# Representing Molecules as Random Walks Over Interpretable Grammars

arXiv: https://arxiv.org/abs/2403.08147 · HTML: https://mlsanity.com/paper/2403.08147/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 51 references that are in the map.
- First posted on arXiv 13 Mar 2024.

## Builds on (most cited first, 18 of 18)

- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Strategies for Pre-training Graph Neural Networks](https://mlsanity.com/paper/1905.12265/) (2019)
- [Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models](https://mlsanity.com/paper/1811.12823/) (2018)
- [Hierarchical Generation of Molecular Graphs using Structural Motifs](https://mlsanity.com/paper/2002.03230/) (2020)
- [Equivariant Subgraph Aggregation Networks](https://mlsanity.com/paper/2110.02910/) (2021)
- [Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries](https://mlsanity.com/paper/2206.11140/) (2022)
- [Retro*: Learning Retrosynthetic Planning with Neural Guided A* Search](https://mlsanity.com/paper/2006.15820/) (2020)
- [Molecular Hypergraph Grammar with its Application to Molecular Optimization](https://mlsanity.com/paper/1809.02745/) (2018)
- [Graph Coarsening with Neural Networks](https://mlsanity.com/paper/2102.01350/) (2021)
- [Learning heat diffusion graphs](https://mlsanity.com/paper/1611.01456/) (2016)
- [A Systematic Survey of Chemical Pre-trained Models](https://mlsanity.com/paper/2210.16484/) (2022)
- [Heterogeneous Molecular Graph Neural Networks for Predicting Molecule Properties](https://mlsanity.com/paper/2009.12710/) (2020)
- [Context-enriched molecule representations improve few-shot drug discovery](https://mlsanity.com/paper/2305.09481/) (2023)
- [Graph coarsening: From scientific computing to machine learning](https://mlsanity.com/paper/2106.11863/) (2021)
- [A graph representation of molecular ensembles for polymer property prediction](https://mlsanity.com/paper/2205.08619/) (2022)
- [A Gromov--Wasserstein Geometric View of Spectrum-Preserving Graph Coarsening](https://mlsanity.com/paper/2306.08854/) (2023)
- [Unsupervised Learning of Graph Hierarchical Abstractions with Differentiable Coarsening and Optimal Transport](https://mlsanity.com/paper/1912.11176/) (2019)
- [Polygrammar: Grammar for Digital Polymer Representation and Generation](https://mlsanity.com/paper/2105.05278/) (2021)

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

- [Graph Diffusion Transformers are In-Context Molecular Designers](https://mlsanity.com/paper/2510.08744/) (2025)
- [Procedural Synthesis of Synthesizable Molecules](https://mlsanity.com/paper/2409.05873/) (2024)
- [Graph-structured Small Molecule Drug Discovery Through Deep Learning: Progress, Challenges, and Opportunities](https://mlsanity.com/paper/2502.08975/) (2025)
- [Directed Graph Grammars for Sequence-based Learning](https://mlsanity.com/paper/2505.22949/) (2025)
- [Post Hoc Regression Refinement via Pairwise Rankings](https://mlsanity.com/paper/2508.16495/) (2025)
- [Multi-scale Graph Autoregressive Modeling: Molecular Property Prediction via Next Token Prediction](https://mlsanity.com/paper/2601.02530/) (2026)
- [Higher-Order Molecular Grammars for Generative and Foundation Models in Chemistry](https://mlsanity.com/paper/2610.02186/) (2026)

## Abstract (arXiv)

Recent research in molecular discovery has primarily been devoted to small, drug-like molecules, leaving many similarly important applications in material design without adequate technology. These applications often rely on more complex molecular structures with fewer examples that are carefully designed using known substructures. We propose a data-efficient and interpretable model for representing and reasoning over such molecules in terms of graph grammars that explicitly describe the hierarchical design space featuring motifs to be the design basis. We present a novel representation in the form of random walks over the design space, which facilitates both molecule generation and property prediction. We demonstrate clear advantages over existing methods in terms of performance, efficiency, and synthesizability of predicted molecules, and we provide detailed insights into the method's chemical interpretability.