: re-assessing the protein structure-function paradigm. J Mol Biol 1999, 293: 321\u2013331. 10.1006\/jmbi.1999.3110","journal-title":"J Mol Biol"},{"key":"1440_CR34","doi-asserted-by":"publisher","first-page":"570","DOI":"10.1016\/j.sbi.2004.08.003","volume":"14","author":"C Bracken","year":"2004","unstructured":"Bracken C, Iakoucheva LM, Romero PR, Dunker AK: Combining prediction, computation and experiment for the characterization of protein disorder. Curr Opin Struct Biol 2004, 14: 570\u20136. 10.1016\/j.sbi.2004.08.003","journal-title":"Curr Opin Struct Biol"},{"key":"1440_CR35","doi-asserted-by":"publisher","first-page":"2577","DOI":"10.1002\/bip.360221211","volume":"22","author":"W Kabsch","year":"1983","unstructured":"Kabsch W, Sander C: Dictionary of protein secondary structure: pattern recognition of hydrogen-bonded and geometrical features. Biopolymers 1983, 22: 2577\u20132637. 10.1002\/bip.360221211","journal-title":"Biopolymers"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1471-2105-8-68.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/1471-2105-8-68\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1471-2105-8-68.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,1,23]],"date-time":"2019-01-23T04:16:51Z","timestamp":1548217011000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/1471-2105-8-68"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007,3,1]]},"references-count":35,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2007,12]]}},"alternative-id":["1440"],"URL":"https:\/\/doi.org\/10.1186\/1471-2105-8-68","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2007,3,1]]},"article-number":"68"}}