Developing Optimally Discriminative Subnetwork Markers for Predicting Response to Chemotherapy

Molecular profiles of tumour samples have been widely and successfully used for classification problems. Many algorithms have been proposed to predict classes of tumor samples based on expression profiles. However, prediction of response to cancer treatment has proved to be more challenging and novel approaches with improved generalizability are still highly needed. Recent studies have clearly demonstrated the advantages of integrating protein–protein interaction data with gene expression profiles for the development of subnetwork markers in classification problems. We hope to design a novel network-based classification algorithm using color coding technique to identify optimally discriminative subnetwork markers. We hope to provide better and more stable performance compared with other subnetwork and single gene methods. Another issue of designing our subnetwork method is to make it being capable of producing predictive markers that are more reproducible across independent cohorts and offer valuable insight into biological processes underlying response to therapy.

Faculty Supervisor:

Cenk Sahinalp

Student:

Partner:

University of British Columbia

Discipline:

Computer science

Sector:

Manufacturing

University:

Simon Fraser University

Program: