CYP3A4 genetic variants are associated with susceptibility of non-small cell lung cancer in a Shaanxi Han population

Metabolomics coupled with network pharmacology study on the protective effect of Keguan-1 granules in LPS-induced acute lung injury

CONTEXT

Keguan-1 (KG-1) plays a vital role in enhancing the curative effects, improving quality of life, and reducing the development of acute lung injury (ALI).

OBJECTIVE

To unravel the protective effect and underlying mechanism of KG-1 against ALI.

MATERIALS AND METHODS

C57BL/6J mice were intratracheally instilled with lipopolysaccharide to establish the ALI model. Then, mice in the KG-1 group received a dose of 5.04 g/kg for 12 h. The levels of proinflammatory cytokines, chemokines, and pathological characteristics were determined to explore the effects of KG-1. Next, untargeted metabolomics was used to identify the differential metabolites and involved pathways for KG-1 anti-ALI. Network pharmacology was carried out to predict the putative active components and drug targets of KG-1 anti-ALI.

RESULTS

KG-1 significantly improved the levels of TNF-α (from 2295.92 ± 529.87 pg/mL to 1167.64 ± 318.91 pg/mL), IL-6 (from 4688.80 ± 481.68 pg/mL to 3604.43 ± 382.00 pg/mL), CXCL1 (from 4361.76 ± 505.73 pg/mL to 2981.04 ± 526.18 pg/mL), CXCL2 (from 5034.09 ± 809.28 pg/mL to 2980.30 ± 747.63 pg/mL), and impaired lung histological damage. Untargeted metabolomics revealed that KG-1 significantly regulated 12 different metabolites, which mainly related to lipid, amino acid, and vitamin metabolism. Network pharmacology showed that KG-1 exhibited anti-ALI effects through 17 potentially active components acting on seven putative drug targets to regulate four metabolites.

DISCUSSION AND CONCLUSIONS

This work elucidated the therapeutic effect and underlying mechanism by which KG-1 protects against ALI from the view of the metabolome, thus providing a scientific basis for the usage of KG-1.

A Knowledge Graph-Enhanced Tensor Factorisation Model for Discovering Drug Targets

The drug discovery and development process is a long and expensive one, costing over 1 billion USD on average per drug and taking 10-15 years. To reduce the high levels of attrition throughout the process, there has been a growing interest in applying machine learning methodologies to various stages of drug discovery and development in the recent decade, especially at the earliest stage - identification of druggable disease genes. In this paper, we have developed a new tensor factorisation model to predict potential drug targets (genes or proteins) for treating diseases. We created a three-dimensional data tensor consisting of 1,048 gene targets, 860 diseases and 230,011 evidence attributes and clinical outcomes connecting them, using data extracted from the Open Targets and PharmaProjects databases. We enriched the data with gene target representations learned from a drug discovery-oriented knowledge graph and applied our proposed method to predict the clinical outcomes for unseen gene target and disease pairs. We designed three evaluation strategies to measure the prediction performance and benchmarked several commonly used machine learning classifiers together with Bayesian matrix and tensor factorisation methods. The result shows that incorporating knowledge graph embeddings significantly improves the prediction accuracy and that training tensor factorisation alongside a dense neural network outperforms all other baselines. In summary, our framework combines two actively studied machine learning approaches to disease target identification, namely tensor factorisation and knowledge graph representation learning, which could be a promising avenue for further exploration in data-driven drug discovery.