Qiao Liu, PhD
Assistant Professor of BiostatisticsAbout
Research
Overview
- Multiomics Integration: We develop AI‑powered frameworks that integrate genetics, genomics, epigenomics, radiomics, and clinical phenotypes at different scales. We build computational models to predict one modality given another, learn joint distribution, perform conditional inference, etc. Beyond association, our ultimate goal is to identify cross‑modal causal pathways (e.g., how exposures propagate through molecular layers to influence phenotypes).
- Causal Inference: We develop causal inference methodologies tailored for high-dimensional data (e.g., high-dimensional covariates). Our group leverages generative AI models to learn structured representations that preserve underlying causal relationships. These representations enable 1) Identifiability of causal effects in settings with latent confounding. 2) Counterfactual inference to simulate outcomes under hypothetical interventions. 3) Quantification of uncertainty for causal effect estimates, which is critical for robust decision-making in biomedical and healthcare applications.
- Single Cell Genomics: We develop tools powered by generative AI that capture cell heterogeneity, cell state transition, cell-cell/environment communications/response, etc. Current research interests lie in identifying/discovering causal effect/structure to analyze time‑course data, lineage tracing, CRISPR, and small‑molecule perturbation screens. Our models provide insights into gene regulation mechanisms by modeling cell development, transition, response, aging, etc.
- Pharmacogenomics: We develop AI-powered tools to inform precision therapeutics that connect molecular profiles and causal mechanisms to drug response and resistance at both cell‑line and patient levels, which could assist clinical decision‑making.
- Genomic Foundation Models: The human genome sequence can be viewed as a ”genome language” that encodes biological information. Our group develop the core technologies of genomic foundation models to gain deep insights into the complex regulatory syntax in DNA sequences and their functional roles. We focus on context-type aware genome foundation models that could provide insights into context-specific gene regulation.
Medical Research Interests
Artificial Intelligence; Causality; Computational Biology; Data Science; Deep Learning; Epigenomics; Gene Expression Regulation; Generative Artificial Intelligence; Genomics; Machine Learning; Single-Cell Analysis
Public Health Interests
Bioinformatics; Genetics, Genomics, Epigenetics; Modeling; Aging; Bayesian Statistics
Academic Achievements & Community Involvement
News
Get In Touch
Contacts
Email
Academic Office Number
Locations
300 George Street
Academic Office
Ste 501
New Haven, CT 06511