{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T00:44:50Z","timestamp":1744159490327},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2007,12,1]],"date-time":"2007-12-01T00:00:00Z","timestamp":1196467200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/2.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms Mol Biol"],"published-print":{"date-parts":[[2007,12]]},"DOI":"10.1186\/1748-7188-2-16","type":"journal-article","created":{"date-parts":[[2007,12,25]],"date-time":"2007-12-25T02:15:47Z","timestamp":1198548947000},"source":"Crossref","is-referenced-by-count":12,"title":["Evaluating deterministic motif significance measures in protein databases"],"prefix":"10.1186","volume":"2","author":[{"given":"Pedro Gabriel","family":"Ferreira","sequence":"first","affiliation":[]},{"given":"Paulo J","family":"Azevedo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2007,12,24]]},"reference":[{"key":"41_CR1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-3783-7","volume-title":"Sequence-Evolution-Function: Computational Approaches in Comparative Genomics","author":"E Koonin","year":"2003","unstructured":"Koonin E, Galperin M: Sequence-Evolution-Function: Computational Approaches in Comparative Genomics. 2003, Kluwer Academic Publishers"},{"key":"41_CR2","volume-title":"Proceedings of Workshop on Feature Extraction, of the 7th Conference on Neural Information Processing Systems","author":"A Ben-Hur","year":"2003","unstructured":"Ben-Hur A, Brutlag D: Sequence Motifs: highly predictive features of protein function. Proceedings of Workshop on Feature Extraction, of the 7th Conference on Neural Information Processing Systems. 2003"},{"key":"41_CR3","first-page":"147","volume-title":"Proceedings of the 4th international conference on Computational molecular biology","author":"R Hart","year":"2000","unstructured":"Hart R, Royyuru A, Stolovitzky G, Califano A: Systematic and Automated Discovery of Patterns in Prosite Families. Proceedings of the 4th international conference on Computational molecular biology. 2000, 147-154. Tokyo, Japan: ACM Press"},{"key":"41_CR4","volume-title":"Proceedings of BIOKDD workshop, 7th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"V Guralnik","year":"2001","unstructured":"Guralnik V, Karypis G: A scalable algorithm for clustering protein sequences. Proceedings of BIOKDD workshop, 7th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2001"},{"key":"41_CR5","doi-asserted-by":"publisher","first-page":"i26","DOI":"10.1093\/bioinformatics\/btg1002","volume":"19","author":"A Ben-Hur","year":"2003","unstructured":"Ben-Hur A, Brutlag D: Remote homology detection:a motif based approach. Bioinformatics. 2003, 19: i26-i33. 10.1093\/bioinformatics\/btg1002","journal-title":"Bioinformatics"},{"issue":"2","key":"41_CR6","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1089\/106652703321825964","volume":"10","author":"E Eskin","year":"2003","unstructured":"Eskin E, Grundy W, Singer Y: Biological sequence analysis: Probabilistic models of proteins and nucleic acids. Journal of Computational Biology. 2003, 10 (2): 187-214. 10.1089\/106652703321825964","journal-title":"Journal of Computational Biology"},{"key":"41_CR7","first-page":"15","volume-title":"Proceedings of 3rd International Conference on Research in Computational Molecular Biology","author":"G Bejerano","year":"1999","unstructured":"Bejerano G, Yona G: Modeling protein families using probabilistic suffix trees. Proceedings of 3rd International Conference on Research in Computational Molecular Biology. 1999, 15-24. ACM press"},{"key":"41_CR8","doi-asserted-by":"publisher","first-page":"1501","DOI":"10.1006\/jmbi.1994.1104","volume":"235","author":"A Krogh","year":"1994","unstructured":"Krogh A, Brown M, Mian IS, Sjolander K, Haussler D: Hidden markov models in computational biology: applications to protein modeling. Journal of Molecular Biology. 1994, 235: 1501-1531. 10.1006\/jmbi.1994.1104","journal-title":"Journal of Molecular Biology"},{"key":"41_CR9","first-page":"236","volume-title":"Proceedings of 12th EPIA Portuguese Conference on Artificial Intelligence","author":"PG Ferreira","year":"2005","unstructured":"Ferreira PG, Azevedo P: Protein Sequence Classification through Relevant Sequence Mining and Bayes Classifiers. Proceedings of 12th EPIA Portuguese Conference on Artificial Intelligence. 2005, 236-247."},{"key":"41_CR10","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1089\/cmb.2005.12.64","volume":"12","author":"K Blekas","year":"2005","unstructured":"Blekas K, Fotiadis D, Likas A: Motif-based protein sequence classification using neural networks. Journal of Computational Biology. 2005, 12: 64-82. 10.1089\/cmb.2005.12.64","journal-title":"Journal of Computational Biology"},{"key":"41_CR11","first-page":"34","volume-title":"Proc Int Conf Intell Syst Mol Biol","author":"E Ukkonen","year":"1996","unstructured":"Ukkonen E, Brazma A, Jonassen I, Vilo J: Discovering Patterns and Subfamilies in Biosequences. Proc Int Conf Intell Syst Mol Biol. 1996, 34-43."},{"issue":"20","key":"41_CR12","doi-asserted-by":"publisher","first-page":"3832","DOI":"10.1093\/bioinformatics\/bti628","volume":"21","author":"S Jensen","year":"2005","unstructured":"Jensen S, Shen L, Liu J: Combining phylogenetic motif discovery and motif clustering to predict co-regulated genes. Bioinformatics. 2005, 21 (20): 3832-3839. 10.1093\/bioinformatics\/bti628","journal-title":"Bioinformatics"},{"issue":"3","key":"41_CR13","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1006\/mben.2000.0151","volume":"2","author":"I Rigoutsos","year":"2000","unstructured":"Rigoutsos I, Floratos A, Parida L, Gao Y, Platt D: The emergence of pattern discovery techniques in computational biology. Metabolic Engineering. 2000, 2 (3): 159-167. 10.1006\/mben.2000.0151","journal-title":"Metabolic Engineering"},{"key":"41_CR14","volume-title":"Proceedings 8th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"P Tan","year":"2002","unstructured":"Tan P, Kumar V, Srivastava J: Selecting the right interesting measure for association patterns. Proceedings 8th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2002, Edmonton, Alberta, Canada"},{"key":"41_CR15","first-page":"487","volume-title":"Procedings of 20th International Conference Very Large Data Bases","author":"R Agrawal","year":"1994","unstructured":"Agrawal R, Srikant R: Fast algorithms for mining association rules. Procedings of 20th International Conference Very Large Data Bases. 1994, 487-499."},{"key":"41_CR16","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1038\/nbt1053","volume":"23","author":"M Tompa","year":"2005","unstructured":"Tompa M, Li N, Bailey T, Church G, Moor BD, Eskin E, Favorov A, Frith M, Fu Y, Kent W, Makeev V, Mironov A, Noble W, Pavesi G, Pesole G, Regnier M, Simonis N, Sinha S, Thijs G, van Helden J, Vandenbogaert M, Weng Z, Workman C, Ye C, Zhu Z: Assessing computational tools for the discovery of transcription factor binding sites. Nature Biotechnology. 2005, 23: 137-144. 10.1038\/nbt1053","journal-title":"Nature Biotechnology"},{"key":"41_CR17","doi-asserted-by":"crossref","unstructured":"Li N, Tompa M: Analysis of computational approaches for motif discovery. Algorithms for Molecular Biology. 2006, 1 (8):","DOI":"10.1186\/1748-7188-1-8"},{"issue":"13","key":"41_CR18","doi-asserted-by":"publisher","first-page":"3784","DOI":"10.1093\/nar\/gkg563","volume":"31","author":"E Gasteiger","year":"2003","unstructured":"Gasteiger E, Gattiker A, Hoogland C, Ivanyi I, Appel R, Bairoch A: ExPASy: the proteomics server for in-depth protein knowledge and analysis. Nucleic Acids Research. 2003, 31 (13): 3784-3788. 10.1093\/nar\/gkg563","journal-title":"Nucleic Acids Research"},{"key":"41_CR19","first-page":"269","volume-title":"Proceedings of the 8th International Conference on Intelligent Systems for Molecular Biology","author":"P Pevzner","year":"2000","unstructured":"Pevzner P, Sze S: Combinatorial approaches to finding subtle signals in DNA sequences. Proceedings of the 8th International Conference on Intelligent Systems for Molecular Biology. 2000, 269-278. AAAI Press"},{"key":"41_CR20","first-page":"69","volume-title":"Proceedings of 5th International Conference on Computational Molecular Biology","author":"J Buhler","year":"2001","unstructured":"Buhler J, Tompa M: Finding motifs using random projections. Proceedings of 5th International Conference on Computational Molecular Biology. 2001, 69-76."},{"key":"41_CR21","doi-asserted-by":"crossref","unstructured":"Sandve G, Drabl\u00f8s F: A survey of motif discovery methods in an integrated framework. Biology Direct. 2006, 1 (11):","DOI":"10.1186\/1745-6150-1-11"},{"issue":"2","key":"41_CR22","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1089\/cmb.1998.5.279","volume":"5","author":"A Brazma","year":"1998","unstructured":"Brazma A, Jonassen I, Eidhammer I, Gilbert D: Approaches to the automatic discovery of patterns in biosequences. Journal of Computational Biology. 1998, 5 (2): 277-304.","journal-title":"Journal of Computational Biology"},{"key":"41_CR23","volume-title":"In 10th International Conference on Intelligent Systems for Molecular Biology","author":"S Lonardi","year":"2002","unstructured":"Lonardi S: Pattern discovery in biosequences \u2013 Tutorial. In 10th International Conference on Intelligent Systems for Molecular Biology. 2002, http:\/\/www.cs.ucr.edu\/~stelo\/ismb02"},{"key":"41_CR24","doi-asserted-by":"crossref","unstructured":"Das M, Dai HK: A survey of DNA motif finding algorithms. BMC Bioinformatics. 2007, 8 (7):","DOI":"10.1186\/1471-2105-8-S7-S21"},{"key":"41_CR25","doi-asserted-by":"crossref","unstructured":"Hulo N, Bairoch A, Bulliard V, Cerutti L, Castro ED, Langendijk-Genevaux P, Pagni M, Sigrist C: The PROSITE database. Nucleic Acids Research. 2006, D227-D230. 34 Database","DOI":"10.1093\/nar\/gkj063"},{"key":"41_CR26","volume-title":"Encyclopedia of Genetics, Genomics, Proteomics and Bioinformatics . Chapter: The Prints protein fingerprint database: functional and evolutionary applications","author":"T Attwood","year":"2006","unstructured":"Attwood T, Mitchell A, Gaulton A, Moulton G, Tabernero L: Encyclopedia of Genetics, Genomics, Proteomics and Bioinformatics . Chapter: The Prints protein fingerprint database: functional and evolutionary applications. Edited by: Dunn M, Jorde L, Little P. 2006, John Wiley and Sons"},{"key":"41_CR27","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1006\/geno.1994.1018","volume":"19","author":"S Henikoff","year":"1994","unstructured":"Henikoff S, Henikoff J: Protein Family Classification based on Searching a Database of Blocks. Genomics. 1994, 19: 97-107. 10.1006\/geno.1994.1018","journal-title":"Genomics"},{"key":"41_CR28","unstructured":"Mulder N, Apweiler R, Attwood T, Bairoch A, Bateman A, Binns D, Bradley P, Bork P, Bucher P, Cerutti L, Copley R, Courcelle E, Das U, Durbin R, Fleischmann W, Gough J, Haft D, Harte N, Hulo N, Kahn D, Kanapin A, Krestyaninova M, Lonsdale D, Lopez R, Letunic I, Madera M, Maslen J, McDowall J, Mitchell A, Nikolskaya A: InterPro, progress and status in 2005. Nucleic Acid Research. 2005, D201-D205. 33 Database"},{"key":"41_CR29","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1093\/nar\/29.1.202","volume":"29","author":"J Huang","year":"2001","unstructured":"Huang J, Brutlag D: The emotif database. Nucleic Acids Research. 2001, 29: 202-204. 10.1093\/nar\/29.1.202","journal-title":"Nucleic Acids Research"},{"key":"41_CR30","volume-title":"Encyclopedia of Life Sciences","author":"S Henikoff","year":"2001","unstructured":"Henikoff S, Henikoff J: Protein family databases. Encyclopedia of Life Sciences. 2001"},{"issue":"12","key":"41_CR31","doi-asserted-by":"publisher","first-page":"e405","DOI":"10.1371\/journal.pbio.0030405","volume":"3","author":"V Neduva","year":"2005","unstructured":"Neduva V, Linding R, Su-Angrand I, Stark A, de Masi F, Gibson T, J JL, Serrano L, Russell R: Systematic discovery of new recognition peptides mediating protein interaction networks. PLoS Biology. 2005, 3 (12): e405- 10.1371\/journal.pbio.0030405","journal-title":"PLoS Biology"},{"key":"41_CR32","unstructured":"Sagot MF: On motifs in biological sequences. citeseer.ist.psu.edu\/473028.html."},{"key":"41_CR33","volume-title":"Data Mining, Concepts and Techniques","author":"J Han","year":"2006","unstructured":"Han J, Kambler M: Data Mining, Concepts and Techniques. 2006, Morgan Kaufmann, second"},{"issue":"5","key":"41_CR34","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1093\/bioinformatics\/16.5.412","volume":"16","author":"P Baldi","year":"2000","unstructured":"Baldi P, Brunak S, Chauvin Y, Andersen C, Nielsen H: Assessing the accuracy of prediction algorithms for classification: an overview. Bionformatics. 2000, 16 (5): 412-442. 10.1093\/bioinformatics\/16.5.412.","journal-title":"Bionformatics"},{"key":"41_CR35","doi-asserted-by":"publisher","first-page":"442","DOI":"10.1016\/0005-2795(75)90109-9","volume":"405","author":"B Matthews","year":"1975","unstructured":"Matthews B: Comparison of predicted and observed secondary structure of t4 lysozyme. Biochimica et Biophysica Acta. 1975, 405: 442-451.","journal-title":"Biochimica et Biophysica Acta"},{"key":"41_CR36","volume-title":"Computational Methods in Molecular Biology. Chapter: An Introduction to Hidden Markov Models for Biological Sequences","author":"A Krogh","year":"1998","unstructured":"Krogh A: Computational Methods in Molecular Biology. Chapter: An Introduction to Hidden Markov Models for Biological Sequences. Edited by: Salzberg S, Searls D, Kasif S. 1998, Elsevier"},{"key":"41_CR37","doi-asserted-by":"publisher","first-page":"i9","DOI":"10.1093\/bioinformatics\/bti1051","volume":"21","author":"A Apostolico","year":"2005","unstructured":"Apostolico A, Comin M, Parida L: Conservative extraction of over-represented extensible motifs. Bioinformatics. 2005, 21: i9-i18. 10.1093\/bioinformatics\/bti1051","journal-title":"Bioinformatics"},{"key":"41_CR38","first-page":"202","volume":"5","author":"C Nevill-Manning","year":"1997","unstructured":"Nevill-Manning C, Sethi K, Wu T, Brutlag D: Enumerating And Ranking Discrete Motifs. Proceedings of 5th International Conference Intelligent Systems Molecular Biology. 1997, 5: 202-209.","journal-title":"Proceedings of 5th International Conference Intelligent Systems Molecular Biology"},{"key":"41_CR39","first-page":"395","volume-title":"Proceedings 7th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"J Yang","year":"2001","unstructured":"Yang J, Yu P, Wang W: Infominer: mining surprising periodic patterns. Proceedings 7th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2001, 395-400. ACM Press"},{"key":"41_CR40","first-page":"402","volume-title":"3rd International Conference on Intelligent Systems for Molecular Biology","author":"T Wu","year":"1995","unstructured":"Wu T, Brutlag D: Identification of protein motifs using conserved amino acid properties and partitioning techniques. 3rd International Conference on Intelligent Systems for Molecular Biology. 1995, 402-410."},{"key":"41_CR41","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1093\/bioinformatics\/15.7.563","volume":"15","author":"G Hertz","year":"1999","unstructured":"Hertz G, Stormo G: Identifying DNA and protein patterns with statistically significant alignments of multiple sequences. Bioinformatics. 1999, 15: 563-577. 10.1093\/bioinformatics\/15.7.563","journal-title":"Bioinformatics"},{"issue":"8","key":"41_CR42","doi-asserted-by":"publisher","first-page":"1587","DOI":"10.1002\/pro.5560040817","volume":"4","author":"I Jonassen","year":"1995","unstructured":"Jonassen I, Collins J, Higgins D: Finding Flexible Patterns in Unaligned Protein Sequences. Protein Science. 1995, 4 (8): 1587-1595.","journal-title":"Protein Science"},{"key":"41_CR43","volume-title":"Technical report, IBM Computational Biology Center","author":"G Stolovitzky","year":"1998","unstructured":"Stolovitzky G, Califano A: Statistical significance of patterns in biosequences. Technical report, IBM Computational Biology Center. 1998"},{"key":"41_CR44","volume-title":"Rule Induction Using Information Theory","author":"P Smyth","year":"1990","unstructured":"Smyth P, Goodman R: Rule Induction Using Information Theory. 1990, MIT press"},{"key":"41_CR45","volume-title":"Information Theory and Coding","author":"NM Abramson","year":"1963","unstructured":"Abramson NM: Information Theory and Coding. 1963, McGraw-Hill, New York"},{"key":"41_CR46","volume-title":"Intelligent Data Analysis. Chapter: Information-Theoretic Tree and Rule Induction","author":"G van den Eijkel","year":"2003","unstructured":"van den Eijkel G: Intelligent Data Analysis. Chapter: Information-Theoretic Tree and Rule Induction. Edited by: Berthold M, Hand D. 2003, Springer, 2"},{"issue":"5\u20136","key":"41_CR47","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1016\/S0950-7051(01)00163-0","volume":"15","author":"M Bramer","year":"2002","unstructured":"Bramer M: Using J-pruning to reduce overfitting in classification trees. Knowledge-Based Systems. 2002, 15 (5\u20136): 301-308. 10.1016\/S0950-7051(01)00163-0.","journal-title":"Knowledge-Based Systems"},{"key":"41_CR48","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1093\/bioinformatics\/14.1.55","volume":"14","author":"I Rigoutsos","year":"1998","unstructured":"Rigoutsos I, Floratos A: Combinatorial pattern discovery in biological sequences. Bioinformatics. 1998, 14: 55-67. 10.1093\/bioinformatics\/14.1.55","journal-title":"Bioinformatics"},{"key":"41_CR49","volume-title":"Bioinformatics: Sequence, structure and databanks. A Practical Approach. Chapter: Methods for discovering conserved patterns in protein sequences and structures","author":"I Jonassen","year":"2000","unstructured":"Jonassen I: Bioinformatics: Sequence, structure and databanks. A Practical Approach. Chapter: Methods for discovering conserved patterns in protein sequences and structures. Edited by: Higgins D, Taylor W. 2000, Oxford University Press"},{"key":"41_CR50","unstructured":"Jonassen I: Pratt \u2013 Pattern Matching. http:\/\/www.ebi.ac.uk\/pratt\/"},{"key":"41_CR51","volume-title":"Biostatistical Analysis","author":"JH Zar","year":"1999","unstructured":"Zar JH: Biostatistical Analysis. 1999, Prentice Hall, 3"},{"key":"41_CR52","volume-title":"Discovering Statistics Using SPSS","author":"A Field","year":"2005","unstructured":"Field A: Discovering Statistics Using SPSS. 2005, Sage Publications Ltd, 2"}],"container-title":["Algorithms for Molecular Biology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1748-7188-2-16.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/1748-7188-2-16\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1748-7188-2-16.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,6]],"date-time":"2019-05-06T02:34:48Z","timestamp":1557110088000},"score":1,"resource":{"primary":{"URL":"https:\/\/almob.biomedcentral.com\/articles\/10.1186\/1748-7188-2-16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007,12]]},"references-count":52,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2007,12]]}},"alternative-id":["41"],"URL":"https:\/\/doi.org\/10.1186\/1748-7188-2-16","relation":{},"ISSN":["1748-7188"],"issn-type":[{"value":"1748-7188","type":"electronic"}],"subject":[],"published":{"date-parts":[[2007,12]]},"article-number":"16"}}