Protective effect of pituitary adenylate cyclase activating polypeptide in diabetic keratopathy

Modeling diabetic epitheliopathy using 3D-Organotypic corneal epithelium

Diabetic keratopathy (DK) is a degenerative corneal disease occurring in more than 50 % of diabetic patients. DK is correlated with the hyperglycemic state causing morphological and functional changes in corneal layers. Currently, most studies on the cornea are performed on two-dimensional (2D) cultures in vitro or animal models. Although 2D culture models can provide large amounts of data at low cost, they poorly represent the complex pathophysiology of the human cornea and hardly predict in vivo responses that can be achieved with animal model studies. However, the use of the latter presents ethical problems. Therefore, it is necessary to identify new strategies and models that can integrate the information validly and effectively, to reduce the number of animals used. Here, we used human corneal epithelial cells (hCECs) derived from donor cornea differentiated into three-dimensional (3D)-organotypic air-liquid interface (ALI), which resemble the features of the corneal epithelium. The 3D-organotypic ALI corneal epithelium was subjected to high-glucose conditions to generate a model of diabetic epitheliopathy. Our model showed well-established molecular and cellular characteristics of this pathology, such as epithelial defects and inflammation, with increased expression of IL-1β, TNF-α, p-NF-kB, COX-2, MMP-2 and MMP-9. The data provided highlight the utility of 3D-organotypic corneal epithelium in modeling diabetic epitheliopathy, offering new avenues in drug screening, as well as in precision and personalized medicine.

NeuroPred-ResSE: Predicting neuropeptides by integrating residual block and squeeze-excitation attention mechanism

Neuropeptides play crucial roles in regulating neurological function acting as signaling molecules, which provide new opportunity for developing drugs for the treatment of neurological diseases. Therefore, it is very necessary to develop a rapid and accurate prediction model for neuropeptides. Although a few prediction tools have been developed, there is room for improvement in prediction accuracy by using deep learning approach. In this paper, we establish the NeuroPred-ResSE model based on residual block and squeeze-excitation attention mechanism. Firstly, we extract multi-features by using one-hot coding based on the NT5CT5 sequence, dipeptide deviation from expected mean and natural vector. Then, we integrate residual block and squeeze-excitation attention mechanism, which can capture and identify the most relevant attribute features. Finally, the accuracies of the training set and test set are 97.16 % and 96.60 % based on the 5-fold cross-validation and independent test, respectively, and other evaluation metrics have also obtained satisfactory results. The experimental results show that the performance of the NeuroPred-ResSE model outperforms those of existing state-of-the-art models, and our model is an effective, intelligent and robust prediction tool. The datasets and source codes are available at https://github.com/yunyunliang88/NeuroPred-ResSE.