NVIDIA | Generative AI Microservices for Virtual Screening @NVIDIA | Uploaded 6 months ago | Updated 22 hours ago
Virtual screening for new medicines is a computationally intractable problem. Existing techniques can only scan billions of compounds and require days on thousands of standard compute nodes. NVIDIA BioNeMo microservices enable a new generative screening paradigm. Using a generated 3D protein structure as a guide, NVIDIA MolMIM generates, optimizes, and screens high-quality candidate molecules in a matter of minutes.
Get Started: www.build.nvidia.com/explore/healthcare
Key Points:
- BioNeMo allows us to build a virtual screening pipeline with microservices: protein folding, molecule generation, and docking.
- MolMIM performs multi-parameter optimization to guide molecule generation.
- MolMIM intertwines physics and generative AI (physics: docking, structure-guided) to guide the generative model.
- BioNeMo's microservices allow us to architect this incredibly powerful application very simply.
#generativeAI #DrugDiscovery #VirtualScreening #GTC24
Virtual screening for new medicines is a computationally intractable problem. Existing techniques can only scan billions of compounds and require days on thousands of standard compute nodes. NVIDIA BioNeMo microservices enable a new generative screening paradigm. Using a generated 3D protein structure as a guide, NVIDIA MolMIM generates, optimizes, and screens high-quality candidate molecules in a matter of minutes.
Get Started: www.build.nvidia.com/explore/healthcare
Key Points:
- BioNeMo allows us to build a virtual screening pipeline with microservices: protein folding, molecule generation, and docking.
- MolMIM performs multi-parameter optimization to guide molecule generation.
- MolMIM intertwines physics and generative AI (physics: docking, structure-guided) to guide the generative model.
- BioNeMo's microservices allow us to architect this incredibly powerful application very simply.
#generativeAI #DrugDiscovery #VirtualScreening #GTC24
