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*

Objective:To investigate the levels of sex hormone and fertility in female patients after hematopoietic stem cell transplantation (HSCT), as well as their correlation with conditioning regimens, and analyse the effect of hormone replacement therapy (HRT) in young women after HSCT.Methods:Retrospective case series study. The clinical data of 147 women who underwent HSCT in the First Affiliated Hospital of Soochow University from January 2010 to January 2021 were retrospectively analyzed. The sex hormone levels were measured and followed-up, and the survival, menstrual fertility and the use of HRT of the patients were also followed-up. The sex hormone levels were measured after transplantation, and the ovarian function was evaluated. Independent sample t test and χ2 test were used for comparison between the two groups. Results:The median age of the 147 patients was 26 (range, 10-45) years. Of them, 135 patients received allogeneic HSCT and 12 patients received autologous HSCT. Furthermore, 129 patients received myeloablative conditioning, and 18 patients received reduced conditioning dose. The median follow-up time was 50 months (range, 18-134 months). Five patients died of disease recurrence during follow-up. Of the 54 patients with subcutaneous injection of zoladex, three recovered menstruation spontaneously after transplantation, and all of them were myeloablative conditioning patients, one patient gave birth to twins through assisted reproductive technology. Ninety-three patients did not use zoladex before conditioning, two patients with aplastic anemia with non-myeloablative transplantation resumed menstruation spontaneously, and conceived naturally. The level of follicle stimulating hormone after transplantation in patients receiving myeloablative conditioning regimen was significantly higher than that in patients receiving reduced-dose conditioning regimen [(95.28±3.94) U/L vs. (71.85±10.72) U/L, P=0.039]. Among 147 patients, 122 patients developed premature ovarian failure, 83 patients received sex hormone replacement therapy after transplantation, and 76 patients recovered menstruation and improved endocrine function. Conclusions:The incidence of premature ovarian failure is high in female patients after HSCT, and patients have a chance at natural conception. Reducing the dose of conditioning regimen and the application of zoladex before transplantation can reduce ovarian of conditioning drugs. HRT after transplantation can partially improve the endocrine function of patients.