Our lab in BC Cancer Research conducts causal inference research to understand the mechanisms of complex disease development and progression using machine learning and data science. We develop causal inference and machine learning methods widely applicable in single-cell genomics, multi-omics data integration, and statistical genetics research. We apply our computational methods to large regulatory genomics and single-cell transcriptomics data generated by international consortia, such as NIH ENCODE and GTEx, Human Cell Atlas, and Tabula Muris/Sapiens (Chan-Zuckerberg BioHub). We are also privileged to contribute to single-cell data analysis in collaborations locally with the experimental labs at BC Cancer Research Institute, including Dr. Samuel Aparicio, Dr. Poul Sorensen, and Dr. Ramon Klein Geltink.
Our lab is uniquely situated across multiple disciplines: single-cell genomics, statistical genetics, causal inference and machine learning. Through this vantage point, not only do we push forward the frontiers of machine learning research in biology, but our research program also seeks to identify uncharted directions in computational biology research. Our computational research involves reproducible, efficient, and widely-applicable software development. We have rich experience in scientific computing and machine learning before and after the deep learning renaissance. If needed, instead of being confined by existing tools and libraries, our computational team can initiate research from a low-level programming language