# Learning a Continuous Representation of 3D Molecular Structures with Deep Generative Models

arXiv: https://arxiv.org/abs/2010.08687 · HTML: https://mlsanity.com/paper/2010.08687/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Oct 2020.

## Built on by (most cited first, 24 of 24)

- [Equivariant Diffusion for Molecule Generation in 3D](https://mlsanity.com/paper/2203.17003/) (2022)
- [3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction](https://mlsanity.com/paper/2303.03543/) (2023)
- [A 3D Generative Model for Structure-Based Drug Design](https://mlsanity.com/paper/2203.10446/) (2022)
- [A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems](https://mlsanity.com/paper/2312.07511/) (2023)
- [MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generation](https://mlsanity.com/paper/2305.07508/) (2023)
- [Mixed Continuous and Categorical Flow Matching for 3D De Novo Molecule Generation](https://mlsanity.com/paper/2404.19739/) (2024)
- [3D molecule generation by denoising voxel grids](https://mlsanity.com/paper/2306.07473/) (2023)
- [Learning to design drug-like molecules in three-dimensional space using deep generative models](https://mlsanity.com/paper/2104.08474/) (2021)
- [FlowMol3: Flow Matching for 3D De Novo Small-Molecule Generation](https://mlsanity.com/paper/2508.12629/) (2025)
- [Equivariant Shape-Conditioned Generation of 3D Molecules for Ligand-Based Drug Design](https://mlsanity.com/paper/2210.04893/) (2022)
- [Structure-based drug design by denoising voxel grids](https://mlsanity.com/paper/2405.03961/) (2024)
- [TAGMol: Target-Aware Gradient-guided Molecule Generation](https://mlsanity.com/paper/2406.01650/) (2024)
- [Unified Guidance for Geometry-Conditioned Molecular Generation](https://mlsanity.com/paper/2501.02526/) (2025)
- [E(3)-equivariant models cannot learn chirality: Field-based molecular generation](https://mlsanity.com/paper/2402.15864/) (2024)
- [Sampling 3D Molecular Conformers with Diffusion Transformers](https://mlsanity.com/paper/2506.15378/) (2025)
- [NEBULA: Neural Empirical Bayes Under Latent Representations for Efficient and Controllable Design of Molecular Libraries](https://mlsanity.com/paper/2407.03428/) (2024)
- [ParticleGrid: Enabling Deep Learning using 3D Representation of Materials](https://mlsanity.com/paper/2211.08506/) (2022)
- [Rapid Review of Generative AI in Smart Medical Applications](https://mlsanity.com/paper/2406.06627/) (2024)
- [Do we need equivariant models for molecule generation?](https://mlsanity.com/paper/2507.09753/) (2025)
- [Predictive Feature Caching for Training-free Acceleration of Molecular Geometry Generation](https://mlsanity.com/paper/2510.04646/) (2025)
- [An In-depth Summary of Recent Artificial Intelligence Applications in Drug Design](https://mlsanity.com/paper/2110.05478/) (2021)
- [Pharmacophore-based design by learning on voxel grids](https://mlsanity.com/paper/2512.02031/) (2025)
- [CORDS: Continuous Representations of Discrete Structures](https://mlsanity.com/paper/2601.21583/) (2026)
- [VecMol: Vector-Field Representations for 3D Molecule Generation](https://mlsanity.com/paper/2603.12734/) (2026)

## Abstract (arXiv)

Machine learning in drug discovery has been focused on virtual screening of molecular libraries using discriminative models. Generative models are an entirely different approach that learn to represent and optimize molecules in a continuous latent space. These methods have been increasingly successful at generating two dimensional molecules as SMILES strings and molecular graphs. In this work, we describe deep generative models of three dimensional molecular structures using atomic density grids and a novel fitting algorithm for converting continuous grids to discrete molecular structures. Our models jointly represent drug-like molecules and their conformations in a latent space that can be explored through interpolation. We are also able to sample diverse sets of molecules based on a given input compound and increase the probability of creating valid, drug-like molecules.