In this talk, I present recent work on causal generative modelling in the context of single-cell genomics. I begin by reviewing some of the key causal questions in biology and exploring how machine learning can address them, highlighting current challenges, limitations, and opportunities for methodological innovation. I then introduce my methods designed to disentangle biological signal from noise, enhancing model interpretability and causal relevance. These approaches support patient stratification and the discovery of disease-specific biomarkers. I finish my talk by presenting some of the ongoing projects in my lab.
Link to join virtually: https://cam-ac-uk.zoom.us/j/89473073451
This talk is being recorded. Any questions asked will also be included in the recording. The recording will be made available on the Department’s webpage
