Nvidia has announced the NVIDIA BioNeMo Agent Toolkit, which turns complex scientific workflows into agent-executable tasks, including model selection, input preparation, workflow execution, output inspection, and results explanation.
The toolkit includes NVIDIA BioNeMo and is powered by NVIDIA NIM microservices, NVIDIA Parabricks, NVIDIA NeMo, and NVIDIA Nemotron and has applications across protein structure prediction, molecular docking, generative chemistry, genomic analysis, protein design, and biomarker discovery.
“For the first time, researchers can build AI agents that understand scientific knowledge, use scientific tools, and execute scientific workflows,” said Jensen Huang, founder and CEO of Nvidia, in a press release. “This is a new way to do science—one that can dramatically accelerate discovery across biology, chemistry, genomics, and medicine.”
Nvidia has entered collaborations with research organizations, including the Arc Institute, Open Molecular Software Foundation, and the University of Washington’s Institute for Protein Design (IPD). The partnership with IPD has accelerated runtimes for the biomolecular complex prediction tool, RosettaFold3, resulting in two times 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, PhD, professor of biochemistry at the University of Washington and director of the Institute for Protein Design, in a public release. “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.”
The toolkit’s applications include virtual screening, where agents identify promising small-molecule drug candidates by generating compound designs, docking them to a target, predicting binding strength, and filtering for developability properties. The agent can then output which candidates should be prioritized to compress timelines.
In genomic analysis and target discovery, agents can identify genetic insights and biological targets from raw sequencing data. Agents can also connect real-world data to reasoning models for biomedical research, improving the efficiency and accuracy of clinical development processes, including literature review, protocol generation, clinical trial screening, and pharmacovigilance. In medical imaging analysis, agents can process, segment, synthesize, and reason over medical imaging data to support biomarker discovery.
AI-native biology companies, including Boltz, Basecamp Research, Chai Discovery, PerturbAI, Dyno, and Proxima, have collaborated with NVIDIA to develop tools to accelerate therapeutic design workflows. Diagnostics and pharmaceutical companies, including Lilly and Natera, are using BioNeMo Agent Toolkit to scale agentic workflows across discovery, translational research, and clinical insight.
