Support Vector Machine Recursive Feature Elimination Research Articles

Abstract A016: Early pancreatic cancer detection using extracellular vesicle DNA methylation signatures in blood

Abstract In 2020, there were 495,773 new cases and 466,003 deaths for pancreatic cancer worldwide. Furthermore, pancreatic cancer is emerging to be the leading cause of cancer related deaths in the U.S. by the year 2030, surpassing lung and colon cancer. The majority of pancreatic cancer patients (∼80%) are diagnosed at the most advanced (metastatic) stage, for which the 5-year survival is 3%. Dramatically, studies show that if it can be detected at an early stage when surgical removal is feasible, the 5-year survival rate significantly increased to 37%. This data highlights the crucial importance of early detection for pancreatic cancer treatment with curative intent. Unfortunately, currently there are no reliable techniques for routine screening to identify pancreatic cancer at early stages. In this Abstract, we developed and validated the performance of those DNA methylation markers to detect pancreatic cancer in a cohort of pancreatic cancer patients. Firstly, we collected a large amount of genome-wide methylation microarray data (targeting over 450,000 methylation sites) of tissue samples from several publicly available databases, including samples of solid pancreatic tumors (n = 384), noncancerous pancreatic tissues (n = 126) and healthy whole blood (n = 453). The raw microarray data were preprocessed using a pipeline implemented in R, which removes inaccurate measurements and corrects for bias caused by technical issues. A two-stage feature selection procedure was designed and implemented in Python, which makes use of various filters and a multivariate embedded method, support vector machine recursive feature elimination (SVM-RFE). The features were evaluated using two metrics, classification performance and stability, based on a tradeoff of which we selected a set of differentially methylated loci for discriminating the samples. The set of prospective markers includes 129 hypermethylated and 142 hypomethylated tumor-specific loci, 8 hypermethylated and 8 hypomethylated pancreatic tissue specific loci. To validate the performance of those pancreatic cancer-specific methylation markers, as a feasibility study, we isolated extracellular vesicles from cancer cells and plasma of cancer patients using lipid nanoprobe (LNP). Extracellular vesicles (EVs) are lipid-bilayer-enclosed vesicles of sub- micrometer size that are secreted by virtually all cell types. In a pilot study encompassing 11 pancreatic cancer patients (Stage I-IV) and age-matched 10 healthy donors (HD), we employed quantitative methylation-specific polymerase chain reaction assays (qMSP) to examine the promoter methylation status of the genes within plasma EV DNA. The receiver operating characteristic (ROC) curves were employed to assess the performance of a combined promoter methylation signature in EV DNA for the detection of pancreatic cancer. Our findings indicate that the promoter methylation of genes can be specific to pancreatic cancer, suggesting the efficient packaging of methylation information from genomic DNA into EVs. Citation Format: Hongzhang He, Siyang Zheng. Early pancreatic cancer detection using extracellular vesicle DNA methylation signatures in blood [abstract]. In: Proceedings of the AACR Special Conference: Liquid Biopsy: From Discovery to Clinical Implementation; 2024 Nov 13-16; San Diego, CA. Philadelphia (PA): AACR; Clin Cancer Res 2024;30(21_Suppl):Abstract nr A016.

Feature genes identification and immune infiltration assessment in abdominal aortic aneurysm using WGCNA and machine learning algorithms

ObjectiveAbdominal aortic aneurysm (AAA) is a life-threatening vascular condition. This study aimed to discover new indicators for the early detection of AAA and explore the possible involvement of immune cell activity in its development.MethodsSourced from the Gene Expression Omnibus, the AAA microarray datasets GSE47472 and GSE57691 were combined to generate the training set. Additionally, a separate dataset (GSE7084) was designated as the validation set. Enrichment analyses were carried out to explore the underlying biological mechanisms using Disease Ontology, Kyoto Encyclopedia of Genes and Genomes, and Gene Ontology. We then utilized weighted gene co-expression network analysis (WGCNA) along with 3 machine learning techniques: least absolute shrinkage and selection operator, support vector machine-recursive feature elimination, and random forest, to identify feature genes for AAA. Moreover, data were validated using the receiver operating characteristic (ROC) curve, with feature genes defined as those having an area under the curve above 85% and a p-value below 0.05. Finally, the single sample gene set enrichment analysis algorithm was applied to probe the immune landscape in AAA and its connection to the selected feature genes.ResultsWe discovered 72 differentially expressed genes (DEGs) when comparing healthy and AAA samples, including 36 upregulated and 36 downregulated genes. Functional enrichment analysis revealed that the DEGs associated with AAA are primarily involved in inflammatory regulation and immune response. By intersecting the result of 3 machine learning algorithms and WGCNA, 3 feature genes were identified, including MRAP2, PPP1R14A, and PLN genes. The diagnostic performance of all these genes was strong, as revealed by the ROC analysis. A significant increase in 15 immune cell types in AAA samples was observed, based on the analysis of immune cell infiltration. In addition, the 3 feature genes show a strong linkage with different types of immune cells.ConclusionThree feature genes (MRAP2, PPP1R14A, and PLN) related to the development of AAA were identified. These genes are linked to immune cell activity and the inflammatory microenvironment, providing potential biomarkers for early detection and a basis for further research into AAA progression.

Analyzing immune cell infiltrates in skeletal muscle of infantile-onset Pompe disease using bioinformatics and machine learning

Pompe disease, a severe lysosomal storage disorder, is marked by heart problems, muscle weakness, and respiratory difficulties. This study aimed to identify novel markers for infantile-onset Pompe disease by analyzing key genes and immune cells infiltrating affected skeletal muscles, building on existing research linking its progression to the immune cell infiltration. The datasets GSE38680 and GSE159062 were downloaded and differential expression genes (DEGs) were identified. Potential markers were screened using support vector machine recursive feature elimination (SVM-RFE) analysis and least absolute shrinkage and selection operator (LASSO) regression models. To analyze DEGs and immune processes, 22 immune cell types in affected tissues were examined using CIBERSORT. Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis revealed significant enrichment in the calcium signaling pathway, phosphatidylinositol signaling system, ubiquitin-mediated proteolysis and JAK-STAT signaling pathway. Machine learning identified GPNMB, CALML6 and TRIM7 as key genes. Immune cell infiltration analysis showed that the expression levels of the above three genes were closely related to immune cells in our target population under study, including T cells regulatory (Tregs), monocytes, macrophages M0, resting and activated dendritic cells, naive and memory B cells. Overall, our study results may provide new clues for exploring markers related to Pompe disease by highlighting key genes and their relationship with immune infiltration, offering insights into the disease’s development. However, previous studies have shown limited evidence of significant immune cell infiltration in muscle biopsies from Pompe patients, and this lack of direct evidence necessitates further investigation and experimental validation in laboratory settings to confirm these associations.

Molecular Indicator for Distinguishing Multi-drug-Resistant Tuberculosis from Drug Sensitivity Tuberculosis and Potential Medications for Treatment.

The issue of multi-drug-resistant tuberculosis (MDR-TB) presents a substantial challenge to global public health. Regrettably, the diagnosis of drug-resistant tuberculosis (DR-TB) frequently necessitates an extended period or more extensive laboratory resources. The swift identification of MDR-TB poses a particularly challenging endeavor. To identify the biomarkers indicative of multi-drug resistance, we conducted a screening of the GSE147689 dataset for differentially expressed genes (DEGs) and subsequently conducted a gene enrichment analysis. Our analysis identified a total of 117 DEGs, concentrated in pathways related to the immune response. Three machine learning methods, namely random forest, decision tree, and support vector machine recursive feature elimination (SVM-RFE), were implemented to identify the top 10 genes according to their feature importance scores. A4GALT and S1PR1, which were identified as common genes among the three methods, were selected as potential molecular markers for distinguishing between MDR-TB and drug-susceptible tuberculosis (DS-TB). These markers were subsequently validated using the GSE147690 dataset. The findings suggested that A4GALT exhibited area under the curve (AUC) values of 0.8571 and 0.7121 in the training and test datasets, respectively, for distinguishing between MDR-TB and DS-TB. S1PR1 demonstrated AUC values of 0.8163 and 0.5404 in the training and test datasets, respectively. When A4GALT and S1PR1 were combined, the AUC values in the training and test datasets were 0.881 and 0.7551, respectively. The relationship between hub genes and 28 immune cells infiltrating MDR-TB was investigated using single sample gene enrichment analysis (ssGSEA). The findings indicated that MDR-TB samples exhibited a higher proportion of type 1T helper cells and a lower proportion of activated dendritic cells in contrast to DS-TB samples. A negative correlation was observed between A4GALT and type 1T helper cells, whereas a positive correlation was found with activated dendritic cells. S1PR1 exhibited a positive correlation with type 1T helper cells and a negative correlation with activated dendritic cells. Furthermore, our study utilized connectivity map analysis to identify nine potential medications, including verapamil, for treating MDR-TB. In conclusion, our research identified two molecular indicators for the differentiation between MDR-TB and DS-TB and identified a total of nine potential medications for MDR-TB.

Deciphering the role of lipid metabolism-related genes in Alzheimer's disease: a machine learning approach integrating Traditional Chinese Medicine.

Alzheimer's disease (AD) represents a progressive neurodegenerative disorder characterized by the accumulation of misfolded amyloid beta protein, leading to the formation of amyloid plaques and the aggregation of tau protein into neurofibrillary tangles within the cerebral cortex. The role of carbohydrates, particularly apolipoprotein E (ApoE), is pivotal in AD pathogenesis due to its involvement in lipid and cholesterol metabolism, and its status as a genetic predisposition factor for the disease. Despite its significance, the mechanistic contributions of Lipid Metabolism-related Genes (LMGs) to AD remain inadequately elucidated. This research endeavor seeks to bridge this gap by pinpointing biomarkers indicative of early-stage AD, with an emphasis on those linked to immune cell infiltration. To this end, advanced machine-learning algorithms and data derived from the Gene Expression Omnibus (GEO) database have been employed to facilitate the identification of these biomarkers. Differentially expressed genes (DEGs) were identified by comparing gene expression profiles between healthy individuals and Alzheimer's disease (AD) patients, using data from two Gene Expression Omnibus (GEO) datasets: GSE5281 and GSE138260. Functional enrichment analysis was conducted to elucidate the biological relevance of the DEGs. To ensure the reliability of the results, samples were randomly divided into training and validation sets. The analysis focused on lipid metabolism-related DEGs (LMDEGs) to explore potential biomarkers for AD. Machine learning algorithms, including Support Vector Machine-Recursive Feature Elimination (SVM-RFE) and the Least Absolute Shrinkage and Selection Operator (LASSO) regression model, were applied to identify a key gene biomarker. Additionally, immune cell infiltration and its relationship with the gene biomarker were assessed using the CIBERSORT algorithm. The Integrated Traditional Chinese Medicine (ITCM) database was also referenced to identify Chinese medicines related to lipid metabolism and their possible connection to AD. This comprehensive strategy aims to integrate modern computational methods with traditional medicine to deepen our understanding of AD and its underlying mechanisms. The study identified 137 genes from a pool of 751 lipid metabolism-related genes (LMGs) significantly associated with autophagy and immune response mechanisms. Through the application of LASSO and SVM-RFE machine-learning techniques, four genes-choline acetyl transferase (CHAT), member RAS oncogene family (RAB4A), acyl-CoA binding domain-containing protein 6 (ACBD6), and alpha-galactosidase A (GLA)-emerged as potential biomarkers for Alzheimer's disease (AD). These genes demonstrated strong therapeutic potential due to their involvement in critical biological pathways. Notably, nine Chinese medicine compounds were identified to target these marker genes, offering a novel treatment approach for AD. Further, ceRNA network analysis revealed complex regulatory interactions involving these genes, underscoring their importance in AD pathology. CIBERSORT analysis highlighted a potential link between changes in the immune microenvironment and CHAT expression levels in AD patients, providing new insights into the immunological dimensions of the disease. The discovery of these gene markers offers substantial promise for the diagnosis and understanding of Alzheimer's disease (AD). However, further investigation is necessary to validate their clinical utility. This study illuminates the role of Lipid Metabolism-related Genes (LMGs) in AD pathogenesis, offering potential targets for therapeutic intervention. It enhances our grasp of AD's complex mechanisms and paves the way for future research aimed at refining diagnostic and treatment strategies.

Metabolic biomarkers of neonatal sepsis: identification using metabolomics combined with machine learning.

Sepsis is a common disease associated with neonatal and infant mortality, and for diagnosis, blood culture is currently the gold standard method, but it has a low positivity rate and requires more than 2days to develop. Meanwhile, unfortunately, the specific biomarkers for the early and timely diagnosis of sepsis in infants and for the determination of the severity of this disease are lacking in clinical practice. Samples from 18 sepsis infants with comorbidities, 25 sepsis infants without comorbidities, and 25 infants with noninfectious diseases were evaluated using a serum metabolomics approach based on liquid chromatography‒mass spectrometry (LC‒MS) technology. Differentially abundant metabolites were screened via multivariate statistical analysis. In addition, least absolute shrinkage and selection operator (LASSO) and support vector machine recursive feature elimination (SVM-RFE) analyses were conducted to identify the key metabolites in infants with sepsis and without infections. The random forest algorithm was applied to determine key differentially abundant metabolites between sepsis infants with and without comorbidities. Receiver operating characteristic (ROC) curves were generated for biomarker value testing. Finally, a metabolic pathway analysis was conducted to explore the metabolic and signaling pathways associated with the identified differentially abundant metabolites. A total of 189 metabolites exhibited significant differences between infectious infants and noninfectious infants, while 137 distinct metabolites exhibited differences between septic infants with and without comorbidities. After screening for the key differentially abundant metabolites using LASSO and SVM-RFE analyses, hexylamine, psychosine sulfate, LysoPC (18:1 (9Z)/0:0), 2,4,6-tribromophenol, and 25-cinnamoyl-vulgaroside were retained for the diagnosis of infant sepsis. ROC curve analysis revealed that the area under the curve (AUC) was 0.9200 for hexylamine, 0.9749 for psychosine sulfate, 0.9684 for LysoPC (18:1 (9Z)/0:0), 0.7405 for 2,4,6-tribromophenol, 0.8893 for 25-cinnamoyl-vulgaroside, and 1.000 for the combination of all metabolites. When the septic infants with comorbidities were compared to those without comorbidities, four endogenous metabolites with the greatest importance were identified using the random forest algorithm, namely, 12-oxo-20-trihydroxy-leukotriene B4, dihydrovaltrate, PA (8:0/12:0), and 2-heptanethiol. The ROC curve analysis of these four key differentially abundant metabolites revealed that the AUC was 1 for all four metabolites. Pathway analysis indicated that phenylalanine, tyrosine, and tryptophan biosynthesis, phenylalanine metabolism, and porphyrin metabolism play important roles in infant sepsis. Serum metabolite profiles were identified, and machine learning was applied to identify the key differentially abundant metabolites in septic infants with comorbidities, septic infants without comorbidities, and infants without infectious diseases. The findings obtained are expected to facilitate the early diagnosis of sepsis in infants and determine the severity of the disease.

The PANoptosis-related hippocampal molecular subtypes and key biomarkers in Alzheimer’s disease patients

Alzheimer’s Disease (AD) is a neurodegenerative disorder, and various molecules associated with PANoptosis are involved in neuroinflammation and neurodegenerative diseases. This work aims to identify key genes, and characterize PANoptosis-related molecular subtypes in AD. Moreover, we establish a scoring system for distinguishing PANoptosis molecular subtypes and constructing diagnostic models for AD differentiation. A total of 5 hippocampal datasets were obtained from the Gene Expression Omnibus (GEO) database. In total, 1324 protein-encoding genes associated with PANoptosis (1313 apoptosis genes, 11 necroptosis genes, and 31 pyroptosis genes) were extracted from the GeneCards database. The Limma package was used to identify differentially expressed genes. Weighted Gene Co-Expression Network Analysis (WGCNA) was conducted to identify gene modules significantly associated with AD. The ConsensusClusterPlus algorithm was used to identify AD subtypes. Gene Set Variation Analysis (GSVA) was used to assess functional and pathway differences among the subtypes. The Boruta, Least Absolute Shrinkage and Selection Operator (LASSO), Random Forest (RF), and Support Vector Machine Recursive Feature Elimination (SVM-RFE) algorithms were used to select the three PANoptosis-related Key AD genes (PKADg). A scoring model was constructed based on the Boruta algorithm. PANoptosis diagnostic models were developed using the RF, SVM-RFE, and Logistic Regression (LR) algorithms. The ROC curves were used to assess the model performance. A total of 48 important genes were identified by intersecting 725 differentially expressed genes and 2127 highly correlated module genes from WGCNA with 1324 protein-encoding genes related to PANoptosis. Machine learning algorithms identified 3 key AD genes related to PANoptosis, including ANGPT1, STEAP3, and TNFRSF11B. These genes had strong discriminatory capacities among samples, with Receiver Operating Characteristic Curve (ROC) analysis indicating Area Under the Curve (AUC) values of 0.839, 0.8, and 0.868, respectively. Using the 48 important genes, the ConsensusClusterPlus algorithm identified 2 PANoptosis subtypes among AD patients, i.e., apoptosis subtype and mild subtype. Apoptosis subtype patients displayed evident cellular apoptosis and severe functionality damage in the hippocampal tissue. Meanwhile, mild subtype patients showed milder functionality damage. These two subtypes had significant differences in apoptosis and necroptosis; however, there was no apparent variation in pyroptosis functionality. The scoring model achieved an AUC of 100% for sample differentiation. The RF PANoptosis diagnostic model demonstrated an AUC of 100% in the training set and 85.85% in the validation set for distinguishing AD. This study identified two PANoptosis-related hippocampal molecular subtypes of AD, identified key genes, and established machine learning models for subtype differentiation and discrimination of AD. We found that in the context of AD, PANoptosis may influence disease progression through the modulation of apoptosis and necrotic apoptosis.

Bioinformatics analysis of effective biomarkers and immune infiltration in type 2 diabetes with cognitive impairment and aging

With the increasing prevalence of diabetes mellitus worldwide, type 2 diabetes mellitus (T2D) combined with cognitive impairment and aging has become one of the common and important complications of diabetes mellitus, which seriously affects the quality of life of the patients, and imposes a heavy burden on the patients’ families and the society. Currently, there are no special measures for the treatment of cognitive impairment and aging in type 2 diabetes mellitus. Therefore, the search for potential biological markers of type 2 diabetes mellitus combined with cognitive impairment and aging is of great significance for future precisive treatment. We downloaded three gene expression datasets from the GEO database: GSE161355 (related to T2D with cognitive impairment and aging), GSE122063, and GSE5281 (related to Alzheimer’s disease). Differentially expressed genes (DEGs) were identified, followed by gene set enrichment analysis (GSEA). A protein-protein interaction (PPI) network was constructed using the STRING database, and the top 15 hub genes were identified using the CytoHubba plugin in Cytoscape. Core genes were ultimately determined using three machine learning methods: LASSO regression, Support Vector Machine Recursive Feature Elimination (SVM-RFE), and Linear Discriminant Analysis (LDA). The diagnostic performance of these genes was assessed using ROC curve analysis and validated in an independent dataset (GSE5281). Regulatory genes related to ferroptosis were screened from the FerrDb database, and their biological functions were further explored through GO and KEGG enrichment analyses. Finally, the CIBERSORT algorithm was used to analyze immune cell infiltration, and the correlation between core genes and immune cell infiltration levels was calculated, leading to the construction of an mRNA-miRNA regulatory network. In the GSE161355 and GSE122063 datasets, 217 common DEGs were identified. GSEA analysis revealed their enrichment in the PI3K-PLC-TRK signaling pathway, TP53 regulation of metabolic genes pathway, Notch signaling pathway, among others. PPI network analysis identified 15 candidate core genes, and further selection using LASSO, LDA, and SVM-RFE machine learning algorithms resulted in 6 core genes: BCL6, TP53, HSP90AA1, CRYAB, IL1B, and DNAJB1. ROC curve analysis indicated that these genes had good diagnostic performance in the GSE161355 dataset, with TP53 and IL1B achieving an AUC of 0.9, indicating the highest predictive accuracy. BCL6, HSP90AA1, CRYAB, and DNAJB1 also had AUCs greater than 0.8, demonstrating moderate predictive accuracy. Validation in the independent dataset GSE5281 showed that these core genes also had good diagnostic performance in Alzheimer’s disease samples (AUC > 0.6). Ferroptosis-related analysis revealed that IL1B and TP53 play significant roles in apoptosis and immune response. Immune cell infiltration analysis showed that IL1B is significantly positively correlated with infiltration levels of monocytes and NK cells, while TP53 is significantly negatively correlated with infiltration levels of follicular helper T cells. The construction of the miRNA-mRNA regulatory network suggested that miR-150a-5p might play a key role in the regulation of T2D-associated cognitive impairment and aging by TP53. This study, by integrating bioinformatics and machine learning methods, identified BCL6, TP53, HSP90AA1, CRYAB, IL1B, and DNAJB1 as potential diagnostic biomarkers for T2D with cognitive impairment and aging, with a particular emphasis on the significance of TP53 and IL1B in immune cell infiltration. These findings not only enhance our understanding of the molecular mechanisms linking type 2 diabetes to cognitive impairment and aging, providing new targets for early diagnosis and treatment, but also offer new directions and targets for basic research.

Integrated approach of machine learning, Mendelian randomization and experimental validation for biomarker discovery in diabetic nephropathy.

To identify potential biomarkers and explore the mechanisms underlying diabetic nephropathy (DN) by integrating machine learning, Mendelian randomization (MR) and experimental validation. Microarray and RNA-sequencing datasets (GSE47184, GSE96804, GSE104948, GSE104954, GSE142025 and GSE175759) were obtained from the Gene Expression Omnibus database. Differential expression analysis identified the differentially expressed genes (DEGs) between patients with DN and controls. Diverse machine learning algorithms, including least absolute shrinkage and selection operator, support vector machine-recursive feature elimination, and random forest, were used to enhance gene selection accuracy and predictive power. We integrated summary-level data from genome-wide association studies on DN with expression quantitative trait loci data to identify genes with potential causal relationships to DN. The predictive performance of the biomarker gene was validated using receiver operating characteristic (ROC) curves. Gene set enrichment and correlation analyses were conducted to investigate potential mechanisms. Finally, the biomarker gene was validated using quantitative real-time polymerase chain reaction in clinical samples from patients with DN and controls. Based on identified 314 DEGs, seven characteristic genes with high predictive performance were identified using three integrated machine learning algorithms. MR analysis revealed 219 genes with significant causal effects on DN, ultimately identifying one co-expressed gene, carbonic anhydrase II (CA2), as a key biomarker for DN. The ROC curves demonstrated the excellent predictive performance of CA2, with area under the curve values consistently above 0.878 across all datasets. Additionally, our analysis indicated a significant association between CA2 and infiltrating immune cells in DN, providing potential mechanistic insights. This biomarker was validated using clinical samples, confirming the reliability of our findings in clinical practice. By integrating machine learning, MR and experimental validation, we successfully identified and validated CA2 as a promising biomarker for DN with excellent predictive performance. The biomarker may play a role in the pathogenesis and progression of DN via immune-related pathways. These findings provide important insights into the molecular mechanisms underlying DN and may inform the development of personalized treatment strategies for this disease.

Predicting cerebral edema in patients with spontaneous intracerebral hemorrhage using machine learning.

The early prediction of cerebral edema changes in patients with spontaneous intracerebral hemorrhage (SICH) may facilitate earlier interventions and result in improved outcomes. This study aimed to develop and validate machine learning models to predict cerebral edema changes within 72 h, using readily available clinical parameters, and to identify relevant influencing factors. An observational study was conducted between April 2021 and October 2023 at the Quzhou Affiliated Hospital of Wenzhou Medical University. After preprocessing the data, the study population was randomly divided into training and internal validation cohorts in a 7:3 ratio (training: N = 150; validation: N = 65). The most relevant variables were selected using Support Vector Machine Recursive Feature Elimination (SVM-RFE) and Least Absolute Shrinkage and Selection Operator (LASSO) algorithms. The predictive performance of random forest (RF), GDBT, linear regression (LR), and XGBoost models was evaluated using the area under the receiver operating characteristic curve (AUROC), precision-recall curve (AUPRC), accuracy, F1-score, precision, recall, sensitivity, and specificity. Feature importance was calculated, and the SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) methods were employed to explain the top-performing model. A total of 84 (39.1%) patients developed cerebral edema changes. In the validation cohort, GDBT outperformed LR and RF, achieving an AUC of 0.654 (95% CI: 0.611-0.699) compared to LR of 0.578 (95% CI, 0.535-0.623, DeLong: p = 0.197) and RF of 0.624 (95% CI, 0.588-0.687, DeLong: p = 0.236). XGBoost also demonstrated similar performance with an AUC of 0.660 (95% CI, 0.611-0.711, DeLong: p = 0.963). However, in the training set, GDBT still outperformed XGBoost, with an AUC of 0.603 ± 0.100 compared to XGBoost of 0.575 ± 0.096. SHAP analysis revealed that serum sodium, HDL, subarachnoid hemorrhage volume, sex, and left basal ganglia hemorrhage volume were the top five most important features for predicting cerebral edema changes in the GDBT model. The GDBT model demonstrated the best performance in predicting 72-h changes in cerebral edema. It has the potential to assist clinicians in identifying high-risk patients and guiding clinical decision-making.

Screening and validating genes associated with cuproptosis in systemic lupus erythematosus by expression profiling combined with machine learning.

Cell death has long been a focal point in life sciences research, and recently, scientists have discovered a novel form of cell death induced by copper, termed cuproptosis. This paper aimed to identify genes associated with cuproptosis in Systemic Lupus Erythematosus (SLE) through machine learning, combined with single-cell sequencing (scRNA-seq), to screen and validate related genes. The analytical results were then experimentally verified. Two published microarray gene expression datasets (GSE65391 and GSE61635) from SLE and control peripheral blood samples were downloaded from the GEO database. The GSE65391 dataset was used as the training group, while the GSE61635 dataset served as the validation group. Differentially expressed genes (DEGs) from GSE65391 identified 12 differential genes. Nine diagnostic genes, considered potential biomarkers, were selected using the least absolute shrinkage and selection operator (LASSO) and support vector machine recursive feature elimination (SVM-RFE) analysis. The Receiver Operating Characteristic (ROC) curves for both the training and validation groups were used to calculate the Area Under the Curve (AUC) to assess discriminatory properties. CIBERSORT was used to assess the relationship between these diagnostic genes and a reference set of infiltrating immune cells. Single-cell RNA sequencing data (GSE162577) from SLE patients were also obtained from the GEO database and analyzed. Experimental validation of the most important SLE biomarkers was performed. Twelve significantly different cuproptosis-related genes were identified in the GSE65391 training set. Immune cell analysis revealed 12 immune cell types and identified nine signature genes, including PDHB, GLS, DLAT, LIAS, MTF1, DLST, DLD, LIPT1, and FDX1. In the GSE61635 validation set, seven genes were weakly expressed, and two genes were strongly expressed in the treatment group. According to the ROC curves, PDHB and GLS demonstrated significant diagnostic value. Additionally, correlation analysis was conducted on the nine characteristic genes in relation to immune infiltration. The distribution of key genes in immune cells was determined using single-cell RNA sequencing data. Finally, the mRNA expression of the nine diagnostic genes was validated using qPCR.

Identification and RT-qPCR Validation of Biomarkers Based on Butyrate Metabolism-Related Genes to Predict Recurrent Miscarriage.

To date, the cause of recurrent miscarriage (RM) in at least 50% of patients remains unknown. However, no study has explored the correlation between butyrate metabolism-related genes (BMRGs) and RM. RM-related datasets (GSE165004, GSE111974, GSE73025, and GSE179996) were obtained from the Gene Expression Omnibus (GEO) database. First, 595 differentially expressed genes (DEGs) were identified between the RM and control samples in GSE165004. Subsequently, 213 differentially expressed BMRGs (DE-BMRGs) were identified by considering the intersection of DEGs with BMRGs. The protein-protein interaction (PPI)network of DE-BMRGs contained 156 nodes and 250 edges, and a key module was obtained. In total, four biomarkers (ACTR2, ANXA2, PFN1, and OAS1) were acquired through least absolute shrinkage and selection operator (LASSO), support vector machine-recursive feature elimination (SVM-RFE), and random forest (RF). Immune analysis revealed two immune cells and three immune-related gene sets that were significantly different between the RM and control groups, namely, T helper cells, regulatory T cells (Treg), MHC class I, parainflammation, and type I IFN response. In addition, a TF-mRNA network based on the top 100 nodes ranked in the order of connectivity was created, including 100 nodes and 253 edges, such as MTERF2-ACTR2, NKX23-PFN1, STAT1-OAS1, and SP100-ANXA2. Finally, 3 drugs (withaferin A, N-ethylmaleimide, and etoposide) were predicted to interact with 2 biomarkers (ANXA2 and ACTR2). Eventually, ANXA2 and OAS1 were significantly downregulated, and PFN1 was markedly overexpressed in the RM group, as determined by reverse transcription quantitative polymerase chain reaction (RT-qPCR). Our findings authenticated four butyrate metabolism-related biomarkers for the diagnosis of RM, providing a scientific reference for further studies on RM treatment.

Identification of potential biomarkers and drug of ischemic stroke in patients with COVID-19 through machine learning

The relationship between COVID-19 and ischemic stroke (IS) has attracted significant attention, yet the precise mechanism at the gene level remains unclear. This study aims to reveal potential biomarkers and drugs for COVID-19-related IS through bioinformatics methods. We collected two gene expression profiling datasets, GSE16561 and GSE213313, and selected GSE179879 and GSE196822 as validation sets for analysis. Through analysis, we identified 77 differentially expressed genes (DEGs) shared between COVID-19 and IS. Further gene enrichment analysis revealed that these genes are primarily involved in immune regulation. By constructing a protein-protein interaction network, we screened out nine hub genes, including FCGR3A, KLRB1, IL2RB, CD2, IL7R, CCR7, CD3D, GZMK, and ITK. In LASSO regression analysis, we evaluated the ROC curve's area under the curve (AUC) scores of key genes to assess their diagnostic accuracy. Subsequently, we performed random forest (RF), Support Vector Machine Recursive Feature Elimination (SVM-RFE), and neural network construction on hub genes to ensure accurate diagnosis of IS. Finally, by intersecting the results of three algorithms (LASSO regression, random forest, and SVM), CD3D and ITK were identified as the ultimate key genes. Based on this, we predicted potential targeted drug Blinatumomab. These research findings provide clues for a deeper understanding of the biological mechanisms of COVID-19-related IS and offer new insights for exploring novel treatment approaches.

Identification of ferroptosis biomarkers and immune infiltration landscapes in atrial fibrillation: A bioinformatics analysis.

Ferroptosis has been recognized as a critical factor in the development of atrial fibrillation (AF), but its precise mechanisms remain unclear. We downloaded the GSE115574 dataset from the gene expression omnibus database to analyze the expression levels of ferroptosis-related genes (FRGs) and identify differentially expressed genes (DEGs). Least absolute shrinkage and selection operator (LASSO) and support vector machine-recursive feature elimination (SVM-RFE) machine learning techniques were employed to identify key genes associated with AF. The diagnostic performance of these genes was evaluated using Receiver operating characteristic curves (ROC) and validated in an independent AF dataset. miRNA and lncRNA predictions for potential binding to these key genes were conducted using miRBase, miRDB, and TargetScan. Furthermore, gene set enrichment analysis (GSEA) enrichment analysis, immune cell infiltration analysis, and targeted drug prediction were performed. The intersection of LASSO regression and SVM-RFE analyses identified 7 DEGs significantly associated with AF. Validation through ROC and an additional dataset confirmed the importance of MAPK14, CAV1, and ADAM23. Significant infiltration of memory B cells, regulatory T cells, and monocytes was observed in atrial tissues. Seventy-two miRNAs were predicted to potentially target MAPK14, and 2 drugs were identified as targeting CAV1. This study underscores the involvement of FRGs in AF through machine learning and validation approaches. The observed immune cell infiltration suggests a potential link between immune response and AF. The predicted ceRNA network offers new insights into gene regulation, presenting potential biomarkers and therapeutic targets for AF.

Identification of a novel immune infiltration-related gene signature, MCEMP1, for coronary artery disease.

This study aims to identify a novel gene signature for coronary artery disease (CAD), explore the role of immune cell infiltration in CAD pathogenesis, and assess the cell function of mast cell-expressed membrane protein 1 (MCEMP1) in human umbilical vein endothelial cells (HUVECs) treated with oxidized low-density lipoprotein (ox-LDL). To identify differentially expressed genes (DEGs) of CAD, datasets GSE24519 and GSE61145 were downloaded from the Gene Expression Omnibus (GEO) database using the R "limma" package with p < 0.05 and |log2 FC| > 1. Gene ontology (GO) and pathway analyses were conducted to determine the biological functions of DEGs. Hub genes were identified using support vector machine-recursive feature elimination (SVM-RFE) and least absolute shrinkage and selection operator (LASSO). The expression levels of these hub genes in CAD were validated using the GSE113079 dataset. CIBERSORT program was used to quantify the proportion of immune cell infiltration. Western blot assay and qRT-PCR were used to detect the expression of hub genes in ox-LDL-treated HUVECs to validate the bioinformatics results. Knockdown interference sequences for MCEMP1 were synthesized, and cell proliferation and apoptosis were examined using a CCK8 kit and Muse® Cell Analyzer, respectively. The concentrations of IL-1β, IL-6, and TNF-α were measured with respective enzyme-linked immunosorbent assay (ELISA) kits. A total of 73 DEGs (four down-regulated genes and 69 up-regulated genes) were identified in the metadata (GSE24519 and GSE61145) cohort. GO and Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis results indicated that these DEGs might be associated with the regulation of platelet aggregation, defense response or response to bacterium, NF-kappa B signaling pathway, and lipid and atherosclerosis. Using SVM-RFE and LASSO, seven hub genes were obtained from the metadata. The upregulated expression of DIRC2 and MCEMP1 in CAD was confirmed in the GSE113079 dataset and in ox-LDL-treated HUVECs. The associations between the two hub genes (DIRC2 and MCEMP1) and the 22 types of immune cell infiltrates in CAD were found. MCEMP1 knockdown accelerated cell proliferation and suppressed cell apoptosis for ox-LDL-treated HUVECs. Additionally, MCEMP1 knockdown appeared to decrease the expression of inflammatory factors IL-1β, IL-6, and TNF-α. The results of this study indicate that MCEMP1 may play an important role in CAD pathophysiology.

Screening and identification of the hub genes in severe acute pancreatitis and sepsis.

Severe acute pancreatitis (SAP) is accompanied with acute onset, rapid progression, and complicated condition. Sepsis is a common complication of SAP with a high mortality rate. This research aimed to identify the shared hub genes and key pathways of SAP and sepsis, and to explore their functions, molecular mechanism, and clinical value. We obtained SAP and sepsis datasets from the Gene Expression Omnibus (GEO) database and employed differential expression analysis and weighted gene co-expression network analysis (WGCNA) to identify the shared differentially expressed genes (DEGs). Functional enrichment analysis and protein-protein interaction (PPI) was used on shared DEGs to reveal underlying mechanisms in SAP-associated sepsis. Machine learning methods including random forest (RF), least absolute shrinkage and selection operator (LASSO) and support vector machine recursive feature elimination (SVM-RFE) were adopted for screening hub genes. Then, receiver operating characteristic (ROC) curve and nomogram were applied to evaluate the diagnostic performance. Finally, immune cell infiltration analysis was conducted to go deeply into the immunological landscape of sepsis. We obtained a total of 123 DEGs through cross analysis between Differential expression analysis and WGCNA important module. The Gene Ontology (GO) analysis uncovered the shared genes exhibited a significant enrichment in regulation of inflammatory response. The Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis revealed that the shared genes were primarily involved in immunoregulation by conducting NOD-like receptor (NLR) signaling pathway. Three machine learning results revealed that two overlapping genes (ARG1, HP) were identified as shared hub genes for SAP and sepsis. The immune infiltration results showed that immune cells played crucial part in the pathogenesis of sepsis and the two hub genes were substantially associated with immune cells, which may be a therapy target. ARG1 and HP may affect SAP and sepsis by regulating inflammation and immune responses, shedding light on potential future diagnostic and therapeutic approaches for SAP-associated sepsis.

Identification of novel biomarkers, shared molecular signatures and immune cell infiltration in heart and kidney failure by transcriptomics.

Heart failure (HF) and kidney failure (KF) are closely related conditions that often coexist, posing a complex clinical challenge. Understanding the shared mechanisms between these two conditions is crucial for developing effective therapies. This study employed transcriptomic analysis to unveil molecular signatures and novel biomarkers for both HF and KF. A total of 2869 shared differentially expressed genes (DEGs) were identified in patients with HF and KF compared to healthy controls. Functional enrichment analysis was performed to explore the common mechanisms underlying these conditions. A protein-protein interaction (PPI) network was constructed, and machine learning algorithms, including Random Forest (RF), Support Vector Machine-Recursive Feature Elimination (SVM-RFE), and Least Absolute Shrinkage and Selection Operator (LASSO), were used to identify key signature genes. These genes were further analyzed using Gene Set Variation Analysis (GSVA) and Gene Set Enrichment Analysis (GSEA), with their diagnostic values validated in both training and validation sets. Molecular docking studies were conducted. Additionally, immune cell infiltration and correlation analyses were performed to assess the relationship between immune responses and the identified biomarkers. The functional enrichment analysis indicated that the common mechanisms are associated with cellular homeostasis, cell communication, cellular replication, inflammation, and extracellular matrix (ECM) production, with the PI3K-Akt signaling pathway being notably enriched. The PPI network revealed two key protein clusters related to the cell cycle and inflammation. CDK2 and CCND1 were identified as signature genes for both HF and KF. Their diagnostic value was validated in both training and validation sets. Additionally, docking studies with CDK2 and CCND1 were performed to evaluate potential drug candidates. Immune cell infiltration and correlation analyses highlighted the immune microenvironment, and that CDK2 and CCND1 are associated with immune responses in HF and KF. This study identifies CDK2 and CCND1 as novel biomarkers linking cell cycle regulation and inflammation in heart and kidney failure. These findings offer new insights into the molecular mechanisms of HF and KF and present potential targets for diagnosis and therapy.

Identification of common signature genes and pathways underlying the pathogenesis association between nonalcoholic fatty liver disease and heart failure.

Non-alcoholic fatty liver disease (NAFLD) and heart failure (HF) are related conditions with an increasing incidence. However, the mechanism underlying their association remains unclear. This study aimed to explore the shared pathogenic mechanisms and common biomarkers of NAFLD and HF through bioinformatics analyses and experimental validation. NAFLD and HF-related transcriptome data were extracted from the Gene Expression Omnibus (GEO) database (GSE126848 and GSE26887). Differential analysis was performed to identify common differentially expressed genes (co-DEGs) between NAFLD and HF. Gene ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG), and gene set enrichment analysis (GSEA) were conducted to explore the functions and regulatory pathways of co-DEGs. Protein-protein interaction (PPI) network and support vector machine-recursive feature elimination (SVM-RFE) methods were used to screen common key DEGs. The diagnostic value of common key DEGs was assessed by receiver operating characteristic (ROC) curve and validated with external datasets (GSE89632 and GSE57345). Finally, the expression of biomarkers was validated in mouse models. A total of 161 co-DEGs were screened out in NAFLD and HF patients. GO, KEGG, and GSEA analyses indicated that these co-DEGs were mainly enriched in immune-related pathways. PPI network revealed 14 key DEGs, and SVM-RFE model eventually identified two genes (CD163 and CCR1) as common key DEGs for NAFLD and HF. Expression analysis revealed that the expression levels of CD163 and CCR1 were significantly down-regulated in HF and NAFLD patients. ROC curve analysis showed that CD163 and CCR1 had good diagnostic values for HF and NAFLD. Single-gene GSEA suggested that CD163 and CCR1 were mainly engaged in immune responses and inflammation. Experimental validation indicated unbalanced macrophage polarization in HF and NAFLD mouse models, and the expression of CD163 and CCR1 were significantly down-regulated. This study identified M2 polarization impairment characterized by decreased expression of CD163 and CCR1 as a common pathogenic pathway in NAFLD and HF. The downregulation of CD163 and CCR1 may reflect key pathological changes in the development and progression of NAFLD and HF, suggesting their potential as diagnostic and therapeutic targets.

Screening, identification and targeted intervention of necroptotic biomarkers of asthma

BackgroundAs a pivotal pathway of programmed cell death, necroptosis significantly contributes to the pathogenesis of respiratory disorders. However, its role in asthma is not yet fully elucidated. Therefore, this study aimed to identify markers associated with necroptosis, evaluate their functions in asthma, and explore potential therapeutic agents targeting necroptosis for the management of asthma. MethodsFirstly, machine learning algorithms, including Least Absolute Shrinkage and Selection Operator (LASSO), Random Forest, and Support Vector Machine-Recursive Feature Elimination (SVM-RFE), were utilized to identify necroptosis-related differentially expressed genes (NRDEGs) in asthma patients compared to healthy controls. Concurrently, the expression of NRDEGs was validated using external datasets, Western blot, and quantitative real-time polymerase chain reaction (qPCR). Secondly, the clinical relevance of NRDEGs was assessed through Receiver Operating Characteristic (ROC) curve analysis and correlation with clinical indicators. Thirdly, the relationship between NRDEGs and pulmonary immune cell infiltration, as well as the signaling interactions between different cells types, were analyzed through immune infiltration and single-cell analysis. Fourthly, Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG), and Gene Set Enrichment Analysis (GSEA), were conducted to elucidate the functional roles of NRDEGs. Finally, compounds targeting NRDEGs were screened, and their binding affinities were evaluated using molecular docking studies. ResultsIn asthma, necroptosis is activated, leading to the identification of four NRDEGs: NLRP3, PYCARD, ALOX15, and VDAC3. Among these, NLRP3, PYCARD, and ALOX15 are upregulated, whereas VDAC3 is downregulated in asthma. Comprehensive clinical evaluations indicated that NRDEGs hold diagnostic value for asthma. Specifically, NLRP3 was inversely correlated with forced expiratory volume in 1 s (FEV1) and forced vital capacity (FVC), while VDAC3 showed an inverse correlation with sputum neutrophils. Conversely, ALOX15 expression was positively correlated with fractional exhaled nitric oxide (FeNO) levels, as well as sputum eosinophils, blood eosinophils, and blood IgE levels. Subsequent immune infiltration analysis revealed associations between NRDEGs and activated dendritic cells, mast cells, and eosinophils. Single-cell RNA sequencing (scRNA-seq) further confirmed the communication signals between myeloid dendritic cells, fibroblasts, neutrophils, and helper T cells, predominantly related to fibrosis and immune-inflammatory responses. Pathway enrichment analysis demonstrated that NRDEGs are involved in ribosomal function, oxidative phosphorylation, and fatty acid metabolism. Finally, resveratrol and triptonide were identified as potential therapeutic agents targeting the proteins encoded by NRDEGs for asthma treatment. ConclusionsThe necroptosis pathway is activated in asthma, with NRDEGs—namely PYCARD, NLRP3, ALOX15, and VDAC3—correlated with declines in lung function and airway inflammation. These genes serve as reliable predictors of asthma risk and are involved in the regulation of the immune-inflammatory microenvironment. Resveratrol and triptolide have been identified as promising therapeutic candidates due to their potential to target the proteins encoded by these genes.

PseU-KeMRF: A Novel Method for Identifying RNA Pseudouridine Sites.

Pseudouridine is a type of abundant RNA modification that is seen in many different animals and is crucial for a variety of biological functions. Accurately identifying pseudouridine sites within the RNA sequence is vital for the subsequent study of various biological mechanisms of pseudouridine. However, the use of traditional experimental methods faces certain challenges. The development of fast and convenient computational methods is necessary to accurately identify pseudouridine sites from RNA sequence information. To address this, we introduce a novel pseudouridine site prediction model called PseU-KeMRF, which can identify pseudouridine sites in three species, H. sapiens, S. cerevisiae, and M. musculus. Through comprehensive analysis, we selected four RNA coding schemes, including binary feature, position-specific trinucleotide propensity based on single strand (PSTNPss), nucleotide chemical property (NCP) and pseudo k-tuple composition (PseKNC). Then the support vector machine-recursive feature elimination (SVM-RFE) method was used for feature selection and the feature subset was optimized. Finally, the best feature subsets are input into the kernel based on multinomial random forests (KeMRF) classifier for cross-validation and independent testing. As a new classification method, compared with the traditional random forest, KeMRF not only improves the node splitting process of decision tree construction based on multinomial distribution, but also combines the easy to interpret kernel method for prediction, which makes the classification performance better. Our results indicate superior predictive performance of PseU-KeMRF over other existing models, which can prove that PseU-KeMRF is a highly competitive predictive model that can successfully identify pseudouridine sites in RNA sequences.