Dataset Information

Identification of Drug-Induced Liver Injury Biomarkers from Multiple Microarrays Based on Machine Learning and Bioinformatics Analysis.

ABSTRACT: Drug-induced liver injury (DILI) is the most common adverse effect of numerous drugs and a leading cause of drug withdrawal from the market. In recent years, the incidence of DILI has increased. However, diagnosing DILI remains challenging because of the lack of specific biomarkers. Hence, we used machine learning (ML) to mine multiple microarrays and identify useful genes that could contribute to diagnosing DILI. In this prospective study, we screened six eligible microarrays from the Gene Expression Omnibus (GEO) database. First, 21 differentially expressed genes (DEGs) were identified in the training set. Subsequently, a functional enrichment analysis of the DEGs was performed. We then used six ML algorithms to identify potentially useful genes. Based on receiver operating characteristic (ROC), four genes, DDIT3, GADD45A, SLC3A2, and RBM24, were identified. The average values of the area under the curve (AUC) for these four genes were higher than 0.8 in both the training and testing sets. In addition, the results of immune cell correlation analysis showed that these four genes were highly significantly correlated with multiple immune cells. Our study revealed that DDIT3, GADD45A, SLC3A2, and RBM24 could be biomarkers contributing to the identification of patients with DILI.

SUBMITTER: Wang K

PROVIDER: S-EPMC9570393 | biostudies-literature | 2022 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Identification of Drug-Induced Liver Injury Biomarkers from Multiple Microarrays Based on Machine Learning and Bioinformatics Analysis.

Wang Kaiyue K Zhang Lin L Li Lixia L Wang Yi Y Zhong Xinqin X Hou Chunyu C Zhang Yuqi Y Sun Congying C Zhou Qian Q Wang Xiaoying X

International journal of molecular sciences 20221008 19

Drug-induced liver injury (DILI) is the most common adverse effect of numerous drugs and a leading cause of drug withdrawal from the market. In recent years, the incidence of DILI has increased. However, diagnosing DILI remains challenging because of the lack of specific biomarkers. Hence, we used machine learning (ML) to mine multiple microarrays and identify useful genes that could contribute to diagnosing DILI. In this prospective study, we screened six eligible microarrays from the Gene Expr ...[more]

PMID: 36233241

Similar Datasets

Project description:BackgroundAcetaminophen (APAP) is commonly used as an antipyretic analgesic. However, acetaminophen overdose may contribute to liver injury and even liver failure. Acetaminophen-induced liver injury (AILI) is closely related to mitochondrial oxidative stress and dysfunction, which play critical roles in cuproptosis. Here, we explored the potential role of cuproptosis-related genes (CRGs) in AILI.MethodsThe gene expression profiles were obtained from the Gene Expression Omnibus database. The differential expression of CRGs was determined between the AILI and control samples. Protein protein interaction, correlation, and functional enrichment analyses were performed. Machine learning was used to identify hub genes. Immune infiltration was evaluated. The AILI mouse model was established by intraperitoneal injection of APAP solution. Quantitative real-time PCR and western blotting were used to validate hub gene expression in the AILI mouse model. The copper content in the mouse liver samples and AML12 cells were quantified using a colorimetric assay kit. Ammonium tetrathiomolybdate (ATTM), was administered to mouse models and AML12 cells in order to investigate the effects of copper chelator on AILI.ResultsThe analysis identified 7,809 differentially expressed genes, 4,245 of which were downregulated and 3,564 of which were upregulated. Four optimal feature genes (OFGs; SDHB, PDHA1, NDUFB2, and NDUFB6) were identified through the intersection of two machine learning algorithms. Further nomogram, decision curve, and calibration curve analyses confirmed the diagnostic predictive efficacy of the four OFGs. Enrichment analysis indicated that the OFGs were involved in multiple pathways, such as IL-17 pathway and chemokine signaling pathway, that are related to AILI progression. Immune infiltration analysis revealed that macrophages were more abundant in AILI than in control samples, whereas eosinophils and endothelial cells were less abundant. Subsequently, the AILI mouse model was successfully established, and histopathological analysis using hematoxylin-eosin staining along with liver function tests revealed a significant induction of liver injury in the APAP group. Consistent with expectations, both mRNA and protein levels of the four OFGs exhibited a substantial decrease. The administration of ATTAM effectively mitigates copper elevation induced by APAP in both mouse model and AML12 cells. However, systemic administration of ATTM did not significantly alleviate AILI in the mouse model.ConclusionThis study first revealed the potential role of CRGs in the pathological process of AILI and offered novel insights into its underlying pathogenesis.

Project description:The constantly emerging evidence indicates a close association between coronary artery disease (CAD) and non-alcoholic fatty liver disease (NAFLD). However, the exact mechanisms underlying their mutual relationship remain undefined. This study aims to explore the common signature genes, potential mechanisms, diagnostic markers, and therapeutic targets for CAD and NAFLD. We downloaded CAD and NAFLD datasets from the Gene Expression Omnibus (GEO) database and analyzed the differentially expressed genes (DEGs) by limma. Protein-protein interaction (PPI) network was constructed with common DEGs (co-DEGs), and hub genes were screened by Maximal Clique Centrality (MCC) algorithm. Candidate biomarkers were selected from intersection of three machine learning algorithms. Expression levels, nomogram, the areas under the receiver operating characteristic curve (AUC) of candidate biomarkers were performed. CIBERSORT algorithm was used to assess the immune cell infiltration, and Spearman's correlations tests were used for calculating the correlation of biomarker genes. A total of 554 overlapping DEGs associated with CAD and NAFLD were obtained by analysis of GSE113079 and GSE89632 datasets. Gene Ontology, Kyoto Encyclopedia of Genes and Genomes enrichment analysis showed that the co-DEGs were significantly enriched in immune effector process, inflammation response and lipid metabolism. The PPI network generated a 1245-edge network, and top 50 genes were selected using the MCC algorithm. The candidate biomarkers were screened from intersection of machine learning in GSE89632, including CEBPA, CXCL2, JUN and FOXO1. The ROC results showed that these four biomarker genes have good diagnostic value for patients with both CAD and NAFLD. Then we explored the immune landscape, immune infiltration and the correlation between biomarker gene expression in CAD and NAFLD samples. In this study, we predict that CEBPA, CXCL2, JUN and FOXO1 can be used to diagnose CAD and NAFLD. Our study provided new insights for potential biomarkers, molecular mechanism and therapeutic targets for both diseases.

Dataset Information

Identification of Drug-Induced Liver Injury Biomarkers from Multiple Microarrays Based on Machine Learning and Bioinformatics Analysis.

Publications

Identification of Drug-Induced Liver Injury Biomarkers from Multiple Microarrays Based on Machine Learning and Bioinformatics Analysis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets