{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T22:26:47Z","timestamp":1778797607047,"version":"3.51.4"},"reference-count":30,"publisher":"Oxford University Press (OUP)","issue":"7","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006,4,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Motivation: Assigning functions for unknown genes based on diverse large-scale data is a key task in functional genomics. Previous work on gene function prediction has addressed this problem using independent classifiers for each function. However, such an approach ignores the structure of functional class taxonomies, such as the Gene Ontology (GO). Over a hierarchy of functional classes, a group of independent classifiers where each one predicts gene membership to a particular class can produce a hierarchically inconsistent set of predictions, where for a given gene a specific class may be predicted positive while its inclusive parent class is predicted negative. Taking the hierarchical structure into account resolves such inconsistencies and provides an opportunity for leveraging all classifiers in the hierarchy to achieve higher specificity of predictions.<\/jats:p>\n               <jats:p>Results: We developed a Bayesian framework for combining multiple classifiers based on the functional taxonomy constraints. Using a hierarchy of support vector machine (SVM) classifiers trained on multiple data types, we combined predictions in our Bayesian framework to obtain the most probable consistent set of predictions. Experiments show that over a 105-node subhierarchy of the GO, our Bayesian framework improves predictions for 93 nodes. As an additional benefit, our method also provides implicit calibration of SVM margin outputs to probabilities. Using this method, we make function predictions for multiple proteins, and experimentally confirm predictions for proteins involved in mitosis.<\/jats:p>\n               <jats:p>Supplementary information: Results for the 105 selected GO classes and predictions for 1059 unknown genes are available at:<\/jats:p>\n               <jats:p>Contact: \u00a0ogt@cs.princeton.edu<\/jats:p>","DOI":"10.1093\/bioinformatics\/btk048","type":"journal-article","created":{"date-parts":[[2006,1,13]],"date-time":"2006-01-13T01:54:20Z","timestamp":1137117260000},"page":"830-836","source":"Crossref","is-referenced-by-count":380,"title":["Hierarchical multi-label prediction of gene function"],"prefix":"10.1093","volume":"22","author":[{"given":"Zafer","family":"Barutcuoglu","sequence":"first","affiliation":[{"name":"Department of Computer Science, Princeton University 1 \u00a0 1 \u00a0 \u00a0 35 Olden Street, Princeton, NJ 08544, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert E.","family":"Schapire","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Princeton University 1 \u00a0 1 \u00a0 \u00a0 35 Olden Street, Princeton, NJ 08544, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Olga G.","family":"Troyanskaya","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Princeton University 1 \u00a0 1 \u00a0 \u00a0 35 Olden Street, Princeton, NJ 08544, USA"},{"name":"Lewis-Sigler Institute for Integrative Genomics, Princeton University 2 \u00a0 2 \u00a0 \u00a0 NJ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2006,1,12]]},"reference":[{"key":"2023012409122577500_b1","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1101\/gad.969602","article-title":"The origin recognition complex: from simple origins to complex functions","volume":"16","author":"Bell","year":"2002","journal-title":"Genes Dev."},{"key":"2023012409122577500_b2","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1007\/BF00058655","article-title":"Bagging predictors","volume":"24","author":"Breiman","year":"1996","journal-title":"Mach. Learn."},{"key":"2023012409122577500_b3","doi-asserted-by":"crossref","first-page":"R23","DOI":"10.1186\/gb-2003-4-3-r23","article-title":"The GRID: the General Repository for Interaction Datasets","volume":"4","author":"Breitkreutz","year":"2003","journal-title":"Genome Biol."},{"key":"2023012409122577500_b4","first-page":"955","article-title":"A tutorial on support vector machines for pattern recognition","volume":"2","author":"Burges","year":"1998","journal-title":"Data Mining Know. Discov."},{"key":"2023012409122577500_b5","first-page":"93","article-title":"Regret bounds for hierarchical classification with linear-threshold functions","author":"Cesa-Bianchi","year":"2004"},{"key":"2023012409122577500_b6","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":"2023012409122577500_b7","first-page":"699","article-title":"[Erratum (1998) The transcriptional program of sporulation in budding Erratum yeast, Science, 282, 1421]","author":"Chu"},{"key":"2023012409122577500_b8","doi-asserted-by":"crossref","first-page":"II42","DOI":"10.1093\/bioinformatics\/btg1058","article-title":"Predicting gene function in Saccharomyces cerevisiase","volume":"19","author":"Clare","year":"2003","journal-title":"Bioinformatics"},{"key":"2023012409122577500_b9","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4899-4541-9","article-title":"An Introduction to the Bootstrap","author":"Efron","year":"1993"},{"key":"2023012409122577500_b10","doi-asserted-by":"crossref","first-page":"3988","DOI":"10.1093\/nar\/29.19.3988","article-title":"PROSPECT improves cis-acting regulatory element prediction by integrating expression profile data with consensus pattern searches","volume":"29","author":"Fujibuchi","year":"2001","journal-title":"Nucleic Acids Res."},{"key":"2023012409122577500_b11","doi-asserted-by":"crossref","first-page":"4241","DOI":"10.1091\/mbc.11.12.4241","article-title":"Genomic expression programs in the response of yeast cells to environmental changes","volume":"11","author":"Gasch","year":"2000","journal-title":"Mol. Biol. Cell"},{"key":"2023012409122577500_b12","doi-asserted-by":"crossref","first-page":"2987","DOI":"10.1091\/mbc.12.10.2987","article-title":"Genomic expression responses to DNA-damaging agents and the regulatory role of the yeast ATR homolog Mec1p","volume":"12","author":"Gasch","year":"2001","journal-title":"Mol. Biol. Cell"},{"key":"2023012409122577500_b13","doi-asserted-by":"crossref","first-page":"D364","DOI":"10.1093\/nar\/gki053","article-title":"CYGD: the Comprehensive Yeast Genome Database","volume":"33","author":"G\u00fcldener","year":"2005","journal-title":"Nucleic Acids Res."},{"key":"2023012409122577500_b14","doi-asserted-by":"crossref","first-page":"686","DOI":"10.1038\/nature02026","article-title":"Global analysis of protein localization in budding yeast","volume":"425","author":"Huh","year":"2003","journal-title":"Nature"},{"key":"2023012409122577500_b15","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1126\/science.1087361","article-title":"A Bayesian networks approach for predicting protein\u2013protein interactions from genomic data","volume":"302","author":"Jansen","year":"2003","journal-title":"Science"},{"key":"2023012409122577500_b16","article-title":"Making large-Scale SVM Learning Practical","volume-title":"Advances in Kernel Methods\u2014Support Vector Learning","author":"Joachims","year":"1999"},{"key":"2023012409122577500_b17","doi-asserted-by":"crossref","first-page":"2888","DOI":"10.1073\/pnas.0307326101","article-title":"Whole-genome annotation by using evidence integration in functional-linkage networks","volume":"101","author":"Karaoz","year":"2004","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"2023012409122577500_b18","doi-asserted-by":"crossref","first-page":"2626","DOI":"10.1093\/bioinformatics\/bth294","article-title":"A statistical framework for genomic data fusion","volume":"20","author":"Lanckriet","year":"2004","journal-title":"Bioinformatics"},{"key":"2023012409122577500_b19","first-page":"300","article-title":"Kernel-based data fusion and its application to protein function prediction in yeast","author":"Lanckriet","year":"2004","journal-title":"Pac. Symp. Biocomput."},{"key":"2023012409122577500_b20","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1083\/jcb.200407036","article-title":"The offloading model for dynein function: differential function of motor subunits","volume":"168","author":"Lee","year":"2005","journal-title":"J. Cell Biol."},{"key":"2023012409122577500_b21","first-page":"5724","article-title":"Evidence that POB1, a Saccharomyces cerevisiae protein that binds to DNA polymerase alpha, acts in DNA metabolism in vivo","volume":"12","author":"Miles","year":"1992","journal-title":"Mol. Cell. Biol."},{"key":"2023012409122577500_b22","doi-asserted-by":"crossref","first-page":"4309","DOI":"10.1091\/mbc.11.12.4309","article-title":"New components of a system for phosphate accumulation and polyphosphate metabolism in Saccharomyces cerevisiae revealed by genomic expression analysis","volume":"11","author":"Ogawa","year":"2000","journal-title":"Mol. Biol. Cell."},{"key":"2023012409122577500_b23","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1089\/10665270252935539","article-title":"Learning gene functional classifications from multiple data types","volume":"9","author":"Pavlidis","year":"2002","journal-title":"J. Comput. Biol."},{"key":"2023012409122577500_b24","doi-asserted-by":"crossref","first-page":"1233","DOI":"10.1091\/mbc.e03-09-0642","article-title":"Transcriptional remodeling in response to iron deprivation in Saccharomyces cerevisiae","volume":"15","author":"Shakoury-Elizeh","year":"2004","journal-title":"Mol. Biol. Cell"},{"key":"2023012409122577500_b25","doi-asserted-by":"crossref","first-page":"3273","DOI":"10.1091\/mbc.9.12.3273","article-title":"Comprehensive identification of cell cycle-regulated genes of the yeast Saccharomyces cerevisiae by microarray hybridization","volume":"9","author":"Spellman","year":"1998","journal-title":"Mol. Biol. Cell"},{"key":"2023012409122577500_b26","doi-asserted-by":"crossref","first-page":"3364","DOI":"10.1073\/pnas.97.7.3364","article-title":"Whole-genome expression analysis of snf\/swi mutants of Saccharomyces cerevisiae","volume":"97","author":"Sudarsanam","year":"2000","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"2023012409122577500_b27","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1038\/75556","article-title":"Gene ontology: tool for the unification of biology","volume":"25","author":"The Gene Ontology Consortium","year":"2000","journal-title":"Nat. Genet."},{"key":"2023012409122577500_b28","doi-asserted-by":"crossref","first-page":"520","DOI":"10.1093\/bioinformatics\/17.6.520","article-title":"Missing value estimation methods for DNA microarrays","volume":"17","author":"Troyanskaya","year":"2001","journal-title":"Bioinformatics"},{"key":"2023012409122577500_b29","doi-asserted-by":"crossref","first-page":"8348","DOI":"10.1073\/pnas.0832373100","article-title":"A Bayesian framework for combining heterogeneous data sources for gene function prediction (in Saccharomyces cerevisiase)","volume":"100","author":"Troyanskaya","year":"2003","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"2023012409122577500_b30","doi-asserted-by":"crossref","first-page":"31079","DOI":"10.1074\/jbc.M202718200","article-title":"Genome-wide analysis of gene expression regulated by the calcineurin\/Crz1p signaling pathway in Saccharomyces cerevisiae","volume":"277","author":"Yoshimoto","year":"2002","journal-title":"J. Biol. Chem."}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/22\/7\/830\/48841235\/bioinformatics_22_7_830.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/22\/7\/830\/48841235\/bioinformatics_22_7_830.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,24]],"date-time":"2023-01-24T09:49:21Z","timestamp":1674553761000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/22\/7\/830\/202161"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006,1,12]]},"references-count":30,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2006,4,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btk048","relation":{},"ISSN":["1367-4811","1367-4803"],"issn-type":[{"value":"1367-4811","type":"electronic"},{"value":"1367-4803","type":"print"}],"subject":[],"published-other":{"date-parts":[[2006,4,1]]},"published":{"date-parts":[[2006,1,12]]}}}