Databricks brings NVIDIA's RFD4-Proteina protein-design model into Genesis Workbench
Databricks published guidance for deploying NVIDIA's RFD4-Proteina protein-design model through its Genesis Workbench blueprint on Databricks AI Runtime, which provides serverless NVIDIA GPU compute for supported workloads. The company says the planned integration connects model execution with research data, experiment tracking and governance, and that pipelines can be assembled with Genie Code, NVIDIA BioNeMo Agent Toolkit skills and coding-agent assistance. Databricks describes RFD4-Proteina as an NVIDIA BioNeMo open model co-developed with the University of Washington Institute for Protein Design that generates a protein's sequence and full atomic structure together and can be steered toward properties such as thermostability or binding affinity.
The post says the setup lets life sciences teams run protein-design models on their own governed data without moving sensitive IP outside their environment, while noting that laboratory validation remains essential.
BringRFD4-Proteina to your research data with AI-assisted development and serverless NVIDIA GPU compute.
- Get started with day-zero model support through Genesis Workbench, an open example blueprint for life sciences workflows.
- Build and adapt pipelines with Genie Code,NVIDIA BioNeMo Agent Toolkit skills, and coding-agent assistance.
- Use Databricks’ generally available AI Runtime to execute supported GPU workloads alongside enterprise data, experiment tracking, and governance.
RFD4-Proteina, an NVIDIABioNeMo open model co-developed with the University of Washington Institute for Protein Design, helps scientists turn ideas for useful proteins into designs they can test. NVIDIA and Databricks are bringing the model intoGenesis Workbench on AI Runtime, giving developers a path to connect protein-design workflows with their research data.
Databricks AI Runtime (AIR) provides serverless NVIDIA GPU compute for supported workloads. The planned integration connects model execution with research data and repeatable workflows on Databricks, reducing the infrastructure overhead required to evaluate and adapt a new model.
Putting a model to work requires more than downloading weights. Developers need to prepare inputs, connect scientific tools, configure execution, and track results—all while protecting proprietary data. Databricks brings these steps into a shared environment, reducing the need to assemble and maintain a separate research stack.
#Databricks#NVIDIA#RFD4-Proteina#Genesis Workbench#Databricks AI Runtime#NVIDIA BioNeMo#University of Washington Institute for Protein Design#Proteina-Complexa#Genie Code#MLflow#Unity Catalog