Event Overview
Designing a protein that binds a molecular target with sufficient affinity and selectivity is a core challenge in molecular design, and a known bottleneck in therapeutic development. Classical approaches require high-throughput laboratory systems that physically search through hundreds of thousands of possible binders, a process that can take weeks to months just to find initial candidates.
ESMFold2’s accuracy and speed makes large-scale computational search tractable, screening tens of thousands of candidate designs in days. In our preprint, we use this approach to design and experimentally validate minibinders and antibodies (scFv’s) against five targets central to oncology and immunology: EGFR and PDGFRβ, receptor tyrosine kinases implicated in tumor growth; PD-L1 and CTLA-4, immune checkpoints that cancer cells exploit to evade immune surveillance; and CD45, a regulator of immune cell signaling. Validated designs demonstrated both high affinity and specificity, confirmed by biolayer interferometry and live-cell immunofluorescence, respectively. Cryo-EM confirmed the predicted binding pose of an EGFR minibinder within experimental accuracy. A designed PD-L1 scFv blocked immune checkpoint suppression of T-cell signaling with nanomolar potency.
In this one-hour webinar, the researchers who led this work will walk through the full protocol, the wet lab validation strategy, and updates to the open-source notebook since launch, including speedups and reduced GPU memory requirements. The session closes with a tutorial on how to use our open source protocol on your own targets.
Speakers
Elise Bruguera
Jehan Keval
Robert Verkuil
