# De Novo Molecular Generation via Connection-aware Motif Mining

arXiv: https://arxiv.org/abs/2302.01129 · HTML: https://mlsanity.com/paper/2302.01129/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 54 references that are in the map.
- First posted on arXiv 2 Feb 2023.

## Builds on (most cited first, 26 of 26)

- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Strategies for Pre-training Graph Neural Networks](https://mlsanity.com/paper/1905.12265/) (2019)
- [Automatic chemical design using a data-driven continuous representation of molecules](https://mlsanity.com/paper/1610.02415/) (2016)
- [Junction Tree Variational Autoencoder for Molecular Graph Generation](https://mlsanity.com/paper/1802.04364/) (2018)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining](https://mlsanity.com/paper/2210.10341/) (2022)
- [Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation](https://mlsanity.com/paper/1806.02473/) (2018)
- [GuacaMol: Benchmarking Models for De Novo Molecular Design](https://mlsanity.com/paper/1811.09621/) (2018)
- [Grammar Variational Autoencoder](https://mlsanity.com/paper/1703.01925/) (2017)
- [Hierarchical Generation of Molecular Graphs using Structural Motifs](https://mlsanity.com/paper/2002.03230/) (2020)
- [Fr'echet ChemNet Distance: A metric for generative models for molecules in drug discovery](https://mlsanity.com/paper/1803.09518/) (2018)
- [Constrained Graph Variational Autoencoders for Molecule Design](https://mlsanity.com/paper/1805.09076/) (2018)
- [Motif-based Graph Self-Supervised Learning for Molecular Property Prediction](https://mlsanity.com/paper/2110.00987/) (2021)
- [Multi-Objective De Novo Drug Design with Conditional Graph Generative Model](https://mlsanity.com/paper/1801.07299/) (2018)
- [Learning to Extend Molecular Scaffolds with Structural Motifs](https://mlsanity.com/paper/2103.03864/) (2021)
- [Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation](https://mlsanity.com/paper/2110.01219/) (2021)
- [Guiding Deep Molecular Optimization with Genetic Exploration](https://mlsanity.com/paper/2007.04897/) (2020)
- [Learning Cut Selection for Mixed-Integer Linear Programming via Hierarchical Sequence Model](https://mlsanity.com/paper/2302.00244/) (2023)
- [Data-Efficient Graph Grammar Learning for Molecular Generation](https://mlsanity.com/paper/2203.08031/) (2022)
- [Improving Molecular Design by Stochastic Iterative Target Augmentation](https://mlsanity.com/paper/2002.04720/) (2020)
- [Learning Task-relevant Representations for Generalization via Characteristic Functions of Reward Sequence Distributions](https://mlsanity.com/paper/2205.10218/) (2022)
- [A Review for Deep Reinforcement Learning in Atari:Benchmarks, Challenges, and Solutions](https://mlsanity.com/paper/2112.04145/) (2021)
- [Generalized Data Distribution Iteration](https://mlsanity.com/paper/2206.03192/) (2022)
- [Modeling Diverse Chemical Reactions for Single-step Retrosynthesis via Discrete Latent Variables](https://mlsanity.com/paper/2208.05482/) (2022)

## Built on by (most cited first, 30 of 46)

- [GenMol: A Drug Discovery Generalist with Discrete Diffusion](https://mlsanity.com/paper/2501.06158/) (2025)
- [Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3D](https://mlsanity.com/paper/2305.13266/) (2023)
- [Molecule Generation with Fragment Retrieval Augmentation](https://mlsanity.com/paper/2411.12078/) (2024)
- [A Deep Instance Generative Framework for MILP Solvers Under Limited Data Availability](https://mlsanity.com/paper/2310.02807/) (2023)
- [Generalist Equivariant Transformer Towards 3D Molecular Interaction Learning](https://mlsanity.com/paper/2306.01474/) (2023)
- [Drug Discovery with Dynamic Goal-aware Fragments](https://mlsanity.com/paper/2310.00841/) (2023)
- [De novo Drug Design using Reinforcement Learning with Multiple GPT Agents](https://mlsanity.com/paper/2401.06155/) (2023)
- [Motif-aware Attribute Masking for Molecular Graph Pre-training](https://mlsanity.com/paper/2309.04589/) (2023)
- [Expressivity and Generalization: Fragment-Biases for Molecular GNNs](https://mlsanity.com/paper/2406.08210/) (2024)
- [Unified Guidance for Geometry-Conditioned Molecular Generation](https://mlsanity.com/paper/2501.02526/) (2025)
- [Lift Your Molecules: Molecular Graph Generation in Latent Euclidean Space](https://mlsanity.com/paper/2406.10513/) (2024)
- [HOG-Diff: Higher-Order Guided Diffusion for Graph Generation](https://mlsanity.com/paper/2502.04308/) (2025)
- [MAGNet: Motif-Agnostic Generation of Molecules from Shapes](https://mlsanity.com/paper/2305.19303/) (2023)
- [Machine Learning Insides OptVerse AI Solver: Design Principles and Applications](https://mlsanity.com/paper/2401.05960/) (2024)
- [GraphBPE: Molecular Graphs Meet Byte-Pair Encoding](https://mlsanity.com/paper/2407.19039/) (2024)
- [FragFM: Hierarchical Framework for Efficient Molecule Generation via Fragment-Level Discrete Flow Matching](https://mlsanity.com/paper/2502.15805/) (2025)
- [Regulatory DNA sequence Design with Reinforcement Learning](https://mlsanity.com/paper/2503.07981/) (2025)
- [Mass Spectra Prediction with Structural Motif-based Graph Neural Networks](https://mlsanity.com/paper/2306.16085/) (2023)
- [Synergistic Benefits of Joint Molecule Generation and Property Prediction](https://mlsanity.com/paper/2504.16559/) (2025)
- [A Review on Fragment-based De Novo 2D Molecule Generation](https://mlsanity.com/paper/2405.05293/) (2024)
- [Learning Rule-Induced Subgraph Representations for Inductive Relation Prediction](https://mlsanity.com/paper/2408.07088/) (2024)
- [Diffusion Twigs with Loop Guidance for Conditional Graph Generation](https://mlsanity.com/paper/2410.24012/) (2024)
- [Data-Efficient Molecular Generation with Hierarchical Textual Inversion](https://mlsanity.com/paper/2405.02845/) (2024)
- [Explainable Molecular Property Prediction: Aligning Chemical Concepts with Predictions via Language Models](https://mlsanity.com/paper/2405.16041/) (2024)
- [Foundations and Frontiers of Graph Learning Theory](https://mlsanity.com/paper/2407.03125/) (2024)
- [Equivariant Blurring Diffusion for Hierarchical Molecular Conformer Generation](https://mlsanity.com/paper/2410.20255/) (2024)
- [Accurate and Scalable Graph Neural Networks via Message Invariance](https://mlsanity.com/paper/2502.19693/) (2025)
- [Tokenizing Electron Cloud in Protein-Ligand Interaction Learning](https://mlsanity.com/paper/2505.19014/) (2025)
- [Recent Developments in GNNs for Drug Discovery](https://mlsanity.com/paper/2506.01302/) (2025)
- [3D Molecule Generation from Rigid Motifs via SE(3) Flows](https://mlsanity.com/paper/2601.16955/) (2026)

## Abstract (arXiv)

De novo molecular generation is an essential task for science discovery. Recently, fragment-based deep generative models have attracted much research attention due to their flexibility in generating novel molecules based on existing molecule fragments. However, the motif vocabulary, i.e., the collection of frequent fragments, is usually built upon heuristic rules, which brings difficulties to capturing common substructures from large amounts of molecules. In this work, we propose a new method, MiCaM, to generate molecules based on mined connection-aware motifs. Specifically, it leverages a data-driven algorithm to automatically discover motifs from a molecule library by iteratively merging subgraphs based on their frequency. The obtained motif vocabulary consists of not only molecular motifs (i.e., the frequent fragments), but also their connection information, indicating how the motifs are connected with each other. Based on the mined connection-aware motifs, MiCaM builds a connection-aware generator, which simultaneously picks up motifs and determines how they are connected. We test our method on distribution-learning benchmarks (i.e., generating novel molecules to resemble the distribution of a given training set) and goal-directed benchmarks (i.e., generating molecules with target properties), and achieve significant improvements over previous fragment-based baselines. Furthermore, we demonstrate that our method can effectively mine domain-specific motifs for different tasks.