Predicting Structural Motifs of Glycosaminoglycans using Cryogenic Infrared Spectroscopy and Random Forest

Abstract

In recent years, glycosaminoglycans (GAGs) have emerged into the focus of biochemical and biomedical research due to their importance in a variety of physiological processes. These molecules show great diversity, which makes their analysis highly challenging. A promising tool for identifying the structural motifs and conformation of shorter GAG chains is cryogenic gas-phase infrared (IR) spectroscopy. In this work, the cryogenic gas-phase IR spectra of mass-selected heparan sulfate (HS) di-, tetra-, and hexasaccharide ions were recorded to extract vibrational features that are characteristic to structural motifs. The data were augmented with chondroitin sulfate (CS) disaccharide spectra to assemble a training library for random forest (RF) classifiers. These were used to discriminate between GAG classes (CS or HS) and different sulfate positions (2-O-, 4-O-, 6-O-, and N-sulfation). With optimized data preprocessing and RF modeling, a prediction accuracy of >97% was achieved for HS tetra- and hexasaccharides based on a training set of only 21 spectra. These results exemplify the importance of combining gas-phase cryogenic IR ion spectroscopy with machine learning to improve the future analytical workflow for GAG sequencing and that of other biomolecules, such as metabolites.

Patch-Based Convolutional Encoder: A Deep Learning Algorithm for Spectral Classification Balancing the Local and Global Information

“…Especially, the nondestructive nature of the spectroscopy methods allows the in situ dynamic tracking of chemical and biological samples. When it comes to the real systems, due to the overwhelming contribution from the complicated matrix, it is hard to identify the spectral information from the target by naked eyes, which could only be realized with the introduction of chemometrics. − In recent years, deep-learning-based chemometrics has grown rapidly owing to the explosion of data volumes and increased computer performance. The strong feature extraction of deep learning allows it to acutely identify and capture subtle differences between complex signals .…”

GlAIcomics: a deep neural network classifier for spectroscopy-augmented mass spectrometric glycans data

“…Support vector machines (SVM) and decision tree ensemble methods were benchmarked on infrared spectra for cancer classification [ 8 ] and many research groups focused their efforts on using machine learning for simulating molecular structures; generating vibrational spectra; and classifying chemical groups based on vibrational features [ 9 – 10 ]. In a recent publication, the random forest approach was proposed to identify the presence of structural features in oligosaccharides based on their gas-phase IR spectra [ 11 ]. To the best of our knowledge, machine learning classification studies have not been reported to identify saccharides using MS–IR carbohydrate analysis.…”

The Structure Determination of Organic Molecules by Co-crystallization of Anthracene-Based Crystallization Chaperone

“…Whether the organic compounds are natural products − or synthesized by chemists, it is extremely important to determine their structures and absolute conformations at the atomic level. Over the past few decades, numerous researchers have developed and refined many methods for the structural identification of organic molecules, such as nuclear magnetic resonance ( NMR ), − infrared spectroscopy ( IR ), − mass spectrometry ( MS ), − single crystal X-ray diffraction ( X-ray SCD ), − etc. Among them, X-ray SCD can provide direct and accurate structural information and is globally recognized as a fairly reliable method for the structural identification of organic compounds, including their stereochemical conformation.…”