mlsanityData to 7 Oct 2026

FeNNol: an Efficient and Flexible Library for Building Force-field-enhanced Neural Network Potentials

arXiv 2405.01491 ↗First posted 2 May 2024physics.chem-ph cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Neural network interatomic potentials (NNPs) have recently proven to be powerful tools to accurately model complex molecular systems while bypassing the high numerical cost of ab-initio molecular dynamics simulations. In recent years, numerous advances in model architectures as well as the development of hybrid models combining machine-learning (ML) with more traditional, physically-motivated, force-field interactions have considerably increased the design space of ML potentials. In this paper, we present FeNNol, a new library for building, training and running force-field-enhanced neural network potentials. It provides a flexible and modular system for building hybrid models, allowing to easily combine state-of-the-art embeddings with ML-parameterized physical interaction terms without the need for explicit programming. Furthermore, FeNNol leverages the automatic differentiation and just-in-time compilation features of the Jax Python library to enable fast evaluation of NNPs, shrinking the performance gap between ML potentials and standard force-fields. This is demonstrated with the popular ANI-2x model reaching simulation speeds nearly on par with the AMOEBA polarizable force-field on commodity GPUs (GPU=Graphics processing unit). We hope that FeNNol will facilitate the development and application of new hybrid NNP architectures for a wide range of molecular simulation problems.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 14 of its 94 references that are in the map. First posted on arXiv 2 May 2024.

Builds on

14 of 94 references.

References · 14

  1. 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 701
  2. 2022Learning Local Equivariant Representations for Large-Scale Atomistic Dynamicscited by 254
  3. 2021SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effectscited by 103
  4. 2022SPICE, A Dataset of Drug-like Molecules and Peptides for Training Machine Learning Potentialscited by 80
  5. 2017Hierarchical modeling of molecular energies using a deep neural networkcited by 37
  6. 2022SchNetPack 2.0: A neural network toolbox for atomistic machine learningcited by 29
  7. 2021Informing Geometric Deep Learning with Electronic Interactions to Accelerate Quantum Chemistrycited by 27
  8. 2019TeaNet: universal neural network interatomic potential inspired by iterative electronic relaxationscited by 16
  9. 2021Gaussian Moments as Physically Inspired Molecular Descriptors for Accurate and Scalable Machine Learning Potentialscited by 15
  10. 2023MLatom 3: Platform for machine learning-enhanced computational chemistry simulations and workflowscited by 10
  11. 2022NNP/MM: Accelerating molecular dynamics simulations with machine learning potentials and molecular mechaniccited by 8
  12. 2020Multi-scale approach for the prediction of atomic scale propertiescited by 3
2 more
  1. 2020End-to-End Differentiable Molecular Mechanics Force Field Constructioncited by 3
  2. 2023Lifelong Machine Learning Potentialscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 2; 2026: 2.

6 papers.

  1. 2024chemtrain: Learning Deep Potential Models via Automatic Differentiation and Statistical Physicscited by 12
  2. 2025Automated Machine Learning Pipeline: Large Language Models-Assisted Automated Dataset Generation for Training Machine-Learned Interatomic Potentialscited by 5
  3. 2025Fast, Modular, and Differentiable Framework for Machine Learning-Enhanced Molecular Simulationscited by 2
  4. 2026Faster Molecular Dynamics with Neural Network Potentials via Distilled Multiple Time-Stepping and Non-Conservative Forcescited by 1
  5. 2024it Asparagus: A Toolkit for Autonomous, User-Guided Construction of Machine-Learned Potential Energy Surfacescited by 0
  6. 2026Enabling Structure-Only Initialization and Out-of-Distribution Generalization in GNN-based Molecular Dynamics Simulatorscited by 0