{"id":{"repo_id":"vt","oai_identifier":"oai:vtechworks.lib.vt.edu:10919/33288"},"canonical_url":"https://search.dev.ndltd.org/etd/vt/oai:vtechworks.lib.vt.edu:10919/33288","repository":{"repo_id":"vt","name":"Virginia Tech","base_url":"https://vtechworks.lib.vt.edu/oai/request"},"display":{"title":"Biologically-Interpretable Disease Classification Based on Gene Expression Data","abstract":"Classification of tissues and diseases based on gene expression data is a powerful application of DNA microarrays. Many popular classifiers like support vector machines, nearest-neighbour methods, and boosting have been applied successfully to this problem. However, it is difficult to determine from these classifiers which genes are responsible for the distinctions between the diseases. We propose a novel framework for classification of gene expression data based on notion of condition-specific clusters of co-expressed genes called xMotifs. Our xMotif-based classifier is biologically interpretable: we show how we can detect relationships between xMotifs and gene functional annotations. Our classifier achieves high-accuracy on leave-one-out cross-validation on both two-class and multi-class data. Our technique has the potential to be the method of choice for researchers interested in disease and tissue classification.","abstract_html":"Classification of tissues and diseases based on gene expression data is a powerful application of DNA microarrays. Many popular classifiers like support vector machines, nearest-neighbour methods, and boosting have been applied successfully to this problem. However, it is difficult to determine from these classifiers which genes are responsible for the distinctions between the diseases. We propose a novel framework for classification of gene expression data based on notion of condition-specific clusters of co-expressed genes called xMotifs. Our xMotif-based classifier is biologically interpretable: we show how we can detect relationships between xMotifs and gene functional annotations. Our classifier achieves high-accuracy on leave-one-out cross-validation on both two-class and multi-class data. Our technique has the potential to be the method of choice for researchers interested in disease and tissue classification.","abstract_has_math":false,"creators":["Grothaus, Gregory"],"institution":"Virginia Tech","degree_name":"Master of Science","degree_level":"masters","degree_discipline":"Computer Science","degree_department":"Computer Science","school":null,"contributors":[],"advisors":[],"committee_chairs":["Murali, T. M."],"committee_members":["Choi, Vicky","Onufriev, Alexey V."],"year":2005,"date_issued":"2005-05-13","date_published":"2005-05-13","updated_at":"2026-07-24T05:56:18Z","subjects":["Classification","Biclustering","Gene Expression","Microarrays"],"languages":[],"rights":["In Copyright"],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["etd-05272005-145543"],"render_values":[{"text":"etd-05272005-145543","href":null,"code":true}]}]},"links":{"outbound_url":"http://hdl.handle.net/10919/33288","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeechair","label":"Committee Chair","values":["Murali, T. M."]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Choi, Vicky","Onufriev, Alexey V."]},{"key":"dc:contributor.department","label":"Department","values":["Computer Science"]},{"key":"dc:creator","label":"Author","values":["Grothaus, Gregory"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2014-03-14T20:38:47Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2014-03-14T20:38:47Z","2005-06-14"]},{"key":"dc:date.issued","label":"Date","values":["2005-05-13"]},{"key":"dc:publisher","label":"Institution","values":["Virginia Tech"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Virginia Polytechnic Institute and State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Classification","Biclustering","Gene Expression","Microarrays"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["etd-05272005-145543"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/10919/33288"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Classification of tissues and diseases based on gene expression data is a powerful application of DNA microarrays. Many popular classifiers like support vector machines, nearest-neighbour methods, and boosting have been applied successfully to this problem. However, it is difficult to determine from these classifiers which genes are responsible for the distinctions between the diseases. We propose a novel framework for classification of gene expression data based on notion of condition-specific clusters of co-expressed genes called xMotifs. Our xMotif-based classifier is biologically interpretable: we show how we can detect relationships between xMotifs and gene functional annotations. Our classifier achieves high-accuracy on leave-one-out cross-validation on both two-class and multi-class data. Our technique has the potential to be the method of choice for researchers interested in disease and tissue classification."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Master of Science"]},{"key":"dc:title","label":"Title","values":["Biologically-Interpretable Disease Classification Based on Gene Expression Data"]}]}],"canonical_facts":{"dc:contributor.committeechair":["Murali, T. M."],"dc:contributor.committeemember":["Choi, Vicky","Onufriev, Alexey V."],"dc:contributor.department":["Computer Science"],"dc:creator":["Grothaus, Gregory"],"dc:date.accessioned":["2014-03-14T20:38:47Z"],"dc:date.available":["2014-03-14T20:38:47Z","2005-06-14"],"dc:date.issued":["2005-05-13"],"dc:description.abstract":["Classification of tissues and diseases based on gene expression data is a powerful application of DNA microarrays. Many popular classifiers like support vector machines, nearest-neighbour methods, and boosting have been applied successfully to this problem. However, it is difficult to determine from these classifiers which genes are responsible for the distinctions between the diseases. We propose a novel framework for classification of gene expression data based on notion of condition-specific clusters of co-expressed genes called xMotifs. Our xMotif-based classifier is biologically interpretable: we show how we can detect relationships between xMotifs and gene functional annotations. Our classifier achieves high-accuracy on leave-one-out cross-validation on both two-class and multi-class data. Our technique has the potential to be the method of choice for researchers interested in disease and tissue classification."],"dc:description.degree":["Master of Science"],"dc:identifier.other":["etd-05272005-145543"],"dc:identifier.uri":["http://hdl.handle.net/10919/33288"],"dc:publisher":["Virginia Tech"],"dc:rights":["In Copyright"],"dc:rights.uri":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["Classification","Biclustering","Gene Expression","Microarrays"],"dc:title":["Biologically-Interpretable Disease Classification Based on Gene Expression Data"],"dc:type":["Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["masters"],"thesis:degree_name":["Master of Science"],"thesis:institution_name":["Virginia Polytechnic Institute and State University"]},"updated_at":"2026-07-24T05:56:18Z"}