Ultrasensitive and Wash-Free Detection of Tumor Extracellular Vesicles by Aptamer-Proximity-Ligation-Activated Rolling Circle Amplification Coupled to Single Particle ICP-MS.

Tumor-derived extracellular vesicles (TEVs) are rich in cellular information and hold great promise as a biomarker for noninvasive cancer diagnosis. However, accurate measurement of TEVs presents challenges due to their low abundance and potential interference from a high number of EVs derived from normal cells. Herein, an aptamer-proximity-ligation-activated rolling circle amplification (RCA) method for EV membrane recognition, coupled with single particle inductively coupled plasma mass spectrometry (sp-ICP-MS) for the quantification of TEVs, is developed. When DNA-labeled ultrasmall gold nanoparticle (AuNP) probes bind to the long chains formed by RCA, they aggregate to form large particles. Notably, small AuNPs scarcely produce pulse signals in sp-ICP-MS, thereby detecting TEVs in a wash-free manner. By leveraging the strong binding affinity of aptamers, dual aptamers for EpCAM and PD-L1 recognition, and the sp-ICP-MS technique, this method offers remarkable sensitivity and selectivity in tracing TEVs. Under optimized conditions, the present method shows a favorable linear relationship between the pulse signal frequency of sp-ICP-MS and TEV concentration within the range of 105-107 particles/mL, along with a detection limit of 1.1 × 104 particles/mL. The pulse signals from sp-ICP-MS combined with machine learning algorithms are used to discriminate cancer patients from healthy donors with 100% accuracy. Due to its simple and fast operation and excellent sensitivity and accuracy, this approach holds significant potential for diverse applications in life sciences and personalized medicine.

Rapid and Accurate Identification of Cell Phenotypes of Different Drug Mechanisms by Using Single-Cell Fluorescence Images Via Deep Learning.

Identification of a drug mechanism is vital for drug development. However, it often resorts to the expensive and cumbersome omics methods along with complex data analysis. Herein, we developed a methodology to analyze organelle staining images of single cells using a deep learning algorithm (TL-ResNet50) for rapid and accurate identification of different drug mechanisms. Based on the organelle-related cell morphological changes caused by drug action, the constructed deep learning model can fast predict the drug mechanism with a high accuracy of 92%. Further analysis reveals that drug combination at different ratios can enhance a certain mechanism or generate a new mechanism. This work would highly facilitate clinical medication and drug screening.

Deep Learning Promotes Profiling of Multiple miRNAs in Single Extracellular Vesicles for Cancer Diagnosis.

Extracellular vesicle microRNAs (EV miRNAs) are critical noninvasive biomarkers for early cancer diagnosis. However, accurate cancer diagnosis based on bulk analysis is hindered by the heterogeneity among EVs. Herein, we report an approach for profiling single-EV multi-miRNA signatures by combining total internal reflection fluorescence (TIRF) imaging with a deep learning (DL) algorithm for the first time. This innovative technique allows for the precise characterization of EV miRNAs at the single-vesicle level, overcoming the challenges posed by EV heterogeneity. TIRF with high resolution and a signal-to-noise ratio can simultaneously detect multi-miRNAs in situ in individual EVs. DL algorithm avoids complicated and inaccurate artificial feature extraction, achieving automated high-resolution image analysis. Using this approach, we reveal that the main variation of EVs from 5 cancer cells and normal plasma is the triple-positive EV subpopulation, and the classification accuracy of single triple-positive EVs from 6 sources can reach above 95%. In the clinical cohort, 20 patients (5 lung cancer, 5 breast cancer, 5 cervical cancer, and 5 colon cancer) and 5 healthy controls are predicted with an overall accuracy of 100%. This single-EV strategy provides new opportunities for exploring more specific EV biomarkers to achieve cancer diagnosis and classification.

A machine learning-based colorimetric sensor array for high-precision pathogen identification in household refrigerators.

A precise and convenient sensor was constructed to identify pathogens in household refrigerators (4 °C, RH = 55%) by integrating a volatile organic compound fingerprint-responsive gel-based colorimetric sensor array and a neural network. The platform is expected to be extended to the intelligent food packaging field and has promise for point-of-need monitoring of pathogens.