Artificial intelligence-enabled microsphere imaging immunosensor based on magnetic metal-organic frameworks-assisted sample pretreatment for detecting aflatoxin B1 in peanuts

Sensitive and rapid detection of aflatoxin B₁ (AFB₁) is vital for safeguarding food safety, considering its potent carcinogenic toxicity. Herein, an artificial intelligence-enabled microsphere imaging (AI-MI) immunosensor based on magnetic metal-organic frameworks-assisted sample pretreatment was developed for detecting AFB₁ in peanuts. In this work, Fe₃O₄@MIL-101(Fe) served as a magnetic adsorbent to efficiently enrich AFB₁. Based on the competitive immunoreaction, the enriched AFB₁ modulated the amount of horseradish peroxidase (HRP)-labeled goat anti-mouse antibody conjugated on the polystyrene (PS) immuno-microsphere. The HRP can catalyze the rapid formation of polydopamine on the surface of the PS microsphere with additional hydrogen peroxide. Due to the abundant functional groups, the polydopamine coating could adsorb amino-functionalized magnetic nanoparticles to form PS probes. The PS probes were magnetically separated, visualized with an optical microscope, and counted using a computer vision algorithm. Finally, the changes in the number of PS probes were correlated with the amount of AFB₁. Under optimized conditions, Fe₃O₄@MIL-101(Fe) exhibited remarkable enrichment capacity (1.59 mg/g), and the AI-MI immunosensor showed a high sensitivity (4.90 pg/mL, 19-fold improvement over enzyme-linked immunosorbent assay) and a wide linear range (from 0.01 to 500 ng/mL) for AFB₁. This AI-MI immunosensor holds significant promise for intelligent detection of trace toxins.