NVIDIA Launches BioNeMo Agent Toolkit to Bring Agentic AI to Life Sciences R&D
核心洞察
NVIDIA (搜索) announced the BioNeMo Agent Toolkit, providing domain-specific tools enabling AI agents to execute scientific workflows across biology, chemistry, genomics, and drug discovery.
Over 50 leading companies including Lilly (搜索), Schrödinger (搜索), Databricks, and the UW Medicine Institute for Protein Design are adopting the toolkit to accelerate discovery.
The toolkit compresses virtual screening timelines from days to minutes and achieved 2x faster performance on protein design models like RosettaFold3 (搜索).
NVIDIA (搜索) today announced the NVIDIA BioNeMo Agent Toolkit, a comprehensive suite of domain-specific tools and skills designed to usher in what the company calls the "agentic life sciences era." The toolkit enables AI agents, scientists, and laboratories to collaborate by gathering evidence, reasoning across findings, running computational experiments, and recommending next steps to accelerate scientific discovery.
"Frontier models are the brains. BioNeMo is the scientific toolbox. Together, they give AI agents the skills of a PhD research assistant and the speed of a supercomputer," said Jensen Huang, founder and CEO of NVIDIA (搜索). "For the first time, researchers can build AI agents that understand scientific knowledge, use scientific tools and execute scientific workflows. This is a new way to do science — one that can dramatically accelerate discovery across biology, chemistry, genomics and medicine."
A Toolkit Spanning the Life Sciences Spectrum
The BioNeMo Agent Toolkit incorporates more than a decade of NVIDIA (搜索) life sciences libraries, tools, and open models. It includes NVIDIA BioNeMo and is powered by NVIDIA NIM microservices, NVIDIA Parabricks, NVIDIA NeMo, and NVIDIA Nemotron technologies, alongside accelerated computing capabilities. The toolkit provides an open and trusted foundation for agentic life sciences, giving any agent or AI platform the tools needed to synthesize and summarize scientific knowledge, call models, evaluate results, reason, and execute subsequent actions.
Key workflow capabilities enabled by the toolkit include virtual screening, where agents can help researchers identify small-molecule drug candidates by generating and screening compounds, docking them to a target, predicting binding strength, and filtering for drug-like properties — compressing screening timelines from days to minutes. In genomic analysis and target discovery, agents can transform raw sequencing data into prioritized genetic insights and biological targets, with NVIDIA (搜索) Parabricks accelerating alignment and variant calling while genomic foundation models score variant effects.
Additional workflows include protein binder design, deep biomedical research spanning literature review, protocol generation, clinical trial screening, and pharmacovigilance, as well as medical imaging analysis to support biomarker discovery.
Ecosystem-Wide Adoption
More than 50 leading companies are already using the toolkit to advance scientific discovery. Frontier labs and scientific agent builders including Anthropic, OpenAI, Edison Scientific, Lila Sciences, and Owkin are integrating with BioNeMo to help agents move from answering questions to completing scientific work.
Pharmaceutical companies including Lilly (搜索) and Natera are using the toolkit to scale repeatable agentic workflows across discovery, translational research, and clinical insight. Computer-aided drug discovery software providers including Dassault Systèmes, Cadence (OpenEye), and Schrödinger (搜索) are integrating the toolkit's capabilities into scientific applications used across discovery teams.
Scientific data and workflow platforms from Benchling, Certara, Databricks, Snowflake, and Seqera are connecting data systems with AI-powered science through the toolkit. Lab instruments and automation companies including Automata, HighRes, Tecan, Thermo Fisher, and autonomous data generation platform Medra are connecting systems with computational discovery powered by BioNeMo skills.
Accelerating Protein Design
Open model and research organizations including the Arc Institute, the Open Molecular Software Foundation, and the University of Washington's Institute for Protein Design (IPD) are working with NVIDIA (搜索) to advance frontier models and make them more accessible through agent-ready workflows. The IPD collaboration has accelerated runtimes for state-of-the-art biodesign models like RosettaFold3 (搜索), resulting in 2x faster performance than the prior-generation model.
"Every tool we've built for protein design is only as powerful as the scientists who can efficiently access it," said David Baker, professor of biochemistry at the University of Washington School of Medicine and director of the Institute for Protein Design. "The next leap in science won't come from a single discovery; it will come from the speed of iterative designs and agents that can repeatedly reason through the complexity of biology at a speed humans never could."
Economic Context and Availability
NVIDIA (搜索) highlighted that global scientific R&D spending has reached $3.8 trillion, with annual pharmaceutical budgets approaching $300 billion. Agentic workflows, the company argues, can help the industry iterate faster while reducing costs and maximizing the probability of success.
The BioNeMo Agent Toolkit and skills are available now through the NVIDIA (搜索) developer resources page and GitHub. AI clouds and infrastructure companies including Baseten, Modal, and Nebius are using the toolkit to help developers build life sciences workflows as reliable hosted services, supporting BioNeMo skills through scalable APIs, managed compute, and production inference environments.