Welcome to Precision health intelligence (Phi φ) Lab

Transforming Biomedical Data into Precision Health Intelligence

Rapid advances in biomedical technologies have generated unprecedented volumes of complex data across multiple biological and population scales—from genomic, epigenomic, transcriptomic, and proteomic measurements at the molecular and single cell level, radiomic and imaging data at the organ level, and electronic health records and other phenomic data at the system level.

Unlike traditional datasets, modern biomedical and public health data are often featured by high-dimensionality, complex hierarchical structures, nonlinear interactions, correlated features, population heterogeneity, and platform-specific measurement characteristics. Our Precision health intelligence (Phi φ) lab develops statistical, machine learning, and artificial intelligence methods to addresses these challenges through rigorous and practical methods for omics analysis, multimodal data integration, risk prediction, causal inference, and precision public health.

Our methodological research is closely connected to real-world applications in aging, dementia, neuroscience, addiction, chronic disease, and health disparities. We work with large-scale resources such as the UK Biobank and the All of Us Research Program, as well as emerging single-cell, spatial, imaging, environmental, and clinical datasets. By integrating modern biostatistics with both discriminative and generative AI (including LLM and emerging AI agents), —the Precision health intelligence (Phi φ) lab aims to transform complex biomedical data into actionable public health intelligence, accelerate scientific discovery, improve disease prevention and risk assessment, and advance more precise and equitable public health decision-making.

Our lab has close collaboration with researchers across multiple disciplines (aging, psychiatry, neurology and cancer) from the University of Maryland (SPH, PSYC, NFSC at UMD; MPRC, UMGCCC at UMB) and other institutions. We are actively seeking for new collaborations with researchers both in and out of UMD. 

Please also visit the research group I co-directed with my collaborators at UMB: www.umdbright.com

Selected papers to highlight

Notes: ^: co-first author; *: corresponding author; students underlined; 

AI for Precision and Equitable Public Health, Population Neuroscience and Aging

• Liang M^, Ye Z^, Velma G^, ..., and Ma T*. (2026). Population-Specific Dementia Risk Prediction Using Deep Transfer  Learning in Diverse Populations. npj Digital Medicine. Accepted. preprint on SSRN  (a preliminary version has won the APHS/STATA SCHOLAR AWARD at APHA 2025; Paper selected to present at Gerontological Society of America annual conference 2026.) [Shiny App for Population-specific dementia risk assessment] [Story on Maryland Today]

• Feng L, Ye Z, Pan Y, ..., Chen S* and Ma T*. (2025). Adherence to Life’s Essential 8 is associated with delayed white matter aging. eBioMedicine (Lancet journal), 115. [Story on Maryland Today] [Report on New Scientist]

• Feng L, Ye Z, Du Z, Pan Y, Canada T, Ke H, ..., Shenassa E* and Ma T*. (2025). Association between allostatic load and accelerated white matter brain aging: findings from the UK Biobank. American Journal of Epidemiology, kwae396. 

• Feng L^, Ye Z^, Mo C, Wang J, …, Chen S* and Ma T*. (2023). Elevated blood pressure accelerates white matter brain aging among late middle-aged women: a Mendelian Randomization study in the UK Biobank. Journal of Hypertension, 10-1097. PMID: 37682053. (a preliminary version has won the APHS/STATA SCHOLAR AWARD at APHA 2023)

• Mo C, Wang J, Ye Z, Ke H, ..., Kochunov P, Hong E, Ma T* and Chen S*. (2023). Evaluating the causal effect of tobacco smoking on white matter brain aging: a two-sample Mendelian randomization analysis in UK Biobank. Addiction, 118(4): 739-749. 10.1111/add.16088

Genomic and Multi-omic Intelligence for Biological and Causal Discovery

• Zong W, Rahman T, Zhu L, Zeng X, Zhang Y, Zou J, Liu S, Ren Z, Litman D, Li JJ, Osterreich S, Ma T* and Tseng GC*. (2023). Transcriptomic congruence analysis for evaluating model organisms. Proceedings of the National Academy of Sciences, 120(6). https://doi.org/10.1073/pnas.2202584120. [Story on Maryland Today] [News on Genetic Engineering and Biotechnology (GEN)] [Shiny] [R package]

• Canida T^, Ye Z^, ... Ma T*. (2026). FM-GPT: Bayesian fine mapping for phenome-wide transcriptome-wide association studies. PLOS Genetics. Accepted. [R package] 

• Canida T, Ke H, Chen S, Ye Z and Ma T*. (2025). Multivariate Bayesian variable selection for multi-trait genetic fine mapping. Journal of the Royal Statistical Society: Series C, qlae055. https://arxiv.org/abs/2212.13294 (a preliminary version has been selected as the ICSA student paper honorable mention). [package]

• Wang N, Ye Z and Ma T*. (2024). TIPS: a novel pathway-guided joint model for transcriptome-wide association analysis. Briefings in Bioinformatics, 25 (6), bbae587. [package]

• Ke H, Ren Z, Qi, J, Chen S, Tseng G, Ye Z and Ma T*. (2022). High-dimension to high-dimension screening for detecting genome-wide epigenetic and noncoding RNA regulators of gene expression. Bioinformatics, 38(17): 4078-4087. 10.1093/bioinformatics/btac518. [R package].  

Statistical Intelligence for High-Dimensional Biomedical Data

• Ma T^, Yang F^, Ke H and Ren Z. (2025). Robust Distance Correlation for Variable Screening. Stat. Accepted.    https://arxiv.org/abs/2212.13292 [package]

• Saegusa T, Zhao Z, Ke H, Ye Z, Xu Z, Chen S and Ma T*. (2021). Detecting survival-associated biomarkers from   heterogeneous populations. Scientific Reports, 11(1): 3203.

• • Ma T, Ren Z and Tseng GC. (2020). Variable screening with multiple studies. Statistica Sinica, 30(2): 925-953. https://www.jstor.org/stable/26968963

News

• July, 2026, Congratulations to Mariam for  successfully defending his dissertation. Great job, Mariam ! 

• May 2026, Our paper "Population-Specific Risk Prediction for Alzheimer’s Disease and Related Dementia Using Deep Transfer Learning " has been selected as oral paper presentation at GSA 2026. 

• Nov, 2025, Congratulations to Charles for winning Pitt SPH Early Career Excellence Alumni Award. 

• July, 2025, Congratulations to Zhenyao for winning the APHS/STATA SCHOLAR AWARD at APHA 2025.

• June, 2025, Congratulations to Neng for  successfully defending his dissertation. Great job, Neng ! 

•  April, 2025, Congratulations to Travis for successfully defending his dissertation. Great job, Traivs ! 

• July, 2024, we got our K01 award funded by NIDA to develop new TWAS methods to study the neurogenetic mechanism of nicotine and cannabis addiction.   

• June, 2024, Congratulations to Hongjie for successfully defending his dissertation. Great job, Hongjie ! 

• May, 2024, Congratulations to Travis for being selected as 2024 ICSA Student Paper Honorable Mentions. Well done, Travis !

• Feb, 2024, Congratulations to Cindy for successfully defending her dissertation. She will start her post-doc fellowship at NCI ITEB in July 2024. Great job, Cindy !  

• Nov, 2023, Congratulations to Cindy for winning the APHS/STATA SCHOLAR AWARD at APHA 2023.

• February 2023, we got the Grand Challenge Grant funded by the University of Maryland to study the genetic and lifestyle risk factors of accelerated brain aging (see news and brief summary).

• January 2023, Congratulations to Hongjie Ke for winning Outstanding Graduate Assistant Award for AY 22-23 by the University of Maryland Graduate School (see SPH news).

FUNDING