mlsanityData to 7 Oct 2026

3DReact: Geometric deep learning for chemical reactions

arXiv 2312.08307 ↗First posted 13 Dec 2023physics.chem-ph cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Geometric deep learning models, which incorporate the relevant molecular symmetries within the neural network architecture, have considerably improved the accuracy and data efficiency of predictions of molecular properties. Building on this success, we introduce 3DReact, a geometric deep learning model to predict reaction properties from three-dimensional structures of reactants and products. We demonstrate that the invariant version of the model is sufficient for existing reaction datasets. We illustrate its competitive performance on the prediction of activation barriers on the GDB7-22-TS, Cyclo-23-TS and Proparg-21-TS datasets in different atom-mapping regimes. We show that, compared to existing models for reaction property prediction, 3DReact offers a flexible framework that exploits atom-mapping information, if available, as well as geometries of reactants and products (in an invariant or equivariant fashion). Accordingly, it performs systematically well across different datasets, atom-mapping regimes, as well as both interpolation and extrapolation tasks.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 17 of its 107 references that are in the map. First posted on arXiv 13 Dec 2023.

Builds on

17 of 107 references.

References · 17

  1. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,037
  2. 2021E(n) Equivariant Graph Neural Networkscited by 951
  3. 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 701
  4. 2019Analyzing Learned Molecular Representations for Property Predictioncited by 373
  5. 2022DiffDock: Diffusion Steps, Twists, and Turns for Molecular Dockingcited by 307
  6. 2022Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphscited by 258
  7. 2022Learning Local Equivariant Representations for Large-Scale Atomistic Dynamicscited by 254
  8. 2018Molecular Transformer - A Model for Uncertainty-Calibrated Chemical Reaction Predictioncited by 225
  9. 2021SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effectscited by 103
  10. 2018Less is more: sampling chemical space with active learningcited by 80
  11. 2016By-passing the Kohn-Sham equations with machine learningcited by 65
  12. 2020OrbNet: Deep Learning for Quantum Chemistry Using Symmetry-Adapted Atomic-Orbital Featurescited by 63
5 more
  1. 2023Accurate transition state generation with an object-aware equivariant elementary reaction diffusion modelcited by 30
  2. 2023Diffusion-based Generative AI for Exploring Transition States from 2D Molecular Graphscited by 19
  3. 2020Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learningcited by 11
  4. 2020Geometric Prediction: Moving Beyond Scalarscited by 10
  5. 2020Deep Reinforcement Learning of Transition Statescited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 2.

7 papers.

  1. 2025Accurate and scalable exchange-correlation with deep learningcited by 8
  2. 2025Molecular Machine Learning in Chemical Process Designcited by 5
  3. 2025Transferable Learning of Reaction Pathways from Geometric Priorscited by 2
  4. 2026FragmentFlow: Scalable Transition State Generation for Large Moleculescited by 2
  5. 2024A General-Purpose Framework for Chemical Reaction Representation with Atomic Correspondence and Flexible Condition Adaptationcited by 1
  6. 2025The impact of conformer quality on learned representations of molecular conformer ensemblescited by 1
  7. 2026A Cross-Domain Graph Learning Protocol for Single-Step Molecular Geometry Refinementcited by 1