SwinDAE: Electrocardiogram Quality Assessment Using 1D Swin Transformer and Denoising AutoEncoder.

OBJECTIVE: Electrocardiogram (ECG) signals have wide-ranging applications in various fields, and thus it is crucial to identify clean ECG signals under different sensors and collection scenarios. Despite the availability of a variety of deep learning algorithms for ECG quality assessment, these methods still lack generalization across different datasets, hindering their widespread use. METHODS: In this paper, an effective model named Swin Denoising AutoEncoder (SwinDAE) is proposed. Specifically, SwinDAE uses a DAE as the basic architecture, and incorporates a 1D Swin Transformer during the feature learning stage of the encoder and decoder. SwinDAE was first pre-trained on the public PTB-XL dataset after data augmentation, with the supervision of signal reconstruction loss and quality assessment loss. Specially, the waveform component localization loss is proposed in this paper and used for joint supervision, guiding the model to learn key information of signals. The model was then fine-tuned on the finely annotated BUT QDB dataset for quality assessment. RESULTS: SwinDAE achieved 0.02-0.13 mean F1 score improvement on the BUT QDB dataset compared to multiple deep learning methods, and demonstrated applicability on two other datasets. CONCLUSION: The proposed SwinDAE shows strong generalization ability on different datasets, and surpasses other state-of-the-art deep learning methods on multiple evaluation metrics. In addition, the statistical analysis for SwinDAE prove the significance of the performance and the rationality of the prediction. SIGNIFICANCE: SwinDAE can learn the commonality between high-quality ECG signals, exhibiting excellent performance in the application of cross-sensors and cross-collection scenarios.

Synthesis and Activity of Aurone and Indanone Derivatives.

INTRODUCTION: Based on bioactive group splicing, classical bioisosterism, and the rule of alkene insertion, forty-eight aurone, and indanone derivatives were designed and synthesized. They were evaluated for inhibitory activity against C. albicans, E. coli, and S. aureus. Among them, thirty compounds exhibited moderate to excellent antibacterial activity. METHODS: The maximum circle of inhibition was 18 mm (compounds B15, B16, and E7), and the minimum values of MIC and MBC were respectively 15.625 µM (compounds A5 and D2) and 62.5 µM (compounds A6, A8, and E7). RESULTS: The SAR showed that aurone and indanone derivatives could strongly inhibit the growth of Gram-positive bacteria. The introduction of electron-withdrawing groups or hydroxyl is beneficial to the activity. It was exciting that the 3-phenylallylbenzofuranone and 3-allylindanone skeletons with antimicrobial activity were first reported in this study. Compounds A5 and E7 were selected for molecular docking studies with targets MetRS (PBD: 7WPI) and PBP (PDB: 6C3K) to determine the binding interactions at the active site. CONCLUSION: On this basis, the physicochemical and pharmacological properties of the compounds were predicted and analyzed. The influence of these properties on antimicrobial activity and their implications for subsequent work were discussed. The ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) predictions showed that most of the compounds had good pharmacokinetic profiles and high safety profiles.

Proton exudation mediated by GmVP2 has widespread effects on plant growth, remobilization of soil phosphorus, and the structure of the rhizosphere microbial community.

Increased root secretion of H+ is a known strategy in plant adaption to low phosphorus (P) stress as it enhances mobilization of sparingly soluble P sources in the soil. However, our knowledge of the full effects induced by this enhanced acidification of the rhizosphere remains incomplete. In this study we found that P deficiency increased the net H+ flux rate from soybean (Glycine max) roots. Among the eight H+-pyrophosphatase (GmVP) genes in the soybean genome, GmVP2 showed the highest expression level under low P conditions. Transient expression of a GmVP2-GFP construct in tobacco (Nicotiana tabacum) leaves, together with functional characterization of GmVP2 in transgenic soybean hairy roots demonstrated that it encodes a plasma-membrane transporter that mediates H+ exudation. Overexpression of GmVP2 in Arabidopsis resulted in enhanced root H+ exudation, promoted root growth, and improved the utilization of sparingly soluble Ca-P. The improved root growth caused by GmVP2-overexpression might be due to the differential expression of genes related to hormone and flavonoid metabolism, and to root development. Overexpression of GmVP2 also changed the structure of the rhizospheric microbial community, as reflected by a preferential accumulation of Acidobacteria. Overall, our results suggest that GmVP2 mediates H+ exudation in the root response to Pi starvation, and that this influences plant growth, the mobilization sparingly soluble P-sources, and the structure of the microbial community in a coordinated manner.

Identification of DELLA Genes and Key Stage for GA Sensitivity in Bolting and Flowering of Flowering Chinese Cabbage.

Flowering Chinese cabbage (Brassica campestris L. ssp. chinensis var. utilis Tsen et Lee) is an important and extensively cultivated vegetable in south China, and its stalk development is mainly regulated by gibberellin (GA). DELLA proteins negatively regulate GA signal transduction and may play an important role in determining bolting and flowering. Nevertheless, no systematic study of the DELLA gene family has been undertaken in flowering Chinese cabbage. In the present study, we found that the two-true-leaf spraying of gibberellin A3 (GA3) did not promote bolting but did promote flowering, whereas the three-true-leaf spraying of GA3 promoted both bolting and flowering. In addition, we identified five DELLA genes in flowering Chinese cabbage. All five proteins contained DELLA, VHYNP, VHIID, and SAW conserved domains. Protein-protein interaction results showed that in the presence of GA3, all five DELLA proteins interacted with BcGID1b (GA-INSENSITIVE DWARF 1b) but not with BcGID1a (GA-INSENSITIVE DWARF 1a) or BcGID1c (GA-INSENSITIVE DWARF 1c). Their expression analysis showed that the DELLA genes exhibited tissue-specific expression, and their reversible expression profiles responded to exogenous GA3 depending on the treatment stage. We also found that the DELLA genes showed distinct expression patterns in the two varieties of flowering Chinese cabbage. BcRGL1 may play a major role in the early bud differentiation process of different varieties, affecting bolting and flowering. Taken together, these results provide a theoretical basis for further dissecting the DELLA regulatory mechanism in the bolting and flowering of flowering Chinese cabbage.

Complex gene regulation between young and old soybean leaves in responses to manganese toxicity.

Manganese (Mn) is an essential micronutrient for plant growth. However, excess manganese is toxic and inhibits crop production. Although it is widely known that physiological and molecular mechanisms underlie plant responses to Mn toxicity, few studies have been conducted to compare Mn tolerance capabilities between young and old leaves in plants; thus, the mechanisms underlying Mn tolerance in different plant tissues or organs are not fully understood. In this study, the dose responses of soybean to Mn availability were investigated. Genome-wide transcriptomic analysis was subsequently conducted to identify the differentially expressed genes (DEGs) in both young and old leaves of soybean in responses to Mn toxicity. Our results showed that excess Mn severely inhibited soybean growth and increased both Mn accumulation in and brown spots on soybean leaves, especially for the old leaves, strongly suggesting that more Mn was allocated to old leaves in soybean. Transcriptomic profiling revealed that totals of 4410 and 2258 DEGs were separately identified in young leaves and old leaves. Furthermore, only 944 DEGs were found to be commonly regulated in both young and old leaves of soybean, strongly suggesting distinct responses present in soybean young and old leaves in responses to Mn toxicity.