mlsanityData to 7 Oct 2026

A Review on Fragment-based De Novo 2D Molecule Generation

arXiv 2405.05293 ↗First posted 8 May 2024q-bio.BM cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

In the field of computational molecule generation, an essential task in the discovery of new chemical compounds, fragment-based deep generative models are a leading approach, consistently achieving state-of-the-art results in molecular design benchmarks as of 2023. We present a detailed comparative assessment of their architectures, highlighting their unique approaches to molecular fragmentation and generative modeling. This review also includes comparisons of output quality, generation speed, and the current limitations of specific models. We also highlight promising avenues for future research that could bridge fragment-based models to real-world applications.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 25 of its 36 references that are in the map. First posted on arXiv 8 May 2024.

Builds on

25 of 36 references.

References · 25

  1. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 762
  2. 2022Equivariant Diffusion for Molecule Generation in 3Dcited by 666
  3. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
  4. 2018MolGAN: An implicit generative model for small molecular graphscited by 392
  5. 2020GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generationcited by 301
  6. 2018GuacaMol: Benchmarking Models for De Novo Molecular Designcited by 294
  7. 2017Grammar Variational Autoencodercited by 283
  8. 2020Hierarchical Generation of Molecular Graphs using Structural Motifscited by 204
  9. 2018Fr'echet ChemNet Distance: A metric for generative models for molecules in drug discoverycited by 191
  10. 2023Geometric Latent Diffusion Models for 3D Molecule Generationcited by 185
  11. 2021MARS: Markov Molecular Sampling for Multi-objective Drug Discoverycited by 125
  12. 2019Deep Set Prediction Networkscited by 71
13 more
  1. 2021Learning to Extend Molecular Scaffolds with Structural Motifscited by 70
  2. 2021Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generationcited by 68
  3. 2019Augmenting Genetic Algorithms with Deep Neural Networks for Exploring the Chemical Spacecited by 66
  4. 2021Molecule Generation by Principal Subgraph Mining and Assemblingcited by 53
  5. 2023De Novo Molecular Generation via Connection-aware Motif Miningcited by 45
  6. 2020Deep Graph Generators: A Surveycited by 36
  7. 2021Top-N: Equivariant set and graph generation without exchangeabilitycited by 36
  8. 2021Artificial Intelligence in Drug Discovery: Applications and Techniquescited by 28
  9. 2023Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3Dcited by 24
  10. 2022Molecule Generation for Drug Design: a Graph Learning Perspectivecited by 13
  11. 2023Deep Learning Methods for Small Molecule Drug Discovery: A Surveycited by 10
  12. 2023MAGNet: Motif-Agnostic Generation of Molecules from Shapescited by 7
  13. 2023The power of motifs as inductive bias for learning molecular distributionscited by 6

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 2.

3 papers.

  1. 2025FLOWR.root: A flow matching based foundation model for joint multi-purpose structure-aware 3D ligand generation and affinity predictioncited by 2
  2. 2024MolMiner: Toward Controllable, 3D-Aware, Fragment-Based Molecular Designcited by 1
  3. 2025Guiding Evolutionary Molecular Design: Adding Reinforcement Learning for Mutation Selectioncited by 0