{
  "id": 16081831,
  "title": "Nvidia, UW Institute for Protein Design Unveil Open-Source Protein Design AI Model",
  "url": "https://urgent.news/2026/10/22/nvidia-uw-institute-for-protein-design-unveil-open-source-protein",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-22T17:48:12.000Z",
  "source": {
    "name": "GEN Biotechnology",
    "slug": "gen-biotechnology",
    "url": "https://www.genengnews.com/topics/artificial-intelligence/nvidia-uw-institute-for-protein-design-unveil-open-source-protein-design-ai-model/"
  },
  "original_language": "en",
  "account": "Nobel laureate David Baker, director of the UW Medicine Institute for Protein Design (IPD), has teamed up with Nvidia to create an open-source artificial intelligence model called RFD4-Proteina. This model uses biomolecular reasoning to help scientists design new proteins with specific functions more efficiently. RFD4-Proteina, built on Nvidia’s NVIDIA BioNeMo platform, generates targeted protein designs that can be refined with molecular inputs, constraints, and scoring objectives. The model has shown a five-fold to 10-fold improvement in design success rates and can create protein candidates up to 10 times faster than previous models. RFD4-Proteina's developers claim it can explore and prioritize candidates for laboratory testing, enabling researchers to develop new medicines and materials. Baker believes RFD4-Proteina will lead to \"new solutions\" in various fields, including medicine, sustainability, materials, and biotechnology. The model is available through several partners, including Amazon Bio Discovery, Anthropic, Benchling, Databricks, Google Cloud, Hugging Face, Nebius, OpenAI, and Tamarind Bio, allowing researchers and developers to integrate it into their workflows.",
  "summary": "RFD4-Proteina is an open model based on Nvidia’s NVIDIA BioNeMo™ artificial intelligence (AI) platform for chemistry and biology that combines programmable protein design with search capabilities. RFD4-Proteina generates targeted protein designs, enabling scientists and agents to search and refine those designs using molecular inputs, constraints, and scoring objectives. The post Nvidia, UW…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}