Researchers from the Xinjiang Technical Institute of Physics and Chemistry (XTIPC) of the Chinese Academy of Sciences have developed a novel method combining Raman spectroscopy with deep learning algorithms. This approach enables accurate differentiation and identification of CA series synthetic cannabinoids—characterized by amide groups as head groups—despite their highly similar molecular structures.
Raman spectroscopy typically struggles with structurally similar compounds as they are often too alike to distinguish visually. However, the research team overcame this hurdle by developing a convolutional neural network (CNN) algorithm integrated with an attention mechanism module, achieving precise differentiation of CA series synthetic cannabinoids.
According to the paper is published in Analytical Chemistry, the team utilized three different CNN models—VGG16, DenseNet121, and ResNet34—but they did not perform well. That is, until the team incorporated the SENet (Squeeze-and-Excitation Network) attention mechanism module into ResNet34. Then, the team elevated the classification accuracy to 100%, enabling precise discrimination of six synthetic cannabinoids.
Furthermore, the researchers employed an attribution algorithm to identify the most discriminative Raman spectral bands used by the SE_ResNet34 model during classification. This analysis revealed how the algorithm distinguishes between multiple targets based on subtle spectral differences, offering insights into the internal logic behind the model's accurate classification—a key step toward understanding deep learning-driven analytical processes.
The SE_ResNet34 model also demonstrated generalization capabilities. Tests confirmed its 100% classification accuracy remains unaffected by variations in target concentration, the presence of structural analogs, or interference from other common drugs.
Data courtesy of Chinese Academy of Sciences