Oscillator Strength Predictor

This model predicts the oscillator strength of a molecule's UV absorption. Oscillator strength is a dimensionless quantity that describes how strongly a molecule absorbs light at its absorption wavelength — a higher value indicates a more intense absorption, which is an important characteristic for UV filter performance.

Training Data

The model was trained on a combined dataset of two sources:

• Computational data: oscillator strength values calculated using quantum chemistry simulations (ORCA software) for a broad and diverse set of organic molecules.
• Experimental data: measured oscillator strength values for known UV filter compounds, sourced from the ECHA (European Chemicals Agency) database.

To ensure that the model performs well for UV filter-like molecules — which are the primary target of this application — the experimental ECHA data was given higher weight during training. Only molecules with λmax ≤ 750 nm were included.

The dataset was split into a training set (80%) and a held-out test set (20%) to evaluate how well the model generalises to new, unseen molecules.

How Molecules Are Represented

Molecules are represented using molecular descriptors — a set of numerical values that capture structural and physicochemical properties of a molecule, such as the number and type of rings, the presence of specific chemical groups, and electronic surface properties. These descriptors are computed automatically from the molecular structure (provided as a SMILES string) using the RDKit cheminformatics library.

Feature Selection

Starting from over 200 molecular descriptors, a multi-step selection process was applied to identify the most informative ones:

1. Descriptors with no variation across the dataset were removed.
2. Highly redundant descriptors (those carrying nearly identical information) were eliminated.
3. A recursive feature elimination procedure was used to rank descriptors by their contribution to prediction accuracy, and cross-validation was used to determine the optimal number to retain.

This process resulted in 20 descriptors being selected for the final model:

BalabanJ, PEOE_VSA5, SMR_VSA2, SMR_VSA6, SMR_VSA9, SlogP_VSA8, VSA_EState3, VSA_EState5, VSA_EState7, NumAromaticCarbocycles, MolLogP, fr_Imine, fr_allylic_oxid, fr_aniline, fr_azo, fr_bicyclic, fr_hdrzone, fr_imidazole, fr_ketone, fr_oxazole

Algorithm

The model is based on XGBoost (Extreme Gradient Boosting).

Performance