RFD3

Headlines · 1

1. Oct 21
   NVIDIA tutorial shows RFD4-Proteina protein design with reward-guided search

   NVIDIA's technical blog published a tutorial on designing protein binders with RFD4-Proteina, an NVIDIA BioNeMo open model co-developed with the Institute for Protein Design at the University of Washington's School of Medicine. The model co-designs protein sequences and all-atom structures and uses reward-guided inference-time search to focus compute on the most promising candidates; the walkthrough targets PD-L1 binder candidates for computational biologists, ML engineers and drug discovery researchers. NVIDIA says users can take the open model for training, inference, method development and direct control over sampling code, or a NIM microservice with an HTTP interface, and that RFD4-Proteina is faster and uses less memory than RFD3, while the accompanying manuscript reports state-of-the-art results across a range of molecular tasks.

   NVIDIA Technical Blog · 🔥 0

Experience and discussion from the community

Share my RFD3 experienceAsk about RFD3