ArticleNature communications2023
Chemistry-intuitive explanation of graph neural networks for molecular property prediction with substructure masking.
Article in Nature communications, 2023. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 44 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
44 citing papers in PubMed, 1 synthesis or guideline pooled it.
- A systematic review of molecular representation learning foundation models.Briefings in bioinformatics · 2026Pooled it
- Chemically Interpretable Explanations for Molecular Property Prediction via Fragment-Level Shapley Values.Journal of chemical information and modeling · 2026Article
- Deep learning directed synthesis of fluid ferroelectric materials.Materials horizons · 2026Article
- Task-adaptive multimodal molecular representations for structure-sensitive property prediction.Chemical science · 2026Article
- Finetuning Foundation Models for Temporal Clinical Transcriptomics Data.Bioinformatics (Oxford, England) · 2026Article
- Geometric Deep Learning-Based Drug Design Models for Small-Molecule Drug Discovery.Molecular informatics · 2026Review
- Computational design of low-volatility lubricants for space using interpretable machine learning.Journal of cheminformatics · 2026Article
- MolProphecy: Bridging medicinal chemists' knowledge and molecular pre-trained models via a multi-modal framework.Journal of advanced research · 2026Article
- Machine-Learning-Driven Molecular Design and Structure-Property-Performance Relationships in Pharmaceutical Chemistry.Molecules (Basel, Switzerland) · 2026Review
- Targeting the intrinsically disordered AR-NTD through a machine learning-based enhanced sampling workflow.Nature communications · 2026Article
- Natural Products in Epilepsy Treatment: From Traditional Medicine Towards Computational Drug Discovery.Current issues in molecular biology · 2026Review
- Artificial intelligence in drug research and development: a review of methods and applications in drug repurposing.Briefings in bioinformatics · 2026Review
- Framework for evaluating explainable AI in antimicrobial drug discovery.Journal of cheminformatics · 2026Article
- Artificial Intelligence in Drug Discovery and Development: Raising Quality per Decision.Pharmacopsychiatry · 2026Review
- Nature meets machine: the AI renaissance in natural product drug discovery.Natural products and bioprospecting · 2026Review
- Mol2Raman: a graph neural network model for predicting Raman spectra from SMILES representations.Digital discovery · 2026Article
- Enhancing the Predictive Power of Macrocyclic Drug Permeability by Knowledge Distillation from Analogous Pretraining Data.Journal of medicinal chemistry · 2026Article
- Perspective on Theoretical Modeling of Soft Molecular Machines and Devices: A Fusion of Data-Driven Approaches with Traditional Computational Chemistry Algorithms.ChemistryOpen · 2025Article
- Machine Learning-Driven Design of Fluorescent Materials: Principles, Methodologies, and Future Directions.Nanomaterials (Basel, Switzerland) · 2025Review
- MaskMol: knowledge-guided molecular image pre-training framework for activity cliffs with pixel masking.BMC biology · 2025Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
11 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Graph neural networks (GNNs) have been widely used in molecular property prediction, but explaining their black-box predictions is still a challenge. Most existing explanation methods for GNNs in chemistry focus on attributing model predictions to individual nodes, edges or fragments that are not necessarily derived from a chemically meaningful segmentation of molecules. To address this challenge, we propose a method named substructure mask explanation (SME). SME is based on well-established molecular segmentation methods and provides an interpretation that aligns with the understanding of chemists. We apply SME to elucidate how GNNs learn to predict aqueous solubility, genotoxicity, cardiotoxicity and blood-brain barrier permeation for small molecules. SME provides interpretation that is consistent with the understanding of chemists, alerts them to unreliable performance, and guides them in structural optimization for target properties. Hence, we believe that SME empowers chemists to confidently mine structure-activity relationship (SAR) from reliable GNNs through a transparent inspection on how GNNs pick up useful signals when learning from data.
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.