Accelerated Computational Drug Discovery

NVIDIA Clara Discovery is a collection of GPU-accelerated and optimized frameworks, tools, applications, and pre-trained models for computational drug discovery. Built to support cross-disciplinary workflows, Clara Discovery helps scientists and researchers get drugs to market faster and enables new possibilities for research into disease mechanisms.  

Powered by deep learning and transformer neural networks.

GPU-enabled deep learning algorithms and transformer models are poised to accelerate every phase of drug discovery. From training large language models (LLMs) that understand chemical space to molecular dynamics simulations, protein structure prediction, and generative drug design, novel deep learning techniques are changing the way scientists explore the ever-expanding chemical universe.

Large Biomolecular Transformer AI Models

Transformer-based large language models work at supercomputing scale with BioNeMo.

Announced at GTC, BioNeMo is an application framework and cloud service built on NVIDIA NeMo Megatron for training and deploying large biomolecular language models at supercomputing scale. BioNeMo comes with pre-trained large language models and is tailored to the language of proteins, DNA, and the simplified molecular-input line-entry system (SMILES).

Introducing MegaMolBART

The training framework for large chemical language models, MegaMoIBART achieves molecule generation at AI-supercomputing scale with high validity and uniqueness.

Accelerate key applications in drug discovery.

Drug discovery spans many workflows, from exploring the chemical universe and predicting protein structures to scanning drug candidates and simulating molecules. Drive breakthroughs in these areas with the powerful tools of Clara Discovery, available in the NVIDIA NGC™ catalog.

Cheminformatics Applications in Drug Discovery

Dive into cheminformatics.

Transformer-based large language models are creating new possibilities for real-time exploration of the chemical universe. BioNeMo is a domain-specific framework for training and deploying biomolecular LLMs at supercomputing scale built on NeMo Megatron. It contains the transformer models MegaMolBART, ESM-1b, and ProtT5. 

MegaMolBART is a generative chemistry model trained on 1.4 billion molecules (SMILES strings) and can be used for a variety of cheminformatics applications in drug discovery such as reaction prediction, molecular optimization, and de novo molecule generation for small molecules. 

ProtT5 and ESM-1b have demonstrated that unsupervised pre-training can be used to generate learned embeddings that contain properties to predict protein structure, function, cellular location, water solubility, membrane-boundness, conserved and variable regions, and more.

Predict protein structures.

Deep learning-based approaches like RELION are powering high-throughput automation of cryogenic electron microscopy (cryo-EM) for protein structure determination. RELION implements an empirical Bayesian approach for analysis of cryo-EM to refine singular or multiple 3D reconstructions as well as 2D class averages.

To understand protein structures with atomistic detail, tools like MELD can be used to infer structures from sparse, ambiguous, or noisy data. MELD harnesses data in a physics-based, Bayesian framework for improved protein structure determination.

Protein Structure Prediction
Virtual Screening

Accelerate virtual screening.

With AI and accelerated computing, millions of drug candidates can be screened against a rigid protein target. AutoDock is a growing collection of methods for computational docking and virtual screening for use in structure-based drug discovery and exploration of the basic mechanisms of biomolecular structure.

Power molecular dynamics simulations.

GPU-powered molecular dynamics frameworks can simulate the fundamental mechanisms of cells and calculate how strongly a candidate drug will bind to its intended protein target. Machine-learned potentials, which show promise for quantum mechanical-level accuracy, energies, and forces, are fundamentally changing molecular simulation.

Clara Discovery includes a variety of tools and frameworks for molecular simulation, including GROMACS, NAMD, Tinker-HP, VMD, TorchANI, and DeePMD-Kit.

GPU-powered molecular dynamics frameworks

Explore accelerated computing solutions

Optimized to power pharma R&D.

Clara Discovery is optimized to run on NVIDIA DGX™ A100, the world’s most advanced AI system delivering five petaFLOPS of performance. Purpose-built for all accelerated computing workloads at scale, DGX A100 provides researchers the fastest time to solution and IT a unified, easy-to-deploy infrastructure to support the next generation of drug discovery.

 View HPC Application Performance  

 View Deep Learning Framework Performance

 Read the Pharma POD Whitepaper

 Learn About Schrodinger’s Advanced Computational Platform

Full Stack Acceleration

Meet the Clara Discovery partners.

Latest Automotive News and Blogs

See All Healthcare News >

Stay up to date with the latest drug discovery news from NVIDIA.