mlsanityData to 7 Oct 2026

Molecular Graph Convolutions: Moving Beyond Fingerprints

arXiv 1603.00856 ↗First posted 2 Mar 2016stat.ML cs.LGcited by 238

Not on the map. Why?

Abstract (arXiv)

Molecular "fingerprints" encoding structural information are the workhorse of cheminformatics and machine learning in drug discovery applications. However, fingerprint representations necessarily emphasize particular aspects of the molecular structure while ignoring others, rather than allowing the model to make data-driven decisions. We describe molecular "graph convolutions", a machine learning architecture for learning from undirected graphs, specifically small molecules. Graph convolutions use a simple encoding of the molecular graph---atoms, bonds, distances, etc.---which allows the model to take greater advantage of information in the graph structure. Although graph convolutions do not outperform all fingerprint-based methods, they (along with other graph-based methods) represent a new paradigm in ligand-based virtual screening with exciting opportunities for future improvement.

Key facts. Cited by 238 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Mar 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 56; 2022: 60; 2023: 45; 2024: 40; 2025: 20; 2026: 17.

238 papers.

Sort:

By area:

  1. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 438
  2. 2021Learning Gradient Fields for Molecular Conformation Generationcited by 162
  3. 2021Graph Unlearningcited by 129
  4. 2022Not too little, not too much: a theoretical analysis of graph (over)smoothingcited by 106
  5. 2021Graph Representation Learning in Biomedicinecited by 79
  6. 2022MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Designcited by 66
  7. 2021Graph Neural Networks Inspired by Classical Iterative Algorithmscited by 60
  8. 2021An End-to-End Framework for Molecular Conformation Generation via Bilevel Programmingcited by 59
  9. 2021Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depthcited by 55
  10. 2022DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotationscited by 54
  11. 2021Molecular Contrastive Learning with Chemical Element Knowledge Graphcited by 50
  12. 2021Model Stealing Attacks Against Inductive Graph Neural Networkscited by 50
38 more
  1. 2022GAP: Differentially Private Graph Neural Networks with Aggregation Perturbationcited by 46
  2. 2022Shortest Path Networks for Graph Property Predictioncited by 46
  3. 2021Molformer: Motif-based Transformer on 3D Heterogeneous Molecular Graphscited by 44
  4. 2022GAUCHE: A Library for Gaussian Processes in Chemistrycited by 40
  5. 2021DGL-LifeSci: An Open-Source Toolkit for Deep Learning on Graphs in Life Sciencecited by 38
  6. 2022Energy-Motivated Equivariant Pretraining for 3D Molecular Graphscited by 37
  7. 2021Chemical-Reaction-Aware Molecule Representation Learningcited by 36
  8. 2022A Systematic Survey of Chemical Pre-trained Modelscited by 34
  9. 2021Graph Neural Networks Accelerated Molecular Dynamicscited by 33
  10. 2021Molecule3D: A Benchmark for Predicting 3D Geometries from Molecular Graphscited by 31
  11. 2022FP-GNN: a versatile deep learning architecture for enhanced molecular property predictioncited by 31
  12. 2021SpreadGNN: Serverless Multi-task Federated Learning for Graph Neural Networkscited by 30
  13. 2023ChatGPT-powered Conversational Drug Editing Using Retrieval and Domain Feedbackcited by 30
  14. 2021Learning 3D Representations of Molecular Chirality with Invariance to Bond Rotationscited by 29
  15. 2021Artificial Intelligence in Drug Discovery: Applications and Techniquescited by 28
  16. 2023LMC: Fast Training of GNNs via Subgraph Sampling with Provable Convergencecited by 26
  17. 2023From Continuous Dynamics to Graph Neural Networks: Neural Diffusion and Beyondcited by 26
  18. 2023Context-enriched molecule representations improve few-shot drug discoverycited by 23
  19. 2021Reliable Graph Neural Networks for Drug Discovery Under Distributional Shiftcited by 22
  20. 2023Is Distance Matrix Enough for Geometric Deep Learning?cited by 22
  21. 2021Relative Molecule Self-Attention Transformercited by 21
  22. 2022Graph Neural Networks for Moleculescited by 21
  23. 2021Multiresolution Equivariant Graph Variational Autoencodercited by 20
  24. 2021Learning Attributed Graph Representations with Communicative Message Passing Transformercited by 20
  25. 2022A graph representation of molecular ensembles for polymer property predictioncited by 20
  26. 2021Bridging the Gap between Spatial and Spectral Domains: A Unified Framework for Graph Neural Networkscited by 18
  27. 2022BARTSmiles: Generative Masked Language Models for Molecular Representationscited by 18
  28. 2022Graph Neural Network and Spatiotemporal Transformer Attention for 3D Video Object Detection from Point Cloudscited by 17
  29. 2023Robust Mid-Pass Filtering Graph Convolutional Networkscited by 17
  30. 2021Hashing-Accelerated Graph Neural Networks for Link Predictioncited by 14
  31. 2022Graph Neural Networks for Temperature-Dependent Activity Coefficient Prediction of Solutes in Ionic Liquidscited by 14
  32. 2022Concept Graph Neural Networks for Surgical Video Understandingcited by 13
  33. 2023Factor Graph Neural Networkscited by 13
  34. 2023Molecular Property Prediction Based on Graph Structure Learningcited by 13
  35. 2024ReactZyme: A Benchmark for Enzyme-Reaction Predictioncited by 13
  36. 2021Implicit vs Unfolded Graph Neural Networkscited by 12
  37. 2021Finding the Right Moment: Human-Assisted Trailer Creation via Task Compositioncited by 12
  38. 2022Graph neural networks for the prediction of molecular structure-property relationshipscited by 12

50 most cited of 238 All 238 (JSON)