Plant diseases cause significant economic losses and food security in agriculture each year, with the critical path to reducing losses being accurate identification and timely diagnosis of plant diseases. Currently, deep neural networks have been extensively applied in plant disease identification, but such approaches still suffer from low identification accuracy and numerous parameters. Hence, this paper proposes a model combining channel attention and channel pruning called CACPNET, suitable for disease identification of common species. The channel attention mechanism adopts a local cross-channel strategy without dimensionality reduction, which is inserted into a ResNet-18-based model that combines global average pooling with global max pooling to effectively improve the features’ extracting ability of plant leaf diseases. Based on the model’s optimum feature extraction condition, unimportant channels are removed to reduce the model’s parameters and complexity via the L1-norm channel weight and local compression ratio. The accuracy of CACPNET on the public dataset PlantVillage reaches 99.7% and achieves 97.7% on the local peanut leaf disease dataset. Compared with the base ResNet-18 model, the floating point operations (FLOPs) decreased by 30.35%, the parameters by 57.97%, the model size by 57.85%, and the GPU RAM requirements by 8.3%. Additionally, CACPNET outperforms current models considering inference time and throughput, reaching 22.8 ms/frame and 75.5 frames/s, respectively. The results outline that CACPNET is appealing for deployment on edge devices to improve the efficiency of precision agriculture in plant disease detection.

No abstract

Recent advances in developmental biology have been made possible by using multi-omic studies at single cell resolution. However, progress in plants has been slowed, owing to the tremendous difficulty in protoplast isolation from most plant tissues and/or oversize protoplasts during flow cytometry purification. Surprisingly, rapid innovations in nucleus research have shed light on plant studies in single cell resolution, which necessitates high quality and efficient nucleus isolation. Herein, we present efficient nuclei isolation protocols from the leaves of ten important plants including Arabidopsis, rice, maize, tomato, soybean, banana, grape, citrus, apple, and litchi. We provide a detailed procedure for nucleus isolation, flow cytometry purification, and absolute nucleus number quantification. The nucleus isolation buffer formula of the ten plants tested was optimized, and the results indicated a high nuclei yield. Microscope observations revealed high purity after flow cytometry sorting, and the DNA and RNA quality extract from isolated nuclei were monitored by using the nuclei in cell division cycle and single nucleus RNA sequencing (snRNA-seq) studies, with detailed procedures provided. The findings indicated that nucleus yield and quality meet the requirements of snRNA-seq, cell division cycle, and likely other omic studies. The protocol outlined here makes it feasible to perform plant omic studies at single cell resolution.

In flowering plants, floral induction signals intersect at the shoot apex to modulate meristem determinacy and growth form. Herein, we reported a snRNA-seq analysis of litchi apical buds at different developmental stages. A total of 41,641 nuclei expressing 21,402 genes were analyzed, revealing 35 cell clusters corresponding to 12 broad populations. We signature genes associated with floral transition and propose a model that profile the key events associated with litchi floral meristem identity by analyzing 567 identified floral meristem cells at single cell resolution. Interestingly, snRNA-seq data indicated that all putative FT and TFL1 genes were not expressed in bud nuclei, but significant expressions of them were detected in bud samples using RT-PCR. Based on the expression patterns and gene silencing results, we highlight the critical role of LcTFL1-2 in inhibiting flowering and propose that LcFT1/LcTFL1-2 expression ratio may determine the success flower transition. And the transport of LcFT1 and LcTFL1-2 mRNA from the leaf to the shoot apical meristem was proposed based on in-situ and dot blot hybridization results. These findings allowed for a more comprehensive understanding of the molecular events that occur during the litchi floral transition, as well as the identification of new regulators.