{"id":{"repo_id":"manitoba","oai_identifier":"oai:mspace.lib.umanitoba.ca:1993/33458"},"canonical_url":"https://search.dev.ndltd.org/etd/manitoba/oai:mspace.lib.umanitoba.ca:1993/33458","repository":{"repo_id":"manitoba","name":"University of Manitoba","base_url":"https://mspace.lib.umanitoba.ca/oai/request"},"display":{"title":"Predicting drug - target interaction network using deep learning models for drug repurposing through genetic information","abstract":"It has been well-known that biological and experimental methods for drug discovery are time-consuming and expensive. New efforts have been explored to perform drug repurposing through predicting drug-target interaction networks using biological and chemical properties of drugs and targets. However, due to the high-dimensional nature of the data sets extracted from drugs and targets, which have hundreds of thousands of features and relatively small numbers of samples, traditional machine learning approaches, such as logistic regression analysis, cannot analyze these data efficiently. To overcome this issue, we proposed a deep neural network model compared with logistic regression and LASSO-based regularized linear classification models to predict drug-target interactions, which were used for drug repurposing for inflammatory bowel disease and breast cancer. Experiments showed that the model over performed than traditional logistic regression models and LASSO models. We used the prediction DTIs network for drug repurposing by direct extraction and enrichment analysis in bipartite clustering. Our repurposed candidates have shown some evidences related to IBD and breast cancer.","abstract_html":"It has been well-known that biological and experimental methods for drug discovery are time-consuming and expensive. New efforts have been explored to perform drug repurposing through predicting drug-target interaction networks using biological and chemical properties of drugs and targets. However, due to the high-dimensional nature of the data sets extracted from drugs and targets, which have hundreds of thousands of features and relatively small numbers of samples, traditional machine learning approaches, such as logistic regression analysis, cannot analyze these data efficiently. To overcome this issue, we proposed a deep neural network model compared with logistic regression and LASSO-based regularized linear classification models to predict drug-target interactions, which were used for drug repurposing for inflammatory bowel disease and breast cancer. Experiments showed that the model over performed than traditional logistic regression models and LASSO models. We used the prediction DTIs network for drug repurposing by direct extraction and enrichment analysis in bipartite clustering. Our repurposed candidates have shown some evidences related to IBD and breast cancer.","abstract_has_math":false,"creators":["You, Jiaying"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Hu, Pingzhao (Electrical and Computer Engineering) McLeod, Robert (Electrical and Computer Engineering)"],"committee_chairs":[],"committee_members":[],"year":2018,"date_issued":"2018-09","date_published":"2018-09","updated_at":"2026-07-24T03:02:05Z","subjects":["Drug repurposing, Machine learning, Deep neural network, LASSO"],"languages":["eng"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/1993/33458","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.supervisor","label":"Supervisor","values":["Hu, Pingzhao (Electrical and Computer Engineering) McLeod, Robert (Electrical and Computer Engineering)"]},{"key":"dc:creator","label":"Author","values":["You, Jiaying"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2018-09-21T18:16:47Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2018-09-21T18:16:47Z"]},{"key":"dc:date.issued","label":"Date","values":["2018-09"]},{"key":"dc:type","label":"Dc Type","values":["master thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Drug repurposing, Machine learning, Deep neural network, LASSO"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/1993/33458"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["It has been well-known that biological and experimental methods for drug discovery are time-consuming and expensive. New efforts have been explored to perform drug repurposing through predicting drug-target interaction networks using biological and chemical properties of drugs and targets. However, due to the high-dimensional nature of the data sets extracted from drugs and targets, which have hundreds of thousands of features and relatively small numbers of samples, traditional machine learning approaches, such as logistic regression analysis, cannot analyze these data efficiently. To overcome this issue, we proposed a deep neural network model compared with logistic regression and LASSO-based regularized linear classification models to predict drug-target interactions, which were used for drug repurposing for inflammatory bowel disease and breast cancer. Experiments showed that the model over performed than traditional logistic regression models and LASSO models. We used the prediction DTIs network for drug repurposing by direct extraction and enrichment analysis in bipartite clustering. Our repurposed candidates have shown some evidences related to IBD and breast cancer."]},{"key":"dc:title","label":"Title","values":["Predicting drug - target interaction network using deep learning models for drug repurposing through genetic information"]}]}],"canonical_facts":{"dc:contributor.supervisor":["Hu, Pingzhao (Electrical and Computer Engineering) McLeod, Robert (Electrical and Computer Engineering)"],"dc:creator":["You, Jiaying"],"dc:date.accessioned":["2018-09-21T18:16:47Z"],"dc:date.available":["2018-09-21T18:16:47Z"],"dc:date.issued":["2018-09"],"dc:description.abstract":["It has been well-known that biological and experimental methods for drug discovery are time-consuming and expensive. New efforts have been explored to perform drug repurposing through predicting drug-target interaction networks using biological and chemical properties of drugs and targets. However, due to the high-dimensional nature of the data sets extracted from drugs and targets, which have hundreds of thousands of features and relatively small numbers of samples, traditional machine learning approaches, such as logistic regression analysis, cannot analyze these data efficiently. To overcome this issue, we proposed a deep neural network model compared with logistic regression and LASSO-based regularized linear classification models to predict drug-target interactions, which were used for drug repurposing for inflammatory bowel disease and breast cancer. Experiments showed that the model over performed than traditional logistic regression models and LASSO models. We used the prediction DTIs network for drug repurposing by direct extraction and enrichment analysis in bipartite clustering. Our repurposed candidates have shown some evidences related to IBD and breast cancer."],"dc:identifier.uri":["http://hdl.handle.net/1993/33458"],"dc:language.iso":["eng"],"dc:subject":["Drug repurposing, Machine learning, Deep neural network, LASSO"],"dc:title":["Predicting drug - target interaction network using deep learning models for drug repurposing through genetic information"],"dc:type":["master thesis"]},"updated_at":"2026-07-24T03:02:05Z"}