Paper summary · Journal of Chemical Theory and Computation · 2026

Faster predictions for excited states

Using a learned correction to improve fast estimates of how organic molecules respond to light.

The question

Detailed calculations of excited-state energies are costly when you want to compare thousands of molecules. Could we start with a much faster method and learn where it tends to get things wrong?

The approach

The model combines a graph representation of the molecule with descriptors from an inexpensive ZINDO calculation. It learns the difference between ZINDO and the TDDFT reference, then adds that correction to the fast prediction.

What we found

On a test set of 9,500 molecules, the best model raised the correlation for first excited-state energies from 0.77 to 0.96. The reference values were calculated with TDDFT for this benchmark. The paper also tested the approach for oscillator strengths, which describe how strongly a transition can absorb or emit light.

Paper

Predicting S1 TDDFT Energies from ZINDO Calculations Using Message-Passing ΔML with Electronically Informed Descriptors
Adam Coxson, Ömer H. Omar, Marcos del Cueto, and Alessandro Troisi

Published JCTC 2026 benchmarks comparing ZINDO vs ZINDO plus ΔML Pearson correlation on M06-2X S1 (0.77 to 0.96), QCDGE (0.88 to 0.99), and oscillator strength (0.52 to 0.84)
Published JCTC 2026 correlation benchmarks across M06-2X (9.5k), QCDGE (24k), and oscillator strength screening (~2 ms ΔML overhead).

Explore hole–electron charge separation in 3D

Rotate real unseen test molecules spanning Charge-Transfer (CT), Local Exciton (LE), and hybrid states, inspect atomic ZINDO/Multiwfn hole and electron weights, and see why electronic descriptors drive Δ-ML accuracy.

Interactive 3D Hole–Electron Charge-Separation Explorer Drag to rotate · Hover atoms · Switch S₁ / T₁
Hole-electron exciton anatomy comparing charge-transfer and local-exciton S1 states
Exciton anatomy (CT vs. LE): Disc area scales with hole + electron participation; arrow marks charge-transfer distance DCT.
Exciton descriptor landscape over 2,744 unseen test molecules showing LE to CT regimes and ZINDO error correlations
Exciton physics landscape (N = 2,744): Hole–electron overlap Sr and spatial separation track systematic raw ZINDO errors.

Sneak peek: ongoing Δ-ML development

Papers inbound over this year—new descriptors, new architectures, and lower errors across singlets, triplets, and singlet–triplet gaps (0.00% state-ordering violations across 2,744 unseen test molecules).

Interactive Parity Raw ZINDO vs. Next-Gen Δ-ML vs. TDDFT (N = 2,744) Switch baselines · Hover/tap molecules · Live RMSE & MAE