Identification of D- and L-phenylalanine enantiomeric mixtures by employing deep neural network models.

Phenylalanine is an aromatic essential amino acid that exhibits the tendency to self-aggregate into fibrillar structures in its enantiomerically pure form. This observation was indicated as the underlying mechanism of phenylketonuria, which is a genetic condition associated with various neurological, physical, and developmental issues, characterized with phenylalanine buildup in the brain. The presence of D-phenylalanine was demonstrated previously to inhibit the formation of fibrils by L-phenlyalanine, indicating its potential use in phenylketonuria treatment. In this study, several combinations of D and L-phenylalanine were examined with the help of state-of-the-art deep learning methods for their fibril forming capacity, demonstrating the usefulness and accuracy of deep learning methods in distinguishing between different self-assembled structures. • This study addressed the classification of D- and L-phenylalanine images. • A total of 525 images for 7 different mixing ratios were collected with a Nikon ECLIPSE LV150N microscope at 500x. • An accuracy value of 99% was obtained by using deep learning models for classification. [ABSTRACT FROM AUTHOR]