mlsanityData to 7 Oct 2026

MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Design

arXiv 2203.14500 ↗First posted 28 Mar 2022cs.LG cs.CE q-bio.BMcited by 66

Not on the map. Why?

Abstract (arXiv)

Molecule design is a fundamental problem in molecular science and has critical applications in a variety of areas, such as drug discovery, material science, etc. However, due to the large searching space, it is impossible for human experts to enumerate and test all molecules in wet-lab experiments. Recently, with the rapid development of machine learning methods, especially generative methods, molecule design has achieved great progress by leveraging machine learning models to generate candidate molecules. In this paper, we systematically review the most relevant work in machine learning models for molecule design. We start with a brief review of the mainstream molecule featurization and representation methods (including 1D string, 2D graph, and 3D geometry) and general generative methods (deep generative and combinatorial optimization methods). Then we summarize all the existing molecule design problems into several venues according to the problem setup, including input, output types and goals. Finally, we conclude with the open challenges and point out future opportunities of machine learning models for molecule design in real-world applications.

Key facts. Cited by 66 papers in the map (data through 7 Oct 2026). Builds on 125 of its 218 references that are in the map. First posted on arXiv 28 Mar 2022.

Builds on

125 of 218 references.

References · 125

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  5. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  7. 2017Graph Attention Networkscited by 8,854
  8. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  9. 2017Inductive Representation Learning on Large Graphscited by 6,284
  10. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  11. 2018How Powerful are Graph Neural Networks?cited by 4,355
  12. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
38 more
  1. 2013Auto-Encoding Variational Bayescited by 3,980
  2. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  3. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  4. 2016Density estimation using Real NVPcited by 2,029
  5. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  6. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  7. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  8. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  9. 2019Strategies for Pre-training Graph Neural Networkscited by 964
  10. 2021E(n) Equivariant Graph Neural Networkscited by 951
  11. 2016Pixel Recurrent Neural Networkscited by 814
  12. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 762
  13. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
  14. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
  15. 2020On the Bottleneck of Graph Neural Networks and its Practical Implicationscited by 624
  16. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 602
  17. 2020Directional Message Passing for Molecular Graphscited by 556
  18. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generationcited by 511
  19. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 504
  20. 2020Principal Neighbourhood Aggregation for Graph Netscited by 477
  21. 2019InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximizationcited by 441
  22. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 438
  23. 2018MolGAN: An implicit generative model for small molecular graphscited by 392
  24. 2018GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoderscited by 375
  25. 2019Analyzing Learned Molecular Representations for Property Predictioncited by 373
  26. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 363
  27. 2021GemNet: Universal Directional Graph Neural Networks for Moleculescited by 342
  28. 2020ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Predictioncited by 332
  29. 2021Do Transformers Really Perform Bad for Graph Representation?cited by 318
  30. 2020GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generationcited by 301
  31. 2018GuacaMol: Benchmarking Models for De Novo Molecular Designcited by 294
  32. 2021GFlowNet Foundationscited by 286
  33. 2017Grammar Variational Autoencodercited by 283
  34. 2021How to Train Your Energy-Based Modelscited by 271
  35. 2018Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Modelscited by 270
  36. 2017Molecular De Novo Design through Deep Reinforcement Learningcited by 264
  37. 2020Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Moleculescited by 254
  38. 2021Pre-training Molecular Graph Representation with 3D Geometrycited by 248

50 most cited of 125 All 125 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 14; 2023: 27; 2024: 15; 2025: 8; 2026: 2.

66 papers.

Sort:

By area:

  1. 2022Structure-based Drug Design with Equivariant Diffusion Modelscited by 213
  2. 2023Machine Learning for Synthetic Data Generation: A Reviewcited by 118
  3. 2022Generating 3D Molecules for Target Protein Bindingcited by 104
  4. 2022Diffusion-based Molecule Generation with Informative Prior Bridgescited by 104
  5. 2023MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generationcited by 96
  6. 2023Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspectivecited by 91
  7. 2024Scientific Large Language Models: A Survey on Biological & Chemical Domainscited by 80
  8. 2022Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matchingcited by 67
  9. 2022DiffBP: Generative Diffusion of 3D Molecules for Target Protein Bindingcited by 58
  10. 2023A new perspective on building efficient and expressive 3D equivariant graph neural networkscited by 46
  11. 2023Gotta be SAFE: A New Framework for Molecular Designcited by 45
  12. 2022GAUCHE: A Library for Gaussian Processes in Chemistrycited by 40
38 more
  1. 2022A Systematic Survey of Chemical Pre-trained Modelscited by 34
  2. 2024Diffusion Models as Constrained Samplers for Optimization with Unknown Constraintscited by 33
  3. 2023Genetic algorithms are strong baselines for molecule generationcited by 31
  4. 2023Learning Joint 2D & 3D Diffusion Models for Complete Molecule Generationcited by 27
  5. 2023Uncovering Neural Scaling Laws in Molecular Representation Learningcited by 23
  6. 2024Speak-to-Structure: Evaluating LLMs in Open-domain Natural Language-Driven Molecule Generationcited by 22
  7. 2023Domain-Agnostic Molecular Generation with Chemical Feedbackcited by 21
  8. 2022Controllable Data Generation by Deep Learning: A Reviewcited by 20
  9. 2022Equivariant Shape-Conditioned Generation of 3D Molecules for Ligand-Based Drug Designcited by 19
  10. 2023De novo Drug Design using Reinforcement Learning with Multiple GPT Agentscited by 19
  11. 2023Automated Scientific Discovery: From Equation Discovery to Autonomous Discovery Systemscited by 18
  12. 2025NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generationcited by 17
  13. 2025ChemMLLM: Chemical Multimodal Large Language Modelcited by 16
  14. 2024Binding-Adaptive Diffusion Models for Structure-Based Drug Designcited by 12
  15. 2023Reinforcement Learning for Generative AI: A Surveycited by 11
  16. 2023Deep Learning Methods for Small Molecule Drug Discovery: A Surveycited by 10
  17. 2024Geometry Informed Tokenization of Molecules for Language Model Generationcited by 10
  18. 2022Probabilistic Generative Transformer Language models for Generative Design of Moleculescited by 8
  19. 2023M2Hub: Unlocking the Potential of Machine Learning for Materials Discoverycited by 8
  20. 2023Molecule Design by Latent Prompt Transformercited by 8
  21. 20243M-Diffusion: Latent Multi-Modal Diffusion for Language-Guided Molecular Structure Generationcited by 8
  22. 2024Expressivity and Generalization: Fragment-Biases for Molecular GNNscited by 8
  23. 2023PrefixMol: Target- and Chemistry-aware Molecule Design via Prefix Embeddingcited by 7
  24. 2023MAGNet: Motif-Agnostic Generation of Molecules from Shapescited by 7
  25. 2024Structure-based Drug Design Benchmark: Do 3D Methods Really Dominate?cited by 7
  26. 2025Unified Guidance for Geometry-Conditioned Molecular Generationcited by 7
  27. 2025PoseX: AI Defeats Physics Approaches on Protein-Ligand Cross Dockingcited by 7
  28. 2022Artificial Intelligence for In Silico Clinical Trials: A Reviewcited by 6
  29. 2023Knowledge-augmented Graph Machine Learning for Drug Discovery: A Surveycited by 6
  30. 2023Explainability Techniques for Chemical Language Modelscited by 6
  31. 2023The power of motifs as inductive bias for learning molecular distributionscited by 6
  32. 2023LLamol: A Dynamic Multi-Conditional Generative Transformer for De Novo Molecular Designcited by 6
  33. 2024Reviving Life on the Edge: Joint Score-Based Graph Generation of Rich Edge Attributescited by 6
  34. 2024Measuring Diversity: Axioms and Challengescited by 6
  35. 2023Interactive Molecular Discovery with Natural Languagecited by 5
  36. 2024Navigating Chemical Space with Latent Flowscited by 5
  37. 2022Improving Molecular Pretraining with Complementary Featurizationscited by 4
  38. 2023Xtal2DoS: Attention-based Crystal to Sequence Learning for Density of States Predictioncited by 4

50 most cited of 66 All 66 (JSON)