Network-based machine learning to discover biomarkers for cancer therapies

Despite enormous progress in research, cancer remains a devastating disease worldwide. Since generally not all patients will respond to a specific therapy, a great challenge in cancer treatment is the ability to predict which patients would benefit (or not) to a therapy of choice. This helps improve treatment efficacy and minimise unnecessary sufferings by non-responders. There is thus a pressing need to identify robust biomarkers (i.e. genes/proteins) that can accurately predict the right patients for the right drugs. With the increasing availability of molecular and drug-response data, machine learning approaches provide a powerful tool for this task. This project will utilise key data science techniques including data processing, integration, analysis and visualisation; and then use these data to develop useful machine-learning frameworks to identify optimal biomarkers for different cancer types. A distinguishing feature of is that we will take advantage of network-based analyses of pharmacogenomics data in order to derive network-based features for the learners, which are expected to boost predictive accuracy. There are several sub-projects with different focus on specific methods to accommodate more than one students. Students will have a unique opportunity to work with real-life biomedical data and contribute towards solving a critical challenge in cancer research in Dr Lan Nguyen’s lab. They will be able to develop their skills in a highly interdisciplinary research group with expertise in both computational & biomedical fields. Experience in Python, R, or MATLAB (or an equivalent language) is essential. There are also potential opportunities to continue to PhD studies