BayesMendel Lab
The BayesMendel Lab develops sophisticated statistical models and software that identify individuals with elevated cancer risk due to inherited genetic factors, providing them with accurate risk assessments, and better access to detection and prevention strategies.
450 Brookline Ave
Boston, MA 02215
What we do
The BayesMendel Lab specializes in the development of predictive tools—including statistical models and software—related to cancer susceptibility genes, which are genes that can increase a person’s risk of developing cancer.
Based at the Dana-Farber Cancer Institute (DFCI) and the Harvard T.H. Chan School of Public Health and led by Drs. Danielle Braun and Giovanni Parmigiani, the BayesMendel Lab combines two powerful approaches:
- Statistical and machine learning methods that go back to Thomas Bayes and which help analyze probability and uncertainty;
- Genetic inheritance models established by Gregor Mendel, the father of modern genetics.
Our prediction algorithms have been used clinically for about 25 years and contributed to better cancer risk assessment and prevention.
Current Methodological Research
Our methodological research focuses on statistical, computational, and machine-learning challenges that are essential for developing, evaluating, and implementing hereditary cancer risk prediction models. These projects extend the classical Mendelian framework to modern multi-gene, multi-cancer, and clinical settings.
Current areas of research include:
- Accounting for misreporting of family history in Mendelian risk prediction models.
- Developing methods for handling missing or partially observed data, including imputation strategies and evaluating the impact of incomplete data on inference.
- Estimating age-specific penetrance functions using likelihood-based and Bayesian approaches, supported by our dedicated penetrance estimation package.
- Improving statistical methods for meta-analysis of penetrance estimates, allowing integration of evidence across heterogeneous studies and populations.
- Evaluating methods for summarizing mutation prevalence and population-specific carrier frequencies.
- Extending Mendelian models to multiple genes and hereditary cancer syndromes simultaneously, including large gene panels used in clinical sequencing.
- Developing ascertainment-adjusted statistical methods, in collaboration with external methodological groups.
- Enhancing model robustness to data quality issues, including deduplication algorithms and tools for detecting inconsistencies in family history data.
- Developing computational approaches to scale Mendelian models to large numbers of genes, cancers, and risk modifiers.
- Updating and extending existing Mendelian models, including; BRCApro, MMRPRO, PancPro, MelaPro, Fam3PRO, and LFSpro.
Clinical Research and Implementation
In addition to methodological development, the BayesMendel Lab leads multiple clinical and implementation-focused research initiatives aimed at improving cancer risk communication, decision-making, and integration of risk models into clinical care.
Our research activities include:
Randomized controlled trials evaluating risk communication and counseling interventions, such as:
- GETFACTS (decision support during breast cancer surgery),
- PERLA (AI-supported genetic counseling).
Implementation science research, studying how risk prediction models are used in clinics and how they influence patient understanding, behavior, and shared decision-making.
Workflow integration studies, examining how clinicians incorporate decision-support systems into surgical counseling, genetic testing, and follow-up care.
Collaborations with clinicians, genetic counselors, and health systems to assess usability, acceptability, and clinical impact.
Software and User Interfaces
Our lab develops the software tools and computational infrastructure that operationalize our statistical models for clinical and research use.
Current software initiatives include:
- ASK2ME — a clinical decision-support platform providing age-specific cancer risk estimates and management guidelines.
- MyLynch — an interactive patient-facing tool providing personalized risk estimates for Lynch syndrome.
- CBC Risk Tools — software to support counseling on contralateral breast cancer risk.
- R packages and computational engines including Fam3PRO, penetrance, and imputation/simulation frameworks.
- Interactive web applications and Shiny interfaces improving accessibility of Mendelian models for clinicians and researchers.
These tools translate methodological innovations into practical applications used across research, clinics, and patient-facing environments.
What is inherited susceptibility to cancer
Cancer is caused by mutations in our genes. While many of these changes occur during one’s lifetime, some—called germline mutations—are inherited. Genetic research has identified many genes where inherited mutations carry a significantly increased risk of one or more types of cancer. Important examples are the BRCA1 and BRCA2 genes, responsible for the familial breast/ovarian cancer syndrome, and certain mismatch repair genes responsible for familial colorectal cancer.
Most mutations of cancer genes do not determine the fate of an individual. Genetic effects are therefore characterized probabilistically by penetrance functions, that is probability distributions of developing cancer by age, given a specific genetic variant, and prevalence functions, that is frequencies of mutation by population strata.
Identifying individuals at high risk of cancer because of inherited genetic susceptibility, and providing them with reliable assessments of cancer risk, is complex and increasingly important. Probabilistic prediction algorithms that exploit domain knowledge of Mendelian inheritance and other biological characteristics of susceptibility genes have successfully contributed to improved screening, prevention, and genetic testing.