Translation of tissue-based artificial intelligence into clinical practice: from discovery to adoption

Environmental pollutants exposure-derived extracellular vesicles: crucial players in respiratory disorders

BACKGROUND

Individual exposure to environmental pollutants, as one of the most influential drivers of respiratory disorders, has received considerable attention due to its preventability and controllability. Considering that the extracellular vesicle (EV) was an emerging intercellular communication medium, recent studies have highlighted the crucial role of environmental pollutants derived EVs (EPE-EVs) in respiratory disorders.

METHODS

PubMed and Web of Science were searched from January 2018 to December 2023 for publications with key words of environmental pollutants, respiratory disorders and EVs.

RESULTS

Environmental pollutants could disrupt airway intercellular communication by indirectly stimulating airway barrier cells to secrete endogenous EVs, or directly transmitting exogenous EVs, mainly by biological pollutants. Mechanistically, EPE-EVs transferred specific contents to modulate biological functions of recipient cells, to induce respiratory inflammation and impair tissue and immune function, which consequently contributed to the development of respiratory diseases, such as asthma, chronic obstructive pulmonary disease, pulmonary fibrosis, pulmonary hypertension, lung cancer and infectious lung diseases. Clinically, EVs could emerged as promising biomarkers and biological agents for respiratory diseases attributed by their specificity, convenience, sensibility and stability.

CONCLUSIONS

Further studies of EPE-EVs are helpful to understand the aetiology and pathology of respiratory diseases, and facilitate the precision respiratory medicine in risk screening, early diagnosis, clinical management and biotherapy.

Artificial intelligence for high content imaging in drug discovery

Artificial intelligence (AI) and high-content imaging (HCI) are contributing to advancements in drug discovery, propelled by the recent progress in deep neural networks. This review highlights AI's role in analysis of HCI data from fixed and live-cell imaging, enabling novel label-free and multi-channel fluorescent screening methods, and improving compound profiling. HCI experiments are rapid and cost-effective, facilitating large data set accumulation for AI model training. However, the success of AI in drug discovery also depends on high-quality data, reproducible experiments, and robust validation to ensure model performance. Despite challenges like the need for annotated compounds and managing vast image data, AI's potential in phenotypic screening and drug profiling is significant. Future improvements in AI, including increased interpretability and integration of multiple modalities, are expected to solidify AI and HCI's role in drug discovery.