A Machine-Learning Protocol for Ultraviolet Protein-Backbone Absorption Spectroscopy under Environmental Fluctuations

Abstract

Ultraviolet (UV) absorption spectra are commonly used for characterizing the global structure of proteins. However, the theoretical interpretation of UV spectra is hindered by the large number of required expensive ab initio calculations of excited states spanning a huge conformation space. We present a machine-learning (ML) protocol for far-UV (FUV) spectra of proteins, which can predict FUV spectra of proteins with comparable accuracy to density functional theory (DFT) calculations but with 3−4 orders of magnitude reduced computational cost. It further shows excellent predictive power and transferability that can be used to probe structural mutations and protein folding pathways.

Efficient and Accurate Simulations of Vibrational and Electronic Spectra with Symmetry-Preserving Neural Network Models for Tensorial Properties

“…These results provide convincing evidence of the high accuracy and efficiency of the T-EANN TDM model. It has been successfully applied in reproducing accurate UV spectra of realistic proteins in solutions under environmental fluctuations with excellent predictive power and transferability . It should be noted that the present UV spectra have not included Franck–Condon factors from vibrational mode calculations, which will be considered in later work.…”

Accurate Machine Learning Prediction of Protein Circular Dichroism Spectra with Embedded Density Descriptors

“…The detailed results about ε 0 of peptide bonds and μ G of amino acid residues can be found in our previous work. 22 The results show that these simple molecular descriptors already warrant good accuracy and robustness of our ML models for ε 0 and μ G .…”

“…The detailed results about ε 0 of peptide bonds and μ G of amino acid residues can be found in our previous work. 22 The results show that these simple molecular descriptors already warrant good accuracy and robustness of our ML models for ε 0 and μ G . For the prediction of the more challenging electric and magnetic transition dipole moments of peptide bonds, we use the tensorial EANN model 29 based on the electron density-like atom-wise descriptors called embedded density descriptors, which are the square of a series of the linear combinations of Gaussian atomic orbitals from neighboring atoms.…”

“… 7 , 18 , 19 Along this track, we have also developed ML tools for predicting protein infrared (IR) and ultraviolet (UV) spectra. 20 − 22 …”

Machine learning recognition of protein secondary structures based on two-dimensional spectroscopic descriptors

“…There is a growing effort in applying data-driven ML approaches toward automated connection of molecular spectra to structures ( 10 – 13 ). This has motivated us to pursue ML protocols for predicting infrared and UV-visible (UV-vis) absorption spectra of proteins from their structures ( 14 – 16 ). Structure inversion (i.e., direct retrieval of protein structures from spectra) is more challenging and not well developed.…”