Fluorescent sensor array for rapid bacterial identification using antimicrobial peptide-functionalized gold nanoclusters and machine learning.

Bacterial infectious diseases pose significant challenges to public health, emphasizing the need for rapid and accurate diagnostic tools. Here, we introduced a multichannel fluorescent sensor array based on antimicrobial peptide-functionalized gold nanoclusters (AMP-AuNCs) designed for precise bacterial identification. By utilizing the unique electrostatic and hydrophobic properties of three AMP-AuNCs, this sensor array generated distinct fluorescence patterns upon binding to different bacterial species. Machine learning algorithms, including Principal Component Analysis (PCA), Hierarchical Clustering Analysis (HCA), and Linear Discriminant Analysis (LDA), were employed to analyze fluorescence fingerprint patterns and identify bacterial strains with high accuracy. The sensor array achieved 100 % accuracy in identifying six common bacterial species and demonstrated an 86.7 % accuracy in classifying clinical Escherichia coli isolates from urinary tract infections. This AMP-AuNC-based sensor array offers a promising approach for rapid and precise bacterial diagnostics, with potential applications in clinical settings for combating antibiotic resistance.