NVIDIA ALCHEMI Accelerates Chemistry and Materials Discovery

NVIDIA has launched new AI-powered tools within its ALCHEMI suite to accelerate chemistry and materials discovery. The NVIDIA Batched Conformer Search (BCS) NIM and NVIDIA Batched Molecular Dynamics (BMD) NIM microservices optimize atomistic simulations, crucial for predicting chemical properties and stability.

Features of ALCHEMI BCS NIM and BMD NIM

The ALCHEMI BCS NIM efficiently identifies and ranks low-energy conformers of molecules using AIMNet2 as a machine learning interatomic potential (MLIP). This reduces the time required to generate low-energy conformers compared to traditional quantum chemistry methods. The BMD NIM facilitates high-throughput molecular dynamics simulations through dynamic batching and GPU-based integrators, supporting various MLIPs like MACE-MPA-0 and TensorNet.

Key Features of BMD NIM

Dynamic batching: Optimizes GPU utilization by dynamically batching atomic systems.
GPU-based integrators: Performs simulations at a constant number of atoms, volume, and temperature (NVT), or a constant number of atoms, pressure, and temperature (NPT).
MLIP support: Supports MACE-MPA-0, TensorNet-MatPES-r2SCAN-v2025.1, TensorNet-MatPES-PBE-v2025.1, AIMNet2, AIMNet2-NSE, and AIMNet2-CPCM.

Real-World Applications

Universal Display Corporation (UDC) is leveraging ALCHEMI BCS and BMD NIM microservices to accelerate OLED molecular discovery, predicting thermal processing stability up to 10,000x faster than traditional density functional theory (DFT). ENEOS has also utilized the NIMs, along with the batched DFT microservice, to discover over 1,000 promising environmentally friendly and non-PFAS immersion cooling fluids in just three weeks.

Conclusion

NVIDIA ALCHEMI’s AI-powered tools are revolutionizing chemistry and materials discovery through advanced simulations and machine learning techniques. These innovations are poised to accelerate scientific breakthroughs and industrial applications.