Our Team

Giovanni Parmigiani is a Professor of Biostatistics in the Department of Biostatistics at the Harvard T.H. Chan School of Public Health. His research focuses on developing statistical models and software for predicting genetic susceptibility to cancer, including risk assessment for breast, ovarian, colorectal, pancreatic, and skin cancers. He also works extensively on statistical methods for high-throughput genomic data, contributing to the analysis of cancer genome sequencing projects and the integration and validation of genomic findings across technologies.
In addition, Professor Parmigiani leads work in comparative effectiveness research, developing comprehensive models of lifetime chronic disease outcomes and advancing Bayesian meta-analysis, Bayesian causal inference, and decision analysis. His methodological interests further include Bayesian modeling and computation, particularly multilevel models, decision-theoretic approaches to inference, and sequential experimental design for adaptive and multistage clinical and epidemiological studies.

Danielle Braun is a Principal Research scientist in the Biostatistics Department at the Harvard T.H. Chan School of Public Health and at the Department of Data Science at Dana-Farber Cancer Institute. Her areas of research include risk prediction, genetic epidemiology, measurement error, survival analysis, frailty models, clinical tool development, causal inference, and environmental health. As a Principal Research Scientist Danielle co-leads the BayesMendel lab and is Director of Data Science for Environmental and Climate Health in the NSAPH group.

Software Contributions

BayesMendel R package: BayesMendel
PanelPRO R package: Fam3PRO
ASK2ME Risk Prediction Tool: ASK2ME
MyLynch: MyLynch
CausalGPS R package: CausalGPS

Sol is a Research Fellow at Harvard University and the Dana-Farber Cancer Institute, working within the BayesMendel Lab in the Department of Data Science. With a background in mathematics and physics, she brings more than ten years of experience in statistics, machine learning, and data science to her research. Her work focuses on developing and applying statistical and machine learning methods for the prediction of genetic mutations and cancer risk.
She has extensive expertise in regression modeling, hypothesis testing, clustering, dimensionality reduction, deep learning, and classification. Sol is a strong interdisciplinary scientist, experienced in collaborating with teams across clinical, biological, and computational fields.

Jintong Zhao is a Biostatistician at the Harvard T.H. Chan School of Public Health and the Dana-Farber Cancer Institute. She works across several clinical and computational research programs, including the development of hereditary cancer risk prediction models in the BayesMendel Lab (Fam3PRO), the analysis of patient-reported outcomes and decision-making in clinical genetics.

Eric Gong is an undergraduate researcher and software developer working at the Dana-Farber Cancer Institute and Harvard University. At Dana-Farber, he develops web applications and API gateways to deploy statistical tools created by DFCI researchers, enabling their use by patients, clinics, and collaborators. His work spans front-end development, backend integration, and bridging computational statistics with accessible clinical tools, using technologies such as R, React.js, and modern web frameworks.

Ben is an undergraduate researcher working on Bayesian and survival-modeling approaches for hereditary cancer risk. His current work focuses on deriving updated age-specific penetrance functions by fitting parametric models to sparse cumulative-risk data and evaluating model behavior across gene–cancer combinations. His broader interests include statistical genomics, hierarchical modeling, and developing interpretable probabilistic tools for clinical genetics.

Koki Takabatake is a medical student at the Boston University Chobanian & Avedisian School of Medicine. At Dana-Farber Cancer Institute, he uses machine learning to study hereditary cancer risk and explores applications of large language models in cancer care and clinical decision-making. He aims to build a career at the intersection of biostatistics, clinical oncology, and epidemiologic research to improve patient outcomes.

Joyce Gong is an undergraduate researcher at Dana-Farber Cancer Institute and the Harvard T.H. Chan School of Public Health. Under the mentorship of Danielle Braun and in collaboration with genetic counselors, she developed TGD CanScreen, a full-stack clinical decision support tool that generates cancer screening recommendations.
Her research interests center on hereditary cancer syndromes, particularly Lynch syndrome, and the ways biostatistical modeling can strengthen risk assessment and screening recommendations to improve patient care.

Shirley Chen was a Master’s student researcher in the BayesMendel Lab from 2023 to 2025 while completing her graduate studies in Computational Biology and Quantitative Genetics at the Harvard T.H. Chan School of Public Health. Her work focused on developing interactive R Shiny applications for hereditary cancer risk modeling, including contributing to updates and feature enhancements for the Fam3PRO Shiny interface.

Nicolas Kubista was a Research Fellow at Harvard University from 2023 to 2025. His work focused on developing machine learning and artificial intelligence methodologies, models, and software for predicting cancer-related risks. He contributed to the design, implementation, and evaluation of computational tools within the BayesMendel framework, integrating statistical modeling with modern AI approaches to advance hereditary cancer risk assessment.