{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T17:35:16Z","timestamp":1761154516349},"reference-count":40,"publisher":"Elsevier BV","issue":"1-2","license":[{"start":{"date-parts":[[2003,10,1]],"date-time":"2003-10-01T00:00:00Z","timestamp":1064966400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information Sciences"],"published-print":{"date-parts":[[2003,10]]},"DOI":"10.1016\/s0020-0255(03)00067-7","type":"journal-article","created":{"date-parts":[[2003,4,30]],"date-time":"2003-04-30T22:24:07Z","timestamp":1051741447000},"page":"1-18","source":"Crossref","is-referenced-by-count":28,"title":["Automated data-driven discovery of motif-based protein function classifiers"],"prefix":"10.1016","volume":"155","author":[{"given":"Xiangyun","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diane","family":"Schroeder","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Drena","family":"Dobbs","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vasant","family":"Honavar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/S0020-0255(03)00067-7_BIB1","doi-asserted-by":"crossref","first-page":"3389","DOI":"10.1093\/nar\/25.17.3389","article-title":"Gapped BLAST and PSI-BLAST: a new generation of protein database search programs","volume":"25","author":"Altschul","year":"1997","journal-title":"Nucleic Acids Res."},{"key":"10.1016\/S0020-0255(03)00067-7_BIB2","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1093\/nar\/29.1.37","article-title":"The InterPro database, an integrated documentation resource for protein families, domains and functional sites","volume":"29","author":"Apweiler","year":"2001","journal-title":"Nucleic Acids Res."},{"key":"10.1016\/S0020-0255(03)00067-7_BIB3","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1093\/nar\/28.1.225","article-title":"PRINT-S: the database formerly known as PRINTS","volume":"28","author":"Attwood","year":"2000","journal-title":"Nucleic Acids Res."},{"key":"10.1016\/S0020-0255(03)00067-7_BIB4","series-title":"Pattern Discovery in Biomolecular Data","first-page":"30","article-title":"Meme, Mast, and Meta-Meme: new tools for motif discovery in protein sequences","author":"Bailey","year":"1999"},{"key":"10.1016\/S0020-0255(03)00067-7_BIB5","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1126\/science.1065659","article-title":"Protein structure prediction and structural genomics","volume":"294","author":"Baker","year":"2001","journal-title":"Science"},{"key":"10.1016\/S0020-0255(03)00067-7_BIB6","series-title":"Bioinformatics: The Machine Learning Approach","author":"Baldi","year":"2001"},{"key":"10.1016\/S0020-0255(03)00067-7_BIB7","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1093\/nar\/29.1.29","article-title":"Protein information resource: a community resource for expert annotation of protein data","volume":"29","author":"Barker","year":"2001","journal-title":"Nucleic Acids Res."},{"key":"10.1016\/S0020-0255(03)00067-7_BIB8","series-title":"Handbook of Proteolytic Enzymes","author":"Barrett","year":"1998"},{"key":"10.1016\/S0020-0255(03)00067-7_BIB9","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1093\/nar\/28.1.263","article-title":"The Pfam protein families database","volume":"28","author":"Bateman","year":"2000","journal-title":"Nucleic Acids Res."},{"key":"10.1016\/S0020-0255(03)00067-7_BIB10","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":"10.1016\/S0020-0255(03)00067-7_BIB11","doi-asserted-by":"crossref","first-page":"1247","DOI":"10.1002\/pro.5560040701","article-title":"The astacin family of metalloendopeptidases","volume":"4","author":"Bond","year":"1995","journal-title":"Protein Sci."},{"key":"10.1016\/S0020-0255(03)00067-7_BIB12","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1016\/S0959-440X(94)90109-0","article-title":"From genome sequences to protein function","volume":"4","author":"Bork","year":"1994","journal-title":"Curr. Opin. Struct. Biol."},{"issue":"6617","key":"10.1016\/S0020-0255(03)00067-7_BIB13","doi-asserted-by":"crossref","first-page":"579","DOI":"10.1038\/385579a0","article-title":"Protein evolution. How far can sequences diverge?","volume":"85","author":"Chothia","year":"1997","journal-title":"Nature"},{"issue":"4","key":"10.1016\/S0020-0255(03)00067-7_BIB14","doi-asserted-by":"crossref","first-page":"823","DOI":"10.1002\/j.1460-2075.1986.tb04288.x","article-title":"The relation between the divergence of sequence and structure in proteins","volume":"5","author":"Chothia","year":"1986","journal-title":"EMBO J."},{"key":"10.1016\/S0020-0255(03)00067-7_BIB15","doi-asserted-by":"crossref","first-page":"524","DOI":"10.1016\/S0076-6879(83)91049-2","article-title":"Establishing homologies in protein sequences","volume":"91","author":"Dayhoff","year":"1983","journal-title":"Methods Enzymol."},{"key":"10.1016\/S0020-0255(03)00067-7_BIB16","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1146\/annurev.biochem.68.1.383","article-title":"Mammalian caspases: structure, activation, substrates, and functions durng apoptosis","volume":"68","author":"Earnshaw","year":"1999","journal-title":"Annu. Rev. Biochem."},{"issue":"6788","key":"10.1016\/S0020-0255(03)00067-7_BIB17","doi-asserted-by":"crossref","first-page":"823","DOI":"10.1038\/35015694","article-title":"Protein function in the post-genomic era","volume":"405","author":"Eisenberg","year":"2000","journal-title":"Nature"},{"key":"10.1016\/S0020-0255(03)00067-7_BIB18","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1093\/nar\/30.1.235","article-title":"The PROSITE database, its status in 2002","volume":"30","author":"Falquet","year":"2002","journal-title":"Nucleic Acids Res."},{"issue":"5","key":"10.1016\/S0020-0255(03)00067-7_BIB19_1","doi-asserted-by":"crossref","first-page":"1005","DOI":"10.1110\/ps.49201","article-title":"Genomic-scale comparison of sequence- and structure-based methods of functionprediction: does structure provide additional insight?","volume":"10","author":"Fetrow","year":"2001","journal-title":"Protein Sci."},{"issue":"1","key":"10.1016\/S0020-0255(03)00067-7_BIB19_2","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1093\/nar\/25.1.231","article-title":"Dali\/FSSP classification of three-dimensional protein folds","volume":"25","author":"Holm","year":"1997","journal-title":"Nucleic Acids Res."},{"key":"10.1016\/S0020-0255(03)00067-7_BIB20","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1093\/nar\/28.1.228","article-title":"Increased coverage of protein families with the blocks database servers","volume":"28","author":"Henikoff","year":"2000","journal-title":"Nucl. Acids Res."},{"key":"10.1016\/S0020-0255(03)00067-7_BIB21","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1126\/science.273.5275.595","article-title":"Mapping the protein universe","volume":"273","author":"Holm","year":"1996","journal-title":"Science"},{"key":"10.1016\/S0020-0255(03)00067-7_BIB22","first-page":"138","article-title":"A comparative analysis of computational motif detection methods","volume":"4","author":"Hudak","year":"1999","journal-title":"Pacific Symp. Biocomput."},{"key":"10.1016\/S0020-0255(03)00067-7_BIB23","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1089\/10665270050081405","article-title":"A discriminative framework for detecting remote protein homologies","volume":"7","author":"Jaakkola","year":"2000","journal-title":"J. Comp. Biol."},{"key":"10.1016\/S0020-0255(03)00067-7_BIB24","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1093\/bioinformatics\/17.5.445","article-title":"The utility of different representations of protein sequence for predicting functional class","volume":"17","author":"King","year":"2001","journal-title":"Bioinformatics"},{"issue":"1","key":"10.1016\/S0020-0255(03)00067-7_BIB25","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1093\/nar\/28.1.257","article-title":"SCOP: a structural classification of proteins database","volume":"28","author":"Lo Conte","year":"2000","journal-title":"Nucleic Acids Res."},{"key":"10.1016\/S0020-0255(03)00067-7_BIB26","series-title":"Machine Learning","author":"Mitchell","year":"1997"},{"key":"10.1016\/S0020-0255(03)00067-7_BIB27","doi-asserted-by":"crossref","first-page":"1618","DOI":"10.1002\/pro.5560040820","article-title":"Gibbs motif sampling: detection of bacterial outer membrane protein repeats","volume":"4","author":"Neuwald","year":"1995","journal-title":"Protein Sci."},{"issue":"3","key":"10.1016\/S0020-0255(03)00067-7_BIB28","doi-asserted-by":"crossref","first-page":"374","DOI":"10.1016\/S0959-440X(99)80051-7","article-title":"From protein structure to function","volume":"9","author":"Orengo","year":"1999","journal-title":"Curr. Opin. Struct. Biol."},{"issue":"1","key":"10.1016\/S0020-0255(03)00067-7_BIB29","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1093\/nar\/29.1.223","article-title":"A rapid classification protocol for the CATH Domain Database to support structural genomics","volume":"29","author":"Pearl","year":"2001","journal-title":"Nucleic Acids Res."},{"key":"10.1016\/S0020-0255(03)00067-7_BIB30","first-page":"185","article-title":"Flexible sequence similarity searching with the FASTA3 program package","volume":"132","author":"Pearson","year":"2000","journal-title":"Methods Mol. Biol."},{"key":"10.1016\/S0020-0255(03)00067-7_BIB31","series-title":"C4.5: Programs for Machine Learning","author":"Quinlan","year":"1992"},{"key":"10.1016\/S0020-0255(03)00067-7_BIB32","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1093\/nar\/28.1.323","article-title":"MEROPS: the peptidase database","volume":"28","author":"Rawlings","year":"2002","journal-title":"Nucleic Acids Res."},{"issue":"2","key":"10.1016\/S0020-0255(03)00067-7_BIB33","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1002\/(SICI)1097-0134(19991101)37:2<264::AID-PROT11>3.0.CO;2-C","article-title":"Dictionary building via unsupervised hierarchical motif discovery in the sequence space of natural proteins","volume":"37","author":"Rigoutsos","year":"1999","journal-title":"Proteins"},{"issue":"2","key":"10.1016\/S0020-0255(03)00067-7_BIB34","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1093\/protein\/12.2.85","article-title":"Twilight zone of protein sequence alignments","volume":"12","author":"Rost","year":"1999","journal-title":"Protein Eng."},{"key":"10.1016\/S0020-0255(03)00067-7_BIB35","first-page":"505","article-title":"A combined approach for ab initio construction of low resolution protein tertiary structures from sequence","volume":"4","author":"Samudrala","year":"1999","journal-title":"Pacific Symp. Biocomput."},{"key":"10.1016\/S0020-0255(03)00067-7_BIB36","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1093\/bioinformatics\/17.3.249","article-title":"MetaFam: a unified classification of protein families. I. Overview and statistics","volume":"17","author":"Silverstein","year":"2001","journal-title":"Bioinformatics"},{"issue":"1","key":"10.1016\/S0020-0255(03)00067-7_BIB37","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/S0167-7799(99)01398-0","article-title":"From genes to protein structure and function: novel applications of computational approaches in the genomic era","volume":"18","author":"Skolnick","year":"2000","journal-title":"Trends Biotechnol."},{"key":"10.1016\/S0020-0255(03)00067-7_BIB38","unstructured":"D. Wang, X. Wang, V. Honavar, D. Dobbs, Data-driven generation of decision trees for motif-based assignment of protein sequences to functional families, in: Proceedings of the Atlantic Symposium on Computational Biology, Genome Information Systems & Technology, 2001"},{"key":"10.1016\/S0020-0255(03)00067-7_BIB39","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1038\/370270a0","article-title":"Structure and mechanism of Interleukin-1\u03b2 converting enzyme","volume":"370","author":"Wilson","year":"1994","journal-title":"Nature"}],"container-title":["Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025503000677?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025503000677?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2020,3,19]],"date-time":"2020-03-19T17:04:47Z","timestamp":1584637487000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0020025503000677"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003,10]]},"references-count":40,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[2003,10]]}},"alternative-id":["S0020025503000677"],"URL":"https:\/\/doi.org\/10.1016\/s0020-0255(03)00067-7","relation":{},"ISSN":["0020-0255"],"issn-type":[{"value":"0020-0255","type":"print"}],"subject":[],"published":{"date-parts":[[2003,10]]}}}