YSPH Biostatistics Seminar: “Leveraging Genomic LLMs and Causal Inference to Elucidate Complex Disease Mechanisms"

NOTE: BIS 525 students are required to attend in person. Others are invited to attend in person, but may also attend via Zoom.

SPEAKER: Qiao Liu, PhD, Assistant Professor, Department of Biostatistics, Yale University

TITLE: “Leveraging Genomic LLMs and Causal Inference to Elucidate Complex Disease Mechanisms"

ABSTRACT: Understanding the causal mechanisms of complex diseases requires integrating high-dimensional multi-omics data with advanced computational frameworks. In this talk, I will present how to leverage genomic large language models (LLMs) and causal inference to bridge the gap in identifying underlying causal pathways in complex diseases. First, I introduce EpiGePT, a context-specific genomic LLM capable of imputing and predicting epigenomic features across diverse biological contexts, outperforming existing models in out-of-sample prediction. Then, I will showcase how epiBrainLLM identifies genotype-brain-clinical pathways in Alzheimer’s disease (AD), revealing novel associations between imputed genomic features and various AD phenotypes, including imaging phenotypes and clinical phenotypes. Finally, I present CausalBGM, an AI-powered Bayesian generative modeling framework that enables robust causal effect estimation with the presence of high-dimensional covariates. Together, these methods offer a new paradigm for causal discovery in biomedical research, combining interpretability, predictive accuracy, and uncertainty quantification.

YSPH values inclusion and access for all participants. If you have questions about accessibility or would like to request an accommodation, please contact Charmila Fernandes at Charmila.fernandes@yale.edu. We will try to provide accommodations requested by October 23, 2025.