Date of Award

2014

Publication Type

Master Thesis

Degree Name

M.Sc.

Department

Computer Science

First Advisor

Ngom, Alioune

Rights

info:eu-repo/semantics/openAccess

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Abstract

In silico prediction of drug target interactions has gained its popularity with the growth of publicly available information in chemical and biological sciences. The old paradigm of 'one drug-one target' is quickly becoming outdated. It was smart way of understanding the drug-protein interactions but the biological systems we are dealing with are made up of myriad of proteins exhibiting multiple functions. To analyze and understand these systems as a whole, we require efficient computational models. In this work we have improved a machine learning method by integrating more correlated information about the drug compounds and extend this method to weighted profile method in order to infer novel interactions for drugs and targets with no prior interaction information, which was not possible with the current model. We have evaluated our method using area under the ROC curve and the results obtained show that the proposed model can predict drug target interactions accurately.

Share

COinS