Irina Gaynanova

Formal short Bio

I develop statistical methods to analyse modern high-dimensional biomedical data. My methodological interests are primarily in data integration, machine learning and high-dimensional statistics, motivated by challenges arising in analyses of multi-omics data (e.g. RNASeq, metabolomics, micribiome) and data from wearable devices (continuous glucose monitors, ambulatory blood pressure monitors, activity trackers). I am convinced that challenging applied problems give rise to better statistical methodology, and that better statistical methodology in turn aids scientific discovery. I believe that collaboration plays a key role in achieving this goal and I enjoy working with both domain scientists and methodological researchers. My research has been supported by the National Science Foundation, the National Institutes of Health, and recognized with a David P. Byar Young Investigator Award from the Biometrics section of the American Statistical Association, NSF CAREER Award, IMS Thelma and Marvin Zelen Emerging Women Leaders in Data Science Award and COPSS Emerging Leader Award. If you would like to join the research group, click here to explore available opportunities.

I deeply care about the training of next generation, and put large emphasis on reproducible research practices and computational skills in my teaching. I embrace integration of my research and education missions, and employ a team-based approach to research with active student engagement. My efforts in mentoring undergraduate students have been recognized with Dr. Judith Edmiston Mentoring Award from the Texas A&M College of Science.

Recent news:

• May 2026: Congratulations to Neo Kok on his graduation with MS in Health Data Science!

• March 2026: Our paper with Neo Kok, Walter Williamson and Joyce Lee on “Impact of Missing Data and Monitoring Duration on Downstream Analyses in Continuous Glucose Monitoring” has been accepted to Diabetes Care.

• March 2026: A new manuscript with Junyoung Park on “Fréchet regression of multivariate distributions with nonparanormal transport” is now available on arXiv.

• February 2026: Our paper with Chistopher Girgis, Stephanie Behme, William Herman, Crystal Holmes and Brian Schmidt on “Do Immediate Perioperative Glucose Measurements Predict Outcomes in Non-Elective Pedal Amputation?” has been accepted to Foot & Ankle Specialist.

• February 2026: A new manuscript with Edward Shao, Junyoung Park, Naresh Punjabi and Hui Jiang on “Fast distance computation of multivariate distributions via nonparanormal transport” is now available on arXiv.

• January 2026: Our paper with Lei Wang and Yang Ni on “Truncated Gaussian copula principal component analysis with application to pediatric acute lymphoblastic leukemia patients’ gut microbiome” has been accepted in Statistical Methods in Medical Research

• December 2025: Our paper with Hee Cheol Chung and Yang Ni on “Sparse semiparametric discriminant analysis for high-dimensional zero-inflated data” has been published in Journal of Machine Learning Research

• December 2025: Our paper with Renat Sergazinov and Armeen Taeb on “A spectral method for multi-view subspace learning using the product of projections” has been accepted to Biometrika

• October 2025: Congratulations to Neo Kok for winning a poster award at the 2025 Caswell Diabetes Institute Metabolism, Obesity, Nutrition, & Diabetes Symposium for our work on impact of incomplete CGM data on downstream inference, paper coming soon!

• September 2025: Our paper with Junsouk Choi, Hee Cheol Chung and Yang Ni on “Bayesian segmented Gaussian copula factor model for single-cell sequencing data” has been accepted to Bayesian Analysis

• July 2025: A new manuscript with Leyuan Qian, “Smooth tensor decomposition with application to ambulatory blood pressure monitoring data”, is now available on arXiv. The corresponding R package SmoothHOOI is available from GitHub.

• May 2025: Findings magazine article on AI, featuring School of Public Health faculty, including Irina

• May 2025: Our paper with Alexander Coulter and Rebecca Lee on “fastfrechet: an R package for fast implementation of Frechet regression with distributional responses” has been published in The Journal of Open Source Software. [R package GitHub link]

• April 2025: Our paper with Alexander Coulter, R. Nisha Aurora and Naresh Punjabi on “Fast Variable Selection for Distributional Regression With Application to Continuous Glucose Monitoring Data” has been accepted to the Annals of Applied Statistics

• March 2025: Interview with Irina on Stats Up AI

• March 2025: R package fastfreshet, project lead by Alexander Coulter with tremendous support from Rebecca Lee, is now public and allows you to perform distributional response regression with variable selection super fast! Check it out on GitHub with corresponding short paper fastfrechet: An R package for fast implementation of Fréchet regression with distributional responses on arXiv

• March 2025: A new manuscript with Rakheon Kim, “A sparse linear model for positive definite estimation of covariance matrices”, is now available on arXiv

• March 2025: Irina is selected as one of the recipients of the 2025 COPSS Emerging Leader Award

• Older news