{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:51:05Z","timestamp":1775191865272,"version":"3.50.1"},"reference-count":70,"publisher":"Public Library of Science (PLoS)","issue":"12","license":[{"start":{"date-parts":[[2009,12,11]],"date-time":"2009-12-11T00:00:00Z","timestamp":1260489600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"DOI":"10.1371\/journal.pcbi.1000605","type":"journal-article","created":{"date-parts":[[2009,12,10]],"date-time":"2009-12-10T18:03:44Z","timestamp":1260468224000},"page":"e1000605","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":611,"title":["Annotation Error in Public Databases: Misannotation of Molecular Function in Enzyme Superfamilies"],"prefix":"10.1371","volume":"5","author":[{"given":"Alexandra M.","family":"Schnoes","sequence":"first","affiliation":[]},{"given":"Shoshana D.","family":"Brown","sequence":"additional","affiliation":[]},{"given":"Igor","family":"Dodevski","sequence":"additional","affiliation":[]},{"given":"Patricia C.","family":"Babbitt","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2009,12,11]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"D26","DOI":"10.1093\/nar\/gkn723","article-title":"GenBank.","volume":"37","author":"DA Benson","year":"2009","journal-title":"Nucleic Acids Res"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1016\/0168-9525(96)60040-7","article-title":"Go hunting in sequence databases but watch out for the traps.","volume":"12","author":"P Bork","year":"1996","journal-title":"Trends Genet"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"753","DOI":"10.1093\/bioinformatics\/14.9.753","article-title":"What we do not know about sequence analysis and sequence databases.","volume":"14","author":"PD Karp","year":"1998","journal-title":"Bioinformatics"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1016\/S0168-9525(99)01706-0","article-title":"Errors in genome annotation.","volume":"15","author":"SE Brenner","year":"1999","journal-title":"Trends Genet"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1016\/S0168-9525(01)02348-4","article-title":"Intrinsic errors in genome annotation.","volume":"17","author":"D Devos","year":"2001","journal-title":"Trends Genet"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1186\/1471-2105-8-284","article-title":"Exploring inconsistencies in genome-wide protein function annotations: a machine learning approach.","volume":"8","author":"C Andorf","year":"2007","journal-title":"BMC Bioinformatics"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"1866","DOI":"10.1096\/fasebj.13.13.1866","article-title":"Structure-based functional motif identifies a potential disulfide oxidoreductase active site in the serine\/threonine protein phosphatase-1 subfamily.","volume":"13","author":"JS Fetrow","year":"1999","journal-title":"Faseb J"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"496","DOI":"10.1016\/j.jmb.2006.03.043","article-title":"Ig-like domains on bacteriophages: a tale of promiscuity and deceit.","volume":"359","author":"JS Fraser","year":"2006","journal-title":"J Mol Biol"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"1457","DOI":"10.1126\/science.281.5382.1453c","article-title":"Errors in genome reviews.","volume":"281","author":"NC Kyrpides","year":"1998","journal-title":"Science"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1186\/1471-2164-5-52","article-title":"Retrieving sequences of enzymes experimentally characterized but erroneously annotated : the case of the putrescine carbamoyltransferase.","volume":"5","author":"DG Naumoff","year":"2004","journal-title":"BMC Genomics"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1006\/abbi.1999.1596","article-title":"Cloning and characterization of glyoxalase I from soybean.","volume":"374","author":"M Skipsey","year":"2000","journal-title":"Arch Biochem Biophys"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1186\/1471-2105-8-170","article-title":"Estimating the annotation error rate of curated GO database sequence annotations.","volume":"8","author":"CE Jones","year":"2007","journal-title":"BMC Bioinformatics"},{"key":"ref13","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":"WR Gilks","year":"2002","journal-title":"Bioinformatics"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1016\/j.mbs.2004.08.001","article-title":"Percolation of annotation errors through hierarchically structured protein sequence databases.","volume":"193","author":"WR Gilks","year":"2005","journal-title":"Math Biosci"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"886","DOI":"10.1046\/j.1365-2958.1999.01380.x","article-title":"Whole-genome sequence annotation: \u2018Going wrong with confidence\u2019.","volume":"32","author":"NC Kyrpides","year":"1999","journal-title":"Mol Microbiol"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1046\/j.1365-2958.1999.01561.x","article-title":"\u2018Going wrong with confidence\u2019: misleading sequence analyses of CiaB and clpX.","volume":"34","author":"M Pallen","year":"1999","journal-title":"Mol Microbiol"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"1616","DOI":"10.1126\/science.319.5870.1616a","article-title":"Preserving accuracy in GenBank.","volume":"319","author":"MI Bidartondo","year":"2008","journal-title":"Science"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1038\/sj.embor.embor932","article-title":"Righting the wrongs.","volume":"4","author":"C Hadley","year":"2003","journal-title":"EMBO Rep"},{"key":"ref19","article-title":"Protein function prediction - the power of multiplicity.","author":"R Rentzsch","year":"2009","journal-title":"Trends Biotechnol"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"324","DOI":"10.1016\/S0968-0004(98)01274-2","article-title":"Conservation of gene order: a fingerprint of proteins that physically interact.","volume":"23","author":"T Dandekar","year":"1998","journal-title":"Trends Biochem Sci"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"911","DOI":"10.1038\/nbt988","article-title":"Analysis of genomic context: prediction of functional associations from conserved bidirectionally transcribed gene pairs.","volume":"22","author":"JO Korbel","year":"2004","journal-title":"Nat Biotechnol"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"751","DOI":"10.1126\/science.285.5428.751","article-title":"Detecting protein function and protein-protein interactions from genome sequences.","volume":"285","author":"EM Marcotte","year":"1999","journal-title":"Science"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"2896","DOI":"10.1073\/pnas.96.6.2896","article-title":"The use of gene clusters to infer functional coupling.","volume":"96","author":"R Overbeek","year":"1999","journal-title":"Proc Natl Acad Sci U S A"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"4285","DOI":"10.1073\/pnas.96.8.4285","article-title":"Assigning protein functions by comparative genome analysis: protein phylogenetic profiles.","volume":"96","author":"M Pellegrini","year":"1999","journal-title":"Proc Natl Acad Sci U S A"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"e77","DOI":"10.1371\/journal.pcbi.0020077","article-title":"Functional classification using phylogenomic inference.","volume":"2","author":"D Brown","year":"2006","journal-title":"PLoS Comput Biol"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1101\/gr.8.3.163","article-title":"Phylogenomics: improving functional predictions for uncharacterized genes by evolutionary analysis.","volume":"8","author":"JA Eisen","year":"1998","journal-title":"Genome Res"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"1362","DOI":"10.1101\/gr.6427907","article-title":"Whole proteome analysis of post-translational modifications: applications of mass-spectrometry for proteogenomic annotation.","volume":"17","author":"N Gupta","year":"2007","journal-title":"Genome Res"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"D129","DOI":"10.1093\/nar\/gkh028","article-title":"The Catalytic Site Atlas: a resource of catalytic sites and residues identified in enzymes using structural data.","volume":"32","author":"CT Porter","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1093\/nar\/gkg030","article-title":"PRINTS and its automatic supplement, prePRINTS.","volume":"31","author":"TK Attwood","year":"2003","journal-title":"Nucleic Acids Res"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"D227","DOI":"10.1093\/nar\/gkj063","article-title":"The PROSITE database.","volume":"34","author":"N Hulo","year":"2006","journal-title":"Nucleic Acids Res"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"D281","DOI":"10.1093\/nar\/gkm960","article-title":"The Pfam protein families database.","volume":"36","author":"RD Finn","year":"2008","journal-title":"Nucleic Acids Res"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"D211","DOI":"10.1093\/nar\/gkn785","article-title":"InterPro: the integrative protein signature database.","volume":"37","author":"S Hunter","year":"2009","journal-title":"Nucleic Acids Res"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1186\/1471-2105-4-41","article-title":"The COG database: an updated version includes eukaryotes.","volume":"4","author":"RL Tatusov","year":"2003","journal-title":"BMC Bioinformatics"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"D363","DOI":"10.1093\/nar\/gkj123","article-title":"OrthoMCL-DB: querying a comprehensive multi-species collection of ortholog groups.","volume":"34","author":"F Chen","year":"2006","journal-title":"Nucleic Acids Res"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"7577","DOI":"10.1093\/nar\/gkm740","article-title":"Multidimensional annotation of the Escherichia coli K-12 genome.","volume":"35","author":"PD Karp","year":"2007","journal-title":"Nucleic Acids Res"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"D577","DOI":"10.1093\/nar\/gkm909","article-title":"Gene Ontology annotations at SGD: new data sources and annotation methods.","volume":"36","author":"EL Hong","year":"2008","journal-title":"Nucleic Acids Res"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"D724","DOI":"10.1093\/nar\/gkm961","article-title":"The Mouse Genome Database (MGD): mouse biology and model systems.","volume":"36","author":"CJ Bult","year":"2008","journal-title":"Nucleic Acids Res"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"860","DOI":"10.1038\/35057062","article-title":"Initial sequencing and analysis of the human genome.","volume":"409","author":"ES Lander","year":"2001","journal-title":"Nature"},{"key":"ref39","doi-asserted-by":"crossref","first-page":"3448","DOI":"10.1021\/cr068303k","article-title":"Protein annotation at genomic scale: the current status.","volume":"107","author":"D Frishman","year":"2007","journal-title":"Chem Rev"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"995","DOI":"10.1038\/nrm2281","article-title":"Predicting protein function from sequence and structure.","volume":"8","author":"D Lee","year":"2007","journal-title":"Nat Rev Mol Cell Biol"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"362","DOI":"10.1016\/j.sbi.2007.05.010","article-title":"Protein function space: viewing the limits or limited by our view?","volume":"17","author":"J Raes","year":"2007","journal-title":"Curr Opin Struct Biol"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"D169","DOI":"10.1093\/nar\/gkn664","article-title":"The Universal Protein Resource (UniProt) 2009.","volume":"37","year":"2009","journal-title":"Nucleic Acids Res"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"D480","DOI":"10.1093\/nar\/gkm882","article-title":"KEGG for linking genomes to life and the environment.","volume":"36","author":"M Kanehisa","year":"2008","journal-title":"Nucleic Acids Res"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"R8","DOI":"10.1186\/gb-2006-7-1-r8","article-title":"A gold standard set of mechanistically diverse enzyme superfamilies.","volume":"7","author":"SD Brown","year":"2006","journal-title":"Genome Biol"},{"key":"ref45","first-page":"358","article-title":"Representing structure-function relationships in mechanistically diverse enzyme superfamilies.","author":"SC Pegg","year":"2005","journal-title":"Pac Symp Biocomput"},{"key":"ref46","doi-asserted-by":"crossref","first-page":"2545","DOI":"10.1021\/bi052101l","article-title":"Leveraging enzyme structure-function relationships for functional inference and experimental design: the structure-function linkage database.","volume":"45","author":"SC Pegg","year":"2006","journal-title":"Biochemistry"},{"key":"ref47","article-title":"Enzyme Nomenclature: Recommendations of the Nomenclature Committee of the International Union of Biochemistry and Molecular Biology (IUBMB)","author":"KF Tipton","year":"1992"},{"key":"ref48","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1016\/j.jmb.2006.04.055","article-title":"Evolution of structure and function in the o-succinylbenzoate synthase\/N-acylamino acid racemase family of the enolase superfamily.","volume":"360","author":"ME Glasner","year":"2006","journal-title":"J Mol Biol"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"17700","DOI":"10.1073\/pnas.0809583105","article-title":"Annotating proteins with generalized functional linkages.","volume":"105","author":"R Llewellyn","year":"2008","journal-title":"Proc Natl Acad Sci U S A"},{"key":"ref50","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1146\/annurev.biochem.70.1.209","article-title":"Divergent evolution of enzymatic function: mechanistically diverse superfamilies and functionally distinct suprafamilies.","volume":"70","author":"JA Gerlt","year":"2001","journal-title":"Annu Rev Biochem"},{"key":"ref51","doi-asserted-by":"crossref","first-page":"I130","DOI":"10.1093\/bioinformatics\/bth948","article-title":"SCOPEC: a database of protein catalytic domains.","volume":"20","author":"RA George","year":"2004","journal-title":"Bioinformatics"},{"key":"ref52","doi-asserted-by":"crossref","first-page":"13913","DOI":"10.1073\/pnas.0702636104","article-title":"Quantitative assessment of protein function prediction from metagenomics shotgun sequences.","volume":"104","author":"ED Harrington","year":"2007","journal-title":"Proc Natl Acad Sci U S A"},{"key":"ref53","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1016\/S0022-2836(02)00016-5","article-title":"Enzyme function less conserved than anticipated.","volume":"318","author":"B Rost","year":"2002","journal-title":"J Mol Biol"},{"key":"ref54","doi-asserted-by":"crossref","first-page":"863","DOI":"10.1016\/j.jmb.2003.08.057","article-title":"How well is enzyme function conserved as a function of pairwise sequence identity?","volume":"333","author":"W Tian","year":"2003","journal-title":"J Mol Biol"},{"key":"ref55","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1006\/jmbi.2001.4513","article-title":"Evolution of function in protein superfamilies, from a structural perspective.","volume":"307","author":"AE Todd","year":"2001","journal-title":"J Mol Biol"},{"key":"ref56","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1089\/omi.2008.0017","article-title":"Toward an online repository of Standard Operating Procedures (SOPs) for (meta)genomic annotation.","volume":"12","author":"SV Angiuoli","year":"2008","journal-title":"Omics"},{"key":"ref57","doi-asserted-by":"crossref","first-page":"55","DOI":"10.3233\/ISB-00007","article-title":"Sources of systematic error in functional annotation of genomes: domain rearrangement, non-orthologous gene displacement and operon disruption.","volume":"1","author":"MY Galperin","year":"1998","journal-title":"In Silico Biol"},{"key":"ref58","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":"SF Altschul","year":"1997","journal-title":"Nucleic Acids Res"},{"key":"ref59","doi-asserted-by":"crossref","first-page":"2498","DOI":"10.1101\/gr.1239303","article-title":"Cytoscape: a software environment for integrated models of biomolecular interaction networks.","volume":"13","author":"P Shannon","year":"2003","journal-title":"Genome Res"},{"key":"ref60","doi-asserted-by":"crossref","first-page":"e4345","DOI":"10.1371\/journal.pone.0004345","article-title":"Using sequence similarity networks for visualization of relationships across diverse protein superfamilies.","volume":"4","author":"HJ Atkinson","year":"2009","journal-title":"PLoS ONE"},{"key":"ref61","doi-asserted-by":"crossref","first-page":"1598","DOI":"10.1126\/science.319.5870.1598","article-title":"DNA data. Proposal to \u2018Wikify\u2019 GenBank meets stiff resistance.","volume":"319","author":"E Pennisi","year":"2008","journal-title":"Science"},{"key":"ref62","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1186\/gb-2007-8-1-102","article-title":"Genome re-annotation: a wiki solution?","volume":"8","author":"SL Salzberg","year":"2007","journal-title":"Genome Biol"},{"key":"ref63","doi-asserted-by":"crossref","first-page":"COMMENT2001","DOI":"10.1186\/gb-2002-3-2-comment2001","article-title":"The past, present and future of genome-wide re-annotation.","volume":"3","author":"CA Ouzounis","year":"2002","journal-title":"Genome Biol"},{"key":"ref64","doi-asserted-by":"crossref","first-page":"D440","DOI":"10.1093\/nar\/gkm883","article-title":"The Gene Ontology project in 2008.","volume":"36","year":"2008","journal-title":"Nucleic Acids Res"},{"key":"ref65","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1038\/75556","article-title":"Gene ontology: tool for the unification of biology. The Gene Ontology Consortium.","volume":"25","author":"M Ashburner","year":"2000","journal-title":"Nat Genet"},{"key":"ref66","doi-asserted-by":"crossref","first-page":"i41","DOI":"10.1093\/bioinformatics\/btm229","article-title":"Manual curation is not sufficient for annotation of genomic databases.","volume":"23","author":"WA Baumgartner Jr","year":"2007","journal-title":"Bioinformatics"},{"key":"ref67"},{"key":"ref68","doi-asserted-by":"crossref","first-page":"1792","DOI":"10.1093\/nar\/gkh340","article-title":"MUSCLE: multiple sequence alignment with high accuracy and high throughput.","volume":"32","author":"RC Edgar","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"ref69","doi-asserted-by":"crossref","first-page":"2175","DOI":"10.1111\/j.1462-2920.2007.01331.x","article-title":"Novel hopanoid cyclases from the environment.","volume":"9","author":"A Pearson","year":"2007","journal-title":"Environ Microbiol"},{"key":"ref70","doi-asserted-by":"crossref","first-page":"1317","DOI":"10.1093\/oxfordjournals.jbchem.a124861","article-title":"Comprehensive site-directed mutagenesis of L-2-halo acid dehalogenase to probe catalytic amino acid residues.","volume":"117","author":"T Kurihara","year":"1995","journal-title":"J Biochem"}],"container-title":["PLoS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/dx.plos.org\/10.1371\/journal.pcbi.1000605","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T14:30:03Z","timestamp":1739457003000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1000605"}},"subtitle":[],"editor":[{"given":"Alfonso","family":"Valencia","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2009,12,11]]},"references-count":70,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2009,12,11]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1000605","relation":{"has-review":[{"id-type":"doi","id":"10.3410\/f.1728982.1378069","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2009,12,11]]}}}