High Throughput and Noninvasive Exosomal PD-L1 Detection for Accurate Immunotherapy Response Prediction via Tim4-Functionalized Magnetic Core-Shell Metal-Organic Frameworks

A highly sensitive point-of-care detection platform for Salmonella typhimurium by integrating magnetic enrichment and fluorescent CsPbBr3@SiO2

A platform was designed based on Fe3O4 and CsPbBr3@SiO2 for integrated magnetic enrichment-fluorescence detection of Salmonella typhimurium, which significantly simplifies the detection process and enhances the working efficiency. Fe3O4 served as a magnetic enrichment unit for the capture of S. typhimurium. CsPbBr3@SiO2 was employed as a fluorescence-sensing unit for quantitative signal output, where SiO2 was introduced to strengthen the stability of CsPbBr3, improve its biomodificability, and prevent lead leakage. More importantly, the SiO2 shell shows neglectable absorption or scattering towards fluorescence, making the CsPbBr3@SiO2 exhibit a high quantum yield of 74.4%. After magnetic enrichment, the decreasing rate of the fluorescence emission intensity of the CsPbBr3@SiO2 supernatant at 527 nm under excitation light at UV 365 nm showed a strong linear correlation with S. typhimurium concentration of 1 × 102~1 × 108 CFU∙mL-1, and the limit of detection (LOD) reached 12.72 CFU∙mL-1. This platform has demonstrated outstanding stability, reproducibility, and resistance to interference, which provides an alternative for convenient and quantitative detection of S. typhimurium.

Advances of machine learning-assisted small extracellular vesicles detection strategy

Detection of extracellular vesicles (EVs), particularly small EVs (sEVs), is of great significance in exploring their physiological characteristics and clinical applications. The heterogeneity of sEVs plays a crucial role in distinguishing different types of cells and diseases. Machine learning, with its exceptional data processing capabilities, offers a solution to overcome the limitations of conventional detection methods for accurately classifying sEV subtypes and sources. Principal component analysis, linear discriminant analysis, partial least squares discriminant analysis, XGBoost, support vector machine, k-nearest neighbor, and deep learning, along with some combined methods such as principal component-linear discriminant analysis, have been successfully applied in the detection and identification of sEVs. This review focuses on machine learning-assisted detection strategies for cell identification and disease prediction via sEVs, and summarizes the integration of these strategies with surface-enhanced Raman scattering, electrochemistry, inductively coupled plasma mass spectrometry and fluorescence. The performance of different machine learning-based detection strategies is compared, and the advantages and limitations of various machine learning models are also evaluated. Finally, we discuss the merits and limitations of the current approaches and briefly outline the perspective of potential research directions in the field of sEV analysis based on machine learning.