# Molecular Generation with Recurrent Neural Networks (RNNs)

arXiv: https://arxiv.org/abs/1705.04612 · HTML: https://mlsanity.com/paper/1705.04612/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 May 2017.

## Built on by (most cited first, 30 of 36)

- [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)
- [Geometric Deep Learning on Molecular Representations](https://mlsanity.com/paper/2107.12375/) (2021)
- [DrugAssist: A Large Language Model for Molecule Optimization](https://mlsanity.com/paper/2401.10334/) (2023)
- [Molecule Generation by Principal Subgraph Mining and Assembling](https://mlsanity.com/paper/2106.15098/) (2021)
- [MolCRAFT: Structure-Based Drug Design in Continuous Parameter Space](https://mlsanity.com/paper/2404.12141/) (2024)
- [A Survey on Graph Diffusion Models: Generative AI in Science for Molecule, Protein and Material](https://mlsanity.com/paper/2304.01565/) (2023)
- [Functional-Group-Based Diffusion for Pocket-Specific Molecule Generation and Elaboration](https://mlsanity.com/paper/2306.13769/) (2023)
- [Searching for High-Value Molecules Using Reinforcement Learning and Transformers](https://mlsanity.com/paper/2310.02902/) (2023)
- [Generation of 3D Molecules in Pockets via Language Model](https://mlsanity.com/paper/2305.10133/) (2023)
- [TAGMol: Target-Aware Gradient-guided Molecule Generation](https://mlsanity.com/paper/2406.01650/) (2024)
- [Deep Learning Methods for Small Molecule Drug Discovery: A Survey](https://mlsanity.com/paper/2303.00313/) (2023)
- [Polygrammar: Grammar for Digital Polymer Representation and Generation](https://mlsanity.com/paper/2105.05278/) (2021)
- [ChemSpaceAL: An Efficient Active Learning Methodology Applied to Protein-Specific Molecular Generation](https://mlsanity.com/paper/2309.05853/) (2023)
- [3M-Diffusion: Latent Multi-Modal Diffusion for Language-Guided Molecular Structure Generation](https://mlsanity.com/paper/2403.07179/) (2024)
- [GraphXForm: Graph transformer for computer-aided molecular design](https://mlsanity.com/paper/2411.01667/) (2024)
- [Empower Structure-Based Molecule Optimization with Gradient Guided Bayesian Flow Networks](https://mlsanity.com/paper/2411.13280/) (2024)
- [Faster and more diverse de novo molecular optimization with double-loop reinforcement learning using augmented SMILES](https://mlsanity.com/paper/2210.12458/) (2022)
- [Discovery of structure-property relations for molecules via hypothesis-driven active learning over the chemical space](https://mlsanity.com/paper/2301.02665/) (2023)
- [Automated patent extraction powers generative modeling in focused chemical spaces](https://mlsanity.com/paper/2303.08272/) (2023)
- [GraphGANFed: A Federated Generative Framework for Graph-Structured Molecules Towards Efficient Drug Discovery](https://mlsanity.com/paper/2304.05498/) (2023)
- [3D Molecular Generation via Virtual Dynamics](https://mlsanity.com/paper/2302.05847/) (2023)
- [Rectified Flow For Structure Based Drug Design](https://mlsanity.com/paper/2412.01174/) (2024)
- [Leveraging Partial SMILES Validation Scheme for Enhanced Drug Design in Reinforcement Learning Frameworks](https://mlsanity.com/paper/2505.00530/) (2025)
- [Implementation of The Future of Drug Discovery: QuantumBased Machine Learning Simulation (QMLS)](https://mlsanity.com/paper/2308.08561/) (2023)
- [AUTODIFF: Autoregressive Diffusion Modeling for Structure-based Drug Design](https://mlsanity.com/paper/2404.02003/) (2024)
- [MolSnap: Snap-Fast Molecular Generation with Latent Variational Mean Flow](https://mlsanity.com/paper/2508.05411/) (2025)
- [HelixMO: Sample-Efficient Molecular Optimization in Scene-Sensitive Latent Space](https://mlsanity.com/paper/2112.00905/) (2021)
- [Target specific peptide design using latent space approximate trajectory collector](https://mlsanity.com/paper/2302.01435/) (2023)
- [D3MES: Diffusion Transformer with multihead equivariant self-attention for 3D molecule generation](https://mlsanity.com/paper/2501.07077/) (2025)

## Abstract (arXiv)

The potential number of drug like small molecules is estimated to be between 10^23 and 10^60 while current databases of known compounds are orders of magnitude smaller with approximately 10^8 compounds. This discrepancy has led to an interest in generating virtual libraries using hand crafted chemical rules and fragment based methods to cover a larger area of chemical space and generate chemical libraries for use in in silico drug discovery endeavors. Here it is explored to what extent a recurrent neural network with long short term memory cells can figure out sensible chemical rules and generate synthesizable molecules by being trained on existing compounds encoded as SMILES. The networks can to a high extent generate novel, but chemically sensible molecules. The properties of the molecules are tuned by training on two different datasets consisting of fragment like molecules and drug like molecules. The produced molecules and the training databases have very similar distributions of molar weight, predicted logP, number of hydrogen bond acceptors and donors, number of rotatable bonds and topological polar surface area when compared to their respective training sets. The compounds are for the most cases synthesizable as assessed with SA score and Wiley ChemPlanner.