mlsanityData to 7 Oct 2026

MolecularRNN: Generating realistic molecular graphs with optimized properties

arXiv 1905.13372 ↗First posted 31 May 2019cs.LG cs.AI q-bio.MNcited by 80

Not on the map. Why?

Abstract (arXiv)

Designing new molecules with a set of predefined properties is a core problem in modern drug discovery and development. There is a growing need for de-novo design methods that would address this problem. We present MolecularRNN, the graph recurrent generative model for molecular structures. Our model generates diverse realistic molecular graphs after likelihood pretraining on a big database of molecules. We perform an analysis of our pretrained models on large-scale generated datasets of 1 million samples. Further, the model is tuned with policy gradient algorithm, provided a critic that estimates the reward for the property of interest. We show a significant distribution shift to the desired range for lipophilicity, drug-likeness, and melting point outperforming state-of-the-art works. With the use of rejection sampling based on valency constraints, our model yields 100% validity. Moreover, we show that invalid molecules provide a rich signal to the model through the use of structure penalty in our reinforcement learning pipeline.

Key facts. Cited by 80 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 19; 2022: 25; 2023: 11; 2024: 16; 2025: 5; 2026: 4.

80 papers.

Sort:

By area:

  1. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 384
  2. 2022Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equationscited by 273
  3. 2021GraphDF: A Discrete Flow Model for Molecular Graph Generationcited by 177
  4. 2022A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Languagecited by 129
  5. 2021MARS: Markov Molecular Sampling for Multi-objective Drug Discoverycited by 125
  6. 2022Exploring Chemical Space with Score-based Out-of-distribution Generationcited by 95
  7. 2021GraphEBM: Molecular Graph Generation with Energy-Based Modelscited by 85
  8. 2022Equivariant Energy-Guided SDE for Inverse Molecular Designcited by 72
  9. 2022A Survey on Deep Graph Generation: Methods and Applicationscited by 69
  10. 2021Keeping it Simple: Language Models can learn Complex Molecular Distributionscited by 68
  11. 2022MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Designcited by 66
  12. 2024Efficient Evolutionary Search Over Chemical Space with Large Language Modelscited by 59
38 more
  1. 2021Molecule Generation by Principal Subgraph Mining and Assemblingcited by 53
  2. 2022On Evaluation Metrics for Graph Generative Modelscited by 44
  3. 2022LIMO: Latent Inceptionism for Targeted Molecule Generationcited by 40
  4. 2023A Survey on Graph Diffusion Models: Generative AI in Science for Molecule, Protein and Materialcited by 34
  5. 2021JANUS: Parallel Tempered Genetic Algorithm Guided by Deep Neural Networks for Inverse Molecular Designcited by 31
  6. 2023Genetic algorithms are strong baselines for molecule generationcited by 31
  7. 2021Artificial Intelligence in Drug Discovery: Applications and Techniquescited by 28
  8. 2021How Much Space Has Been Explored? Measuring the Chemical Space Covered by Databases and Machine-Generated Moleculescited by 27
  9. 2024Diffusion Models in textitDe Novo Drug Designcited by 26
  10. 2023Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3Dcited by 24
  11. 2021MolGrow: A Graph Normalizing Flow for Hierarchical Molecular Generationcited by 22
  12. 2023Data-centric Graph Learning: A Surveycited by 22
  13. 2022Graph Neural Networks for Moleculescited by 21
  14. 2023Domain-Agnostic Molecular Generation with Chemical Feedbackcited by 21
  15. 2022Target-aware Molecular Graph Generationcited by 18
  16. 2025NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generationcited by 17
  17. 2022MGCVAE: Multi-objective Inverse Design via Molecular Graph Conditional Variational Autoencodercited by 16
  18. 2022Interpretable Molecular Graph Generation via Monotonic Constraintscited by 15
  19. 2021Improving exploration in policy gradient search: Application to symbolic optimizationcited by 14
  20. 2022MolCPT: Molecule Continuous Prompt Tuning to Generalize Molecular Representation Learningcited by 12
  21. 2022Modular Flows: Differential Molecular Generationcited by 11
  22. 2024LLM-Based Multi-Agent Systems are Scalable Graph Generative Modelscited by 11
  23. 2021GraphGen-Redux: a Fast and Lightweight Recurrent Model for labeled Graph Generationcited by 9
  24. 2022Accurate Machine Learned Quantum-Mechanical Force Fields for Biomolecular Simulationscited by 9
  25. 2023Node-Aligned Graph-to-Graph (NAG2G): Elevating Template-Free Deep Learning Approaches in Single-Step Retrosynthesiscited by 9
  26. 2021Addressing Action Oscillations through Learning Policy Inertiacited by 8
  27. 2022Conditional β-VAE for De Novo Molecular Generationcited by 8
  28. 2022MARS: A Motif-based Autoregressive Model for Retrosynthesis Predictioncited by 8
  29. 2023ChemSpaceAL: An Efficient Active Learning Methodology Applied to Protein-Specific Molecular Generationcited by 8
  30. 2024Generating Graphs via Spectral Diffusioncited by 8
  31. 20243M-Diffusion: Latent Multi-Modal Diffusion for Language-Guided Molecular Structure Generationcited by 8
  32. 2023MAGNet: Motif-Agnostic Generation of Molecules from Shapescited by 7
  33. 2021Incorporating domain knowledge into neural-guided searchcited by 6
  34. 2022Graph Generative Model for Benchmarking Graph Neural Networkscited by 6
  35. 2023The power of motifs as inductive bias for learning molecular distributionscited by 6
  36. 2022An efficient graph generative model for navigating ultra-large combinatorial synthesis librariescited by 5
  37. 2024Text-guided Diffusion Model for 3D Molecule Generationcited by 5
  38. 2021Graph Energy-based Model for Substructure Preserving Molecular Designcited by 4

50 most cited of 80 All 80 (JSON)