Chemical Space-Informed Machine Learning Models for Rapid Predictions of X-ray Photoelectron Spectra of Organic Molecules

TL;DR

This study develops machine learning models using kernel-ridge regression and transfer learning to rapidly predict X-ray photoelectron spectra of organic molecules, enabling efficient virtual screening with reasonable accuracy.

Contribution

The paper introduces a cost-effective ML framework combining kernel-ridge regression, transfer learning, and baseline spectra to predict core-electron binding energies for organic molecules.

Findings

Models show strong linear correlation with target CEBEs.

Applicable to large, substituted molecules beyond training set.

Dataset and models are available as an open Python module.

Abstract

We present machine learning models based on kernel-ridge regression for predicting X-ray photoelectron spectra of organic molecules originating from the $K$-shell ionization energies of carbon (C), nitrogen (N), oxygen (O), and fluorine (F) atoms. We constructed the training dataset through high-throughput calculations of $K$-shell core-electron binding energies (CEBEs) for 12,880 small organic molecules in the bigQM7$\omega$ dataset, employing the $\Delta$-SCF formalism coupled with meta-GGA-DFT and a variationally converged basis set. The models are cost-effective, as they require the atomic coordinates of a molecule generated using universal force fields while estimating the target-level CEBEs corresponding to DFT-level equilibrium geometry. We explore transfer learning by utilizing the atomic environment feature vectors learned using a graph neural network framework in kernel-ridge regression. Additionally, we enhance accuracy within the $\Delta$-machine learning framework by leveraging inexpensive baseline spectra derived from Kohn--Sham eigenvalues. When applied to 208 combinatorially substituted uracil molecules larger than those in the training set, our analyses suggest that the models may not provide quantitatively accurate predictions of CEBEs but offer a strong linear correlation relevant for virtual high-throughput screening. We present the dataset and models as the Python module, ${\tt cebeconf}$, to facilitate further explorations.