Site Search
Computer Science

Photos

Xiaobu Yuan, Ph.D.Dr. Xiaobu Yuan
Dr. Xiaobu Yuan
Christie Ezeife, Ph.D.Dr. Christie Ezeife
Dr. Christie Ezeife
Dr. Robert KentDr. Robert Kent
Dr. Robert Kent
Lambton TowerLambton Tower
Lambton Tower
Dr. Luis RuedaDr. Luis Rueda
Dr. Luis Rueda
Jessica Chen, Ph.D.Dr. Jessica Chen
Dr. Jessica Chen
Robin Gras, Ph.D.Dr. Robin Gras
Dr. Robin Gras
Dr. Scott GoodwinDr. Scott Goodwin
Dr. Scott Goodwin
Imran Ahmad, Ph.D.Dr. Imran Ahmad
Dr. Imran Ahmad
Dr. Ziad Kobti lecturingDr. Ziad Kobti
Dr. Ziad Kobti
Arunita Jaekel, Ph.D.Dr. Arunita Jaekel
Dr. Arunita Jaekel
Windsor WaterfrontWindsor Waterfront Park
Windsor Waterfront Park
Alioune Ngom, Ph.D.Dr. Alioune Ngom
Dr. Alioune Ngom

Machine Learning approaches for Drug target interaction prediction

Add this event into your calendar using the iCAL format
  • Thu, 12/14/2017 - 3:00pm - 4:30pm




Machine Learning approaches for Drug target interaction prediction

PhD. Comprehensive Exam by:

Hetal Rahul Rajpura

Date: Thursday, December 14th, 2017
Time: 3:00 9m
Location: Lambton Tower, 3105      

Abstract: In-silico based approaches to drug-target interaction prediction use computational methods as a cheaper and time-effective solution towards the discovery of new drugs / new targets as well as uncover previously unknown drug target interactions. Availability of heterogeneous databases containing comprehensive bio-informatics, chemo-informatics and chemo-genomic data related to drugs, targets and drug target interactions have further fuelled the research for novel predictions to a larger scale.  Biochemical information from potential drug compounds and genomic, transcriptomic, inter-atomic information from potential protein targets can be combined using machine learning approaches to derive new drug-target interactions. Some of the issues as observed in the literature include lack of negative interactions and small sample of positive drug target interactions thereby causing class imbalance. This presentation will cover the current approaches for predicting novel interactions like, similarity based approach, feature vector based approach and the very popular matrix factorization based approach. Also, we shall introduce a recent PU –Learning based approach, which is positive and unknown labelled learning based method to predict new interactions from positive and unknown datasets.

Thesis Committee:    
Internal Reader: Dr Luis Rueda, Dr Mehdi Kargar  
External Reader: Dr Siyaram Pandey
Advisor: Dr Alioune Ngom   



csgradinfo@uwindsor.ca
(519)253-3000


See More: