Information Bottleneck in Peptide Conformation Determination by X-ray Absorption Spectroscopy

TL;DR

This paper introduces an machine learning approach using emulator-based component analysis to identify key structural features from X-ray spectra of peptides, reducing complexity and providing insights into spectral behavior.

Contribution

The study applies a novel machine learning technique to analyze peptide spectra, demonstrating effective dimensionality reduction and revealing limitations in spectral interpretability of secondary structures.

Findings

Spectral variation correlates with structural differences across phase space.

Neural network successfully predicts spectral intensities from structure.

Secondary structure information is not recoverable solely from spectra.

Abstract

We apply a recently developed technique utilizing machine learning for statistical analysis of computational nitrogen K-edge spectra of aqueous triglycine. This method, the emulator-based component analysis, identifies spectrally relevant structural degrees of freedom from a data set filtering irrelevant ones out. Thus tremendous reduction in the dimensionality of the ill-posed nonlinear inverse problem of spectrum interpretation is achieved. Structural and spectral variation across the sampled phase space is notable. Using these data, we train a neural network to predict the intensities of spectral regions of interest from the structure. These regions are defined by the temperature-difference profile of the simulated spectra, and the analysis yields a structural interpretation for their behavior. Even though the utilized local many-body tensor representation implicitly encodes the secondary structure of the peptide, our approach proves that this information is irrecoverable from the spectra. A hard X-ray Raman scattering experiment confirms the overall sensibility of the simulated spectra, but the predicted temperature-dependent effects therein remain beyond the achieved statistical confidence level.