A Novel Virus Detection Strategy Enabled by TR512-Peptide-Based Bioorthogonal Capture and Enrichment of Preamplified Nucleic Acid.

High-cost viral nucleic acid detection devices (e.g., qPCR system) are limited resources for developing counties and rural areas, leading to underdiagnosis or even pandemics of viral infectious diseases. Herein, a novel virus detection strategy is reported. Such detection method is enabled by TR512-peptide-based biorthogonal capture and enrichment of commercially available Texas red fluorophore labeled nucleic acid on the functionalized paper. The GST-TR512 fusion protein electrostatically immobilized on the paper is constructed to retain the binding affinity of TR512-peptide toward Texas red fluorophore labeled nucleic acid released in the preamplification process, then the enrichment of analytes enhances fluorescence signal for rapid detection as volume of sample filters through the paper. The method is generally applicable to different nucleic acid preamplification strategies (PCR, RAA, CRISPR) and different virus types (Hepatitis B virus (HBV), African swine fever virus (ASFV), human papillomavirus (HPV), and severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2 or 2019 nCoV)). Finally, a full-set virus detection device is developed in house to detect the presence of Hepatitis B virus (HBV) viral gene in patients' blood samples. Taken together, we first apply TR512-peptide in the signal enrichment and the novel detection strategy may offer an inexpensive, rapid, and portable solution for areas with limited access to a standard diagnosis laboratory.

A deep adversarial model for segmentation-assisted COVID-19 diagnosis using CT images.

The outbreak of coronavirus disease 2019 (COVID-19) is spreading rapidly around the world, resulting in a global pandemic. Imaging techniques such as computed tomography (CT) play an essential role in the diagnosis and treatment of the disease since lung infection or pneumonia is a common complication. However, training a deep network to learn how to diagnose COVID-19 rapidly and accurately in CT images and segment the infected regions like a radiologist is challenging. Since the infectious area is difficult to distinguish manually annotation, the segmentation results are time-consuming. To tackle these problems, we propose an efficient method based on a deep adversarial network to segment the infection regions automatically. Then, the predicted segment results can assist the diagnostic network in identifying the COVID-19 samples from the CT images. On the other hand, a radiologist-like segmentation network provides detailed information of the infectious regions by separating areas of ground-glass, consolidation, and pleural effusion, respectively. Our method can accurately predict the COVID-19 infectious probability and provide lesion regions in CT images with limited training data. Additionally, we have established a public dataset for multitask learning. Extensive experiments on diagnosis and segmentation show superior performance over state-of-the-art methods.