Sudeep Sarma

DFMDock is a diffusion model for protein docking that combines generative sampling and energy-based ranking, achieving higher success rates than existing methods.

This paper examines whether diffusion models can extract physics-like energies for protein docking, finding they can recover energy funnels comparable to Rosetta in 9 out of 25 cases.

The paper designs peptides as alternatives to antibodies for detecting protein biomarkers on extracellular vesicles, showing comparable affinity to antibodies.

The paper designs 7-mer peptides that self-assemble into parallel β-sheets using computational screening, simulations, and experimental validation.

The paper develops MHC class I blocking peptides to inhibit CD8+ T cell activation in MASH, reducing inflammation and fibrosis.