Experimental dipole moment prediction with a progressive 2D–3D hybrid framework and twin-pair-based diagnostic evaluation
Open Access
- 14 June 2026
- journal article
- Published by Springer Nature in Journal of Cheminformatics
- Vol. 18 (1)
Abstract
Accurate prediction of molecular dipole moments ( $$\mu$$ ) is essential for modeling electrostatic interactions in solvation, molecular recognition, and materials. While modern 3D learning models can approach saturation on low-noise quantum-chemical benchmarks, performance often degrades on experimentally compiled datasets where measurement noise, stereochemical ambiguity, and conformer variability introduce a substantial gap between idealized theory and practical data. Here, we present a progressive 2D–3D hybrid framework for experimental dipole-moment prediction under heterogeneous labels. The framework is constructed in two stages. First, a strong 2D tabular CatBoost model based on SMILES-derived multi-view fingerprints is enriched with physicochemical, dipole-related, and conformer-dependent 3D shape descriptors, introducing a first level of 2D+3D integration and improving performance over the 2D representation alone. Second, this enriched tabular predictor is linearly fused with a geometry-aware 3D graph neural network operating on conformer-derived molecular graphs, yielding a further gain through complementary structural learning. On the experimental test set, the resulting framework achieves $$R^{2}=0.844$$ with $$\textrm{MAE}=0.399~\textrm{D}$$ , outperforming a nonparametric fingerprint k -NN baseline ( $$R^{2}=0.65$$ ) and remaining close to the similarity-conditioned diagnostic reference range estimated from twin-pair dispersion ( $$R^{2}\approx 0.86$$ –0.91) under Tanimoto similarity thresholds of 0.95, 0.97, 0.98, and 0.99. Scientific contribution: The main scientific contribution of this study is the development of an experimentally grounded progressive 2D–3D hybrid learning framework that integrates enriched tabular chemical representations, geometry-aware graph learning, and twin-pair-based diagnostic evaluation to predict dipole moments under heterogeneous experimental labels. To contextualize performance in this noise-affected experimental setting, we further use twin-pair analysis within a test-to-train similarity-stratified evaluation protocol, while baseline comparisons and component-wise interpretability analyses help clarify the roles of representation diversity and learner complementarity. Relative to three recently published dipole-prediction studies, the proposed framework remains competitively positioned, although these comparisons are intended only for cautious literature contextualization because the underlying datasets, label sources, and noise regimes are not directly matched. In contrast to prior studies focused mainly on lower-noise theoretical benchmarks or narrower molecular domains, the present work targets the comparatively underexplored Stenutz experimental compilation.
Keywords
This publication has 34 references indexed in Scilit:
- Origin‐Dependence of Dipole Moments of Charged Proteins: Theoretical Foundations and Implications, RevisitedJournal of Computational Chemistry, 2025
- Q‐DFTNet: A Chemistry‐Informed Neural Network Framework for Predicting Molecular Dipole Moments via DFT‐Driven QM9 DataJournal of Computational Chemistry, 2025
- Machine Learning Orchestrating the Materials Discovery and Performance Optimization of Redox Flow BatteryChemElectroChem, 2024
- Rapid Prediction of Energy Level Alignment and Conductance of Single‐Molecule Junctions Through Intramolecular Dipole MomentAdvanced Functional Materials, 2024
- Machine Learning Paves the Way for High Entropy Compounds Exploration: Challenges, Progress, and OutlookAdvanced Materials, 2023
- Ground and Excited State Dipole Moments of Metformin Hydrochloride using Solvatochromic Effects and Density Functional TheoryJournal of Fluorescence, 2023
- The pyridazine heterocycle in molecular recognition and drug discoveryMedicinal Chemistry Research, 2023
- Physicochemical, spectral, molecular docking and ADMET studies of Bisphenol analogues; A computational approachInformatics in Medicine Unlocked, 2021
- Chemoinformatics at the CADD Group of the National Cancer Institute2018
- Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settingsAdvanced Drug Delivery Reviews, 1997