ArticleJournal of cheminformatics2021
Could graph neural networks learn better molecular representation for drug discovery? A comparison study of descriptor-based and graph-based models.
Article in Journal of cheminformatics, 2021. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 182 papers, 1 of them a synthesis that pooled it.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
182 citing papers in PubMed, 1 synthesis or guideline pooled it.
- Knowledge mapping of graph neural networks for drug discovery: a bibliometric and visualized analysis.Frontiers in pharmacology · 2024Pooled it
- Benchmarking machine learning and molecular dynamics methods for the prediction of the thermophysical properties of organic liquids.Digital discovery · 2026Article
- Physical priors improve performance of structure-based binding affinity models.bioRxiv : the preprint server for biology · 2026Article
- Artificial Intelligence-Powered One Health: A Predictive Framework for Managing Persistent Chemical Threats across Human, Animal, and Environmental Systems.Global challenges (Hoboken, NJ) · 2026Review
- MSF-HierGNN: a multi-source substructure-fusion hierarchical GNN method and web server to predict molecular property for drug design.Briefings in bioinformatics · 2026Article
- Molecular active learning approaches for predicting skin cytotoxicity.Molecular diversity · 2026Article
- Can Graph Neural Networks Understand Chemical Elements?Journal of chemical information and modeling · 2026Article
- SSEL-CPP: A SHAP-based feature-selection ensemble learning framework identifies molecular properties of cell-penetrating peptides.Protein science : a publication of the Protein Society · 2026Article
- Integrating Artificial Intelligence Into Drug Discovery From Medicinal Plants: Current Applications and Infrastructural Challenges.Chemical biology & drug design · 2026Review
- Technical review of artificial intelligence in TCR-T therapy.Journal of the National Cancer Center · 2026Review
- Activity-cliff awareness enables robust graph learning for molecular property prediction.Nature communications · 2026Article
- Blood‒brain barrier permeability assessment: from biomimetic models to multimodal imaging.Journal of Zhejiang University. Science. B · 2026Review
- DeepCYP: an integrated deep learning web server for the holistic "pathway-site product" prediction of CYP450 metabolism.Nucleic acids research · 2026Article
- NeutronJittor: Efficient CPU-GPU memory management for GNN training with Jittor.Fundamental research · 2026Article
- Predicting Surfactant Oil-Water Interfacial Tension Using Gated Message-Passing Graph Neural Networks.ACS omega · 2026Article
- Predicting Blood-Brain Barrier Permeability from Experimental Data: An Interpretable and Externally Validated Machine Learning Framework.Pharmaceutics · 2026Article
- Learning molecular determinants of selective small-molecule partitioning across biomolecular condensates.bioRxiv : the preprint server for biology · 2026Article
- Bridging predictive reliability and explainability: a multi-representation deep learning framework for chemical space analysis of immune bioassays.Journal of cheminformatics · 2026Article
- Insights into SIRT2 inhibition from machine learning-assisted multi-level screening of the NCI database.Scientific reports · 2026Article
- Molecular fingerprints are strong models for peptide function prediction.Bioinformatics (Oxford, England) · 2026Article
122 more citing papers are in PubMed but not listed here.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
10 authors.
Funding
Abstract
Graph neural networks (GNN) has been considered as an attractive modelling method for molecular property prediction, and numerous studies have shown that GNN could yield more promising results than traditional descriptor-based methods. In this study, based on 11 public datasets covering various property endpoints, the predictive capacity and computational efficiency of the prediction models developed by eight machine learning (ML) algorithms, including four descriptor-based models (SVM, XGBoost, RF and DNN) and four graph-based models (GCN, GAT, MPNN and Attentive FP), were extensively tested and compared. The results demonstrate that on average the descriptor-based models outperform the graph-based models in terms of prediction accuracy and computational efficiency. SVM generally achieves the best predictions for the regression tasks. Both RF and XGBoost can achieve reliable predictions for the classification tasks, and some of the graph-based models, such as Attentive FP and GCN, can yield outstanding performance for a fraction of larger or multi-task datasets. In terms of computational cost, XGBoost and RF are the two most efficient algorithms and only need a few seconds to train a model even for a large dataset. The model interpretations by the SHAP method can effectively explore the established domain knowledge for the descriptor-based models. Finally, we explored use of these models for virtual screening (VS) towards HIV and demonstrated that different ML algorithms offer diverse VS profiles. All in all, we believe that the off-the-shelf descriptor-based models still can be directly employed to accurately predict various chemical endpoints with excellent computability and interpretability.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.