Work

Chirality recognition of amino acid by combining machine learning method and sliding window technique

Year: 2025

Type: article

Abstract: Chiral molecule recognition is crucial in life sciences, pharmaceuticals, disease diagnostics, and environmental protection. Infrared (IR) spectroscopy enables amino acid identification by detecting characteristic absorption peaks of the functional groups. However, the complexity of IR spectral data limits the use of traditional analytical methods. This work integrated machine learning (ML) with experimental IR spectroscopy to distinguish L- and D-amino acids using a sliding-window approach across spectral regions. Three ML algorithms - error-correcting output codes-support vector machine (ECOC-SVM), principal component analysis-random forest (PCA-RF), and partial least squares-discrimination analysis (PLS-DA) - were employed to distinguish alanine (Ala), cysteine (Cys), and glutamine (Gln), respectively. Results revealed that the sensitivity of chiral recognition varies significantly with spectral region, window size, and step length. Experimental findings highlight the potential of ML-assisted IR spectroscopy for precise chiral amino acid recognition, advancing its applications in analytical chemistry, biomedicine, and pharmaceutical sciences.

Source: Optics & Laser Technology

DOI: 10.1016/j.optlastec.2025.113937