Screening for small molecules in drug discovery faces several challenges, including the vastness of chemical space, the cost and time associated with experimental screening, and the limitations of traditional methods in exploring novel chemical structures.
Biomolecular generative models and the computational power of GPUs efficiently explore the chemical space, rapidly generating diverse sets of small molecules tailored to specific drug targets or properties. This reduces cost and time by prioritizing candidates most likely to be effective and offering insights into structure-activity relationships. Paired with a molecular docking model and leveraging 3D information from protein structure prediction models, this approach accelerates the end-to-end virtual screening of small molecules.
With NVIDIA’s accelerated computing and AI platform for drug discovery, BioNeMo™, researchers and application developers can:
- Customize and deploy AI models for 3D protein structure prediction, de novo and guided small molecule generation, property prediction, and molecular docking.
- Access pretrained models through NIM APIs for accelerated inference.
- Experience the ultimate flexibility for experimenting and building enterprise-grade generative AI workflows with portable NIM deployments on any cloud or on-premise computing infrastructure.