DA-ActNN-YOLOV5: Hybrid YOLO v5 Model with Data Augmentation and Activation of Compression Mechanism for Potato Disease Identification.

To solve the problems of weak generalization of potato early and late blight recognition models in real complex scenarios, susceptibility to interference from crop varieties, colour characteristics, leaf spot shapes, disease cycles and environmental factors, and strong dependence on storage and computational resources, an improved YOLO v5 model (DA-ActNN-YOLOV5) is proposed to study potato diseases of different cycles in multiple regional scenarios. Thirteen data augmentation techniques were used to expand the data to improve model generalization and prevent overfitting; potato leaves were extracted by YOLO v5 image segmentation and labelled with LabelMe for building data samples; the component modules of the YOLO v5 network were replaced using model compression technology (ActNN) for potato disease detection when the device is low on memory. Based on this, the features extracted from all network layers are visualized, and the extraction of features from each network layer can be distinguished, from which an understanding of the feature learning behavior of the deep model can be obtained. The results show that in the scenario of multiple complex factors interacting, the identification accuracy of early and late potato blight in this study reached 99.81%. The introduced data augmentation technique improved the average accuracy by 9.22%. Compared with the uncompressed YOLO v5 model, the integrated ActNN runs more efficiently, the accuracy loss due to compressed parameters is less than 0.65%, and the time consumption does not exceed 30 min, which saves a lot of computational cost and time. In summary, this research method can accurately identify potato early and late blight in various scenarios.

Metabolism of GTI-2040, a phosphorothioate oligonucleotide antisense, using ion-pair reversed phase high performance liquid chromatography (HPLC) coupled with electrospray ion-trap mass spectrometry.

GTI-2040 is a 20-mer phosphorothioate oligonucleotide, which is complementary to the messenger ribonucleic acid (mRNA) of the R2 subunit of ribonucleotide reductase. This study characterized both the in vivo and in vitro metabolism of GTI-2040. A highly specific ion-pair reversed-phase electrospray ionization (IP-RP-ESI) liquid chromatography-mass spectrometry (LC-MS) method was used for the identification of GTI-2040 and metabolites from a variety of biological samples including exonuclease enzyme solutions, plasma, urine, mouse liver/kidney homogenates, and human liver microsomes. Progressively chain-shortened metabolites truncated from the 3' terminal of GTI-2040 were detected in all of the evaluated biological samples. GTI-2040 was found to be a good substrate for 3' but not 5' exonuclease. While the pattern of n-1 chain-shortened 3'-exonucleolytic degradation was similar in the mouse liver and kidney homogenates, the latter was found to contain a larger number of shortenmers, the kidneys appeared to possess higher enzymatic reactivity toward GTI-2040. Thus, metabolism of GTI-2040 was found to occur in a variety of biological samples, mainly mediated by the 3' exonuclease.