# 3DMolNet: A Generative Network for Molecular Structures

arXiv: https://arxiv.org/abs/2010.06477 · HTML: https://mlsanity.com/paper/2010.06477/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Oct 2020.

## Built on by (most cited first, 19 of 19)

- [Generating 3D Molecules for Target Protein Binding](https://mlsanity.com/paper/2204.09410/) (2022)
- [Inverse design of 3d molecular structures with conditional generative neural networks](https://mlsanity.com/paper/2109.04824/) (2021)
- [Equivariant Energy-Guided SDE for Inverse Molecular Design](https://mlsanity.com/paper/2209.15408/) (2022)
- [MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Design](https://mlsanity.com/paper/2203.14500/) (2022)
- [Learning to design drug-like molecules in three-dimensional space using deep generative models](https://mlsanity.com/paper/2104.08474/) (2021)
- [Learning Joint 2D & 3D Diffusion Models for Complete Molecule Generation](https://mlsanity.com/paper/2305.12347/) (2023)
- [DiffSDS: A language diffusion model for protein backbone inpainting under geometric conditions and constraints](https://mlsanity.com/paper/2301.09642/) (2023)
- [ChemSpaceAL: An Efficient Active Learning Methodology Applied to Protein-Specific Molecular Generation](https://mlsanity.com/paper/2309.05853/) (2023)
- [PrefixMol: Target- and Chemistry-aware Molecule Design via Prefix Embedding](https://mlsanity.com/paper/2302.07120/) (2023)
- [Augmenting Molecular Deep Generative Models with Topological Data Analysis Representations](https://mlsanity.com/paper/2106.04464/) (2021)
- [Text-guided Diffusion Model for 3D Molecule Generation](https://mlsanity.com/paper/2410.03803/) (2024)
- [Learning Invariances with Generalised Input-Convex Neural Networks](https://mlsanity.com/paper/2204.07009/) (2022)
- [3D Molecular Generation via Virtual Dynamics](https://mlsanity.com/paper/2302.05847/) (2023)
- [Learning Conditional Invariance through Cycle Consistency](https://mlsanity.com/paper/2111.13185/) (2021)
- [Tokenizing 3D Molecule Structure with Quantized Spherical Coordinates](https://mlsanity.com/paper/2412.01564/) (2024)
- [Cluster Generation via Deep Energy-Based Model](https://mlsanity.com/paper/2206.09002/) (2022)
- [Long Short-Term Memory to predict 3D Amino acids Positions in GPCR Molecular Dynamics](https://mlsanity.com/paper/2207.05682/) (2022)
- [CardioGenAI: A Machine Learning-Based Framework for Re-Engineering Drugs for Reduced hERG Liability](https://mlsanity.com/paper/2403.07632/) (2024)
- [Energy Loss Functions for Physical Systems](https://mlsanity.com/paper/2511.02087/) (2025)

## Abstract (arXiv)

With the recent advances in machine learning for quantum chemistry, it is now possible to predict the chemical properties of compounds and to generate novel molecules. Existing generative models mostly use a string- or graph-based representation, but the precise three-dimensional coordinates of the atoms are usually not encoded. First attempts in this direction have been proposed, where autoregressive or GAN-based models generate atom coordinates. Those either lack a latent space in the autoregressive setting, such that a smooth exploration of the compound space is not possible, or cannot generalize to varying chemical compositions. We propose a new approach to efficiently generate molecular structures that are not restricted to a fixed size or composition. Our model is based on the variational autoencoder which learns a translation-, rotation-, and permutation-invariant low-dimensional representation of molecules. Our experiments yield a mean reconstruction error below 0.05 Angstrom, outperforming the current state-of-the-art methods by a factor of four, and which is even lower than the spatial quantization error of most chemical descriptors. The compositional and structural validity of newly generated molecules has been confirmed by quantum chemical methods in a set of experiments.