mlsanityData to 7 Oct 2026

Augmenting Molecular Deep Generative Models with Topological Data Analysis Representations

arXiv 2106.04464 ↗First posted 8 Jun 2021physics.chem-ph cs.LG math.ATcited by 6

Not on the map. Why?

Abstract (arXiv)

Deep generative models have emerged as a powerful tool for learning useful molecular representations and designing novel molecules with desired properties, with applications in drug discovery and material design. However, most existing deep generative models are restricted due to lack of spatial information. Here we propose augmentation of deep generative models with topological data analysis (TDA) representations, known as persistence images, for robust encoding of 3D molecular geometry. We show that the TDA augmentation of a character-based Variational Auto-Encoder (VAE) outperforms state-of-the-art generative neural nets in accurately modeling the structural composition of the QM9 benchmark. Generated molecules are valid, novel, and diverse, while exhibiting distinct electronic property distribution, namely higher sample population with small HOMO-LUMO gap. These results demonstrate that TDA features indeed provide crucial geometric signal for learning abstract structures, which is non-trivial for existing generative models operating on string, graph, or 3D point sets to capture.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 34 of its 65 references that are in the map. First posted on arXiv 8 Jun 2021.

Builds on

34 of 65 references.

References · 34

  1. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  2. 2013Auto-Encoding Variational Bayescited by 3,980
  3. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  4. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 762
  5. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
  6. 2018MolGAN: An implicit generative model for small molecular graphscited by 392
  7. 2018GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoderscited by 375
  8. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 363
  9. 2017Grammar Variational Autoencodercited by 283
  10. 2018Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Modelscited by 270
  11. 2015Persistence Images: A Stable Vector Representation of Persistent Homologycited by 235
  12. 2018Constrained Graph Variational Autoencoders for Molecule Designcited by 182
22 more
  1. 2019Symmetry-adapted generation of 3d point sets for the targeted discovery of moleculescited by 171
  2. 2017Deep Reinforcement Learning for De-Novo Drug Designcited by 161
  3. 2018Syntax-Directed Variational Autoencoder for Structured Datacited by 103
  4. 2018Multi-Objective De Novo Drug Design with Conditional Graph Generative Modelcited by 101
  5. 2019A Topology Layer for Machine Learningcited by 79
  6. 2017Sliced Wasserstein Kernel for Persistence Diagramscited by 77
  7. 2014A Stable Multi-Scale Kernel for Topological Machine Learningcited by 74
  8. 2018Molecular generative model based on conditional variational autoencoder for de novo molecular designcited by 73
  9. 2018NeVAE: A Deep Generative Model for Molecular Graphscited by 66
  10. 2021An End-to-End Framework for Molecular Conformation Generation via Bilevel Programmingcited by 59
  11. 2020Symmetry-Aware Actor-Critic for 3D Molecular Designcited by 55
  12. 2020Reinforcement Learning for Molecular Design Guided by Quantum Mechanicscited by 51
  13. 2018Conditional molecular design with deep generative modelscited by 44
  14. 2018Persistence Fisher Kernel: A Riemannian Manifold Kernel for Persistence Diagramscited by 33
  15. 2017Application of generative autoencoder in de novo molecular designcited by 32
  16. 2019Generating valid Euclidean distance matricescited by 19
  17. 20203DMolNet: A Generative Network for Molecular Structurescited by 19
  18. 2015Interactive Visualization of 2-D Persistence Modulescited by 18
  19. 2013Confidence sets for persistence diagramscited by 17
  20. 2018A Kernel for Multi-Parameter Persistent Homologycited by 12
  21. 2020CogMol: Target-Specific and Selective Drug Design for COVID-19 Using Deep Generative Modelscited by 8
  22. 2020Characterizing the Latent Space of Molecular Deep Generative Models with Persistent Homology Metricscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 1; 2024: 2; 2025: 0; 2026: 1.

6 papers.

  1. 2022Data-Efficient Graph Grammar Learning for Molecular Generationcited by 26
  2. 2024GP-MoLFormer: A Foundation Model For Molecular Generationcited by 11
  3. 2023Deep Learning Methods for Small Molecule Drug Discovery: A Surveycited by 10
  4. 2022Accelerating Inhibitor Discovery With A Deep Generative Foundation Model: Validation for SARS-CoV-2 Drug Targetscited by 0
  5. 2024LightGBM robust optimization algorithm based on topological data analysiscited by 0
  6. 2026MacroGuide: Topological Guidance for Macrocycle Generationcited by 0