{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T15:14:59Z","timestamp":1769094899813,"version":"3.49.0"},"reference-count":34,"publisher":"Oxford University Press (OUP)","issue":"13","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2007,7,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Motivation: Despite advances in the gene annotation process, the functions of a large portion of gene products remain insufficiently characterized. In addition, the in silico prediction of novel Gene Ontology (GO) annotations for partially characterized gene functions or processes is highly dependent on reverse genetic or functional genomic approaches. To our knowledge, no prediction method has been demonstrated to be highly accurate for sparsely annotated GO terms (those associated to fewer than 10 genes).<\/jats:p>\n               <jats:p>Results: We propose a novel approach, information theory-based semantic similarity (ITSS), to automatically predict molecular functions of genes based on existing GO annotations. Using a 10-fold cross-validation, we demonstrate that the ITSS algorithm obtains prediction accuracies (precision 97%, recall 77%) comparable to other machine learning algorithms when compared in similar conditions over densely annotated portions of the GO datasets. This method is able to generate highly accurate predictions in sparsely annotated portions of GO, where previous algorithms have failed. As a result, our technique generates an order of magnitude more functional predictions than previous methods. A 10-fold cross validation demonstrated a precision of 90% at a recall of 36% for the algorithm over sparsely annotated networks of the recent GO annotations (about 1400 GO terms and 11\u2009000 genes in Homo sapiens). To our knowledge, this article presents the first historical rollback validation for the predicted GO annotations, which may represent more realistic conditions than more widely used cross-validation approaches. By manually assessing a random sample of 100 predictions conducted in a historical rollback evaluation, we estimate that a minimum precision of 51% (95% confidence interval: 43\u201358%) can be achieved for the human GO Annotation file dated 2003.<\/jats:p>\n               <jats:p>Availability: The program is available on request. The 97\u2009732 positive predictions of novel gene annotations from the 2005 GO Annotation dataset and other supplementary information is available at http:\/\/phenos.bsd.uchicago.edu\/ITSS\/<\/jats:p>\n               <jats:p>Contact: Lussier@uchicago.edu<\/jats:p>\n               <jats:p>Supplementary information: Supplementary data are available atBioinformatics online.<\/jats:p>","DOI":"10.1093\/bioinformatics\/btm195","type":"journal-article","created":{"date-parts":[[2007,7,23]],"date-time":"2007-07-23T16:13:46Z","timestamp":1185207226000},"page":"i529-i538","source":"Crossref","is-referenced-by-count":132,"title":["Information theory applied to the sparse gene ontology annotation network to predict novel gene function"],"prefix":"10.1093","volume":"23","author":[{"given":"Ying","family":"Tao","sequence":"first","affiliation":[{"name":"1 Department of Biomedical Informatics, Columbia University, 622 West 168th Street, VC5, New York, NY 100322Center for Biomedical Informatics, The University of Chicago, 5841 S Maryland Avenue, Chicago, IL 60637, USA 3UCCRC, The University of Chicago, 5841\u2009S Maryland Avenue, Chicago, IL 60637, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lee","family":"Sam","sequence":"additional","affiliation":[{"name":"1 Department of Biomedical Informatics, Columbia University, 622 West 168th Street, VC5, New York, NY 100322Center for Biomedical Informatics, The University of Chicago, 5841 S Maryland Avenue, Chicago, IL 60637, USA 3UCCRC, The University of Chicago, 5841\u2009S Maryland Avenue, Chicago, IL 60637, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianrong","family":"Li","sequence":"additional","affiliation":[{"name":"1 Department of Biomedical Informatics, Columbia University, 622 West 168th Street, VC5, New York, NY 100322Center for Biomedical Informatics, The University of Chicago, 5841 S Maryland Avenue, Chicago, IL 60637, USA 3UCCRC, The University of Chicago, 5841\u2009S Maryland Avenue, Chicago, IL 60637, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carol","family":"Friedman","sequence":"additional","affiliation":[{"name":"1 Department of Biomedical Informatics, Columbia University, 622 West 168th Street, VC5, New York, NY 100322Center for Biomedical Informatics, The University of Chicago, 5841 S Maryland Avenue, Chicago, IL 60637, USA 3UCCRC, The University of Chicago, 5841\u2009S Maryland Avenue, Chicago, IL 60637, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yves A.","family":"Lussier","sequence":"additional","affiliation":[{"name":"1 Department of Biomedical Informatics, Columbia University, 622 West 168th Street, VC5, New York, NY 100322Center for Biomedical Informatics, The University of Chicago, 5841 S Maryland Avenue, Chicago, IL 60637, USA 3UCCRC, The University of Chicago, 5841\u2009S Maryland Avenue, Chicago, IL 60637, USA"},{"name":"1 Department of Biomedical Informatics, Columbia University, 622 West 168th Street, VC5, New York, NY 100322Center for Biomedical Informatics, The University of Chicago, 5841 S Maryland Avenue, Chicago, IL 60637, USA 3UCCRC, The University of Chicago, 5841\u2009S Maryland Avenue, Chicago, IL 60637, USA"},{"name":"1 Department of Biomedical Informatics, Columbia University, 622 West 168th Street, VC5, New York, NY 100322Center for Biomedical Informatics, The University of Chicago, 5841 S Maryland Avenue, Chicago, IL 60637, USA 3UCCRC, The University of Chicago, 5841\u2009S Maryland Avenue, Chicago, IL 60637, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2007,7,1]]},"reference":[{"key":"2023062708513222400_B1","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1093\/bioinformatics\/14.7.600","article-title":"Automatic extraction of keywords from scientific text: application to the knowledge domain of protein families","volume":"14","author":"Andrade","year":"1998","journal-title":"Bioinformatics"},{"key":"2023062708513222400_B2","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":"Ashburner","year":"2000","journal-title":"Nat. Genet"},{"key":"2023062708513222400_B3","first-page":"27","volume-title":"Using Reasoning to Guide Annotation with Gene Ontology Terms in GOAT","author":"Bada","year":"2004"},{"key":"2023062708513222400_B4","doi-asserted-by":"crossref","first-page":"S7","DOI":"10.1186\/1471-2105-8-S3-S7","article-title":"Evaluation of high-throughput functional categorization of human disease genes","volume":"8","author":"Chen","year":"2007","journal-title":"BMC Bioinformat"},{"key":"2023062708513222400_B5","doi-asserted-by":"crossref","first-page":"6414","DOI":"10.1093\/nar\/gkh978","article-title":"Global protein function annotation through mining genome-scale data in yeast Saccharomyces cerevisiae","volume":"32","author":"Chen","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"2023062708513222400_B6","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1093\/nar\/26.1.73","article-title":"SGD: saccharomyces genome database","volume":"26","author":"Cherry","year":"1998","journal-title":"Nucleic Acids Res"},{"key":"2023062708513222400_B7","doi-asserted-by":"crossref","first-page":"392","DOI":"10.1186\/1471-2105-7-392","article-title":"GeneLibrarian: an effective gene-information summarization and visualization system","volume":"7","author":"Chiang","year":"2006","journal-title":"BMC Bioinformat"},{"key":"2023062708513222400_B8","volume-title":"Pattern Classification and Scene Analysis","author":"Duda","year":"1973"},{"key":"2023062708513222400_B9","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1006\/bbrc.2000.3624","article-title":"Molecular cloning, genomic structure, chromosomal localization, and alternative splice forms of the platelet collagen receptor glycoprotein VI","volume":"277","author":"Ezumi","year":"2000","journal-title":"Biochem. Biophys. Res. Commun"},{"key":"2023062708513222400_B10","doi-asserted-by":"crossref","first-page":"839","DOI":"10.1148\/radiology.148.3.6878708","article-title":"A method of comparing the areas under receiver operating characteristic curves derived from the same cases","volume":"148","author":"Hanley","year":"1983","journal-title":"Radiology"},{"key":"2023062708513222400_B11","doi-asserted-by":"crossref","first-page":"6496","DOI":"10.1038\/sj.onc.1203059","article-title":"VEGI, a new member of the TNF family activates nuclear factor-kappa B and c-Jun N-terminal kinase and modulates cell growth","volume":"18","author":"Haridas","year":"1999","journal-title":"Oncogene"},{"key":"2023062708513222400_B12","first-page":"407","article-title":"Multi-word complex concept retrieval via lexical semantic similarity","author":"Jiang","year":"1999"},{"key":"2023062708513222400_B13","first-page":"19","article-title":"semantic similarity based on corpus statistics and lexical taxonomy","author":"Jiang","year":"1997"},{"key":"2023062708513222400_B14","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1186\/1471-2105-6-272","article-title":"Automated methods of predicting the function of biological sequences using GO and BLAST","volume":"6","author":"Jones","year":"2005","journal-title":"BMC Bioinformat"},{"key":"2023062708513222400_B15","doi-asserted-by":"crossref","first-page":"1644","DOI":"10.1093\/bioinformatics\/bti103","article-title":"Predicting gene function through systematic analysis and quality assessment of high-throughput data","volume":"21","author":"Kemmeren","year":"2005","journal-title":"Bioinformatics"},{"key":"2023062708513222400_B16","doi-asserted-by":"crossref","first-page":"2484","DOI":"10.1093\/bioinformatics\/btg338","article-title":"GoFigure: automated gene ontologyTM annotation","volume":"19","author":"Khan","year":"2003","journal-title":"Bioinformatics"},{"key":"2023062708513222400_B17","doi-asserted-by":"crossref","first-page":"896","DOI":"10.1101\/gr.440803","article-title":"Predicting gene function from patterns of annotation","volume":"13","author":"King","year":"2003","journal-title":"Genome Res"},{"key":"2023062708513222400_B18","doi-asserted-by":"crossref","first-page":"614","DOI":"10.1016\/j.jmb.2005.05.067","article-title":"Protein function prediction using local 3D templates","volume":"351","author":"Laskowski","year":"2005","journal-title":"J. Mol. Biol"},{"key":"2023062708513222400_B19","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/0165-6074(93)90067-U","article-title":"Using term dependencies of a thesaurus in the fuzzy set model","volume":"39","author":"Lee","year":"1993","journal-title":"Microproc. Microprog"},{"key":"2023062708513222400_B20","first-page":"296","article-title":"An information-theoretic definition of similarity. Machine learning","author":"Lin","year":"1998"},{"key":"2023062708513222400_B21","doi-asserted-by":"crossref","first-page":"1275","DOI":"10.1093\/bioinformatics\/btg153","article-title":"Investigating semantic similarity measures across the gene ontology: the relationship between sequence and annotation","volume":"19","author":"Lord","year":"2003","journal-title":"Bioinformatics"},{"key":"2023062708513222400_B22","first-page":"601","article-title":"Semantic similarity measures as tools for exploring the gene ontology","author":"Lord","year":"2003","journal-title":"Pac. Symp. Biocomput"},{"key":"2023062708513222400_B23","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1016\/S0001-2998(78)80014-2","article-title":"Basic principles of ROC analysis","volume":"8","author":"Metz","year":"1978","journal-title":"Semin. Nucl. Med"},{"key":"2023062708513222400_B24","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1055\/s-0038-1634383","article-title":"From phenotype to genotype: issues in navigating the available information resources","volume":"42","author":"Mitchell","year":"2003","journal-title":"Methods Inf. Med"},{"key":"2023062708513222400_B25","doi-asserted-by":"crossref","first-page":"2084","DOI":"10.1093\/bioinformatics\/bth207","article-title":"Gene annotation from scientific literature using mappings between keyword systems","volume":"20","author":"Perez","year":"2004","journal-title":"Bioinformatics"},{"key":"2023062708513222400_B26","first-page":"448","article-title":"Using information content to evaluate semantic similarity in a taxonomy","volume-title":"IJCAT-95 Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence","author":"Resnik","year":"1995"},{"key":"2023062708513222400_B27","doi-asserted-by":"crossref","first-page":"4940","DOI":"10.1073\/pnas.0600591103","article-title":"Microparadigms: chains of collective reasoning in publications about molecular interactions","volume":"103","author":"Rzhetsky","year":"2006","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"2023062708513222400_B28","doi-asserted-by":"crossref","first-page":"448","DOI":"10.1186\/1471-2105-7-448","article-title":"Gene function classification using Bayesian models with hierarchy-based priors","volume":"7","author":"Shahbaba","year":"2006","journal-title":"BMC Bioinformat"},{"key":"2023062708513222400_B29","volume-title":"Biometry: The Principles and Practice of Statistics in Biological Research","author":"Sokal","year":"1995"},{"key":"2023062708513222400_B30","doi-asserted-by":"crossref","first-page":"566","DOI":"10.1093\/bioinformatics\/btk019","article-title":"Improving missing value estimation in microarray data with gene ontology","volume":"22","author":"Tuikkala","year":"2006","journal-title":"Bioinformatics"},{"key":"2023062708513222400_B31","first-page":"389","article-title":"An ontology-driven clustering method for supporting gene expression analysis","author":"Wang","year":"2005"},{"key":"2023062708513222400_B32","first-page":"25","article-title":"Gene expression correlation and gene ontology-based similarity: an assessment of quantitative relationships","author":"Wang","year":"2004"},{"key":"2023062708513222400_B33","doi-asserted-by":"crossref","first-page":"2137","DOI":"10.1093\/nar\/gkl219","article-title":"Prediction of yeast protein-protein interaction network: insights from the gene ontology and annotations","volume":"34","author":"Wu","year":"2006","journal-title":"Nucleic Acids Res"},{"key":"2023062708513222400_B34","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1023\/A:1014540107013","article-title":"Collocation dictionary optimization using WordNet and k-nearest neighbor learning","volume":"16","author":"Yuseop","year":"2001","journal-title":"Mach. Trans"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/23\/13\/i529\/50718172\/bioinformatics_23_13_i529.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/23\/13\/i529\/50718172\/bioinformatics_23_13_i529.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,27]],"date-time":"2023-06-27T08:53:48Z","timestamp":1687856028000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/23\/13\/i529\/231121"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007,7,1]]},"references-count":34,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2007,7,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btm195","relation":{},"ISSN":["1367-4811","1367-4803"],"issn-type":[{"value":"1367-4811","type":"electronic"},{"value":"1367-4803","type":"print"}],"subject":[],"published-other":{"date-parts":[[2007,7]]},"published":{"date-parts":[[2007,7,1]]}}}