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

This dataset provides curated molecular conformations and predefined splits for benchmarking machine learning models in optical absorption prediction. The core file, absorption_conformations.zip, contains an LMDB database of molecular geometries optimized at multiple levels of theory (xTB, DFT in vacuum, and DFT with implicit solvent). The accompanying CSV files (absorption_pairs_all.csv, absorption_train.csv, absorption_val.csv, absorption_test.csv) define the train/validation/test splits for supervised absorption prediction. To support robust evaluation, scaffold-based cross-validation splits are also provided for both single-property absorption (absorption_crossval.zip) and multitarget learning (multitarget_crossval.zip). The files smiles_to_replace.csv and smiles_to_remove.csv document corrections and exclusions applied during curation to ensure dataset quality. Together, these resources enable reproducible training and evaluation of 2D and 3D models for molecular optical property prediction.

Examples of how to read from the LMDB databases are available at: https://github.com/AI4DD/nablaColors.

This dataset compiles experimental data on absorption and emission maxima, as well as photoluminescence quantum yield, from the following sources: Joung et al. (2020), Ju et al. (2021), Venkatraman et al. (2018), and Venkatraman & Chellappan (2020).

In addition to the dataset and splits, this release includes four pretrained UniProp checkpoints trained on the provided conformations. Examples of validation and inference available at: https://github.com/AI4DD/nablaColors.