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

2026-01-02

AI Summary

This work addresses the limited generalization of existing machine learning interatomic potentials across the chemical space of drug-like molecules by proposing an efficient force field model based on an enhanced TensorNet2 architecture. The model is the first to comprehensively support all 12 key elements prevalent in medicinal chemistry—including their charged states—within a unified framework, and it is pretrained on a large-scale dataset of drug-like small molecules. It achieves near-DFT accuracy while enabling high-throughput inference. Extensive benchmarking demonstrates consistent and significant improvements over current methods in torsional energy scans, molecular dynamics trajectory prediction, batched geometry optimization, and energy and force prediction, establishing a new state-of-the-art for organic molecular force fields. The model has been publicly released.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Natural Language Processing: (Large) Language Models
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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. 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 forces and anergy accuracy demonstrates that AceFF establishes a new state-of-the-art for organic molecules. The AceFF-2 model weights and inference code are available at https://huggingface.co/Acellera/AceFF-2.0.

Problem

• machine learning interatomic potential
• generalizability
• chemical space
• small molecules
• drug discovery

Innovation

• machine learning interatomic potential
• TensorNet2
• drug discovery
• DFT-level accuracy
• charged states