Research
Our research is driven by the question: How do we optimally apply computational statistics and machine learning to big biological data to produce actionable insights and predictions? Our work on this question involves core research projects, management and analysis of big biological data, and development of new analysis methods and associated algorithms. Our core research projects fall within four major areas: (1) Genome Variation - where our published work includes papers on inferring relatedness, whole-genome analysis of human migration, and analysis of genome admixture, (2) Statistical Genetics - where our published work includes papers on association analysis of phenotypes ranging from molecular (including expression quantitative trait loci (eQTL) and related), to complex diseases (including pedigree analysis, genome-wide association studies (GWAS), and analysis of rare diseases), (3) Network Discovery - where our published work includes papers on causal modeling and network analysis of mixed genomic data types, (4) Disease Risk Prediction - where our published work includes papers on behavioral and environmental biomarkers, identification of disease subtypes, polygenic risk scores (PRS), and clinical predictors of cancer risk.
Current Projects:
- Phylogenetic methods for microbiome analysis
- Improving polygenic risk scores
- Multi-omics cancer detection diagnostics
- Image biomarkers of disease severity
- Data mining electronic health records
Bio
Professor Mezey received his undergraduate degree from the University of Pennsylvania, his PhD from Yale University, and he has been at Cornell University since 2006 and at Weill Cornell Medicine since 2009. He was awarded lifetime tenure in 2011 and was promoted to Full Professor in 2018 at Cornell in the Department of Biological Statistics and Computational Biology (now the Department of Computational Biology) and to Full Professor at Weill Cornell Medicine in both the Department of Genetic Medicine and in the Institute for Computational Biomedicine.
Distinctions:
- Genetics Pre-Doctoral Training Grant - National Institutes of Health
- University Fellowship – Yale University
- David Phillips Fellowship – United Kingdom
- Director of the Graduate Field of Computational Biology (2014-2020)
- Affiliate Member – New York Genome Center
Selected Publications:
Kulm S., Kofman L., Mezey J., Elemento O. 2022. Simple linear cancer risk prediction models with novel features outperform complex approaches. JCO Clinical Cancer Informatics 6:e2100166 PMID: 35239414.
Shafquat A., Crystal R., Mezey J. 2020. Identifying novel associations in GWAS by hierarchical Bayesian latent variable detection of differentially misclassified phenotypes. BMC Bioinformatics 21:178 PMID: 32381021.
Ramstetter, M., Shenoy, S., Dyer T., Lehman D., Curran J., Duggirala, J., Blangero, J., Mezey J. Williams A. 2018. Inferring identical by descent sharing of sample ancestors promotes high resolution relative detection. American Journal of Human Genetics 103: 30-44.
Ju J., Shenoy S., Crystal R. Mezey J. 2017. An independent component analysis confounding factor correction framework for identifying broad impact expression quantitative trait loci. PLoS Computational Biology 13:e1005537 PMID: 28505156.
Rodriguez-Flores J., Fakhro K., Agosto-Perez F., Vincent T., Robay A., Malek J., Suhre K., Chouchane L., Badii R., Al-Marri A., Khalil C., Zirie M., Jayyousi A., Salit J., Clark A., Crystal R., Mezey J. 2016. Indigenous Arabs are descendants of the earliest split from ancient Eurasian populations. Genome Research 26:151-162 PMID: 26728717.