Yang Ni
University of Texas at Austin, TX·Mathematics & Statistics
Deciding what works for whom, whether that means the right drug dose for a patient or what a gene does in a particular cell, requires knowing cause and effect, not just correlation. Most real-world data, however, come from observation rather than controlled experiments.
- Fields
Mathematics & Statistics
Computer Science
Genetics
- Topics
Bayesian statistics
causal inference
unmeasured confounding
- Grants
- 2 known grants, through May 2029
What they work on
- Develop a Bayesian joint model of treatment, outcome, covariates, and hidden confounders that identifies causal effects from observational data without instrumental or proxy variables.
- Build dynamic Bayesian causal models and optimization methods for sequential, continuous-dose decisions, and apply them to kidney transplant data to personalize immunosuppressive dosing.
- Develop a differential zero-inflated negative binomial Bayesian network that maps how cell-type-specific causal gene regulatory networks change between two experimental conditions in single-cell RNA sequencing data.
- Create a trajectory-dependent directed cyclic graph model that captures feedback loops in cell-specific causal networks, and a scalable Bayesian clustering method that detects differences in cell composition and marker genes between groups.
More about the research
This research develops Bayesian statistical methods, which update probabilities as evidence accumulates and report how uncertain the answers are. The methods aim to pull causal conclusions out of complex biomedical data, from hospital records to single-cell measurements.
Why it matters
Reliable personalized decisions from medical records could help doctors tailor medicines like transplant immunosuppressants to lower the risk of organ rejection and harmful side effects. Methods that reveal how disease or treatment rewires gene regulation in individual cells could improve understanding of disease and eventually inform diagnosis, treatment, and prevention.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Peng Liu
Iowa State University, IA·Mathematics & Statistics
Develop functional regression models for imaging outcomes built on a distributed learning framework, so that estimation and inference stay accurate yet scalable for large imaging datasets.
Xinyi Li
Clemson University, SC·Mathematics & Statistics
Develop interpretable statistical learning methods for single-stage individualized treatment rules that combine medical imaging, genomics and clinical variables, with valid uncertainty quantification and statistical inference.
Li-Wei H Lehman
Massachusetts Institute of Technology, MA·Medicine & Clinical Research
Estimate what would happen under different treatment strategies for neuromuscular blockade and steroids in ARDS by emulating target trials in intensive care records, using g-methods that correct for the fact that sicker patients receive more aggressive care.
The school
University of Texas at Austin: 49 labs on PI Pages, $1.1B a year on research, 871 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.