|Title:||Leveraging Multiple Drug Modalities for Drug Repurposing
|Supervisors:||Kira Radinsky, Benny Kimelfeld, Varda Shalv
|Currently accessibly only within the Technion network|
|Abstract:||Drug repurposing is the process of applying known drugs to treat new diseases. Successful repurposing can reduce costs and time to market as medications have already passed studies of human safety. It is an important task due to the length of time and large cost of novel drug development. In recent years, alongside the growing resources needed for developing new drugs, large biomedical repositories are becoming available as well as the maturing technology for analyzing them. These factors make the task of drug repurposing a relevant and important one.
In this thesis we address the task of drug repurposing using three data modalities: (1) Electronic Health Records collected for over 10 years for over 2 million patients. (2) Biomedical literature consisting of over 28 million publications. (3) The chemical structure of the drug compound. These modalities are complementary as each of them provide different information. Electronic health records hold comprehensive observational data, biomedical literature holds theoretical knowledge and the chemical structure describes the fundamental properties of the drug.
We describe the results obtained from analyzing electronic health records using statistical methods including correlation discovery, propensity score matching and hazard models, regarding the task of drug re-purposing for Hypertension and Type II Diabetes as well as consequent discoveries made regrading the effects of beta-blockers on Parkinson's morbidity. We discuss the challenges in such an analysis and continue to demonstrate how combining literature based knowledge may aid this task. We further employ natural language processing, text and graph embedding methods to build a medical-condition causal graph based on these two repositories. We then demonstrate the use of the chemical structure modality: alone, introducing a multi cycle network architecture for the task of lead optimization, and combined with biomedical literature by demonstrating a drug embedding that combines both modalities. We show this embedding is useful in predicting drug repurposing.
|Copyright||The above paper is copyright by the Technion, Author(s), or others. Please contact the author(s) for more information|
Remark: Any link to this technical report should be to this page (http://www.cs.technion.ac.il/users/wwwb/cgi-bin/tr-info.cgi/2021/PHD/PHD-2021-07), rather than to the URL of the PDF files directly. The latter URLs may change without notice.
To the list of the PHD technical reports of 2021
To the main CS technical reports page
Computer science department, Technion