mlsanityData to 14 Oct 2026

Automatic chemical design using a data-driven continuous representation of molecules

arXiv 1610.02415 ↗First posted 7 Oct 2016cs.LG physics.chem-phcited by 765

Not on the map. Why?

Cited by 52 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We report a method to convert discrete representations of molecules to and from a multidimensional continuous representation. This model allows us to generate new molecules for efficient exploration and optimization through open-ended spaces of chemical compounds. A deep neural network was trained on hundreds of thousands of existing chemical structures to construct three coupled functions: an encoder, a decoder and a predictor. The encoder converts the discrete representation of a molecule into a real-valued continuous vector, and the decoder converts these continuous vectors back to discrete molecular representations. The predictor estimates chemical properties from the latent continuous vector representation of the molecule. Continuous representations allow us to automatically generate novel chemical structures by performing simple operations in the latent space, such as decoding random vectors, perturbing known chemical structures, or interpolating between molecules. Continuous representations also allow the use of powerful gradient-based optimization to efficiently guide the search for optimized functional compounds. We demonstrate our method in the domain of drug-like molecules and also in the set of molecules with fewer that nine heavy atoms.

Key facts. Cited by 765 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 Oct 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 96; 2022: 134; 2023: 145; 2024: 160; 2025: 126; 2026: 103.

765 papers.

Sort:

By area:

  1. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 631
  2. 2020Permutation Invariant Graph Generation via Score-Based Generative Modelingcited by 270
  3. 2021Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Developmentcited by 264
  4. 2021Weisfeiler and Lehman Go Cellular: CW Networkscited by 218
  5. 2022Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pocketscited by 183
  6. 2021GraphDF: A Discrete Flow Model for Molecular Graph Generationcited by 180
  7. 20233D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Predictioncited by 177
  8. 2021E(n) Equivariant Normalizing Flowscited by 165
  9. 2023Protein Design with Guided Discrete Diffusioncited by 157
  10. 2021Equivariant Subgraph Aggregation Networkscited by 154
  11. 2022A 3D Generative Model for Structure-Based Drug Designcited by 149
  12. 2022GOOD: A Graph Out-of-Distribution Benchmarkcited by 141
38 more
  1. 2022A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Languagecited by 131
  2. 2024Unlocking Guidance for Discrete State-Space Diffusion and Flow Modelscited by 129
  3. 2021MARS: Markov Molecular Sampling for Multi-objective Drug Discoverycited by 125
  4. 2022Equivariant 3D-Conditional Diffusion Models for Molecular Linker Designcited by 122
  5. 2023Machine Learning for Synthetic Data Generation: A Reviewcited by 120
  6. 2021Geometric Deep Learning on Molecular Representationscited by 113
  7. 2022Understanding and Extending Subgraph GNNs by Rethinking Their Symmetriescited by 112
  8. 2022Generating 3D Molecules for Target Protein Bindingcited by 104
  9. 2022Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoderscited by 102
  10. 2023Return of Unconditional Generation: A Self-supervised Representation Generation Methodcited by 98
  11. 2022Exploring Chemical Space with Score-based Out-of-distribution Generationcited by 95
  12. 2023Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspectivecited by 92
  13. 2021Conservative Objective Models for Effective Offline Model-Based Optimizationcited by 88
  14. 2021GraphEBM: Molecular Graph Generation with Energy-Based Modelscited by 85
  15. 2021Graph Representation Learning in Biomedicinecited by 80
  16. 2022Local Latent Space Bayesian Optimization over Structured Inputscited by 79
  17. 2022SELFIES and the future of molecular string representationscited by 76
  18. 2022Recent Advances in Bayesian Optimizationcited by 76
  19. 2024Discrete-state Continuous-time Diffusion for Graph Generationcited by 76
  20. 2023A Comprehensive Survey on Deep Graph Representation Learningcited by 72
  21. 2021Learning to Extend Molecular Scaffolds with Structural Motifscited by 71
  22. 2022A Survey on Deep Graph Generation: Methods and Applicationscited by 69
  23. 2021Keeping it Simple: Language Models can learn Complex Molecular Distributionscited by 68
  24. 2023InstructZero: Efficient Instruction Optimization for Black-Box Large Language Modelscited by 68
  25. 2022MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Designcited by 66
  26. 2023MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generationcited by 65
  27. 2024Efficient Evolutionary Search Over Chemical Space with Large Language Modelscited by 61
  28. 2023Language models can generate molecules, materials, and protein binding sites directly in three dimensions as XYZ, CIF, and PDB filescited by 59
  29. 2022MDM: Molecular Diffusion Model for 3D Molecule Generationcited by 58
  30. 2021High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learningcited by 54
  31. 2021Molecule Generation by Principal Subgraph Mining and Assemblingcited by 54
  32. 2022Conformal Prediction Under Feedback Covariate Shift for Biomolecular Designcited by 54
  33. 2024Mixed Continuous and Categorical Flow Matching for 3D De Novo Molecule Generationcited by 54
  34. 2021Differentiable Scaffolding Tree for Molecular Optimizationcited by 53
  35. 2024Feedback Efficient Online Fine-Tuning of Diffusion Modelscited by 53
  36. 2025Position: Graph Learning Will Lose Relevance Due To Poor Benchmarkscited by 53
  37. 2021Improving black-box optimization in VAE latent space using decoder uncertaintycited by 51
  38. 2022Pareto Set Learning for Expensive Multi-Objective Optimizationcited by 51

50 most cited of 765 All 765 (JSON)