Designing Programmable Biologics with Generative Sequence Models

12th March 2026

Timing : 1 pm ET

Please use this zoom link for joining the webinar

For a list of all talks at the NanoBio seminar series Spring'26, see here


The Chatterjee Lab at the University of Pennsylvania develops generative algorithms to design functional biologics directly from sequence. Our work has centered on protein language models that de novo design peptides to bind and modulate undruggable disease targets, with broad experimental validation across rare neurodegenerative disorders, pediatric cancers, and viral infections. However, because therapeutic design depends not only on binding but also on clinically-viable properties (solubility, half-life, non-toxicity, etc.), we have developed new discrete diffusion modeling algorithms to generate peptides, proteins, mRNAs that are "Pareto-optimal" across these properties. We have extended these frameworks further to discrete flow matching models that generate and refine highly specific, domain- and motif-resolved binders under competing therapeutic objectives, enabling the design of inhibitors and novel CAR T cell ligands. Beyond therapeutics, our generative frameworks have extended to metal sequestrants and environmental toxins for bioremediation applications. Finally, we’ve recently pioneered a new class of generative models, termed Schrödinger Bridges, that not only model biological states but also the trajectories connecting them, from protein folding to cell-state transitions, establishing a unified and programmable framework for molecular design built upon physics and context-aware dynamics.