Date of Award

1-22-2020

Publication Type

Master Thesis

Degree Name

M.Sc.

Department

Computer Science

Supervisor

Alioune Ngom

Rights

info:eu-repo/semantics/openAccess

Abstract

Pharmaceutical drug development is a complex, time-consuming and expensive process which is also limited to a relatively small number of targets. Drug repositioning is a vital function which involves finding new uses and indications for already approved and existing drugs. It is a cost-effective process in contrast to experimental drug discovery. Previous studies have shown that the network-based method is a versatile platform for drug repositioning as there exists more biological networks which can be used to model interaction between the biological concepts. In this thesis, we are interested in finding the best drugs for one of the most prevailing disease, the Breast Cancer using the existing Protein-protein interaction (PPI) networks. The proposed method is based on the idea that if a perturbation gene expression profile inversely corelates with the disease gene expression profile, the drug may have a curing effect on the disease. Six samples of stroma surrounding invasive breast primary tumours and six matched samples of normal stroma are extracted from the public functional genomics data repository, Gene Expression Omnibus. The perturbation gene expression data corresponding to MCF7 cell line was extracted from the National Institute of Health’s (NIH) Library of Integrated Network-Based Cellular Signatures (LINCS) dataset. Machine Learning techniques are used to select the best suited drug for the breast cancer disease. We have used a ranking algorithm to obtain a ranked list of suitable drug repurposing and repositioning candidates.

Download

Share

COinS