{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:36:50Z","timestamp":1772138210050,"version":"3.50.1"},"reference-count":30,"publisher":"Oxford University Press (OUP)","license":[{"start":{"date-parts":[[2017,3,18]],"date-time":"2017-03-18T00:00:00Z","timestamp":1489795200000},"content-version":"vor","delay-in-days":76,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,1,1]]},"DOI":"10.1093\/database\/bax021","type":"journal-article","created":{"date-parts":[[2017,2,22]],"date-time":"2017-02-22T07:16:21Z","timestamp":1487747781000},"source":"Crossref","is-referenced-by-count":8,"title":["Literature consistency of bioinformatics sequence databases is effective for assessing record quality"],"prefix":"10.1093","volume":"2017","author":[{"given":"Mohamed Reda","family":"Bouadjenek","sequence":"first","affiliation":[{"name":"The University of Melbourne, Australia"}]},{"given":"Karin","family":"Verspoor","sequence":"additional","affiliation":[{"name":"The University of Melbourne, Australia"}]},{"given":"Justin","family":"Zobel","sequence":"additional","affiliation":[{"name":"The University of Melbourne, Australia"}]}],"member":"286","published-online":{"date-parts":[[2017,3,18]]},"reference":[{"key":"key\n\t\t\t\t20180618185720_bax021-B1","article-title":"Data quality in genome databases. Eighth International Conference on Information Quality (IQ 2003)","author":"Muller","year":"2003"},{"key":"key\n\t\t\t\t20180618185720_bax021-B2","first-page":"53","article-title":"A classification of biological data artifacts","author":"Koh","year":"2005","journal-title":"Workshop on Database Issues in Biological Databases"},{"key":"key\n\t\t\t\t20180618185720_bax021-B3","first-page":"35","article-title":"Duplicate detection in biological data using association rule mining","author":"Koh","year":"2004","journal-title":"European Workshop on Data Mining and Text Mining in Bioinformatics"},{"key":"key\n\t\t\t\t20180618185720_bax021-B4","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1145\/2811163.2811175","volume-title":"Proceedings of the ACM Ninth International Workshop on Data and Text Mining in Biomedical Informatics","author":"Chen","year":"2015"},{"key":"key\n\t\t\t\t20180618185720_bax021-B5","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1016\/S0168-9525(99)01706-0","article-title":"Errors in genome annotation","volume":"15","author":"Brenner","year":"1999","journal-title":"Trends Genet"},{"key":"key\n\t\t\t\t20180618185720_bax021-B6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1471-2105-6-46","volume":"6","author":"Kaplan","year":"2005","journal-title":"BMC Bioinform"},{"key":"key\n\t\t\t\t20180618185720_bax021-B7","article-title":"Automated detection of records in biological sequence databases that are inconsistent with the literature","author":"Bouadjenek","year":"2017","journal-title":"BioRxiv"},{"key":"key\n\t\t\t\t20180618185720_bax021-B8","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1016\/S0022-2836(05)80360-2","article-title":"Basic local alignment search tool","volume":"215","author":"Altschul","year":"1990","journal-title":"J. Mol. Biol"},{"key":"key\n\t\t\t\t20180618185720_bax021-B9","doi-asserted-by":"crossref","first-page":"40.","DOI":"10.1515\/jib-2006-40","article-title":"Data cleaning and semantic improvement in biological databases","volume":"3","author":"Apiletti","year":"2006","journal-title":"J. Integr. Bioinform"},{"key":"key\n\t\t\t\t20180618185720_bax021-B10","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1504\/IJDMB.2010.034196","article-title":"Detecting duplicate biological entities using shortest path edit distance","volume":"4","author":"Rudniy","year":"2010","journal-title":"Int. J. Data Min. Bioinformatics"},{"key":"key\n\t\t\t\t20180618185720_bax021-B11","author":"Song","year":"2008"},{"key":"key\n\t\t\t\t20180618185720_bax021-B12","first-page":"141","article-title":"Detecting redundancy in biological databases? an efficient approach","volume":"9","author":"Chellamuthu","year":"2009","journal-title":"Glob. J. Comput. Sci. Technol"},{"key":"key\n\t\t\t\t20180618185720_bax021-B13","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1093\/bioinformatics\/14.5.423","article-title":"Removing near-neighbour redundancy from large protein sequence collections","volume":"14","author":"Holm","year":"1998","journal-title":"Bioinformatics"},{"key":"key\n\t\t\t\t20180618185720_bax021-B14","doi-asserted-by":"crossref","first-page":"1658","DOI":"10.1093\/bioinformatics\/btl158","article-title":"Cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences","volume":"22","author":"Li","year":"2006","journal-title":"Bioinformatics"},{"key":"key\n\t\t\t\t20180618185720_bax021-B15","doi-asserted-by":"crossref","first-page":"1913","DOI":"10.1093\/bioinformatics\/btv053","article-title":"Starcode: sequence clustering based on all-pairs search","volume":"31","author":"Zorita","year":"2015","journal-title":"Bioinformatics"},{"key":"key\n\t\t\t\t20180618185720_bax021-B16","doi-asserted-by":"crossref","first-page":"3448","DOI":"10.1021\/cr068303k","article-title":"Protein annotation at genomic scale: the current status","volume":"107","author":"Frishman","year":"2007","journal-title":"Chem. Rev"},{"key":"key\n\t\t\t\t20180618185720_bax021-B17","doi-asserted-by":"crossref","first-page":"1641","DOI":"10.1093\/bioinformatics\/18.12.1641","article-title":"Modeling the percolation of annotation errors in a database of protein sequences","volume":"18","author":"Gilks","year":"2002","journal-title":"Bioinformatics"},{"key":"key\n\t\t\t\t20180618185720_bax021-B18","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1371\/journal.pcbi.1000605","article-title":"Annotation error in public databases: misannotation of molecular function in enzyme superfamilies","volume":"5","author":"Schnoes","year":"2009","journal-title":"PLoS Comput. Biol"},{"key":"key\n\t\t\t\t20180618185720_bax021-B19","doi-asserted-by":"crossref","first-page":"717","DOI":"10.1093\/bioinformatics\/btg077","article-title":"Evaluation of annotation strategies using an entire genome sequence","volume":"19","author":"Iliopoulos","year":"2003","journal-title":"Bioinformatics"},{"key":"key\n\t\t\t\t20180618185720_bax021-B20","doi-asserted-by":"crossref","first-page":"i342","DOI":"10.1093\/bioinformatics\/bth938","article-title":"Filtering erroneous protein annotation","volume":"20(suppl 1)","author":"Wieser","year":"2004","journal-title":"Bioinformatics"},{"key":"key\n\t\t\t\t20180618185720_bax021-B21","first-page":"164","volume-title":"12th International Conference on Database Systems for Advanced Applications","author":"Koh","year":"2007"},{"key":"key\n\t\t\t\t20180618185720_bax021-B22","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1145\/564376.564429","volume-title":"Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Cronen-Townsend","year":"2002"},{"key":"key\n\t\t\t\t20180618185720_bax021-B23","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1016\/j.is.2005.11.003","article-title":"Query performance prediction","volume":"31","author":"He","year":"2006","journal-title":"Information Syst"},{"key":"key\n\t\t\t\t20180618185720_bax021-B24","doi-asserted-by":"crossref","first-page":"564","DOI":"10.1145\/1571941.1572038","volume-title":"Proceedings of the 32nd International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Kumaran","year":"2009"},{"key":"key\n\t\t\t\t20180618185720_bax021-B25","first-page":"43","volume-title":"11th International Conference, SPIRE 2004","author":"He","year":"2004"},{"key":"key\n\t\t\t\t20180618185720_bax021-B26","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1145\/383952.384019","volume-title":"Proceedings of the 24th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Zhai","year":"2001"},{"key":"key\n\t\t\t\t20180618185720_bax021-B27","first-page":"52","volume-title":"30th European Conference on IR Research","author":"Zhao","year":"2008"},{"key":"key\n\t\t\t\t20180618185720_bax021-B28","author":"Sayers","year":"2010"},{"key":"key\n\t\t\t\t20180618185720_bax021-B29","volume-title":"Principal Component Analysis","author":"Jolliffe","year":"2002"},{"key":"key\n\t\t\t\t20180618185720_bax021-B30","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1145\/342009.335388","volume-title":"Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data","author":"Breunig","year":"2000"}],"container-title":["Database"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/database\/article-pdf\/doi\/10.1093\/database\/bax021\/19232099\/bax021.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,24]],"date-time":"2022-07-24T11:36:54Z","timestamp":1658662614000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/database\/article\/doi\/10.1093\/database\/bax021\/3074790"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,1,1]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1093\/database\/bax021","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/101873","asserted-by":"object"}]},"ISSN":["1758-0463"],"issn-type":[{"value":"1758-0463","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2017]]},"published":{"date-parts":[[2017,1,1]]}}}