A compact review of molecular property prediction with graph neural networks.

As graph neural networks are becoming more and more powerful and useful in the field of drug discovery, many pharmaceutical companies are getting interested in utilizing these methods for their own in-house frameworks. This is especially compelling for tasks such as the prediction of molecular properties which is often one of the most crucial tasks in computer-aided drug discovery workflows. The immense hype surrounding these kinds of algorithms has led to the development of many different types of promising architectures and in this review we try to structure this highly dynamic field of AI-research by collecting and classifying 80 GNNs that have been used to predict more than 20 molecular properties using 48 different datasets.

• Publication year

  2020

• Venue

  Drug Discovery Today : Technologies

• Publication date

  2020-12-01

• Fields of study

  Chemistry, Medicine, Computer Science

• Identifiers
  DOI 10.1016/j.ddtec.2020.11.009PMID 34895648
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Building attention and edge message passing neural networks for bioactivity and physical–chemical property prediction

  2020cited by this paper
• ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property Prediction

  2020cited by this paper
• Multi-View Graph Neural Networks for Molecular Property Prediction

  2020cited by this paper
• Effective Training Strategies for Deep Graph Neural Networks

  2020cited by this paper
• Optimal Transport Graph Neural Networks

  2020cited by this paper
• Open Graph Benchmark: Datasets for Machine Learning on Graphs

  2020cited by this paper
• Improvement in ADMET Prediction with Multitask Deep Featurization.

  2020cited by this paper
• MxPool: Multiplex Pooling for Hierarchical Graph Representation Learning

  2020cited by this paper
• A self-attention based message passing neural network for predicting molecular lipophilicity and aqueous solubility

  2020cited by this paper
• Can graph neural networks count substructures?

  2020cited by this paper
• StructPool: Structured Graph Pooling via Conditional Random Fields

  2020cited by this paper
• Property Prediction of Molecules in Graph Convolutional Neural Network Expansion

  2019cited by this paper
• A Comprehensive Survey on Graph Neural Networks

  2019cited by this paper
• LanczosNet: Multi-Scale Deep Graph Convolutional Networks

  2019cited by this paper
• Molecular Geometry Prediction using a Deep Generative Graph Neural Network

  2019cited by this paper
• Graph Convolutional Networks with EigenPooling

  2019cited by this paper
• Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification

  2019cited by this paper
• Provably Powerful Graph Networks

  2019cited by this paper
• Pre-training Graph Neural Networks

  2019cited by this paper
• Analyzing Learned Molecular Representations for Property Prediction

  2019cited by this paper
• InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization

  2019cited by this paper
• Molecule Property Prediction Based on Spatial Graph Embedding

  2019cited by this paper
• Gated Graph Recursive Neural Networks for Molecular Property Prediction

  2019cited by this paper
• Graph Nets for Partial Charge Prediction

  2019cited by this paper
• A Fair Comparison of Graph Neural Networks for Graph Classification

  2019cited by this paper
• Relational Graph Attention Networks

  2018cited by this paper
• Enhanced Deep‐Learning Prediction of Molecular Properties via Augmentation of Bond Topology

  2018cited by this paper
• An End-to-End Deep Learning Architecture for Graph Classification

  2018cited by this paper
• Adaptive Graph Convolutional Neural Networks

  2018cited by this paper
• Review on Reliable Pattern Recognition with Machine Learning Techniques

  2018cited by this paper
• Edge Attention-based Multi-Relational Graph Convolutional Networks

  2018cited by this paper
• Large-scale comparison of machine learning methods for drug target prediction on ChEMBL

  2018cited by this paper
• Deeply learning molecular structure-property relationships using attention- and gate-augmented graph convolutional network

  2018cited by this paper
• PotentialNet for Molecular Property Prediction

  2018cited by this paper
• Capsule Graph Neural Network

  2018cited by this paper
• Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs

  2017cited by this paper
• Convolutional Embedding of Attributed Molecular Graphs for Physical Property Prediction

  2017cited by this paper
• Recent Trends in Deep Learning Based Natural Language Processing

  2017cited by this paper
• Learning Graph-Level Representation for Drug Discovery

  2017cited by this paper
• Neural Message Passing for Quantum Chemistry

  2017cited by this paper
• Deep Learning Based Regression and Multiclass Models for Acute Oral Toxicity Prediction with Automatic Chemical Feature Extraction

  2017cited by this paper
• Modeling Relational Data with Graph Convolutional Networks

  2017cited by this paper
• Inductive Representation Learning on Large Graphs

  2017cited by this paper
• enchmark for molecular machine learning †

  2017cited by this paper
• Learning Convolutional Neural Networks for Graphs

  2016cited by this paper
• Low Data Drug Discovery with One-Shot Learning

  2016cited by this paper
• Deep Convolutional Networks on Graph-Structured Data

  2015cited by this paper
• Convolutional Networks on Graphs for Learning Molecular Fingerprints

  2015cited by this paper
• Deep Architectures and Deep Learning in Chemoinformatics: The Prediction of Aqueous Solubility for Drug-Like Molecules

  2013cited by this paper
• The Graph Neural Network Model

  2009cited by this paper
• Classical and enriched finite element formulations for Bloch‐periodic boundary conditions

  2009cited by this paper
• Neural Network for Graphs: A Contextual Constructive Approach

  2009cited by this paper
• Automatic Generation of Complementary Descriptors with Molecular Graph Networks

  2005cited by this paper
• ChemNet: A Novel Neural Network Based Method for Graph/Property Mapping

  1995cited by this paper

• Improving Fidelity and Diversity in Chemical Language Transformers for Inverse Molecular Design.

  2026cites this paper
• Online intelligent closed-loop correction of drop-offset defects in OLED printing algorithm using visual graph attention and reinforcement learning

  2026cites this paper
• A review on integrated machine learning and deep learning driven artificial intelligence models for pharmacokinetics and toxicokinetics predictions, and their application.

  2026cites this paper
• Machine Learning Applications for Surface Complexation Models

  2026cites this paper
• Graph Neural Networks for Polymer Characterization and Property Prediction: Opportunities and Challenges

  2026cites this paper
• AI-aided virtual screening and biological evaluation for discovering new potential poly (ADP-ribose) polymerase-1 (PARP-1) inhibitors.

  2026cites this paper
• Artificial Intelligence-Driven Natural Product Discovery for Cancer Metastasis and Chemoresistance: From Computational Prediction to Preclinical Validation

  2026cites this paper
• XIMP: Cross Graph Inter-Message Passing for Molecular Property Prediction

  2026cites this paper
• Multimodal Bond Reconstruction toward Generative Molecular Design.

  2026cites this paper
• Graph-based transformer to predict the octanol-water partition coefficient.

  2026cites this paper
• Iterative discovery of potent polymeric antibiotics via multi-stage and multi-task learning against antimicrobial resistance

  2026cites this paper
• TradePool: A Novel Interpretable Framework for Quantifying Atomic Attribution Values in Molecular Property Prediction.

  2026cites this paper
• Computational Ligand-Binding Site Prediction.

  2026cites this paper
• Heterogeneous Graph Alignment for Joint Reasoning and Interpretability

  2026cites this paper
• OptimES: Optimizing federated learning using remote embeddings for graph neural networks

  2026cites this paper
• Pairwise Neural Networks for Ranking Molecular Structures Based on Properties.

  2026cites this paper
• Invariant-Stratified Propagation for Expressive Graph Neural Networks

  2026cites this paper
• PSoSOQY: A Deep Learning–Driven Singlet Oxygen Quantum Yield Prediction Platform for Expediting Photosensitizer Development

  2026cites this paper
• Multimodal Multi-Granularity Fusion Model with Mamba Architecture for Ames Mutagenicity Prediction.

  2026cites this paper
• KGG: Knowledge-Guided Graph Self-Supervised Learning to Enhance Molecular Property Predictions

  2025cites this paper
• SBGD: Improving Graph Diffusion Generative Model via Stochastic Block Diffusion

  2025cites this paper
• PAC-Bayesian Generalization Bounds for Graph Convolutional Networks on Inductive Node Classification

  2025cites this paper
• A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools

  2025cites this paper
• HL-HGAT: Heterogeneous Graph Attention Network via Hodge-Laplacian Operator

  2025cites this paper
• Exploring Plant‐Derived Natural Products Against Plasmodium falciparum Malaria Causative Agent by Targeting Protein Kinase 5: Insights Into Computational Approaches

  2025cites this paper
• Tri-level interaction fusion network for graph similarity learning

  2025cites this paper
• Quantum-Embedded Graph Neural Network Architecture for Molecular Property Prediction

  2025cites this paper
• Graph Neural Diffusion via Generalized Opinion Dynamics

  2025cites this paper
• Enhancing Chemical Explainability Through Counterfactual Masking

  2025cites this paper
• Leveraging molecular graphs for natural product classification

  2025cites this paper
• Multiview Spatiotemporal Dynamic Graph Convolution Network for Traffic Flow Prediction

  2025cites this paper
• Edges are all you need: Potential of medical time series analysis on complete blood count data with graph neural networks

  2025cites this paper
• BSL: A Unified and Generalizable Multitask Learning Platform for Virtual Drug Discovery from Design to Synthesis

  2025cites this paper
• A Survey of Graph Neural Networks for Drug Discovery: Recent Developments and Challenges

  2025cites this paper
• Effective and Explainable Molecular Property Prediction by Chain-of-Thought Enabled Large Language Models and Multi-Modal Molecular Information Fusion

  2025cites this paper
• Rhomboid Tiling for Geometric Graph Deep Learning

  2025cites this paper
• Multi-source medical knowledge adaptive fusion network for combinatorial medication recommendation

  2025cites this paper
• “Amide − amine + alcohol = carboxylic acid.” chemical reactions as linear algebraic analogies in graph neural networks

  2025cites this paper
• Machine Learning for Toxicity Prediction Using Chemical Structures: Pillars for Success in the Real World

  2025cites this paper
• Hyperparameter optimization and neural architecture search algorithms for graph Neural Networks in cheminformatics

  2025cites this paper
• Uncertainty quantification with graph neural networks for efficient molecular design

  2025cites this paper
• Unlocking the Potential of Machine Learning in Enhancing Quantum Chemical Calculations for Infrared Spectral Prediction

  2025cites this paper
• SimSon: simple contrastive learning of SMILES for molecular property prediction

  2025cites this paper
• Multimodal Bonds Reconstruction Towards Generative Molecular Design

  2025cites this paper
• AI technology in smart drying of foods: A critical review of research and applications

  2025cites this paper
• Learning Repetition-Invariant Representations for Polymer Informatics

  2025cites this paper
• Uncertainty-Aware Metabolic Stability Prediction with Dual-View Contrastive Learning

  2025cites this paper
• Optimizing Federated Learning using Remote Embeddings for Graph Neural Networks

  2025cites this paper
• Bayesian uncertainty quantification of graph neural networks using stochastic gradient Hamiltonian Monte Carlo

  2025cites this paper
• An open-source family of large encoder-decoder foundation models for chemistry

  2025cites this paper
• CEGA: A Cost-Effective Approach for Graph-Based Model Extraction and Acquisition

  2025cites this paper
• MolUNet++: Adaptive-grained Explicit Substructure and Interaction Aware Molecular Representation Learning

  2025cites this paper
• Expert-Guided Substructure Information Bottleneck for Molecular Property Prediction

  2025cites this paper
• Hardware-Aware Quantum Kernel Design Based on Graph Neural Networks

  2025cites this paper
• Research on GNNs with stable learning

  2025cites this paper
• Mol-SGGI: an attention-guided comprehensive molecular multi-representation learning and adaptive fusion framework for molecular property prediction.

  2025cites this paper
• GNN-SKAN: Advancing Molecular Representation Learning with SwallowKAN

  2025cites this paper
• Relevance of 3D Rotationally Equivariant Neural Networks for Predicting Protein-Ligand Binding Affinities.

  2025cites this paper
• Fragment-Wise Interpretability in Graph Neural Networks via Molecule Decomposition and Contribution Analysis

  2025cites this paper
• Heterogeneous graph structure learning based on feature and topology information extraction

  2025cites this paper
• Environmental impacts prediction using graph neural networks on molecular graphs

  2025cites this paper
• AI-Guided Fragment-Based Drug Design for Virtual Library Screening and Hit Optimization

  2025cites this paper
• Optimizing drug-target binding affinity prediction for kinase proteins: a novel all-MLP-transformer approach

  2025cites this paper
• FragFormer: A Fragment-based Representation Learning Framework for Molecular Property Prediction

  2025cites this paper
• B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data

  2025cites this paper
• A comprehensive update on the use of molecular topology applications for anti-infective drug discovery

  2025cites this paper
• LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation Models

  2025cites this paper
• Graph neural networks extrapolate out-of-distribution for shortest paths

  2025cites this paper
• NPI-HGNN: A Heterogeneous Graph Neural Network-Based Approach for Predicting ncRNA-Protein Interactions

  2025cites this paper
• Quantifying the non-isomorphism of global urban road networks using GNNs and graph kernels

  2025cites this paper
• Topological signal processing and learning: Recent advances and future challenges

  2025cites this paper
• AGDIFF: Attention-Enhanced Diffusion for Molecular Geometry Prediction

  2025cites this paper
• Designing Selective Drugs: Multi-Objective Optimization to Mitigate Off-Target Effects

  2025cites this paper
• TransPeakNet for solvent-aware 2D NMR prediction via multi-task pre-training and unsupervised learning

  2025cites this paper
• RT-Pred: A web server for accurate, customized liquid chromatography retention time prediction of chemicals.

  2025cites this paper
• Smart distributed data factory volunteer computing platform for active learning-driven molecular data acquisition

  2025cites this paper
• Efficient substructure feature encoding based on graph neural network blocks for drug-target interaction prediction

  2025cites this paper
• CoDNet: controlled diffusion network for structure-based drug design

  2025influential citation
• Two Birds with One Stone: Enhancing Uncertainty Quantification and Interpretability with Graph Functional Neural Process

  2025cites this paper
• Electron-Informed Coarse-Graining Molecular Representation Learning for Real-World Molecular Physics

  2025cites this paper
• MatterTune: An Integrated, User-Friendly Platform for Fine-Tuning Atomistic Foundation Models to Accelerate Materials Simulation and Discovery

  2025cites this paper
• Pooling solvent mixtures for solvation free energy predictions

  2025cites this paper
• Self-Supervised Diffusion Models for Electron-Aware Molecular Representation Learning

  2025cites this paper
• Accurate Predictions of Molecular Properties of Proteins via Graph Neural Networks and Transfer Learning

  2025cites this paper
• Optimization and application of image recognition algorithm based on DouN-GNN model in two-node graph neural network

  2025cites this paper
• Evaluating Effects of Augmented SELFIES for Molecular Understanding Using QK-LSTM

  2025cites this paper
• A Review of Artificial Intelligence Driven Drug Discovery Programs for Infectious Disease Management in Nigerian Healthcare

  2025cites this paper
• Prediction of blood–brain barrier and Caco-2 permeability through the Enalos Cloud Platform: combining contrastive learning and atom-attention message passing neural networks

  2025cites this paper
• Toward Accurate PAH IR Spectra Prediction: Handling Charge Effects with Classical and Deep Learning Models

  2025cites this paper
• Graph Neural Network for 3‐Dimensional Structures Including Dihedral Angles for Molecular Property Prediction

  2025cites this paper
• Knowledge graph information bottleneck enhanced molecular representation learning

  2025cites this paper
• Pure Component Property Estimation Framework Using Explainable Machine Learning Methods

  2025cites this paper
• The Final Layer Holds the Key: A Unified and Efficient GNN Calibration Framework

  2025cites this paper
• Deep learning guided discovery of antibacterial polymeric nanoparticles

  2025cites this paper
• A Benchmark Dataset for Graph Regression with Homogeneous and Multi-Relational Variants

  2025cites this paper
• A Molecular Property Prediction Method for Antibiotic Discovery with Multimodal and Transfer Learning

  2025cites this paper
• Recent Developments in GNNs for Drug Discovery

  2025cites this paper
• Virtual Bonding Enhanced Graph Self‐Supervised Learning for Molecular Property Prediction

  2025cites this paper
• Enhancing Molecular Contrastive Prediction by Recognizing Metric Distribution Separation

  2025cites this paper
• SynthMol: A Drug Safety Prediction Framework Integrating Graph Attention and Molecular Descriptors into Pre-Trained Geometric Models

  2025cites this paper