Accurate prediction of drug-target interactions (DTIs) plays a pivotal role in drug discovery, facilitating optimization of lead compounds, drug repurposing and elucidation of drug side effects. However, traditional DTI prediction methods are often limited by incomplete biological data and insufficient representation of protein features. In this study, we proposed KG-CNNDTI, a novel knowledge graph-enhanced framework for DTI prediction, which integrates heterogeneous biological information to improve model generalizability and predictive performance. The proposed model utilized protein embeddings derived from a biomedical knowledge graph via the Node2Vec algorithm, which were further enriched with contextualized sequence representations obtained from ProteinBERT. For compound representation, multiple molecular fingerprint schemes alongside the Uni-Mol pre-trained model were evaluated. The fused representations served as inputs to both classical machine learning models and a convolutional neural network-based predictor. Experimental evaluations across benchmark datasets demonstrated that KG-CNNDTI achieved superior performance compared to state-of-the-art methods, particularly in terms of Precision, Recall, F1-Score and area under the precision-recall curve (AUPR). Ablation analysis highlighted the substantial contribution of knowledge graph-derived features. Moreover, KG-CNNDTI was employed for virtual screening of natural products against Alzheimer's disease, resulting in 40 candidate compounds. 5 were supported by literature evidence, among which 3 were further validated in vitro assays.
Alzheimer Disease/drug therapy* ; Biological Products/therapeutic use* ; Humans ; Neural Networks, Computer ; Machine Learning ; Drug Discovery/methods* ; Algorithms ; Drug Evaluation, Preclinical/methods*

The regulator of expression of virion(Rev)protein binds specifically to the Rev-responsive element(RRE)RNA in order to regulate the expression of the human immunodeficiency virus(HIV)-1 genes.Fluores-cence indicator displacement assays have been used to identify ligands that can inhibit the Rev-RRE interaction;however,the small fluorescence indicators cannot fully replace the Rev peptide or protein.As a result,a single rhodamine B labeled Rev(RB-Rev)model peptide was utilized in this study to develop a direct and efficient Rev-RRE inhibitor screening model.Due to photon-induced electron transfer quenching of the tryptophan residue on the RB fluorophore,the fluorescence of RB in Rev was weakened and could be dramatically reactivated by interaction with RRE RNA in ammonium acetate buffer(approximately six times).The interaction could reduce the electron transfer between tryptophan and RB,and RRE could also increase RB fluorescence.The inhibitor screening model was evaluated using three known positive Rev-RRE inhibitors,namely,proflavin,6-chloro-9-[3-(2-chloroethylamino)pro-pylamino]-2-methoxyacridine(ICR 191),and neomycin,as well as a negative drug,arginine.With the addition of the positive drugs,the fluorescence of the Rev-RRE decreased,indicating the displacement of RB-Rev.This was confirmed using atomic force microscopy(AFM)and the fluorescence was essentially unaffected by the addition of arginine.The results demonstrated that RB-Rev can be used as a fluorescent probe for recognizing small ligands that target RRE RNA.The Rev-RRE inhibitor screening model offers a novel approach to evaluating and identifying long-acting Rev inhibitors.

Cryopreservation of bovine articular cartilage and Human Bone Marrow Fibroblast (HBMF) monolayer cells is studied in the paper. The results show that the high concentrations of Cryoprotective agents (CPA) coupled with the appearance of sucrose and high contents of 1,2-propanediol contribute to reducing the formation and growth of ice nuclei and have the potential to obtain good protective effects. High concentrations of CPA can result in great damages to cartilage and HBMF monolayer cells, which can be moderated by decreasing the temperature of adding and removal of CPA. In the frozen cartilage, which is put into liquid nitrogen without adding of any CPA, the architectures of both the chondrocytes and extracellular matrix have been severely damaged. While in the control group, the chondrocytes are intact and well preserved.

In this paper,a portable chemical oxygen generator was discribed. It mainly consists of oxygen-generating bag and oxygen-generating pow- der.The oxygen-generating bag is made of PVC plastic film,and the oxygen-generating powder is sodium carbonate peroxide.This oxygen ge- nerator can be used to produce oxygen gas for human respiration.and is particularly applicable to first aid for emergency patients,home treatm- ent for respiratory patients and oxygen supply in field hospitals or in clinics in rural and remote areas.