BriefsWorkflowAvailable now
Nvidia releases the RFD4-Proteina AI model for protein design
Nvidia and the Institute for Protein Design introduce RFD4-Proteina, an AI model and NIM microservice for co-designing protein sequences and all-atom structures.
Summary
Nvidia and the Institute for Protein Design released RFD4-Proteina, an AI model that co-designs protein sequences and all-atom structures. The system uses reward-guided inference-time search with CUDA-accelerated oracles like OpenFold3 to score and refine candidates, delivering faster generation and lower memory use than prior methods. Developers can use the open model on GitHub or access the NIM microservice through an HTTP interface.
What changed
- RFD4-Proteina co-designs protein sequences and all-atom structures using reward-guided inference-time search.
- The model removes the separate inverse-folding handoff by combining explicit backbone coordinates with latent representation.
- Sampling drops from about 400 steps to 60, giving 3.8x faster generation and 84% less peak memory than RFD3 at 200 residues.
- Developers can access the open model on GitHub or deploy the NIM microservice with an HTTP interface.
Availability
Available now“You can access RFD4-Proteina in two ways: - Choose the open model for training, inference, method development, and direct control over sampling code or - Choose the NIM microservice for rapid inference deployment with an HTTP interface”
Founder takeaway
Review the open model repository on GitHub or test the NIM microservice if you build protein generation pipelines.
Source
Researched and drafted with AI from the official sources above, then checked automatically before publishing. Spotted a mistake? Tell us.
Related
More briefs
LangChain open-sources its AI paid media agent
LangChain details the architecture and technical lessons behind its open-source paid media agent that manages advertising campaigns.
LangChain1 min read
Supabase adds Make integration for AI agents and workflows
Connect your Supabase account to Make to let automation workflows and AI agents query databases, read logs, and deploy Edge Functions.
Supabase1 min read
AWS details distributed PyTorch training with Ray Train DLCs and EFA on EKS
AWS published a guide on running distributed PyTorch training on Amazon EKS using Ray Train Deep Learning Containers and Elastic Fabric Adapter.
AWS1 min read
One email, every Monday
Briefs are published here through the day. Monday Heist is the email: one useful AI workflow, the files to use it, and the catch. The first issue is being prepared; subscribers get it first. Free, and you can leave in one click.
One email. Every Monday.