Network Driven Bio-Data Integration and Mining for Bio-Medical Predictions
atmire.migration.oldid | 1189 | |
dc.contributor.advisor | Alhajj, Reda | |
dc.contributor.author | Qabaja, Ala | |
dc.date.accessioned | 2013-07-29T18:19:09Z | |
dc.date.available | 2013-11-12T08:00:17Z | |
dc.date.issued | 2013-07-29 | |
dc.date.submitted | 2013 | en |
dc.description.abstract | Drug repositioning is increasingly attracting much attention from pharmaceutical community to tackle the problem of long term development in drug discovery. The complex nature of human diseases, for example cancer, poses major challenges in pharmaceutical industry nowadays. With the increasing amount of research conducted to understand associations between drugs and diseases, a new direction of research has come to light. Thanks to the development of high-throughput technologies to generate tremendous amount of data and to the web-based systems to store and organize the generated data, drug repositioning has become cost and time effective. Since biomolecular interactions and omics-data integration has had success in drug development, we have been motivated to develop a new paradigm that integrates data from three major sources to predict novel therapeutic drug indications. Microarray data, biomedical text mining data and biomolecular interactions are all integrated to predict ranked lists of genes based on their relevance to a particular drug’s or disease’s molecular action. These ranked lists of genes are used as raw input for building a disease-drug connectivity map based on enrichment statistical measure. This integrative paradigm was able to report a sensitivity improvement of 18% and 26% in comparison with using text-mining and microarray data, respectively, independently. In addition, this paradigm was able to predict many clinically validated disease-drug associations that could not be captured with using microarray or text mining data independently. The robustness of the integrative paradigm has been further investigated to predict functional miRNA-disease associations. In here, disease-gene associations from microarray experiments and text mining together with miRNA-gene associations from computational predictions and protein networks have been integrated to build miRNA-disease associations. The findings of the proposed model were validated against gold standard datasets using ROC analysis and results were promising (AUC = 0.81). The proposed integrated approach allowed us to reconstruct functional associations between miRNAs and human diseases and to uncover functional roles of newly discovered miRNAs | en_US |
dc.identifier.citation | Qabaja, A. (2013). Network Driven Bio-Data Integration and Mining for Bio-Medical Predictions (Master's thesis, University of Calgary, Calgary, Canada). Retrieved from https://prism.ucalgary.ca. doi:10.11575/PRISM/27076 | en_US |
dc.identifier.doi | http://dx.doi.org/10.11575/PRISM/27076 | |
dc.identifier.uri | http://hdl.handle.net/11023/849 | |
dc.language.iso | eng | |
dc.publisher.faculty | Graduate Studies | |
dc.publisher.institution | University of Calgary | en |
dc.publisher.place | Calgary | en |
dc.rights | University of Calgary graduate students retain copyright ownership and moral rights for their thesis. You may use this material in any way that is permitted by the Copyright Act or through licensing that has been assigned to the document. For uses that are not allowable under copyright legislation or licensing, you are required to seek permission. | |
dc.subject | Bioinformatics | |
dc.subject.classification | Drug repositioning | en_US |
dc.subject.classification | pharmaceutical | en_US |
dc.subject.classification | microarray | en_US |
dc.subject.classification | text mining | en_US |
dc.subject.classification | biological networks | en_US |
dc.subject.classification | enrichment analysis | en_US |
dc.subject.classification | data integration | en_US |
dc.subject.classification | Data Mining | en_US |
dc.subject.classification | biological predictions | en_US |
dc.title | Network Driven Bio-Data Integration and Mining for Bio-Medical Predictions | |
dc.type | master thesis | |
thesis.degree.discipline | Computer Science | |
thesis.degree.grantor | University of Calgary | |
thesis.degree.name | Master of Science (MSc) | |
ucalgary.item.requestcopy | true |