Genesis Workbench: A blueprint for industry AI in life sciences, powered by Databricks and NVIDIA

Bringing GPU-accelerated drug discovery to your dataLife sciences leaders need domain-specific, production-ready AI built directly on their own governed data. Together, Databricks and NVIDIA are enabling this shift: by combining Databricks (Unity Catalog governance, MLflow, Model Serving, and serverless GPU compute) with NVIDIA BioNeMo Agent Toolkit, including NVIDIA CUDA-X libraries, Parabricks, and a growing catalog of biology and chemistry models such as Proteina-Complexa, customers can run specialized AI where the data already lives, rather than shipping sensitive data to third-party APIs. This post focuses on one of the hardest applications of that combination: life-sciences R&D and drug discovery - work that can take years and billions in investment, on data that is overwhelmingly unstructured and sensitive, across genomics, transcriptomics, structural biology, and chemistry - disciplines that rarely share a common toolchain. Genesis Workbench is what this looks like in practice.What is Genesis Workbench?Genesis Workbench is an open blueprint for a life-sciences application on Databricks - a modular workbench that brings the major stages of computational drug discovery under one roof, one UI, and one governance model. Each scientific domain is an independently deployable module:Genomics Single Cell Large Molecule Small Molecule NVIDIA BioNeMo model Fine-tuning This platform transforms a standard toolbox into a cohesive scientific workbench. Best of all, the entire environment is easily deployable via a single script. Using a point-and-click UI powered by Databricks Apps, bench scientists can navigate the entire discovery workflow without writing code. The underlying architecture relies on open-source models managed in Unity Catalog, tracked via MLflow, and served on GPU endpoints. By centralizing both public and proprietary datasets with Databricks AI Search, we've entirely eliminated external API dependencies. Ultimately, this seamless setup connects every step of the process—allowing genomics findings to flow effortlessly into single-cell validation, target structure prediction, candidate docking, ADMET, and ranking.How Genesis Workbench accelerates Life Sciences R&DBy bringing every stage of discovery onto one Databricks-native and NVIDIA-accelerated platform, Genesis Workbench directly addresses four problems that have historically kept AI from delivering in life-sciences R&D:AI-Assisted Workflow Generation. Use the workbench declaratively - describe the science you want and get a runnable pipeline, no wiring or boilerplate. This lowers the barrier from "I know how to build this" to "I know what I want", so more scientists can turn ideas into experiments and innovate faster. Vortex is the visual canvas that makes it happen.MCP Support. Genesis Workbench becomes a work horse for the broader AI ecosystem - its models and workflows become tools any agent or MCP client can call, so the platform powers your assistants and pipelines instead of living in a silo. A companion Model Context Protocol (MCP) server exposes it to the Databricks AI Playground, Claude, Cursor, or your own agents; deployed automatically with core.IP risk and security. Sequences, compound libraries, assay results, and patient data are among an organization's most regulated assets. Models and data are downloaded once into Unity Catalog, inference runs on Model Serving endpoints in your own workspace, and there's no runtime external-API dependency - your IP never leaves your governed perimeter.A constantly changing model landscape. Bio-AI moves fast. Genesis Workbench's modular architecture treats every model as an independently deployable sub-module in the same registry-and-serving substrate, so adopting GenMol, Proteina-Complexa, or a newer model is a deploy step - not a rewrite.Fine-tuning. Fine tuning open source models on highly governed, proprietary datasets in your Lakehouse, makes it easy to leverage existing in-house knowledge for faster ideation and candidate discovery.Complex cross-discipline plumbing. Because every module shares one platform, governance model, and job/serving/MLflow substrate, the disciplines connect natively - with in-app handoffs (including gene→sequence resolution) instead of brittle copy-paste between systems. The workbench is the integration layer.Keeping non-computational scientists in the loop. A point-and-click React UI - with interactive 3D viewers and AI-generated, plain-language result interpretations - lets a biologist call variants, simulate a knockout, design a binder, and rank candidates without writing code, while computational colleagues retain full access to the underlying jobs, models, and artifacts with NVIDIA at every stage of the pipeline.At nearly every stage, the heavy lifting is done by NVIDIA accelerated computing and models:Discovery stageNVIDIA technologyWhat it does in Genesis WorkbenchGenomicsParabricksPart of Genomics WorkflowGPU-accelerated germline variant calling and annotation - surfacing pathogenic variants from data in your lakehouseSingle CellRAPIDS-singlecell (part of scverse)Part of Single Cell WorkflowGPU-accelerated clustering, UMAP, and differential expression on large datasets at scale - turning an overnight batch job into interactive explorationSmall MoleculeGenMol (NV-GenMol-89M-v2)Part of Guided Molecule Design workflowGenerates novel, synthesizable molecules from a seed scaffold in a closed generate→score→reseed loop, under hard constraints with optional docking in the rewardLarge MoleculeProteina-ComplexaPart of Enzyme Design WorkflowFlow-matching protein binder design and motif scaffolding (with ProteinMPNN + ESMFold) - from a target structure to ranked, designed binder candidatesVarious StagesBioNeMo RecipesFine-tunes and runs inference with pre-packaged models in BioNeMo container on your data, on your infrastructureThe Future of Genesis WorkbenchLooking ahead, we are focused on making the workbench even more accessible and powerful for scientific discovery. Our roadmap includes:Automated Workflow Generation: We are introducing AI-driven automation to generate complex scientific workflows, making it easier to integrate new models and diverse data sources seamlessly.NVIDIA AI Skills Integration: We are integrating NVIDIA BioNeMo Skills and how BioNeMo Agent Toolkit can enhance the platform's native intelligence and capabilities. More skills will be integrated as they become available.MCP Services: We are planning to add MCP (Model Context Protocol) services to ensure Genesis Workbench can easily provide high-quality data and insights to downstream consuming applications.From disease to candidate, on one governed platformGenesis Workbench empowers scientists to securely drive the entire drug discovery process - from hypothesis to ranked therapeutics - without their data ever leaving the environment. By unifying GPU-accelerated tools like Parabricks, CUDA-X Data Science, Proteina-Complexa, GenMol, and BioNeMo Agent Toolkit under Unity Catalog governance, it provides an intuitive UI built specifically for bench scientists. This powerful in-silico pipeline ensures that only the highest-probability targets advance to the wet lab, dramatically reducing wasted time and resources. This is the promise of industry AI made concrete: bringing specialized, secure AI directly to your data.Ready to accelerate your drug discovery? Deploy Genesis Workbench today from our GitHub repository. We also provide Claude Code skills to assist you with deployments and modifications. We welcome contributions, so feel free to contribute back to the project if you can! If you are already a Databricks customer and interested in a live demo, please talk to your Databricks Account team.Genesis Workbench is an open Databricks Industry Solutions blueprint.

Raccontata dadatabricks.com