AceFF: A State-of-the-Art Machine Learning Potential for Small Molecules

TL;DR

AceFF is a new machine learning potential optimized for small molecules that achieves DFT-level accuracy with high speed, supporting diverse chemical elements and charged states, thus advancing drug discovery applications.

Contribution

Introduces AceFF, a pre-trained MLIP with a refined architecture trained on diverse drug-like molecules, improving accuracy and generalizability for small molecule modeling.

Findings

Achieves DFT-level accuracy in force and energy predictions.

Supports a wide range of medicinal chemistry elements and charged states.

Demonstrates state-of-the-art performance on benchmark tests.

Abstract

We introduce AceFF, a pre-trained machine learning interatomic potential (MLIP) optimized for small molecule drug discovery. While MLIPs have emerged as efficient alternatives to Density Functional Theory (DFT), generalizability across diverse chemical spaces remains difficult. AceFF addresses this via a refined TensorNet2 architecture trained on a comprehensive dataset of drug-like compounds. This approach yields a force field that balances high-throughput inference speed with DFT-level accuracy. \mbox{AceFF} fully supports the essential medicinal chemistry elements (H, B, C, N, O, F, Si, P, S, Cl, Br, I) and is explicitly trained to handle charged states. Validation against rigorous benchmarks, including complex torsional energy scans, molecular dynamics trajectories, batched minimizations, and tests of force and energy accuracy, demonstrates that AceFF is state-of-the-art for organic molecules in the accuracy and speed regime important for drug discovery. The AceFF-2 model weights and inference code are available at https://huggingface.co/Acellera/AceFF-2.0.