Machine learning modelling for AI-guided drug response prediction

We are making use of network pharmacology approaches to map target addictions and other dependency mechanisms that underlie individual drug sensitivity profiles, with the aim to identify synergistic drug-target combinations that can effectively inhibit multiple cancer driving sub-clones and other escape routes of cancer cells.

Identification of synthetic lethal interactions and anticancer drug combinations

We are combining pan-cancer genomic and functional profiling efforts to predict co-essential partners of genes that drive cancer growth or treatment resistance, specific targeting of which holds great promise for highly selective and effective means to kill cancer cells without severe side-effects to normal cells.

Mining of clinical and molecular markers predictive of medical outcomes

We are implementing computationally efficient statistical and machine learning models for mining combinations of molecular and clinical features most predictive of individual medical outcomes, such as differences in disease risk or treatment responses, which may eventually provide predictive biomarkers for clinical translation.