tmGNN-XAI: An Explainable Graph Neural Network Tool for Predicting Electronic Properties of Transition Metal Complexes from SMILES
Journal of Chemical Information and Modeling · 27.07.2026 · 66 (14) · 8059-8075
DOI: 10.1021/acs.jcim.6c01047 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 03.07.2026. Verfasst von Abdulmujeeb T Onawole. Beteiligte Einrichtung: Institute for Molecular Bioscience, The University of Queensland, Brisbane, Queensland4072, Australia. Hauptthemen laut MEDLINE: Graph Neural Networks, Transition Elements, Electrons, Coordination Complexes. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 43 Literaturangaben.
Abstract (Originalsprache)
Predicting the electronic properties of transition metal complexes (TMCs) from 2D molecular graphs remains challenging; organic-trained property models lack TMC transferability, universal interatomic potentials require 3D coordinates rather than SMILES, and tools providing holistic electronic property prediction with atom-level explainability and calibrated uncertainty remain limited. We present tmGNN-XAI, a multitask relational graph convolutional network that predicts seven quantum-chemical properties of TMCs directly from SMILES strings and produces perturbation-based atom-level attributions for each prediction. The model encodes dative coordination bonds as a dedicated edge type distinct from covalent bonds and is trained on 100,703 complexes from the tmQM data set spanning 30 transition metals. Test-set performance is competitive with a Chemprop D-MPNN baseline, achieving R2 = 0.979 for metal partial charge and R2 = 0.964 and 0.949 for HOMO and LUMO energies. Across all 100,703 complexes, donor atoms (N, O, S, P) appear among the top-five most important atoms in more than 99.8% of complexes for every property, a large-scale data-driven result consistent with ligand field theory. A trust framework combining ensemble agreement with attribution direction separates predictions into four reliability scenarios; confident predictions achieve 1.6 to 2.5 times lower mean absolute error than uncertain ones for five of seven properties. The framework generalizes to cross-level DFT validation, phototherapy candidate screening (area under the ROC curve (AUC) = 0.735), and indirect redox prediction via Koopmans’ theorem. An interactive web application makes property predictions, atom-level attributions, and trust labels accessible without programming or DFT expertise. tmGNN-XAI is designed as an explainable, first-tier screening tool for TMC electronic property estimation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Institute for Molecular Bioscience, The University of Queensland, Brisbane, Queensland4072, Australia.
ORCID-Profile: Abdulmujeeb T Onawole
Zitieren
APA
Onawole, A. T. (2026). tmGNN-XAI: An Explainable Graph Neural Network Tool for Predicting Electronic Properties of Transition Metal Complexes from SMILES. Journal of Chemical Information and Modeling, 66(14), 8059-8075. https://doi.org/10.1021/acs.jcim.6c01047
Vancouver
Onawole AT. tmGNN-XAI: An Explainable Graph Neural Network Tool for Predicting Electronic Properties of Transition Metal Complexes from SMILES. Journal of Chemical Information and Modeling. 2026;66(14):8059-8075. doi:10.1021/acs.jcim.6c01047
BibTeX
@article{Onawole2026,
author = {Onawole, Abdulmujeeb T},
title = {tmGNN-XAI: An Explainable Graph Neural Network Tool for Predicting Electronic Properties of Transition Metal Complexes from SMILES},
journal = {Journal of Chemical Information and Modeling},
year = {2026},
volume = {66},
number = {14},
pages = {8059--8075},
doi = {10.1021/acs.jcim.6c01047}
}
EUVIMED