TradePool: A Novel Interpretable Framework for Quantifying Atomic Attribution Values in Molecular Property Prediction
Authors:
- 6 January 2026
- journal article
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 66 (2) , 881-893
Abstract
The interpretability of GNNs (Graph Neural Network Models) has always been a focal point in the field of compound property prediction. GNNs perform well in modeling small-sample compound data sets, but current interpretable methods struggle to accurately interpret atomic attribution values, quantitative measures of individual atom attribution to model predictions. This makes the optimization of lead compounds reliant on the experience of senior chemists, slowing the drug development process. The rapid expansion of the AI-generated chemical space necessitates efficient interpretation of AI (XAI) methods. These tools can uncover insights beyond human intuition, complementing expert knowledge and significantly accelerating optimization cycles. To tackle these challenges, we propose a novel two-stage atomic attribution value calculation framework for GNNs, which includes model training based on structural pooling and atomic attribution value calculation based on substructure mapping. Our interpretable framework quantifies task-specific atomic attribution values─enhancing atomic attribution accuracy (agreement between computed and ground-truth atomic attribution values) by 30%/20%/15% with 0.93/0.63/0.88 Pearson correlation coefficient (Pearson's r) for GCNs on aromaticity/LogP/TPSA data sets, surpassing commonly used interpretable methods that achieve only 0-0.3 Pearson's r. Additionally, our method is not sensitive to changes in model parameters and provides relatively stable prediction results for changes in the compound structures.Keywords
Funding Information
- Science and Technology Development Fund (FDCT0001/2024/ITP1)
- Macao Polytechnic University (RP/FCA-13/2023)
- the ?Pioneer? and ?Leading Goose? R&D Program of Zhejiang (No.2023C03038)
This publication has 53 references indexed in Scilit:
- In silico prediction of pKa values using explainable deep learning methodsJournal of Pharmaceutical Analysis, 2024
- Explainable AI in drug discovery: self-interpretable graph neural network for molecular property prediction using concept whiteningMachine Learning, 2023
- A high-quality feature selection method based on frequent and correlated items for text classificationSoft Computing, 2023
- Interpretation of Structure–Activity Relationships in Real-World Drug Design Data Sets Using Explainable Artificial IntelligenceJournal of Chemical Information and Modeling, 2022
- Coloring Molecules with Explainable Artificial Intelligence for Preclinical Relevance AssessmentJournal of Chemical Information and Modeling, 2021
- A compact review of molecular property prediction with graph neural networksDrug Discovery Today: Technologies, 2020
- Overview of the SAMPL6 host–guest binding affinity prediction challengeJournal of Computer-Aided Molecular Design, 2018
- Perturbation-Based Explanations of Prediction Models2018
- Large, chemically diverse dataset of logP measurements for benchmarking studiesEuropean Journal of Pharmaceutical Sciences, 2013
- On the Art of Compiling and Using 'Drug‐Like' Chemical Fragment SpacesChemMedChem, 2008