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

Wang, Kaiyue; Zhang, Lin; Li, Lixia; Wang, Yi; Zhong, Xinqin; Hou, Chunyu; Zhang, Yuqi; Sun, Congying; Zhou, Qian; Wang, Xiaoying

doi:10.3390/ijms231911945

Cited by 9 publications

(9 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Upon DNA damage, GADD45A is rapidly produced in the cell to participate in the DNA damage repair process, and at the same time, it induces cell cycle arrest and/or apoptosis 34 . As HIRI is often accompanied by acute and severe impairment of mitochondrial and DNA damage 35 , given which GADD45A is up-regulated and involved in pathological processes in HIRI, a small number of studies have reported on the predictive and diagnostic potential of GADD45A in drug-induced liver injury 36 , 37 . However, there are currently very few studies reporting on the exact mechanism of GADD45A involvement in HIRI.…”

Section: Discussionmentioning

confidence: 99%

Analysis and experimental validation of IL-17 pathway and key genes as central roles associated with inflammation in hepatic ischemia–reperfusion injury

Tan,

Lu,

Chen

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Hepatic ischemia–reperfusion injury (HIRI) elicits an immune-inflammatory response that may result in hepatocyte necrosis and apoptosis, ultimately culminating in postoperative hepatic dysfunction and hepatic failure. The precise mechanisms governing the pathophysiology of HIRI remain incompletely understood, necessitating further investigation into key molecules and pathways implicated in disease progression to guide drug discovery and potential therapeutic interventions. Gene microarray data was downloaded from the GEO expression profile database. Integrated bioinformatic analyses were performed to identify HIRI signature genes, which were subsequently validated for expression levels and diagnostic efficacy. Finally, the gene expression was verified in an experimental HIRI model and the effect of anti-IL17A antibody intervention in three time points (including pre-ischemic, post-ischemic, and at 1 h of reperfusion) on HIRI and the expression of these genes was investigated. Bioinformatic analyses of the screened characterized genes revealed that inflammation, immune response, and cell death modulation were significantly associated with HIRI pathophysiology. CCL2, BTG2, GADD45A, FOS, CXCL10, TNFRSF12A, and IL-17 pathway were identified as key components involved in the HIRI. Serum and liver IL-17A expression were significantly upregulated during the initial phase of HIRI. Pretreatment with anti-IL-17A antibody effectively alleviated the damage of liver tissue, suppressed inflammatory factors, and serum transaminase levels, and downregulated the mRNA expression of CCL2, GADD45A, FOS, CXCL10, and TNFRSF12A. Injection of anti-IL17A antibody after ischemia and at 1 h of reperfusion failed to demonstrate anti-inflammatory and attenuating HIRI benefits relative to earlier intervention. Our study reveals that the IL-17 pathway and related genes may be involved in the proinflammatory mechanism of HIRI, which may provide a new perspective and theoretical basis for the prevention and treatment of HIRI.

show abstract

Section: Discussionmentioning

confidence: 99%

Analysis and experimental validation of IL-17 pathway and key genes as central roles associated with inflammation in hepatic ischemia–reperfusion injury

Tan,

Lu,

Chen

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…In addition, the rise of machine learning in biomedicine is now facilitating the use of high-dimensional data to improve the sensitivity and speci city of biomarkers [14]. Machine Learning (ML) has sophisticated algorithms for the automatic organisation and analysis of large data sets.ML includes a wide range of algorithms such as the Least Absolute Shrinkage and Selection Operator (LASSO), Support Vector Machines (SVM) [15]. LASSO is a machine learning technique that is well suited to regressing massive data sets [16].…”

Section: Introductionmentioning

confidence: 99%

RRM2: a crosstalk gene for COVID-19 and intervertebral disc degeneration revealed by integrated WGCNA and machine learning

Cai,

Liu,

Yang

et al. 2024

Preprint

View full text Add to dashboard Cite

Background: Intervertebral disc degeneration (IDD) is a major cause of low back pain (LBP), and COVID-19 has been reported to be an important risk factor for IDD. The aim of this study was to explore the molecular mechanisms underlying the effects of COVID-19 on IDD by identifying overlapping crosstalk genes associated with these two conditions. The identification of crosstalk genes between COVID-19 and IDD patients will have important clinical implications for early intervention in COVID-19 secondary IDD. Methods: The gene expression profiles of GSE157103 and GSE70362 were extracted from the GEO database. These profiles were then subjected to analysis using WGCNA, Lasso, and SVM-RFE, resulting in the identification of RRM2 as a crosstalk gene for both COVID-19 and IDD. Additionally, GSEA was employed to investigate the potential mechanisms by which RRM2 exerts its effects in disease. Furthermore, a relationship between RRM2 and immune cells was revealed through correlation analysis. Finally, independent external datasets (GSE171110 and GSE146904) were utilized to validate the diagnostic efficacy of RRM2. Results: The crosstalk gene RRM2 for both COVID-19 and IDD was identified through the application of WGCNA and machine learning algorithm. GSEA analysis further revealed that RRM2 participates in fatty acid metabolism, thereby promoting disc degeneration in IDD. Moreover, immunocorrelation analyses unveiled a negative regulatory role of RRM2 in CD56-bright natural killer cells and its induction of IDD disc degeneration. Conclusions: A crosstalk gene of COVID-19 and IDD, RRM2, was identified using WGCNA and machine learning algorithm, providing a new perspective for exploring possible mechanisms of secondary IDD in COVID-19.

show abstract

“…Still, these approaches may have missed potential genes [ 20 ]. Compared with a single ML algorithm, the integrated ML (IML) approach [ 21 – 23 ] we developed is more advantageous in variable screening and model building. IML helps identify potential genes mistakenly deleted by a single ML and find more meaningful variables [ 21 ].…”

Section: Introductionmentioning

confidence: 99%

Integration of machine learning to identify diagnostic genes in leukocytes for acute myocardial infarction patients

Zhang,

Liu,

Wang

et al. 2023

J Transl Med

Self Cite

View full text Add to dashboard Cite

Background Acute myocardial infarction (AMI) has two clinical characteristics: high missed diagnosis and dysfunction of leukocytes. Transcriptional RNA on leukocytes is closely related to the course evolution of AMI patients. We hypothesized that transcriptional RNA in leukocytes might provide potential diagnostic value for AMI. Integration machine learning (IML) was first used to explore AMI discrimination genes. The following clinical study was performed to validate the results. Methods A total of four AMI microarrays (derived from the Gene Expression Omnibus) were included in bioanalysis (220 sample size). Then, the clinical validation was finished with 20 AMI and 20 stable coronary artery disease patients (SCAD). At a ratio of 5:2, GSE59867 was included in the training set, while GSE60993, GSE62646, and GSE48060 were included in the testing set. IML was explicitly proposed in this research, which is composed of six machine learning algorithms, including support vector machine (SVM), neural network (NN), random forest (RF), gradient boosting machine (GBM), decision trees (DT), and least absolute shrinkage and selection operator (LASSO). IML had two functions in this research: filtered optimized variables and predicted the categorized value. Finally, The RNA of the recruited patients was analyzed to verify the results of IML. Results Thirty-nine differentially expressed genes (DEGs) were identified between controls and AMI individuals from the training sets. Among the thirty-nine DEGs, IML was used to process the predicted classification model and identify potential candidate genes with overall normalized weights > 1. Finally, two genes (AQP9 and SOCS3) show their diagnosis value with the area under the curve (AUC) > 0.9 in both the training and testing sets. The clinical study verified the significance of AQP9 and SOCS3. Notably, more stenotic coronary arteries or severe Killip classification indicated higher levels of these two genes, especially SOCS3. These two genes correlated with two immune cell types, monocytes and neutrophils. Conclusion AQP9 and SOCS3 in leukocytes may be conducive to identifying AMI patients with SCAD patients. AQP9 and SOCS3 are closely associated with monocytes and neutrophils, which might contribute to advancing AMI diagnosis and shed light on novel genetic markers. Multiple clinical characteristics, multicenter, and large-sample relevant trials are still needed to confirm its clinical value.

show abstract

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

Cited by 9 publications

References 84 publications

Analysis and experimental validation of IL-17 pathway and key genes as central roles associated with inflammation in hepatic ischemia–reperfusion injury

Analysis and experimental validation of IL-17 pathway and key genes as central roles associated with inflammation in hepatic ischemia–reperfusion injury

RRM2: a crosstalk gene for COVID-19 and intervertebral disc degeneration revealed by integrated WGCNA and machine learning

Integration of machine learning to identify diagnostic genes in leukocytes for acute myocardial infarction patients

Contact Info

Product

Resources

About