NVIDIA has long supported life sciences research through its full GPU-accelerated computing stack, which includes hardware, frameworks, libraries, models, microservices, and domain-specific tools. This week, Anthropic announced Claude Science, an AI workbench for science research that allows scientists to interact with agents using natural language to execute their workflows end to end. The platform integrates with NVIDIA BioNeMo Agent Toolkit, which provides scientists with access to NVIDIA-accelerated capabilities as callable skills, enabling the system to select the right tool, prepare valid inputs, and execute workflows while connecting to NVIDIA compute resources deployed anywhere. This integration brings NVIDIA's accelerated models, libraries, and NIM microservices directly into the same environment where most research occurs.
The BioNeMo Agent Toolkit enhances this by offering access to accelerated workflows and models such as Evo 2, Boltz-2, and OpenFold3, allowing analyses that benefit from acceleration to run faster. A scientist begins by describing a research task, such as analyzing a genomic sequence or predicting a protein structure, in natural language. Claude Science interprets the request and orchestrates the work through preconfigured domain-specialized agents that understand established workflows in genomics, proteomics, single-cell analysis, cheminformatics, and clinical research. BioNeMo Agent Toolkit provides these agents with the context needed to connect each step with an appropriate NVIDIA scientific capability. Each skill includes information about its purpose and required inputs, helping agents prepare and execute the workflow and return outputs for review.
NVIDIA BioNeMo Agent Toolkit is open and harness-agnostic, allowing the same scientific skills to work across agent frameworks and research platforms. The toolkit and its skills are available now through NVIDIA developer resources and GitHub. Scientists can access BioNeMo-powered workflows through Anthropic’s Claude Science, which is entering public beta today. As part of the public beta, Anthropic is inviting researchers to provide feedback on additional domain specialists and integrations they need.
Source: nvidia
