nablaColors: A 3D Benchmark for Optical Property Prediction with Solvent-aware Graph Neural Networks

Accurately predicting optical spectra of molecules is essential for creating better OLED emitters, solar-cell dyes, and fluorescent probes. Traditional methods, such as time-dependent density- functional theory, are computationally expensive and often inaccurate. Current Graph Neural Network (GNN) approaches for optical properties prediction are faster and offer better perfor- mance. Still, they operate on 2D graphs and ignore the 3D geometrical features that control excited-state behavior. We present ∇Colors-3D, a rigorously curated dataset for the prediction of optical properties consisting of 26 369 chromophore-solvent pairs with three conformations opti- mized at different levels of quantum theory. Based on this dataset, we establish a scaffold-split benchmark for 3D GNNs and systematically quantify how the fidelity of geometry optimization affects accuracy. Furthermore, we propose a solvent-aware modification for pretrained SE(3)- invariant architectures. Our best model, built on UniMol+, achieves MAE of 17.7 nm on a held-out test set, improving the previous state of the art by nearly 25%.