# 3DReact: Geometric deep learning for chemical reactions

arXiv: https://arxiv.org/abs/2312.08307 · HTML: https://mlsanity.com/paper/2312.08307/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 107 references that are in the map.
- First posted on arXiv 13 Dec 2023.

## Builds on (most cited first, 17 of 17)

- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [E(n) Equivariant Graph Neural Networks](https://mlsanity.com/paper/2102.09844/) (2021)
- [E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials](https://mlsanity.com/paper/2101.03164/) (2021)
- [Analyzing Learned Molecular Representations for Property Prediction](https://mlsanity.com/paper/1904.01561/) (2019)
- [DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking](https://mlsanity.com/paper/2210.01776/) (2022)
- [Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs](https://mlsanity.com/paper/2206.11990/) (2022)
- [Learning Local Equivariant Representations for Large-Scale Atomistic Dynamics](https://mlsanity.com/paper/2204.05249/) (2022)
- [Molecular Transformer - A Model for Uncertainty-Calibrated Chemical Reaction Prediction](https://mlsanity.com/paper/1811.02633/) (2018)
- [SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects](https://mlsanity.com/paper/2105.00304/) (2021)
- [Less is more: sampling chemical space with active learning](https://mlsanity.com/paper/1801.09319/) (2018)
- [By-passing the Kohn-Sham equations with machine learning](https://mlsanity.com/paper/1609.02815/) (2016)
- [OrbNet: Deep Learning for Quantum Chemistry Using Symmetry-Adapted Atomic-Orbital Features](https://mlsanity.com/paper/2007.08026/) (2020)
- [Accurate transition state generation with an object-aware equivariant elementary reaction diffusion model](https://mlsanity.com/paper/2304.06174/) (2023)
- [Diffusion-based Generative AI for Exploring Transition States from 2D Molecular Graphs](https://mlsanity.com/paper/2304.12233/) (2023)
- [Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning](https://mlsanity.com/paper/2003.12081/) (2020)
- [Geometric Prediction: Moving Beyond Scalars](https://mlsanity.com/paper/2006.14163/) (2020)
- [Deep Reinforcement Learning of Transition States](https://mlsanity.com/paper/2011.06700/) (2020)

## Built on by (most cited first, 7 of 7)

- [Accurate and scalable exchange-correlation with deep learning](https://mlsanity.com/paper/2506.14665/) (2025)
- [Molecular Machine Learning in Chemical Process Design](https://mlsanity.com/paper/2508.20527/) (2025)
- [Transferable Learning of Reaction Pathways from Geometric Priors](https://mlsanity.com/paper/2504.15370/) (2025)
- [FragmentFlow: Scalable Transition State Generation for Large Molecules](https://mlsanity.com/paper/2602.02310/) (2026)
- [A General-Purpose Framework for Chemical Reaction Representation with Atomic Correspondence and Flexible Condition Adaptation](https://mlsanity.com/paper/2411.17629/) (2024)
- [The impact of conformer quality on learned representations of molecular conformer ensembles](https://mlsanity.com/paper/2502.13220/) (2025)
- [A Cross-Domain Graph Learning Protocol for Single-Step Molecular Geometry Refinement](https://mlsanity.com/paper/2601.22723/) (2026)

## 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.