Dataset Information

Machine Learning-Based Identification of Potentially Novel Non-Alcoholic Fatty Liver Disease Biomarkers.

ABSTRACT: Non-alcoholic fatty liver disease (NAFLD) is a chronic liver disease that presents a great challenge for treatment and prevention.. This study aims to implement a machine learning approach that employs such datasets to identify potential biomarker targets. We developed a pipeline to identify potential biomarkers for NAFLD that includes five major processes, namely, a pre-processing step, a feature selection and a generation of a random forest model and, finally, a downstream feature analysis and a provision of a potential biological interpretation. The pre-processing step includes data normalising and variable extraction accompanied by appropriate annotations. A feature selection based on a differential gene expression analysis is then conducted to identify significant features and then employ them to generate a random forest model whose performance is assessed based on a receiver operating characteristic curve. Next, the features are subjected to a downstream analysis, such as univariate analysis, a pathway enrichment analysis, a network analysis and a generation of correlation plots, boxplots and heatmaps. Once the results are obtained, the biological interpretation and the literature validation is conducted over the identified features and results. We applied this pipeline to transcriptomics and lipidomic datasets and concluded that the C4BPA gene could play a role in the development of NAFLD. The activation of the complement pathway, due to the downregulation of the C4BPA gene, leads to an increase in triglyceride content, which might further render the lipid metabolism. This approach identified the C4BPA gene, an inhibitor of the complement pathway, as a potential biomarker for the development of NAFLD.

SUBMITTER: Shafiha R

PROVIDER: S-EPMC8615894 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundChronic kidney disease (CKD) and non-alcoholic fatty liver disease (NAFLD) are closely related to immune and inflammatory pathways. This study aimed to explore the diagnostic markers for CKD patients with NAFLD.MethodsCKD and NAFLD microarray data sets were screened from the GEO database and analyzed the differentially expressed genes (DEGs) in GSE10495 of CKD date set. Weighted Gene Co-Expression Network Analysis (WGCNA) method was used to construct gene coexpression networks and identify functional modules of NAFLD in GSE89632 date set. Then obtaining NAFLD-related share genes by intersecting DEGs of CKD and modular genes of NAFLD. Then functional enrichment analysis of NAFLD-related share genes was performed. The NAFLD-related hub genes come from intersection of cytoscape software and machine learning. ROC curves were used to examine the diagnostic value of NAFLD related hub genes in the CKD data sets and GSE89632 date set of NAFLD. CIBERSORTx was also used to explore the immune landscape in GSE104954, and the correlation between immune infiltration and hub genes expression was investigated.ResultsA total of 45 NAFLD-related share genes were obtained, and 4 were NAFLD-related hub genes. Enrichment analysis showed that the NAFLD-related share genes were significantly enriched in immune-related pathways, programmed cell death, and inflammatory response. ROC curve confirmed 4 NAFLD-related hub genes in CKD training set GSE104954 and other validation sets. Then they were used as diagnostic markers for CKD. Interestingly, these 4 diagnostic markers of CKD also showed good diagnostic value in the NAFLD date set GSE89632, so these genes may be important targets of NAFLD in the development of CKD. The expression levels of the 4 diagnostic markers for CKD were significantly correlated with the infiltration of immune cells.Conclusion4 NAFLD-related genes (DUSP1, NR4A1, FOSB, ZFP36) were identified as diagnostic markers in CKD patients with NAFLD. Our study may provide diagnostic markers and therapeutic targets for CKD patients with NAFLD.

Project description:BackgroundEvidence indicates that chronic non-alcoholic fatty liver disease (NAFLD) can increase the risk of atherosclerosis (AS), but the underlying mechanism remains unclear.ObjectiveThis study is intended for confirming key genes shared between NAFLD and AS, and their clinical diagnostic value to establish a foundation for searching novel therapeutic targets.MethodsWe downloaded the Gene Expression Omnibus (GEO) datasets, GSE48452 and GSE89632 for NAFLD and GSE100927, GSE40231 and GSE28829 for AS. The progression of NAFLD co-expression gene modules were recognized via weighted gene co-expression network analysis (WGCNA). We screened for differentially expressed genes (DEGs) associated with AS and identified common genes associated with NAFLD and AS using Venn diagrams. We investigated the most significant core genes between NAFLD and AS using machine learning algorithms. We then constructed a diagnostic model by creating a nomogram and evaluating its performance using ROC curves. Furthermore, the CIBERSORT algorithm was utilized to explore the immune cell infiltration between the two diseases, and evaluate the relationship between diagnostic genes and immune cells.ResultsThe WGCNA findings associated 1,129 key genes with NAFLD, and the difference analysis results identified 625 DEGs in AS, and 47 genes that were common to both diseases. We screened the core RPS6KA1 and SERPINA3 genes associated with NAFLD and AS using three machine learning algorithms. A nomogram and ROC curves demonstrated that these genes had great clinical meaning. We found differential expression of RPS6KA1 in patients with steatosis and NASH, and of SERPINA3 only in those with NASH compared with normal individuals. Immune infiltration findings revealed that macrophage and mast cell infiltration play important roles in the development of NAFLD and AS. Notably, SERPINA3 correlated negatively, whereas RPS6KA1 correlated positively with macrophages and mast cells.ConclusionWe identified RPS6KA1 and SERPINA3 as potential diagnostic markers for NAFLD and AS. The most promising marker for a diagnosis of NAFLD and AS might be RPS6KA1, whereas SERPINA3 is the most closely related gene for NASH and AS. We believe that further exploration of these core genes will reveal the etiology and a pathological relationship between NAFLD and AS.

Project description:BackgroundStudies had shown that autophagy was closely related to nonalcoholic fat liver disease (NAFLD), while N6-methyladenosine (m6A) was involved in the regulation of autophagy. However, the mechanism of m6A related autophagy in NAFLD was unclear.MethodsThe NAFLD related datasets were gained via the Gene Expression Omnibus (GEO) database, and we also extracted 232 autophagy-related genes (ARGs) and 37 m6A. First, differentially expressed ARGs (DE-ARGs) and differentially expressed m6A (DE-m6A) were screened out by differential expression analysis. DE-ARGs associated with m6A were sifted out by Pearson correlation analysis, and the m6A-ARGs relationship pairs were acquired. Then, autophagic genes in m6A-ARGs pairs were analyzed for machine learning algorithms to obtain feature genes. Further, we validated the relationship between feature genes and NAFLD through quantitative real-time polymerase chain reaction (qRT-PCR), Western blot (WB). Finally, the immuno-infiltration analysis was implement, and we also constructed the TF-mRNA and drug-gene networks.ResultsThere were 19 DE-ARGs and four DE-m6A between NAFLD and normal samples. The three m6A genes and five AGRs formed the m6A-ARGs relationship pairs. Afterwards, genes obtained from machine learning algorithms were intersected to yield three feature genes (TBK1, RAB1A, and GOPC), which showed significant positive correlation with astrocytes, macrophages, smooth muscle, and showed significant negative correlation with epithelial cells, and endothelial cells. Besides, qRT-PCR and WB indicate that TBK1, RAB1A and GOPC significantly upregulated in NAFLD. Ultimately, we found that the TF-mRNA network included FOXP1-GOPC, ATF1-RAB1A and other relationship pairs, and eight therapeutic agents such as R-406 and adavosertib were predicted based on the TBK1.ConclusionThe study investigated the potential molecular mechanisms of m6A related autophagy feature genes (TBK1, RAB1A, and GOPC) in NAFLD through bioinformatic analyses and animal model validation. However, it is critical to note that these findings, although consequential, demonstrate correlations rather than cause-and-effect relationships. As such, more research is required to fully elucidate the underlying mechanisms and validate the clinical relevance of these feature genes.

Dataset Information

Machine Learning-Based Identification of Potentially Novel Non-Alcoholic Fatty Liver Disease Biomarkers.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets