Raman spectra of amino acids and peptides from machine learning polarizabilities

TL;DR

This paper develops machine learning models to predict Raman spectra of amino acids and peptides by estimating polarizabilities, demonstrating transferability and good agreement with experimental data.

Contribution

It introduces neural network models trained on first-principles data for polarizability prediction, extending to peptides and improving transferability.

Findings

Neural network models outperform other ML models in transferability.

Predicted Raman spectra align well with experimental results.

Including peptide bonds in training enhances prediction accuracy for peptides.

Abstract

Raman spectroscopy is an important tool in the study of vibrational properties and composition of molecules, peptides and even proteins. Raman spectra can be simulated based on the change of the electronic polarizability with vibrations, which can nowadays be efficiently obtained via machine learning models trained on first-principles data. However, the transferability of the models trained on small molecules to larger structures is unclear and direct training on large structures in prohibitively expensive. In this work, we first train two machine learning models to predict polarizabilities of all 20 amino acids. Both models are carefully benchmarked and compared to DFT calculations, with neural network method found to offer better transferability. By combining machine learning models with classical force field molecular dynamics, Raman spectra of all amino acids are also obtained and investigated, showing good agreement with experiments. The models are further extended to small peptides. We find that adding structures containing peptide bonds to the training set greatly improves predictions even for peptides not included in training sets.