dc.contributor.author | Wang, Sheng | |
dc.contributor.author | Zhai, ChengXiang | |
dc.contributor.author | Peng, Jian | |
dc.contributor.author | Cho, Hyunghoon | |
dc.contributor.author | Berger Leighton, Bonnie | |
dc.date.accessioned | 2016-10-13T17:54:36Z | |
dc.date.available | 2016-10-13T17:54:36Z | |
dc.date.issued | 2015-06 | |
dc.identifier.issn | 1367-4803 | |
dc.identifier.issn | 1460-2059 | |
dc.identifier.uri | http://hdl.handle.net/1721.1/104798 | |
dc.description.abstract | Motivation: Systematically predicting gene (or protein) function based on molecular interaction networks has become an important tool in refining and enhancing the existing annotation catalogs, such as the Gene Ontology (GO) database. However, functional labels with only a few (<10) annotated genes, which constitute about half of the GO terms in yeast, mouse and human, pose a unique challenge in that any prediction algorithm that independently considers each label faces a paucity of information and thus is prone to capture non-generalizable patterns in the data, resulting in poor predictive performance. There exist a variety of algorithms for function prediction, but none properly address this ‘overfitting’ issue of sparsely annotated functions, or do so in a manner scalable to tens of thousands of functions in the human catalog.
Results: We propose a novel function prediction algorithm, clusDCA, which transfers information between similar functional labels to alleviate the overfitting problem for sparsely annotated functions. Our method is scalable to datasets with a large number of annotations. In a cross-validation experiment in yeast, mouse and human, our method greatly outperformed previous state-of-the-art function prediction algorithms in predicting sparsely annotated functions, without sacrificing the performance on labels with sufficient information. Furthermore, we show that our method can accurately predict genes that will be assigned a functional label that has no known annotations, based only on the ontology graph structure and genes associated with other labels, which further suggests that our method effectively utilizes the similarity between gene functions. | en_US |
dc.description.sponsorship | National Institute of General Medical Sciences (U.S.) (Grant 1U54GM114838) | en_US |
dc.language.iso | en_US | |
dc.publisher | Oxford University Press | en_US |
dc.relation.isversionof | http://dx.doi.org/10.1093/bioinformatics/btv260 | en_US |
dc.rights | Creative Commons Attribution-NonCommercial 4.0 International | en_US |
dc.rights.uri | http://creativecommons.org/licenses/by-nc/4.0/ | en_US |
dc.source | Oxford University Press | en_US |
dc.title | Exploiting ontology graph for predicting sparsely annotated gene function | en_US |
dc.type | Article | en_US |
dc.identifier.citation | Wang, Sheng, Hyunghoon Cho, ChengXiang Zhai, Bonnie Berger, and Jian Peng. “Exploiting Ontology Graph for Predicting Sparsely Annotated Gene Function.” Bioinformatics 31, no. 12 (June 13, 2015): i357–i364. | en_US |
dc.contributor.department | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory | en_US |
dc.contributor.department | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science | en_US |
dc.contributor.department | Massachusetts Institute of Technology. Department of Mathematics | en_US |
dc.contributor.mitauthor | Cho, Hyunghoon | |
dc.contributor.mitauthor | Berger Leighton, Bonnie | |
dc.relation.journal | Bioinformatics | en_US |
dc.eprint.version | Final published version | en_US |
dc.type.uri | http://purl.org/eprint/type/JournalArticle | en_US |
eprint.status | http://purl.org/eprint/status/PeerReviewed | en_US |
dspace.orderedauthors | Wang, Sheng; Cho, Hyunghoon; Zhai, ChengXiang; Berger, Bonnie; Peng, Jian | en_US |
dspace.embargo.terms | N | en_US |
dc.identifier.orcid | https://orcid.org/0000-0002-2713-0150 | |
dc.identifier.orcid | https://orcid.org/0000-0002-2724-7228 | |
mit.license | PUBLISHER_CC | en_US |