Accurate staging of chick embryonic tissues via deep learning of salient features.

Recent work shows that the developmental potential of progenitor cells in the HH10 chick brain changes rapidly, accompanied by subtle changes in morphology. This demands increased temporal resolution for studies of the brain at this stage, necessitating precise and unbiased staging. Here, we investigated whether we could train a deep convolutional neural network to sub-stage HH10 chick brains using a small dataset of 151 expertly labelled images. By augmenting our images with biologically informed transformations and data-driven preprocessing steps, we successfully trained a classifier to sub-stage HH10 brains to 87.1% test accuracy. To determine whether our classifier could be generally applied, we re-trained it using images (269) of randomised control and experimental chick wings, and obtained similarly high test accuracy (86.1%). Saliency analyses revealed that biologically relevant features are used for classification. Our strategy enables training of image classifiers for various applications in developmental biology with limited microscopy data.

Study on the Effect of Wing Bud Chitin Metabolism and Its Developmental Network Genes in the Brown Planthopper, Nilaparvata lugens, by Knockdown of TRE Gene.

The brown planthopper, Nilaparvata lugens is one of the most serious pests of rice, and there is so far no effective way to manage this pest. However, RNA interference not only can be used to study gene function, but also provide potential opportunities for novel pest management. The development of wing plays a key role in insect physiological activities and mainly involves chitin. Hence, the regulating role of trehalase (TRE) genes on wing bud formation has been studied by RNAi. In this paper, the activity levels of TRE and the contents of the two sugars trehalose and glucose were negatively correlated indicating the potential role of TRE in the molting process. In addition, NlTRE1-1 and NlTRE2 were expressed at higher levels in wing bud tissue than in other tissues, and abnormal molting and wing deformity or curling were noted 48 h after the insect was injected with any double-stranded TRE (dsTRE), even though different TREs have compensatory functions. The expression levels of NlCHS1b, NlCht1, NlCht2, NlCht6, NlCht7, NlCht8, NlCht10, NlIDGF, and NlENGase decreased significantly 48 h after the insect was injected with a mixture of three kinds of dsTREs. Similarly, the TRE inhibitor validamycin can inhibit NlCHS1 and NlCht gene expression. However, the wing deformity was the result of the NlIDGF, NlENGase, NlAP, and NlTSH genes being inhibited when a single dsTRE was injected. These results demonstrate that silencing of TRE gene expression can lead to wing deformities due to the down-regulation of the AP and TSH genes involved in wing development and that the TRE inhibitor validamycin can co-regulate chitin metabolism and the expression of wing development-related genes in wing bud tissue. The results provide a new approach for the prevention and management of N. lugens.