mlsanityData to 7 Oct 2026

Learning to Extend Molecular Scaffolds with Structural Motifs

arXiv 2103.03864 ↗First posted 5 Mar 2021cs.LG q-bio.QMcited by 70

Not on the map. Why?

Abstract (arXiv)

Recent advancements in deep learning-based modeling of molecules promise to accelerate in silico drug discovery. A plethora of generative models is available, building molecules either atom-by-atom and bond-by-bond or fragment-by-fragment. However, many drug discovery projects require a fixed scaffold to be present in the generated molecule, and incorporating that constraint has only recently been explored. Here, we propose MoLeR, a graph-based model that naturally supports scaffolds as initial seed of the generative procedure, which is possible because it is not conditioned on the generation history. Our experiments show that MoLeR performs comparably to state-of-the-art methods on unconstrained molecular optimization tasks, and outperforms them on scaffold-based tasks, while being an order of magnitude faster to train and sample from than existing approaches. Furthermore, we show the influence of a number of seemingly minor design choices on the overall performance.

Key facts. Cited by 70 papers in the map (data through 7 Oct 2026). Builds on 34 of its 60 references that are in the map. First posted on arXiv 5 Mar 2021.

Builds on

34 of 60 references.

References · 34

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2016Layer Normalizationcited by 5,579
  5. 2018How Powerful are Graph Neural Networks?cited by 4,355
  6. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  7. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  8. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  9. 2015Gated Graph Sequence Neural Networkscited by 792
  10. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 762
  11. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
  12. 2015Generating Sentences from a Continuous Spacecited by 607
22 more
  1. 2020Principal Neighbourhood Aggregation for Graph Netscited by 477
  2. 2018MolGAN: An implicit generative model for small molecular graphscited by 392
  3. 2018GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoderscited by 375
  4. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 363
  5. 2018GuacaMol: Benchmarking Models for De Novo Molecular Designcited by 294
  6. 2019Efficient Graph Generation with Graph Recurrent Attention Networkscited by 231
  7. 2018Learning Deep Generative Models of Graphscited by 227
  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. 2018Constrained Graph Variational Autoencoders for Molecule Designcited by 182
  11. 2018Multi-Objective De Novo Drug Design with Conditional Graph Generative Modelcited by 101
  12. 2020Molecule Edit Graph Attention Network: Modeling Chemical Reactions as Sequences of Graph Editscited by 87
  13. 2019GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulationcited by 75
  14. 2020Guiding Deep Molecular Optimization with Genetic Explorationcited by 51
  15. 2020Barking up the right tree: an approach to search over molecule synthesis DAGscited by 31
  16. 2018DEFactor: Differentiable Edge Factorization-based Probabilistic Graph Generationcited by 24
  17. 2020Scaffold-constrained molecular generationcited by 18
  18. 2019DeepScaffold: a comprehensive tool for scaffold-based de novo drug discovery using deep learningcited by 15
  19. 2020Reinforced Molecular Optimization with Neighborhood-Controlled Grammarscited by 9
  20. 2019Scaffold-based molecular design using graph generative modelcited by 6
  21. 2020Comparison of Atom Representations in Graph Neural Networks for Molecular Property Predictioncited by 5
  22. 2020Deep Evolutionary Learning for Molecular Designcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 12; 2023: 20; 2024: 13; 2025: 14; 2026: 8.

70 papers.

Sort:

By area:

  1. 2022DiGress: Discrete Denoising diffusion for graph generationcited by 503
  2. 2023MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generationcited by 96
  3. 2021Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generationcited by 68
  4. 2022Graph-based Molecular Representation Learningcited by 51
  5. 2022Regression Transformer: Concurrent sequence regression and generation for molecular language modelingcited by 49
  6. 2025GenMol: A Drug Discovery Generalist with Discrete Diffusioncited by 47
  7. 2023De Novo Molecular Generation via Connection-aware Motif Miningcited by 45
  8. 2023Gotta be SAFE: A New Framework for Molecular Designcited by 45
  9. 2022Retrieval-based Controllable Molecule Generationcited by 44
  10. 2022LIMO: Latent Inceptionism for Targeted Molecule Generationcited by 40
  11. 2024DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimizationcited by 27
  12. 2023Re-evaluating Retrosynthesis Algorithms with Syntheseuscited by 26
38 more
  1. 2023Sparse Training of Discrete Diffusion Models for Graph Generationcited by 26
  2. 2024Molecule Generation with Fragment Retrieval Augmentationcited by 22
  3. 2022Equivariant Shape-Conditioned Generation of 3D Molecules for Ligand-Based Drug Designcited by 19
  4. 2023Drug Discovery with Dynamic Goal-aware Fragmentscited by 19
  5. 2023De novo Drug Design using Reinforcement Learning with Multiple GPT Agentscited by 19
  6. 2021C5T5: Controllable Generation of Organic Molecules with Transformerscited by 15
  7. 2022Accelerating Material Design with the Generative Toolkit for Scientific Discoverycited by 15
  8. 2024DrugLLM: Open Large Language Model for Few-shot Molecule Generationcited by 15
  9. 2024Saturn: Sample-efficient Generative Molecular Design using Memory Manipulationcited by 14
  10. 2022Molecule Generation for Drug Design: a Graph Learning Perspectivecited by 13
  11. 2022ToDD: Topological Compound Fingerprinting in Computer-Aided Drug Discoverycited by 13
  12. 2023t-SMILES: A Scalable Fragment-based Molecular Representation Framework for De Novo Molecule Generationcited by 13
  13. 2025Flatten Graphs as Sequences: Transformers are Scalable Graph Generatorscited by 12
  14. 2023Deep Learning Methods for Small Molecule Drug Discovery: A Surveycited by 10
  15. 2024RetroGFN: Diverse and Feasible Retrosynthesis using GFlowNetscited by 10
  16. 2023Molecule Design by Latent Prompt Transformercited by 8
  17. 2024Expressivity and Generalization: Fragment-Biases for Molecular GNNscited by 8
  18. 2023MAGNet: Motif-Agnostic Generation of Molecules from Shapescited by 7
  19. 2024Lift Your Molecules: Molecular Graph Generation in Latent Euclidean Spacecited by 7
  20. 2025Unified Guidance for Geometry-Conditioned Molecular Generationcited by 7
  21. 2023The power of motifs as inductive bias for learning molecular distributionscited by 6
  22. 2023ChiENN: Embracing Molecular Chirality with Graph Neural Networkscited by 6
  23. 2023Language models in molecular discoverycited by 6
  24. 2022An efficient graph generative model for navigating ultra-large combinatorial synthesis librariescited by 5
  25. 2024Chemist-aligned retrosynthesis by ensembling diverse inductive bias modelscited by 5
  26. 2025FragFM: Hierarchical Framework for Efficient Molecule Generation via Fragment-Level Discrete Flow Matchingcited by 5
  27. 2025Controllable Graph Generation with Diffusion Models via Inference-Time Tree Search Guidancecited by 5
  28. 2023Multiresolution Graph Transformers and Wavelet Positional Encoding for Learning Hierarchical Structurescited by 4
  29. 2025Refine Drugs, Don't Complete Them: Uniform-Source Discrete Flows for Fragment-Based Drug Discoverycited by 4
  30. 2022Investigation of a Data Split Strategy Involving the Time Axis in Adverse Event Prediction Using Machine Learningcited by 3
  31. 2024A Review on Fragment-based De Novo 2D Molecule Generationcited by 3
  32. 2025Recent Developments in GNNs for Drug Discoverycited by 3
  33. 20263D Molecule Generation from Rigid Motifs via SE(3) Flowscited by 3
  34. 2023De Novo Drug Design with Joint Transformerscited by 2
  35. 2025HybridLinker: Topology-Guided Posterior Sampling for Enhanced Diversity and Validity in 3D Molecular Linker Generationcited by 2
  36. 2025A Reinforcement Learning-Driven Transformer GAN for Molecular Generationcited by 2
  37. 2026CombiMOTS: Combinatorial Multi-Objective Tree Search for Dual-Target Molecule Generationcited by 2
  38. 2021An In-depth Summary of Recent Artificial Intelligence Applications in Drug Designcited by 1

50 most cited of 70 All 70 (JSON)