Congratulations to our group member (now alumnus), Tyler Lovelace, for the acceptance of his paper in the journal GigaScience. His paper is entitled “New causal discovery algorithm over censored variables identifies subtype-specific drivers of breast cancer progression” and constitutes one major part of his thesis.
In this important paper, Tyler presents a new causal discovery algorithm that extends previous mixed causal graph learning framework (for continuous and discrete variables) to censored variables. The efficiency of the new method (CausalCoxMGM) ws first evaluated on synthetic data with various levels of censoring and then applied on cardiovascular and breast cancer biological data. Previously, this algorithm had been applied to data from people with COPD to distinguish between factors affecting all-cause vs COPD-specific mortality (Tyler, et al, 2024, eClinicalMedicine).
Paper availability: [journal web site]
Congratulations Tyler!
