Visit your regional NVIDIA website for local content, pricing, and where to buy partners specific to your country.
Accelerate drug discovery with NVIDIA Clara™ for Biopharma, a collection of frameworks, applications, generative AI solutions, and pretrained models.
Accelerate breakthrough drug identification and improve the accuracy of target and compound selection.
Keep pace with AI innovation and drive outcomes within your organization.
Improve developer productivity and accelerate time to outcome.
NVIDIA NIM™ Agent Blueprints provide a comprehensive toolkit designed to simplify AI deployment and customization. It includes ready-to-use interactive applications, public datasets for workflow testing, and pretrained models for quick integration. With detailed reference architecture and API definitions, customization tools for modifying and evaluating AI models, and orchestration tools for managing and deploying workflow microservices, the blueprints streamline the entire process of developing, customizing, and deploying AI solutions.
The blueprint starts with AlphaFold2, which predicts the 3D structure of the target protein with high accuracy. The initial small molecules are then passed to MolMIM, which is then used to generate diverse small molecules for exploring chemical space to identify potential binders. These small molecules are evaluated by an Oracle model, which scores them based on predicted binding affinity and other crucial properties. Finally, DiffDock is employed to refine the interactions, predicting the optimal binding poses and enhancing the binding configurations. This integrated blueprint streamlines the identification and optimization of promising drug-like molecules, significantly reducing the time and cost associated with traditional drug discovery methods.
Head to the NVIDIA API catalog to experience BioNeMo with NIM microservices now or go to GitHub to start your deployment.
The blueprint begins with the user passing an amino acid sequence to AlphaFold2, which predicts the initial 3D structure of the target protein. This structural information is then refined and optimized using RFDiffusion, which explores various conformations to identify the most favorable binding configurations. Next, ProteinMPNN generates and optimizes the amino acid sequences according to the RFDiffusion-generated conformational information, ensuring they exhibit the necessary biochemical properties for effective binding. Finally, AlphaFold-Multimer is used to validate the interactions and stability of the resulting protein complexes. This integrated approach enables the precise and efficient design of protein binders, facilitating advancements in therapeutic protein development and other biomedical applications.
NVIDIA NIM offers a set of optimized microservices for AI models used in drug discovery. These prebuilt containers provide state-of-the-art performance and can be deployed anywhere to go from zero to inference in five minutes. Use à la carte NIM microservices to build your own workflow for custom drug discovery workflows.
Predicts the 3D structure of two proteins binding each other.
Predicts the 3D structure of a protein from its amino acid sequence.
Generates protein backbones for protein binder design.
Predicts 3D binding structure of a molecule to a protein.
Performs controlled generation, finding molecules with the right properties.
Predicts amino acid sequences for protein backbones.
Generates embeddings of proteins from their amino acid sequences.
NVIDIA BioNeMo Framework is a collection of ready-made tools for accelerating the design and training of biomolecular AI models for drug discovery. It includes pretrained models, domain-specific workflows, and support for full-stack optimization of your distributed workloads. Download BioNeMo Framework from GitHub or NVIDIA NGC™, and run it on prem or on any cloud provider to quickly get insights from your data to use in your drug discovery research.
NVIDIA AI Enterprise is an end-to-end, cloud-native software platform that accelerates data science pipelines and streamlines the development and deployment of production-grade co-pilots and other generative AI applications.
Using Generative AI to Enhance Biologics Discovery and Development
Drug Discovery Platform Explores Novel Chemical Space with Higher Accuracy
Accelerating Protein Structure Discovery
Fuel Faster Insights for Healthcare and Life Sciences
NVIDIA BioNeMo is a generative AI platform for chemistry and biology. It provides drug discovery researchers and developers a fast and easy way to build and integrate state-of-the-art generative AI applications across the entire drug discovery pipeline, from target identification to lead optimization. The platform offers workflows for 3D protein structure prediction, de novo design, virtual screening, docking, and property prediction.
NVIDIA BioNeMo Framework is a collection of programming tools and libraries that streamline the building and adapting of biomolecular AI models, accelerating the most time-consuming and costly stages of computational drug discovery.
NIM microservices is a set of optimized, easy-to-use, portable microservices designed for biomolecular scientists in drug discovery needing secure, reliable AI model inferencing.
BioNeMo Framework: Users can access BioNeMo Framework in two ways. NVIDIA’s offering for enterprise-grade use of BioNeMo with an NVIDIA AI Enterprise license offers the BioNeMo container via the NVIDIA GPU Cloud, which provides enterprise developers and researchers with a secure, scalable toolchain to build biomolecular workflows. The open-source version of BioNeMo that researchers and data scientists use is available for installation from GitHub, including all of its components.
See the latest list of system requirements for BioNeMo Framework on the NGC Catalog Container page.
See the latest system requirements for NIM microservices at NVIDIA API Documentation.
Please contact us with your question.
Sign up for healthcare news—from exciting product releases to essential news updates.
Got questions? Our healthcare experts are here to assist you!
NVIDIA Privacy Policy