Fig. 4: Machine learning (ML)-based identification and classification of proteoliposomes functionalized with different biomarkers. | npj 2D Materials and Applications

Fig. 4: Machine learning (ML)-based identification and classification of proteoliposomes functionalized with different biomarkers.

From: Proteoliposomes on 2D-MoS₂ plasmonic nanocavities for enhanced Raman spectroscopy with machine learning-based identification and classification

Fig. 4: Machine learning (ML)-based identification and classification of proteoliposomes functionalized with different biomarkers.

a Schematic representation of the ML pipeline used for SERS data analysis. b, c Normalized confusion matrices showing classification performance for different proteoliposome complexes using Random Forest Classifier (RFC) and Support Vector Machine (SVM), respectively. d, e Receiver Operating Characteristic (ROC) curves for each proteoliposome class generated by RFC and SVM, respectively. f, g Average classification accuracy across five independent train/test splits for RFC and SVM models, respectively, demonstrating model generalizability; note that training accuracy remained at 100%.

Back to article page