Spindle footage courtesy of Reza Farhadifar (Flatiron)

Model Predict Control

click to explore

    We develop theory- and physics-guided statistical inference and scientific machine learning techniques for modeling and analyzing noisy, high-dimensional biological datasets.

    Explore Research → Publications
    What We Do

    Research Agenda

    Our lab aims to merge mechanistic biophysical modeling with AI-driven representation learning to create scalable frameworks for modeling, simulating, and controlling biological systems.

    Biophysical & Mathematical Modeling

    Developing theoretical and computational frameworks to uncover the physical principles governing the organization, dynamics, and function of complex biological systems.

    Learn more →

    Statistical Inference & SciML

    Developing principled statistical inference and ML techniques to infer dynamics, mechanisms, and governing laws from noisy, sparse, and high-dimensional data.

    Learn more →

    Applications in Life Sciences & Medicine

    Applying these approaches to build predictive and mechanistic models across scales, from gene regulation and cell-state dynamics to cell-fate decisions and tissue organization during development and disease progression.

    Learn more →
    Updates

    Latest
    from the Lab

    Recent publications, awards, and lab news.

    August 2026
    DSAI Institute Member
    Now a formal member of the Data Science and AI Institute (DSAI) at Johns Hopkins.
    August 2026
    Invited to NITMB Workshop
    Surya Maddu is an invited speaker at the NITMB workshop on spatio-temporal dynamical models, Chicago, March 2027.

    Interested in Joining the Lab?

    We are always looking for curious and motivated PhD students, postdocs, and undergraduates with backgrounds in mathematics, statistics, physics, computer science, or biophysics.

    View Open Positions →