Jin Zhao | PubMed Health

PubMed2026

Library strategies differentially shape microbial, functional, and host signals in clinical metagenomic sequencing.

Metagenomic next-generation sequencing (mNGS) is increasingly used in infectious disease diagnostics, yet how library preparation shapes the microbial, functional, and host signals recovered from clinical samples remains poorly defined. Here, we performed a within-sample parallel comparison of three mNGS library preparation strategies-DNA-based libraries (DNAlib), RNA-based libraries (RNAlib), and total nucleic acid-based libraries (TNAlib)-across a diverse range of clinical specimens spanning five sample types. Using a curated clinical infectome as a benchmark, we show that library strategies are not interchangeable but capture distinct biological dimensions of the same specimen. RNAlib provided the most comprehensive standalone recovery of the clinical infectome, with improved detection of RNA viruses and cellular pathogens, enhanced resolution of resistance and virulence signals, and preservation of infection-associated host immune signatures. DNAlib showed stronger baseline recovery of DNA viruses and broader host genome coverage, whereas the TNAlib workflow evaluated here largely behaved as an intermediate strategy rather than a consistent improvement over dedicated DNA- or RNA-based workflows. Together, these results establish that the library preparation protocol is a major determinant of how clinical mNGS data should be interpreted and provide a framework for selecting sequencing strategies according to specific diagnostic and biological questions.IMPORTANCEMetagenomic sequencing is increasingly used in infectious disease research and clinical diagnostics, but different library preparation strategies may recover fundamentally different biological signals from the same sample. These signals include not only pathogens but also background microbes, microbial functional activity, and host immune-response patterns. Here, we systematically compared DNA-, RNA-, and total nucleic acid-based metagenomic sequencing libraries using the same clinical samples processed in parallel. We found that the three strategies did not provide equivalent information. RNA-based sequencing generated the most informative single-library view of infection, particularly for RNA viruses, cellular pathogens, functional microbial signals, and host immune-response patterns. DNA-based sequencing was more effective for DNA virus and host genome recovery, whereas the total nucleic acid sequencing workflow evaluated here generally behaved as an intermediate strategy. These findings show that library preparation can substantially influence the interpretation of metagenomic data.

functional characterization↗

PubMed2026

Automated Classification of Lymphoma Subtypes From Histopathological Images Using a U-Net Deep Learning Model: Comparative Evaluation Study.

BACKGROUND: Accurate classification and grading of lymphoma subtypes are essential for treatment planning. Traditional diagnostic methods face challenges of subjectivity and inefficiency, highlighting the need for automated solutions based on deep learning techniques. OBJECTIVE: This study aimed to investigate the application of deep learning technology, specifically the U-Net model, in classifying and grading lymphoma subtypes to enhance diagnostic precision and efficiency. METHODS: In this study, the U-Net model was used as the primary tool for image segmentation integrated with attention mechanisms and residual networks for feature extraction and classification. A total of 620 high-quality histopathological images representing 3 major lymphoma subtypes were collected from The Cancer Genome Atlas and the Cancer Imaging Archive. All images underwent standardized preprocessing, including Gaussian filtering for noise reduction, histogram equalization, and normalization. Data augmentation techniques such as rotation, flipping, and scaling were applied to improve the model's generalization capability. The dataset was divided into training (70%), validation (15%), and test (15%) subsets. Five-fold cross-validation was used to assess model robustness. Performance was benchmarked against mainstream convolutional neural network architectures, including fully convolutional network, SegNet, and DeepLabv3+. RESULTS: The U-Net model achieved high segmentation accuracy, effectively delineating lesion regions and improving the quality of input for classification and grading. The incorporation of attention mechanisms further improved the model's ability to extract key features, whereas the residual structure of the residual network enhanced classification accuracy for complex images. In the test set (N=1250), the proposed fusion model achieved an accuracy of 92% (1150/1250), a sensitivity of 91.04% (1138/1250), a specificity of 89.04% (1113/1250), and an F1-score of 90% (1125/1250) for the classification of the 3 lymphoma subtypes, with an area under the receiver operating characteristic curve of 0.95 (95% CI 0.93-0.97). The high sensitivity and specificity of the model indicate strong clinical applicability, particularly as an assistive diagnostic tool. CONCLUSIONS: Deep learning techniques based on the U-Net architecture offer considerable advantages in the automated classification and grading of lymphoma subtypes. The proposed model significantly improved diagnostic accuracy and accelerated pathological evaluation, providing efficient and precise support for clinical decision-making. Future work may focus on enhancing model robustness through integration with advanced algorithms and validating performance across multicenter clinical datasets. The model also holds promise for deployment in digital pathology platforms and artificial intelligence-assisted diagnostic workflows, improving screening efficiency and promoting consistency in pathological classification.

Humans↗