We combine the genome and the health record to estimate who is at risk and when, to find the genetic causes of disease, and to learn what actually changes its course.
Three questions, one Bayesian generative model of lifetime disease — Aladynoulli — applied to hundreds of thousands of individuals in the UK Biobank, Mass General Brigham, and All of Us.
Calibrated, individual lifetime risk that combines polygenic scores, monogenic variants, and the clinical record — estimating not just whether disease will come but when, so screening and prevention can be timed to the person.
Sharing strength across conditions, tissues, and time to find what inherited variation does. Genes don't just tilt the odds — they reshape which diseases cluster and when they arrive, for common polygenic risk and rare pathogenic variants alike.
The genome is fixed at birth — a natural experiment upstream of everything in the record. We use genetic anchors to connect drug targets to disease, and individual disease signatures to ask who benefits from which therapy, with negative controls built in.
Priors, posteriors, and borrowing strength — a Bayesian generative model fit at biobank scale, built so that every parameter means something a clinician and a geneticist can both interrogate.
The genome and the longitudinal stream of diagnoses, labs, and timing.
A small set of interpretable disease processes, shared across people and time.
Genetics warps the rate and order in which signatures emerge over a lifetime.
Calibrated trajectories that move to a new health system — the model, not just the weights.
One idea — borrow strength across what looks unrelated, and keep it interpretable — at four scales: tissues, conditions, individuals, time.
Everything is open: the framework, the figures, and the code. Start here whether you want to understand the method, reproduce a result, or build on it.
The essential mental model — how Aladynoulli separates discovering latent disease signatures from predicting an individual's trajectory.
Read the framework ↗The full documentation site: signatures, the Delphi-2M head-to-head, calibration, and the methods behind every figure.
Open the docs ↗Step-by-step notebooks that regenerate the main paper figures from the released outputs — see exactly how each result was made.
Reproduce the paper ↗The model implementation and training pipelines, in PyTorch. Clone it, run it on your cohort, extend it.
View the repository ↗A short teaching primer on Bayesian mixture modeling for genetics — priors, posteriors, and sharing strength across conditions.
Open the primer (PDF) ↗Slides from the Program in Quantitative Genomics seminar: the shape of a disease story, latent signatures, and genetic warping.
View the slides (PDF) ↗Sarah is a physician-scientist who builds parsimonious, interpretable statistical methods to decipher patterns in large-scale genomic and clinical data — working at the seam between statistics and genomics, science and medicine.
Her path runs from a Princeton thesis on adaptive false-discovery methods, through an MD–PhD at the University of Chicago — where, with Matthew Stephens, she developed mash, now a widely used tool for sharing evidence across conditions — to cardiology and the build-out of Aladynoulli. The same idea recurs at every scale she works on: borrow strength across what looks unrelated — tissues, conditions, individuals, time — and never lose the ability to say what each parameter means.
She views probabilistic modeling as a way to narrate the complex patient stories she encounters in the lab and the clinic. An avid cyclist who commutes between MGH, the Broad, and Cambridge — and a loyal, often heartbroken, Chicago White Sox fan.
We welcome students, postdocs, and clinicians interested in Bayesian methods, statistical genetics, and disease prevention. Backgrounds in statistics, computer science, genetics, or medicine are all a good fit.
Generative models, probabilistic machine learning, and scalable inference for large health data.
Bayesian methods, longitudinal and survival data, genetic discovery, and causal inference.
Physicians with quantitative training who want to bring clinical questions to large-scale data.