Deep fusion learning facilitates anatomical therapeutic chemical recognition in drug repurposing and discovery.

The advent of large-scale biomedical data and computational algorithms provides new opportunities for drug repurposing and discovery. It is of great interest to find an appropriate data representation and modeling method to facilitate these studies. The anatomical therapeutic chemical (ATC) classification system, proposed by the World Health Organization (WHO), is an essential source of information for drug repurposing and discovery. Besides, computational methods are applied to predict drug ATC classification. We conducted a systematic review of ATC computational prediction studies and revealed the differences in data sets, data representation, algorithm approaches, and evaluation metrics. We then proposed a deep fusion learning (DFL) framework to optimize the ATC prediction model, namely DeepATC. The methods based on graph convolutional network, inferring biological network and multimodel attentive fusion network were applied in DeepATC to extract the molecular topological information and low-dimensional representation from the molecular graph and heterogeneous biological networks. The results indicated that DeepATC achieved superior model performance with area under the curve (AUC) value at 0.968. Furthermore, the DFL framework was performed for the transcriptome data-based ATC prediction, as well as another independent task that is significantly relevant to drug discovery, namely drug-target interaction. The DFL-based model achieved excellent performance in the above-extended validation task, suggesting that the idea of aggregating the heterogeneous biological network and node's (molecule or protein) self-topological features will bring inspiration for broader drug repurposing and discovery research.

Potential mechanisms of Chinese Herbal Medicine that implicated in the treatment of COVID-19 related renal injury.

Clinical studies have shown that renal injury in Corona Virus Disease 2019 (COVID-19) patients has been a real concern, which is associated with high mortality and an inflammation/apoptosis-related causality. Effective target therapy for renal injury has yet been developed. Besides, potential anti-COVID-19 medicines have also been reported to cause adverse side effects to kidney. Chinese Herbal Medicine (CHM), however, has rich experience in treating renal injury and has successfully applied in China in the battle of COVID-19. Nevertheless, the molecular mechanisms of CHM treatment are still unclear. In this study, we searched prescriptions in the treatment of renal injury extensively and the potential mechanisms to treat COVID-19 related renal injury were investigated. The association rules analysis showed that the core herbs includes Huang Qi, Fu Ling, Bai Zhu, Di Huang, Shan Yao. TCM herbs regulate core pathways, such as AGE-RAGE, PI3K-AKT, TNF and apoptosis pathway, etc. The ingredients (quercetin, formononetin, kaempferol, etc.,) from core herbs could modulate targets (PTGS2 (COX2), PTGS1 (COX1), IL6, CASP3, NOS2, and TNF, etc.), and thereby prevent the pharmacological and non-pharmacological renal injury comparable to that from COVID-19 infection. This study provides therapeutic potentials of CHM to combat COVID-19 related renal injury to reduce complications and mortality.