Discriminative local subspaces in gene expression data for effective gene function prediction. Puelma, T., Gutierrez, R., & Soto, A. Bioinformatics, 28(17):2256-64, 2012. Paper abstract bibtex 3 downloads Motivation: Massive amounts of genome-wide gene expression data have become available, motivating the development of computatio- nal approaches that leverage this information to predict gene func- tion. Among successful approaches, supervised machine learning methods, such as Support Vector Machines, have shown superior prediction accuracy. However, these methods lack the simple biologi- cal intuition provided by coexpression networks, limiting their practical usefulness. Results: In this work we present Discriminative Local Subspaces (DLS), a novel method that combines supervised machine learning and coexpression techniques with the goal of systematically predict genes involved in specific biological processes of interest. Unlike tra- ditional coexpression networks, DLS uses the knowledge available in Gene Ontology (GO) to generate informative training sets that guide the discovery of expression signatures: expression patterns that are discriminative for genes involved in the biological process of interest. By linking genes coexpressed with these signatures, DLS is able to construct a discriminative coexpression network that links both, known and previously uncharacterized genes, for the selected bio- logical process. This paper focuses on the algorithm behind DLS and shows its predictive power using an Arabidopsis thaliana dataset and a representative set of 101 GO-terms from the Biological Process Ontology. Our results show that DLS has a superior average accuracy than both, Support Vector Machines and Coexpression Networks. Thus, DLS is able to provide the prediction accuracy of supervised learning methods, while maintaining the intuitive understanding of coexpression networks. Availability and Implementation: A MATLAB R implementation of DLS is available at http://virtualplant.bio.puc.cl/ cgi-bin/Lab/tools.cgi.
@Article{ puelma:etal:2012,
author = {T. Puelma and R. Gutierrez and A. Soto},
title = {Discriminative local subspaces in gene expression data for
effective gene function prediction},
journal = {Bioinformatics},
volume = {28},
number = {17},
pages = {2256-64},
year = {2012},
abstract = {Motivation: Massive amounts of genome-wide gene expression
data have become available, motivating the development of
computatio- nal approaches that leverage this information
to predict gene func- tion. Among successful approaches,
supervised machine learning methods, such as Support Vector
Machines, have shown superior prediction accuracy. However,
these methods lack the simple biologi- cal intuition
provided by coexpression networks, limiting their practical
usefulness. Results: In this work we present Discriminative
Local Subspaces (DLS), a novel method that combines
supervised machine learning and coexpression techniques
with the goal of systematically predict genes involved in
specific biological processes of interest. Unlike tra-
ditional coexpression networks, DLS uses the knowledge
available in Gene Ontology (GO) to generate informative
training sets that guide the discovery of expression
signatures: expression patterns that are discriminative for
genes involved in the biological process of interest. By
linking genes coexpressed with these signatures, DLS is
able to construct a discriminative coexpression network
that links both, known and previously uncharacterized
genes, for the selected bio- logical process. This paper
focuses on the algorithm behind DLS and shows its
predictive power using an Arabidopsis thaliana dataset and
a representative set of 101 GO-terms from the Biological
Process Ontology. Our results show that DLS has a superior
average accuracy than both, Support Vector Machines and
Coexpression Networks. Thus, DLS is able to provide the
prediction accuracy of supervised learning methods, while
maintaining the intuitive understanding of coexpression
networks. Availability and Implementation: A MATLAB R
implementation of DLS is available at
http://virtualplant.bio.puc.cl/ cgi-bin/Lab/tools.cgi. },
url = {http://saturno.ing.puc.cl/media/papers_alvaro/DLS_Revised_Paper.pdf}
}
Downloads: 3
{"_id":{"_str":"53427a470e946d920a0018d4"},"__v":1,"authorIDs":["32ZR23o2BFySHbtQK","3ear6KFZSRqbj6YeT","4Pq6KLaQ8jKGXHZWH","54578d9a2abc8e9f370004f0","5e126ca5a4cabfdf01000053","5e158f76f1f31adf01000118","5e16174bf67f7dde010003ad","5e1f631ae8f5ddde010000eb","5e1f7182e8f5ddde010001ff","5e26da3642065ede01000066","5e3acefaf2a00cdf010001c8","5e62c3aecb259cde010000f9","5e65830c6e5f4cf3010000e7","5e666dfc46e828de010002c9","6cMBYieMJhf6Nd58M","6w6sGsxYSK2Quk6yZ","7xDcntrrtC62vkWM5","ARw5ReidxxZii9TTZ","BjzM7QpRCG7uCF7Zf","DQ4JRTTWkvKXtCNCp","GbYBJvxugXMriQwbi","HhRoRmBvwWfD4oLyK","JFk6x26H6LZMoht2n","JvArGGu5qM6EvSCvB","LpqQBhFH3PxepH9KY","MT4TkSGzAp69M3dGt","QFECgvB5v2i4j2Qzs","RKv56Kes3h6FwEa55","Rb9TkQ3KkhGAaNyXq","RdND8NxcJDsyZdkcK","SpKJ5YujbHKZnHc4v","TSRdcx4bbYKqcGbDg","W8ogS2GJa6sQKy26c","WTi3X2fT8dzBN5d8b","WfZbctNQYDBaiYW6n","XZny8xuqwfoxzhBCB","Xk2Q5qedS5MFHvjEW","bbARiTJLYS79ZMFbk","cBxsyeZ37EucQeBYK","cFyFQps7W3Sa2Wope","dGRBfr8zhMmbwK6eP","eRLgwkrEk7T7Lmzmf","fMYSCX8RMZap548vv","g6iKCQCFnJgKYYHaP","h2hTcQYuf2PB3oF8t","h83jBvZYJPJGutQrs","jAtuJBcGhng4Lq2Nd","pMoo2gotJcdDPwfrw","q5Zunk5Y2ruhw5vyq","rzNGhqxkbt2MvGY29","uC8ATA8AfngWpYLBq","vMiJzqEKCsBxBEa3v","vQE6iTPpjxpuLip2Z","wQDRsDjhgpMJDGxWX","wbNg79jvDpzX9zHLK","wk86BgRiooBjy323E","zCbPxKnQGgDHiHMWn","zf9HENjsAzdWLMDAu"],"author_short":["Puelma, T.","Gutierrez, R.","Soto, A."],"bibbaseid":"puelma-gutierrez-soto-discriminativelocalsubspacesingeneexpressiondataforeffectivegenefunctionprediction-2012","bibdata":{"bibtype":"article","type":"article","author":[{"firstnames":["T."],"propositions":[],"lastnames":["Puelma"],"suffixes":[]},{"firstnames":["R."],"propositions":[],"lastnames":["Gutierrez"],"suffixes":[]},{"firstnames":["A."],"propositions":[],"lastnames":["Soto"],"suffixes":[]}],"title":"Discriminative local subspaces in gene expression data for effective gene function prediction","journal":"Bioinformatics","volume":"28","number":"17","pages":"2256-64","year":"2012","abstract":"Motivation: Massive amounts of genome-wide gene expression data have become available, motivating the development of computatio- nal approaches that leverage this information to predict gene func- tion. Among successful approaches, supervised machine learning methods, such as Support Vector Machines, have shown superior prediction accuracy. However, these methods lack the simple biologi- cal intuition provided by coexpression networks, limiting their practical usefulness. Results: In this work we present Discriminative Local Subspaces (DLS), a novel method that combines supervised machine learning and coexpression techniques with the goal of systematically predict genes involved in specific biological processes of interest. Unlike tra- ditional coexpression networks, DLS uses the knowledge available in Gene Ontology (GO) to generate informative training sets that guide the discovery of expression signatures: expression patterns that are discriminative for genes involved in the biological process of interest. By linking genes coexpressed with these signatures, DLS is able to construct a discriminative coexpression network that links both, known and previously uncharacterized genes, for the selected bio- logical process. This paper focuses on the algorithm behind DLS and shows its predictive power using an Arabidopsis thaliana dataset and a representative set of 101 GO-terms from the Biological Process Ontology. Our results show that DLS has a superior average accuracy than both, Support Vector Machines and Coexpression Networks. Thus, DLS is able to provide the prediction accuracy of supervised learning methods, while maintaining the intuitive understanding of coexpression networks. Availability and Implementation: A MATLAB R implementation of DLS is available at http://virtualplant.bio.puc.cl/ cgi-bin/Lab/tools.cgi. ","url":"http://saturno.ing.puc.cl/media/papers_alvaro/DLS_Revised_Paper.pdf","bibtex":"@Article{\t puelma:etal:2012,\n author\t= {T. Puelma and R. Gutierrez and A. Soto},\n title\t\t= {Discriminative local subspaces in gene expression data for\n\t\t effective gene function prediction},\n journal\t= {Bioinformatics},\n volume\t= {28},\n number\t= {17},\n pages\t\t= {2256-64},\n year\t\t= {2012},\n abstract\t= {Motivation: Massive amounts of genome-wide gene expression\n\t\t data have become available, motivating the development of\n\t\t computatio- nal approaches that leverage this information\n\t\t to predict gene func- tion. Among successful approaches,\n\t\t supervised machine learning methods, such as Support Vector\n\t\t Machines, have shown superior prediction accuracy. However,\n\t\t these methods lack the simple biologi- cal intuition\n\t\t provided by coexpression networks, limiting their practical\n\t\t usefulness. Results: In this work we present Discriminative\n\t\t Local Subspaces (DLS), a novel method that combines\n\t\t supervised machine learning and coexpression techniques\n\t\t with the goal of systematically predict genes involved in\n\t\t specific biological processes of interest. Unlike tra-\n\t\t ditional coexpression networks, DLS uses the knowledge\n\t\t available in Gene Ontology (GO) to generate informative\n\t\t training sets that guide the discovery of expression\n\t\t signatures: expression patterns that are discriminative for\n\t\t genes involved in the biological process of interest. By\n\t\t linking genes coexpressed with these signatures, DLS is\n\t\t able to construct a discriminative coexpression network\n\t\t that links both, known and previously uncharacterized\n\t\t genes, for the selected bio- logical process. This paper\n\t\t focuses on the algorithm behind DLS and shows its\n\t\t predictive power using an Arabidopsis thaliana dataset and\n\t\t a representative set of 101 GO-terms from the Biological\n\t\t Process Ontology. Our results show that DLS has a superior\n\t\t average accuracy than both, Support Vector Machines and\n\t\t Coexpression Networks. Thus, DLS is able to provide the\n\t\t prediction accuracy of supervised learning methods, while\n\t\t maintaining the intuitive understanding of coexpression\n\t\t networks. Availability and Implementation: A MATLAB R\n\t\t implementation of DLS is available at\n\t\t http://virtualplant.bio.puc.cl/ cgi-bin/Lab/tools.cgi. },\n url\t\t= {http://saturno.ing.puc.cl/media/papers_alvaro/DLS_Revised_Paper.pdf}\n}\n\n","author_short":["Puelma, T.","Gutierrez, R.","Soto, A."],"key":"puelma:etal:2012","id":"puelma:etal:2012","bibbaseid":"puelma-gutierrez-soto-discriminativelocalsubspacesingeneexpressiondataforeffectivegenefunctionprediction-2012","role":"author","urls":{"Paper":"http://saturno.ing.puc.cl/media/papers_alvaro/DLS_Revised_Paper.pdf"},"metadata":{"authorlinks":{"soto, a":"https://asoto.ing.puc.cl/publications/"}},"downloads":3},"bibtype":"article","biburl":"https://raw.githubusercontent.com/ialab-puc/ialab.ing.puc.cl/master/pubs.bib","downloads":3,"keywords":[],"search_terms":["discriminative","local","subspaces","gene","expression","data","effective","gene","function","prediction","puelma","gutierrez","soto"],"title":"Discriminative local subspaces in gene expression data for effective gene function prediction","year":2012,"dataSources":["3YPRCmmijLqF4qHXd","sg6yZ29Z2xB5xP79R","sj4fjnZAPkEeYdZqL","m8qFBfFbjk9qWjcmJ","QjT2DEZoWmQYxjHXS"]}