Drug repurposing offers a promising alternative to traditional drug development and significantly reduces costs and timelines by identifying new therapeutic uses for existing drugs. However, the current approaches often rely on limited data sources and simplistic hypotheses, which restrict their ability to capture the multi-faceted nature of biological systems. This study introduces adaptive multi-view learning (AMVL), a novel methodology that integrates chemical-induced transcriptional profiles (CTPs), knowledge graph (KG) embeddings, and large language model (LLM) representations, to enhance drug repurposing predictions. AMVL incorporates an innovative similarity matrix expansion strategy and leverages multi-view learning (MVL), matrix factorization, and ensemble optimization techniques to integrate heterogeneous multi-source data. Comprehensive evaluations on benchmark datasets (Fdataset, Cdataset, and Ydataset) and the large-scale iDrug dataset demonstrate that AMVL outperforms state-of-the-art (SOTA) methods, achieving superior accuracy in predicting drug-disease associations across multiple metrics. Literature-based validation further confirmed the model's predictive capabilities, with seven out of the top ten predictions corroborated by post-2011 evidence. To promote transparency and reproducibility, all data and codes used in this study were open-sourced, providing resources for processing CTPs, KG, and LLM-based similarity calculations, along with the complete AMVL algorithm and benchmarking procedures. By unifying diverse data modalities, AMVL offers a robust and scalable solution for accelerating drug discovery, fostering advancements in translational medicine and integrating multi-omics data. We aim to inspire further innovations in multi-source data integration and support the development of more precise and efficient strategies for advancing drug discovery and translational medicine.

Objective:To investigate the factors influencing mortality within one year following hip fracture surgery in elderly patients.Methods:This study retrospectively analyzed clinical data from 1 263 elderly patients with hip fractures who underwent surgery at the First Affiliated Hospital of Air Force Medical University between January 2014 and December 2022.Based on their survival status one-year post-surgery, the patients were categorized into two groups: the death group(212 cases)and the survival group(1 051 cases).Univariate and multivariate logistic regression models were employed to identify factors associated with 1-year mortality.Results:The 1-year mortality rate was found to be 16.78%.Multivariate logistic regression analysis identified several significant predictors of 1-year mortality in elderly patients with hip fractures.These predictors include gender( OR=0.67, 95% CI: 0.48-0.95), age greater than 85 years( OR=2.23, 95% CI: 1.56-3.19), body mass index(BMI)less than 18.5( OR=1.74, 95% CI: 1.17-2.60), BMI between 30 and 40( OR=3.14, 95% CI: 1.20-8.21), history of stroke( OR=1.59, 95% CI: 1.06-2.38), presence of anemia( OR=1.75, 95% CI: 1.07-2.86), fibrinogen(FIB)levels either below 1.8 or above 3.5( OR=1.63, 95% CI: 1.12-2.37), deep vein thrombosis( OR=1.57, 95% CI: 1.13-2.18), and American Society of Anesthesiologists(ASA)grade Ⅲ/Ⅳ( OR=2.37, 95% CI: 1.56-3.59). Conclusions:In elderly patients with hip fractures, age over 85 years, a BMI less than 18.5 or between 30 and 40, the presence of stroke, anemia, FIB levels below 1.8 or above 3.5, deep vein thrombosis(DVT), and ASA classifications Ⅲ or Ⅳ are identified as independent risk factors for 1-year mortality.Conversely, being female serves as a protective factor.

Animals ; Mice ; Spinal Neoplasms/pathology* ; Disease Models, Animal