StateFlux: DFT-Validated Quantum Reactivity across Predicted Metabolic State Networks Shows Limited Incremental Value for Broad Toxicity Prediction
- 1Stanford University, 415 Broadway, Redwood City, California, 94063
Abstract
Mechanistic molecular representations are increasingly used to supplement parent structure with protonation, metabolism, and quantum-chemical reactivity, but added physical detail does not necessarily provide predictive information beyond structure. StateFlux represents each drug as a network of chemical and predicted metabolic states with node-level GFN2-xTB properties and edge-resolved changes in ionization potential, electron affinity, electrophilicity, solvation, and local reactivity. On a locked DILIrank 2.0 development set (n = 376; 156 positive and 220 negative), 10 × 5 scaffold-grouped validation gave AUROC/AUPRC values of 0.8249/0.7727 for ECFP, 0.8049/0.7430 for ECFP + FluxCore, and 0.8010/0.7261 for ECFP + StateFluxCore. Strict temporal and scaffold-novel tests showed no consistent gain, and an independent 5,367-compound genotoxicity transfer benchmark reproduced the pattern (AUROC 0.7765 for ECFP versus 0.7732 for StateFluxCore). To separate limited predictive utility from inaccurate low-cost quantum chemistry, 24 parent-to-metabolite transformations were evaluated with 144 ωB97X-D/6-31+G*/SMD single-point calculations. GFN2-xTB closely tracked DFT changes in electrophilicity (Pearson r = 0.963; MAE = 0.408 eV; 79.2% sign agreement). Thus, transformation-induced quantum reactivity can be consistent with higher-level DFT without providing reliable incremental information for broad toxicity classification. Quantum-chemical fidelity and predictive utility should therefore be evaluated as separate claims in chemical machine learning.
Related
- StateFlux: Physically Validated Quantum Metabolic State Networks Reveal Limited Incremental Value for Toxicity Prediction
- Site-Resolved Prediction of Mayr Nucleophilicity with Reactivity-Pretrained Graph Neural Networks
- Rotamer-Dependent Amino Acid Descriptors as Protein and Peptide Representation for Reactivity and Property Prediction
- Tensor-based Approximation of Molecular Kinetics: Generator Learning, Reaction Coordinates and Incremental Updating
- Reactivity of a Bis(alkynyl)-Vinylidene Osmium Complex: Access to Carbynes, Vinyl Ester Derivatives, and C–C and C–N Bond-Forming Reactions
BibTeX
@misc{tsai2026stateflux,
title = {{StateFlux: DFT-Validated Quantum Reactivity across Predicted Metabolic State Networks Shows Limited Incremental Value for Broad Toxicity Prediction}},
author = {Aris Tsai},
howpublished = {ChemRxiv},
year = {2026},
month = sep,
doi = {10.26434/chemrxiv.15009594/v1},
url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009594/v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - StateFlux: DFT-Validated Quantum Reactivity across Predicted Metabolic State Networks Shows Limited Incremental Value for Broad Toxicity Prediction
AU - Aris Tsai
PY - 2026
DA - 2026/09/28
PB - ChemRxiv
DO - 10.26434/chemrxiv.15009594/v1
UR - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009594/v1
AB - Mechanistic molecular representations are increasingly used to supplement parent structure with protonation, metabolism, and quantum-chemical reactivity, but added physical detail does not necessarily provide predictive information beyond structure. StateFlux represents each drug as a network of chemical and predicted metabolic states with node-level GFN2-xTB properties and edge-resolved changes in ionization potential, electron affinity, electrophilicity, solvation, and local reactivity. On a locked DILIrank 2.0 development set (n = 376; 156 positive and 220 negative), 10 × 5 scaffold-grouped validation gave AUROC/AUPRC values of 0.8249/0.7727 for ECFP, 0.8049/0.7430 for ECFP + FluxCore, and 0.8010/0.7261 for ECFP + StateFluxCore. Strict temporal and scaffold-novel tests showed no consistent gain, and an independent 5,367-compound genotoxicity transfer benchmark reproduced the pattern (AUROC 0.7765 for ECFP versus 0.7732 for StateFluxCore). To separate limited predictive utility from inaccurate low-cost quantum chemistry, 24 parent-to-metabolite transformations were evaluated with 144 ωB97X-D/6-31+G*/SMD single-point calculations. GFN2-xTB closely tracked DFT changes in electrophilicity (Pearson r = 0.963; MAE = 0.408 eV; 79.2% sign agreement). Thus, transformation-induced quantum reactivity can be consistent with higher-level DFT without providing reliable incremental information for broad toxicity classification. Quantum-chemical fidelity and predictive utility should therefore be evaluated as separate claims in chemical machine learning.
ER -