KDGene: knowledge graph completion for disease gene prediction using interactional tensor decomposition.

The accurate identification of disease-associated genes is crucial for understanding the molecular mechanisms underlying various diseases. Most current methods focus on constructing biological networks and utilizing machine learning, particularly deep learning, to identify disease genes. However, these methods overlook complex relations among entities in biological knowledge graphs. Such information has been successfully applied in other areas of life science research, demonstrating their effectiveness. Knowledge graph embedding methods can learn the semantic information of different relations within the knowledge graphs. Nonetheless, the performance of existing representation learning techniques, when applied to domain-specific biological data, remains suboptimal. To solve these problems, we construct a biological knowledge graph centered on diseases and genes, and develop an end-to-end knowledge graph completion framework for disease gene prediction using interactional tensor decomposition named KDGene. KDGene incorporates an interaction module that bridges entity and relation embeddings within tensor decomposition, aiming to improve the representation of semantically similar concepts in specific domains and enhance the ability to accurately predict disease genes. Experimental results show that KDGene significantly outperforms state-of-the-art algorithms, whether existing disease gene prediction methods or knowledge graph embedding methods for general domains. Moreover, the comprehensive biological analysis of the predicted results further validates KDGene's capability to accurately identify new candidate genes. This work proposes a scalable knowledge graph completion framework to identify disease candidate genes, from which the results are promising to provide valuable references for further wet experiments. Data and source codes are available at https://github.com/2020MEAI/KDGene.

[Meta-analysis on the co-morbidity rate between tuberculosis and diabetes mellitus in China].

OBJECTIVE: To understand the co-morbidity rate between tuberculosis and diabetes mellitus in the mainland of China. METHODS: Based on the related literature regarding tuberculosis and diabetes mellitus published in China National Knowledge Infrastructure Databases (CNKI), Wangfang Databases and the Chinese Science and Technology Journal Database (VIP), PubMed and Medline in the last 13 years. Related information was extracted and the generic inverse variance model was applied to estimate the following parameters including rate of co-morbidity, differences on gender, age, results on sputum smear samples, sources and regions of the samples. Quality of the literature was evaluated through the STROBE statement and sensitivity analysis was performed to evaluate the impact of the quality. RESULTS: Twenty two papers were included for Meta-analysis, with a total sample of 56 805. The combined prevalence rate of diabetes among patients with tuberculosis was 7.20% (95%CI:6.01%-8.39%). According to results from subgroup analysis, at a = 0.05 level, the comorbidity rates among subgroups as:age 40 and above (12.18%), smear positives (11.40%), samples from the hospitals (9.67%)and from the northern regions (9.13%)were higher than the subgroups as age below 40 (2.33%), with smear negative (4.00%), samples from the community level (6.10%)and from southern region (5.94%). CONCLUSION: The co-morbidity rate of tuberculosis and diabetes mellitus was high in mainland China, and were high among cases: at age 40 or above, with smear positive, from hospitals or from the northern region etc.