DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning.

We report a fast, easy-to-implement, highly sensitive, sequence-specific, and point-of-care (POC) DNA virus detection system, which combines recombinase polymerase amplification (RPA) and CRISPR/Cas12a system for trace detection of DNA viruses. Target DNA is amplified and recognized by RPA and CRISPR/Cas12a separately, which triggers the collateral cleavage activity of Cas12a that cleaves a fluorophore-quencher labeled DNA reporter and generalizes fluorescence. For POC detection, portable smartphone microscopy is built to take fluorescent images. Besides, deep learning models for binary classification of positive or negative samples, achieving high accuracy, are deployed within the system. Frog virus 3 (FV3, genera Ranavirus, family Iridoviridae) was tested as an example for this DNA virus POC detection system, and the limits of detection (LoD) can achieve 10 aM within 40 min. Without skilled operators and bulky instruments, the portable and miniature RPA-CRISPR/Cas12a-SPM with artificial intelligence (AI) assisted classification shows great potential for POC DNA virus detection and can help prevent the spread of such viruses.

Detection of Frog Virus 3 by Integrating RPA-CRISPR/Cas12a-SPM with Deep Learning.

A fast, easy-to-implement, highly sensitive, and point-of-care (POC) detection system for frog virus 3 (FV3) is proposed. Combining recombinase polymerase amplification (RPA) and CRISPR/Cas12a, a limit of detection (LoD) of 100 aM (60.2 copies/µL) is achieved by optimizing RPA primers and CRISPR RNAs (crRNAs). For POC detection, smartphone microscopy is implemented, and an LoD of 10 aM is achieved in 40 min. The proposed system detects four positive animal-derived samples with a quantitation cycle (Cq) value of quantitative PCR (qPCR) in the range of 13 to 32. In addition, deep learning models are deployed for binary classification (positive or negative samples) and multiclass classification (different concentrations of FV3 and negative samples), achieving 100 and 98.75% accuracy, respectively. Without temperature regulation and expensive equipment, the proposed RPA-CRISPR/Cas12a combined with smartphone readouts and artificial-intelligence-assisted classification showcases the great potential for FV3 detection, specifically POC detection of DNA virus.

RCMNet: A deep learning model assists CAR-T therapy for leukemia.

Acute leukemia is a type of blood cancer with a high mortality rate. Current therapeutic methods include bone marrow transplantation, supportive therapy, and chemotherapy. Although a satisfactory remission of the disease can be achieved, the risk of recurrence is still high. Therefore, novel treatments are demanding. Chimeric antigen receptor-T (CAR-T) therapy has emerged as a promising approach to treating and curing acute leukemia. To harness the therapeutic potential of CAR-T cell therapy for blood diseases, reliable cell morphological identification is crucial. Nevertheless, the identification of CAR-T cells is a big challenge posed by their phenotypic similarity with other blood cells. To address this substantial clinical challenge, herein we first construct a CAR-T dataset with 500 original microscopy images after staining. Following that, we create a novel integrated model called RCMNet (ResNet18 with Convolutional Block Attention Module and Multi-Head Self-Attention) that combines the convolutional neural network (CNN) and Transformer. The model shows 99.63% top-1 accuracy on the public dataset. Compared with previous reports, our model obtains satisfactory results for image classification. Although testing on the CAR-T cell dataset, a decent performance is observed, which is attributed to the limited size of the dataset. Transfer learning is adapted for RCMNet and a maximum of 83.36% accuracy is achieved, which is higher than that of other state-of-the-art models. This study evaluates the effectiveness of RCMNet on a big public dataset and translates it to a clinical dataset for diagnostic applications.

Pigment analysis based on a line-scanning fluorescence hyperspectral imaging microscope combined with multivariate curve resolution.

A rapid and cost-effective system is vital for the detection of harmful algae that causes environmental problems in terms of water quality. The approach for algae detection was to capture images based on hyperspectral fluorescence imaging microscope by detecting specific fluorescence signatures. With the high degree of overlapping spectra of algae, the distribution of pigment in the region of interest was unknown according to a previous report. We propose an optimization method of multivariate curve resolution (MCR) to improve the performance of pigment analysis. The reconstruction image described location and concentration of the microalgae pigments. This result indicated the cyanobacterial pigment distribution and mapped the relative pigment content. In conclusion, with the advantage of acquiring two-dimensional images across a range of spectra, HSI conjoining spectral features with spatial information efficiently estimated specific features of harmful microalgae in MCR models.

CONNECTIONS BET WEEN VESICULAR GLUTAMATE TRANSPORTERS-,GAD-LIKE IMMUNOREACTIVE TERMINALS AND GABA_A RECEPTOR ?3 SUBUNIT- LIKE POSITIVE NEURONS IN MESENCEPHALIC TRIGEMINAL NUCLEUS OF THE RAT / 解剖学报

Objective To observe the association of vesicular glutamate transporter of typeⅠ (VGluT1 ) like immunoreactive(LI) ,the differentiation-associated Na+ dependent inorganic phosphate cotransporter(DNPI) LI and glutami cacid decarboxy lase(GAD) LI terminals with GABAA receptor ?3 subunit(GABAAR ?3) LI neurons in mesencephalic trige minal nucleus of the rat.Methods Triple immun of luorescencehis to chemical staining technique and confo call aser scanning micros copy were used.Results Alargenumber of neuronal cell bodies showed GABAA R?3 LI immunoreactivity atallrostrocaudal level softhe Vme ,and most of GABAAR ?3 LI cells were large (2 5 5 0 ?m)pseudouni polarneurons.The dense VGluT1 LI,DNPL LI and GAD LIterminal sdistri buted widelyin Vme ,some VGlu T1 DNPI LI and GAD LIterminals surrounded the somata of the GABAAR ?3 LI Vmeneurons ,and made close contacts with them .Conclusion Proprioceptive sensory signals from the or of acialregionmight be modulated at the level of the primary afferent cell bodies in the Vme both by glutamatergic and GABAergic axonal terminals from other brain areas,and the effect of GABAergic terminals might be mediated by post synaptical GABAA receptors .