mlsanityData to 7 Oct 2026

Genetic algorithms are strong baselines for molecule generation

arXiv 2310.09267 ↗First posted 13 Oct 2023cs.NE cs.LG q-bio.QMcited by 31

Not on the map. Why?

Abstract (arXiv)

Generating molecules, both in a directed and undirected fashion, is a huge part of the drug discovery pipeline. Genetic algorithms (GAs) generate molecules by randomly modifying known molecules. In this paper we show that GAs are very strong algorithms for such tasks, outperforming many complicated machine learning methods: a result which many researchers may find surprising. We therefore propose insisting during peer review that new algorithms must have some clear advantage over GAs, which we call the GA criterion. Ultimately our work suggests that a lot of research in molecule generation should be re-assessed.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Builds on 14 of its 24 references that are in the map. First posted on arXiv 13 Oct 2023.

Builds on

14 of 24 references.

References · 14

  1. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
  2. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 363
  3. 2020GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generationcited by 301
  4. 2018GuacaMol: Benchmarking Models for De Novo Molecular Designcited by 294
  5. 2018Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Modelscited by 270
  6. 2020MoFlow: An Invertible Flow Model for Generating Molecular Graphscited by 183
  7. 2021GraphDF: A Discrete Flow Model for Molecular Graph Generationcited by 177
  8. 2022Sample Efficiency Matters: A Benchmark for Practical Molecular Optimizationcited by 151
  9. 2019GraphNVP: An Invertible Flow Model for Generating Molecular Graphscited by 115
  10. 2021GraphEBM: Molecular Graph Generation with Energy-Based Modelscited by 85
  11. 2019MolecularRNN: Generating realistic molecular graphs with optimized propertiescited by 80
  12. 2022MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Designcited by 66
2 more
  1. 2020Categorical Normalizing Flows via Continuous Transformationscited by 36
  2. 2022Modular Flows: Differential Molecular Generationcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 13; 2025: 8; 2026: 10.

31 papers.

Sort:

By area:

  1. 2025GenMol: A Drug Discovery Generalist with Discrete Diffusioncited by 47
  2. 2024Graph Diffusion Transformers for Multi-Conditional Molecular Generationcited by 44
  3. 2024Genetic-guided GFlowNets for Sample Efficient Molecular Optimizationcited by 36
  4. 2024A survey and benchmark of high-dimensional Bayesian optimization of discrete sequencescited by 22
  5. 2024Molecule Generation with Fragment Retrieval Augmentationcited by 22
  6. 2024Generative Artificial Intelligence for Navigating Synthesizable Chemical Spacecited by 18
  7. 2024Saturn: Sample-efficient Generative Molecular Design using Memory Manipulationcited by 14
  8. 2025NMR-Solver: Automated Structure Elucidation via Large-Scale Spectral Matching and Physics-Guided Fragment Optimizationcited by 11
  9. 2024Diagnosing and fixing common problems in Bayesian optimization for molecule designcited by 9
  10. 2024Active learning for affinity prediction of antibodiescited by 4
  11. 2025Gradient GA: Gradient Genetic Algorithm for Drug Molecular Designcited by 4
  12. 2025A Genetic Algorithm for Navigating Synthesizable Molecular Spacescited by 4
19 more
  1. 2025Refine Drugs, Don't Complete Them: Uniform-Source Discrete Flows for Fragment-Based Drug Discoverycited by 4
  2. 2025MADD: Multi-Agent Drug Discovery Orchestracited by 4
  3. 2025Efficient and Programmable Exploration of Synthesizable Chemical Spacecited by 3
  4. 2025VALID-Mol: a Systematic Framework for Validated LLM-Assisted Molecular Designcited by 2
  5. 2026Graph-GRPO: Training Graph Flow Models with Reinforcement Learningcited by 2
  6. 2024Using GNN property predictors as molecule generatorscited by 1
  7. 2024Conditional Latent Space Molecular Scaffold Optimization for Accelerated Molecular Designcited by 1
  8. 2026Controllable Molecular Generative Foundation Modelscited by 1
  9. 2024Gradient-based Design of Computational Granular Crystalscited by 0
  10. 2024What Ails Generative Structure-based Drug Design: Expressivity is Too Little or Too Much?cited by 0
  11. 2024Hybrid Generative AI for De Novo Design of Co-Crystals with Enhanced Tabletabilitycited by 0
  12. 2026MolLIBRA: Genetic Molecular Optimization with Multi-Fingerprint Surrogates and Text-Molecule Aligned Criticcited by 0
  13. 2026Amortized Molecular Optimization via Group Relative Policy Optimizationcited by 0
  14. 2026MolRGen: A Training and Evaluation Setting for De Novo Molecular Generation with Reasonning Modelscited by 0
  15. 2026GLACIER: Rethinking Mass Spectrum Prediction as an Object Detection Problemcited by 0
  16. 2026Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmarkcited by 0
  17. 2026Adopting Reinforcement Learning with Verifiable Rewards for Molecular Generationcited by 0
  18. 2026PGFS++: Molecular Property Improvement under Synthesis and Diversity Constraintscited by 0
  19. 2026Elite-Weighted Supervised Fine-tuning for Goal-Directed Molecular Optimizationcited by 0