Support Vector Machine Recursive Feature Elimination Research Articles

Machine learning models reveal the critical role of nighttime systolic blood pressure in predicting functional outcome for acute ischemic stroke after endovascular thrombectomy

BackgroundBlood pressure (BP) is a key factor for the clinical outcomes of acute ischemic stroke (AIS) receiving endovascular thrombectomy (EVT). However, the effect of the circadian pattern of BP on functional outcome is unclear.MethodsThis multicenter, retrospective, observational study was conducted from 2016 to 2023 at three hospitals in China (ChiCTR2300077202). A total of 407 patients who underwent endovascular thrombectomy (EVT) and continuous 24-h BP monitoring were included. Two hundred forty-one cases from Beijing Hospital were allocated to the development group, while 166 cases from Peking University Shenzhen Hospital and Hainan General Hospital were used for external validation. Postoperative systolic BP (SBP) included daytime SBP, nighttime SBP, and 24-h average SBP. Least absolute shrinkage and selection operator (LASSO), support vector machine-recursive feature elimination (SVM-RFE), Boruta were used to screen for potential features associated with functional dependence defined as 3-month modified Rankin scale (mRS) score ≥ 3. Nine algorithms were applied for model construction and evaluated using area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy.ResultsThree hundred twenty-eight of 407 (80.6%) patients achieved successful recanalization and 182 patients (44.7%) were functional independent. NIHSS at onset, modified cerebral infarction thrombolysis grade, atrial fibrillation, coronary atherosclerotic heart disease, hypertension were identified as prognostic factors by the intersection of three algorithms to construct the baseline model. Compared to daytime SBP and 24-h SBP models, the AUC of baseline + nighttime SBP showed the highest AUC in all algorithms. The XGboost model performed the best among all the algorithms. ROC results showed an AUC of 0.841 in the development set and an AUC of 0.752 in the validation set for the baseline plus nighttime SBP model, with a brier score of 0.198.ConclusionThis study firstly explored the association between circadian BP patterns with functional outcome for AIS. Nighttime SBP may provide more clinical information regarding the prognosis of patients with AIS after EVT.

The shared circulating diagnostic biomarkers and molecular mechanisms of systemic lupus erythematosus and inflammatory bowel disease

BackgroundSystemic lupus erythematosus (SLE) is a multi-organ chronic autoimmune disease. Inflammatory bowel disease (IBD) is a common chronic inflammatory disease of the gastrointestinal tract. Previous studies have shown that SLE and IBD share common pathogenic pathways and genetic susceptibility, but the specific pathogenic mechanisms remain unclear.MethodsThe datasets of SLE and IBD were downloaded from the Gene Expression Omnibus (GEO). Differentially expressed genes (DEGs) were identified using the Limma package. Weighted gene coexpression network analysis (WGCNA) was used to determine co-expression modules related to SLE and IBD. Pathway enrichment was performed using Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis for co-driver genes. Using the Least AbsoluteShrinkage and Selection Operator (Lasso) regressionand Support Vector Machine-Recursive Feature Elimination (SVM-RFE), common diagnostic markers for both diseases were further evaluated. Then, we utilizedthe CIBERSORT method to assess the abundance of immune cell infiltration. Finally,we used the single-cell analysis to obtain the location of common diagnostic markers.Results71 common driver genes were identified in the SLE and IBD cohorts based on the DEGs and module genes. KEGG and GO enrichment results showed that these genes were closely associated with positive regulation of programmed cell death and inflammatory responses. By using LASSO regression and SVM, five hub genes (KLRF1, GZMK, KLRB1, CD40LG, and IL-7R) were ultimately determined as common diagnostic markers for SLE and IBD. ROC curve analysis also showed good diagnostic performance. The outcomes of immune cell infiltration demonstrated that SLE and IBD shared almost identical immune infiltration patterns. Furthermore, the majority of the hub genes were commonly expressed in NK cells by single-cell analysis.ConclusionThis study demonstrates that SLE and IBD share common diagnostic markers and pathogenic pathways. In addition, SLE and IBD show similar immune cellinfiltration microenvironments which provides newperspectives for future treatment.

Bioinformatics to Identify Biomarkers of Diabetic Nephropathy based on Sphingolipid Metabolism and their Molecular Mechanisms.

Diabetes mellitus (DM) frequently results in Diabetic Nephropathy (DN), which has a significant negative impact on the quality of life of diabetic patients. Sphingolipid metabolism is associated with diabetes, but its relationship with DN is unclear. Therefore, screening biomarkers related to sphingolipid metabolism is crucial for treating DN. To identify Differentially Expressed Genes (DEGs) in the GSE142153 dataset, we conducted a differential expression analysis (DN samples versus control samples). The intersection genes were obtained by overlapping DEGs and Sphingolipid Metabolism-Related Genes (SMRGs). Furthermore, The Least Absolute Shrinkage and Selection Operator (LASSO) and Support Vector Machine Recursive Feature Elimination (SVM-RFE) algorithms were used to filter biomarkers. We further analyzed the Gene Set Enrichment analysis (GSEA) and the immunoinfiltrational analysis based on biomarkers. We identified 2,186 DEGs associated with DN. Then, five SMR-DEGs were obtained. Subsequently, biomarkers associated with sphingolipid metabolism (S1PR1 and SELL) were identified by applying machine learning and expression analysis. In addition, GSEA showed that these biomarkers were correlated with cytokine cytokine receptor interaction'. Significant variations in B cells, DCs, Tems, and Th2 cells between the two groups suggested that these cells might have a role in DN. Overall, we obtained two sphingolipid metabolism-related biomarkers (S1PR1 and SELL) associated with DN, which laid a theoretical foundation for treating DN.

Novel candidate genes for environmental stresses response in Synechocystis sp. PCC 6803 revealed by machine learning algorithms.

Cyanobacteria have developed acclimation strategies to adapt to harsh environments, making them a model organism. Understanding the molecular mechanisms of tolerance to abiotic stresses can help elucidate how cells change their gene expression patterns in response to stress. Recent advances in sequencing techniques and bioinformatics analysis methods have led to the discovery of many genes involved in stress response in organisms. The Synechocystis sp. PCC 6803 is a suitable microorganism for studying transcriptome response under environmental stress. Therefore, for the first time, we employed two effective feature selection techniques namely and support vector machine recursive feature elimination (SVM-RFE) and LASSO (Least Absolute Shrinkage Selector Operator) to pinpoint the crucial genes responsive to environmental stresses in Synechocystis sp. PCC 6803. We applied these algorithms of machine learning to analyze the transcriptomic data of Synechocystis sp. PCC 6803 under distinct conditions, encompassing light, salt and iron stress conditions. Seven candidate genes namely sll1862, slr0650, sll0760, slr0091, ssl3044, slr1285, and slr1687 were selected by both LASSO and SVM-RFE algorithms. RNA-seq analysis was performed to validate the efficiency of our feature selection approach in selecting the most important genes. The RNA-seq analysis revealed significantly high expression for five genes namely sll1862, slr1687, ssl3044, slr1285, and slr0650 under ion stress condition. Among these five genes, ssl3044 and slr0650 could be introduced as new potential candidate genes for further confirmatory genetic studies, to determine their roles in their response to abiotic stresses.

Exosome secretion related gene signature predicts chemoresistance in patients with colorectal cancer

BackgroundColorectal cancer (CRC) is a highly heterogeneous malignancy, and patients often have different responses to treatment. In this study, the genetic characteristics related to exosome formation and secretion procedure were used to predict chemoresistance and guide the individualized treatment of patients. MethodsFirstly, seven microarray datasets in Gene Expression Omnibus (GEO) and RNA-Seq dataset from the Cancer Genome Atlas (TCGA) were used to analysis the transcriptome profiles and associated characteristics of CRC patients. Then, a predictive model based on gene features linked to exosome formation and secretion was created and validated using Least Absolute Shrinkage and Selection Operator (LASSO) regression analysis and Support Vector Machine-Recursive Feature Elimination (SVM-RFE) machine learning. Finally, we evaluated the model using chemoresistant/chemosensitive cells and tissues by immunofluorescence (IF), western blot (WB), quantitative real-time PCR (qRT-PCR) and immunocytochemistry (IHC) experiments, and the predictive value of integrated model in the clinical validation cohort were performed by Receiver Operating Characteristic (ROC) and Kaplan-Meier (K-M) curves analyses. ResultsWe established a risk score signature based on three genes related to exosome secretion in CRC. Better Overall Survival (OS) and greater chemosensitivity were seen in the low-risk group, whereas the high-risk group exhibited chemoresistance and a subpar response to immune checkpoint blockade (ICB) therapy. Higher expression of the model genes EXOC2, EXOC3 and STX4 were observed in chemoresistant cells and specimens. The AUC of 5-year disease-free survival (DFS) was 0.804. Compared with that in the low-risk group, patients’ DFS was found to be significantly worse in the high-risk group. ConclusionsIn summary, the gene signature related to exosome formation and secretion could reliably predict patients' chemosensitivity and ICB treatment response, which providing new independent biomarkers for the treatment of CRC.

Machine learning and weighted gene co-expression network analysis identify a three-gene signature to diagnose rheumatoid arthritis.

Rheumatoid arthritis (RA) is a systemic immune-related disease characterized by synovial inflammation and destruction of joint cartilage. The pathogenesis of RA remains unclear, and diagnostic markers with high sensitivity and specificity are needed urgently. This study aims to identify potential biomarkers in the synovium for diagnosing RA and to investigate their association with immune infiltration. We downloaded four datasets containing 51 RA and 36 healthy synovium samples from the Gene Expression Omnibus database. Differentially expressed genes were identified using R. Then, various enrichment analyses were conducted. Subsequently, weighted gene co-expression network analysis (WGCNA), random forest (RF), support vector machine-recursive feature elimination (SVM-RFE), and least absolute shrinkage and selection operator (LASSO) were used to identify the hub genes for RA diagnosis. Receiver operating characteristic curves and nomogram models were used to validate the specificity and sensitivity of hub genes. Additionally, we analyzed the infiltration levels of 28 immune cells in the expression profile and their relationship with the hub genes using single-sample gene set enrichment analysis. Three hub genes, namely, ribonucleotide reductase regulatory subunit M2 (RRM2), DLG-associated protein 5 (DLGAP5), and kinesin family member 11 (KIF11), were identified through WGCNA, LASSO, SVM-RFE, and RF algorithms. These hub genes correlated strongly with T cells, natural killer cells, and macrophage cells as indicated by immune cell infiltration analysis. RRM2, DLGAP5, and KIF11 could serve as potential diagnostic indicators and treatment targets for RA. The infiltration of immune cells offers additional insights into the underlying mechanisms involved in the progression of RA.

Investigating potential biomarkers of acute pancreatitis in patients with a BMI>30 using Mendelian randomization and transcriptomic analysis

BackgroundAcute pancreatitis (AP) has become a significant global health concern, and a high body mass index (BMI) has been identified as a key risk factor exacerbating this condition. Within this context, lipid metabolism assumes a critical role. The complex relationship between elevated BMI and AP, mediated by lipid metabolism, markedly increases the risk of complications and mortality. This study aimed to accurately define the correlation between BMI and AP, incorporating a comprehensive analysis of the interactions between individuals with high BMI and AP.MethodsMendelian randomization (MR) analysis was first applied to determine the causal relationship between BMI and the risk of AP. Subsequently, three microarray datasets were obtained from the GEO database. This was followed by an analysis of differentially expressed genes and the application of weighted gene coexpression network analysis (WGCNA) to identify key modular genes associated with AP and elevated BMI. Functional enrichment analysis was then performed to shed light on disease pathogenesis. To identify the most informative genes, machine learning algorithms, including Random Forest (RF), Support Vector Machine-Recursive Feature Elimination (SVM-RFE), and Least Absolute Shrinkage and Selection Operator (LASSO), were employed. Subsequent analysis focused on the colocalization of the Quantitative Trait Loci (eQTL) data associated with the selected genes and Genome-Wide Association Studies (GWAS) data related to the disease. Preliminary verification of gene expression trends was conducted using external GEO datasets. Ultimately, the diagnostic potential of these genes was further confirmed through the development of an AP model in mice with a high BMI.ResultsA total of 21 intersecting genes related to BMI>30, AP, and lipid metabolism were identified from the datasets. These genes were primarily enriched in pathways related to cytosolic DNA sensing, cytokine‒cytokine receptor interactions, and various immune and inflammatory responses. Next, three machine learning techniques were utilized to identify HADH as the most prevalent diagnostic gene. Colocalization analysis revealed that HADH significantly influenced the risk factors associated with BMI and AP. Furthermore, the trend in HADH expression within the external validation dataset aligned with the trend in the experimental data, thus providing a preliminary validation of the experimental findings.The changes in its expression were further validated using external datasets and quantitative real-time polymerase chain reaction (qPCR).ConclusionThis study systematically identified HADH as a potential lipid metabolism-grounded biomarker for AP in patients with a BMI>30.

Establishment of a diagnostic model of endometriosis based on disulfidptosis-related genes.

We aimed to establish a diagnostic model of endometriosis (EM) based on disulfidptosis-related genes (DRGs). The mRNA expression data of EM were downloaded from the gene expression omnibus database and subjected to differential analysis, and co-expression analysis was performed based on 10 disulfidptosis genes to acquire DRGs. The differentially expressed DRGs were subjected to biofunctional analysis. Lasso analysis and support vector machine-recursive feature elimination (SVM-RFE) analysis were employed to extract the intersection of feature genes as biomarkers, and the diagnostic values of biomarkers for EM were evaluated based on receiver operating characteristic curves. The correlations between biomarkers and the immune microenvironment were assessed by Pearson analysis of biomarkers and immune cell infiltration levels. Transforming growth factor β stimulated protein clone 22 domain family member 4 (TSC22D4), and F-box/SPRY domain-containing protein 1 (FBXO45) worked as the diagnostic classifiers in EM, with an obvious decrease in FBXO45 expression and an evident increase in TSC22D4 expression. The areas under the curves of FBXO45 and TSC22D4 were 0.752 and 0.706, respectively, and the area of FBXO45 combined with TSC22D4 reached 0.865, suggesting that TSC22D4 and FBXO45 had high predictive values. The diagnostic markers were closely correlated with immune cell infiltration. The diagnostic markers constructed based on disulfidptosis are good predictors for EM, which have close correlations with EM.

Discovery and validation of molecular patterns and immune characteristics in the peripheral blood of ischemic stroke patients.

Stroke is a disease with high morbidity, disability, and mortality. Immune factors play a crucial role in the occurrence of ischemic stroke (IS), but their exact mechanism is not clear. This study aims to identify possible immunological mechanisms by recognizing immune-related biomarkers and evaluating the infiltration pattern of immune cells. We downloaded datasets of IS patients from GEO, applied R language to discover differentially expressed genes, and elucidated their biological functions using GO, KEGG analysis, and GSEA analysis. The hub genes were then obtained using two machine learning algorithms (least absolute shrinkage and selection operator (LASSO) and support vector machine-recursive feature elimination (SVM-RFE)) and the immune cell infiltration pattern was revealed by CIBERSORT. Gene-drug target networks and mRNA-miRNA-lncRNA regulatory networks were constructed using Cytoscape. Finally, we used RT-qPCR to validate the hub genes and applied logistic regression methods to build diagnostic models validated with ROC curves. We screened 188 differentially expressed genes whose functional analysis was enriched to multiple immune-related pathways. Six hub genes (ANTXR2, BAZ2B, C5AR1, PDK4, PPIH, and STK3) were identified using LASSO and SVM-RFE. ANTXR2, BAZ2B, C5AR1, PDK4, and STK3 were positively correlated with neutrophils and gamma delta T cells, and negatively correlated with T follicular helper cells and CD8, while PPIH showed the exact opposite trend. Immune infiltration indicated increased activity of monocytes, macrophages M0, neutrophils, and mast cells, and decreased infiltration of T follicular helper cells and CD8 in the IS group. The ceRNA network consisted of 306 miRNA-mRNA interacting pairs and 285 miRNA-lncRNA interacting pairs. RT-qPCR results indicated that the expression levels of BAZ2B, C5AR1, PDK4, and STK3 were significantly increased in patients with IS. Finally, we developed a diagnostic model based on these four genes. The AUC value of the model was verified to be 0.999 in the training set and 0.940 in the validation set. Our research explored the immune-related gene expression modules and provided a specific basis for further study of immunomodulatory therapy of IS.

Bioinformatics-based analysis of the relationship between plasminogen regulatory genes and photoaging.

Ultraviolet radiation causes skin photoaging by producing a variety of enzymes, which impact both skin health and hinder beauty. Currently, the early diagnosis and treatment of photoaging remain a challenge. Bioinformatics analysis has strong advantages in exploring core genes and the biological pathways of photoaging. To screen and validate key risk genes associated with plasminogen in photoaging and to identify potential target genes for photoaging. Two human transcriptome datasets were obtained by searching the Gene Expression Omnibus (GEO) database, and the mRNAs in the GSE131789 dataset were differentially analyzed, and then the weighted gene co-expression network analysis (WGCNA) was performed to find out the strongest correlations. Template genes, interaction analysis of differentially expressed genes (DEGs), modular genes with the most WGCNA correlations, and genecard database genes related to plasminogen were performed, and further Kyoto genes and Genome Encyclopedia (KEGG) pathway analysis. Two different algorithms, least absolute shrinkage and selection operator (LASSO) and support vector machines-recursive feature elimination (SVM-RFE), were used to find key genes. Then the data set (GSE206495) was validated and analyzed. Real-time PCR was performed to validate the expression of key genes through invitro cellular experiments. IFI6, IFI44L, HRSP12, and BMP4 were screened from datasets as key genes for photoaging and further analysis showed that these genes have significant diagnostic value for photoaging. IFI6, IFI44L, HRSP12, and BMP4 play a key role in the pathogenesis of photoaging, and serve as promising potential predictive biomarkers for photoaging.

Identification of shared molecular mechanisms and diagnostic biomarkers between heart failure and idiopathic pulmonary fibrosis

BackgroundHeart failure (HF) and idiopathic pulmonary fibrosis (IPF) are global public health concerns. The relationship between HF and IPF is widely acknowledged. However, the interaction mechanisms between these two diseases remain unclear, and early diagnosis is particularly difficult. Through the integration of bioinformatics and machine learning, our work aims to investigate common gene features, putative molecular causes, and prospective diagnostic indicators of IPF and HF. MethodsThe Gene Expression Omnibus (GEO) database provided the RNA-seq datasets for HF and IPF. Utilizing a weighted gene co-expression network analysis (WGCNA), possible genes linked to HF and IPF were found. The Kyoto Encyclopedia of Genes and Genomes (KEGG) and Gene Ontology (GO) were then employed to analyze the genes that were shared by HF and IPF. Using the cytoHubba and iRegulon algorithms, a competitive endogenous RNA (ceRNA) network was built based on seven basic diagnostic indicators. Additionally, hub genes were identified using machine learning approaches. External datasets were used to validate the findings. Lastly, the association between the number of immune cells in tissues and the discovered genes was estimated using the CIBERSORT method. ResultsIn total, 63 shared genes were identified between HF- and IPF-related modules using WGCNA. Extracellular matrix (ECM)/structure organization, ECM-receptor interactions, focal, and protein digestion and absorption, were shown to be the most enrichment categories in GO and KEGG enrichment analysis of common genes. Furthermore, a total of seven fundamental genes, including COL1A1, COL3A1, THBS2, CCND1, ASPN, FAP, and S100A12, were recognized as pivotal genes implicated in the shared pathophysiological pathways of HF and IPF, and TCF12 may be the most important regulatory transcription factor. Two characteristic molecules, CCND1 and NAP1L3, were selected as potential diagnostic markers for HF and IPF, respectively, using a support vector machine-recursive feature elimination (SVM-RFE) model. Furthermore, the development of diseases and diagnostic markers may be associated with immune cells at varying degrees. ConclusionsThis study demonstrated that ECM/structure organisation, ECM-receptor interaction, focal adhesion, and protein digestion and absorption, are common pathogeneses of IPF and HF. Additionally, CCND1 and NAP1L3 were identified as potential diagnostic biomarkers for both HF and IPF. The results of our study contribute to the comprehension of the co-pathogenesis of HF and IPF at the genetic level and offer potential biological indicators for the early detection of both conditions.

Bioinformatic validation and machine learning-based exploration of purine metabolism-related gene signatures in the context of immunotherapeutic strategies for nonspecific orbital inflammation.

Nonspecific orbital inflammation (NSOI) represents a perplexing and persistent proliferative inflammatory disorder of idiopathic nature, characterized by a heterogeneous lymphoid infiltration within the orbital region. This condition, marked by the aberrant metabolic activities of its cellular constituents, starkly contrasts with the metabolic equilibrium found in healthy cells. Among the myriad pathways integral to cellular metabolism, purine metabolism emerges as a critical player, providing the building blocks for nucleic acid synthesis, such as DNA and RNA. Despite its significance, the contribution of Purine Metabolism Genes (PMGs) to the pathophysiological landscape of NSOI remains a mystery, highlighting a critical gap in our understanding of the disease's molecular underpinnings. To bridge this knowledge gap, our study embarked on an exploratory journey to identify and validate PMGs implicated in NSOI, employing a comprehensive bioinformatics strategy. By intersecting differential gene expression analyses with a curated list of 92 known PMGs, we aimed to pinpoint those with potential roles in NSOI. Advanced methodologies, including Gene Set Enrichment Analysis (GSEA) and Gene Set Variation Analysis (GSVA), facilitated a deep dive into the biological functions and pathways associated with these PMGs. Further refinement through Lasso regression and Support Vector Machine-Recursive Feature Elimination (SVM-RFE) enabled the identification of key hub genes and the evaluation of their diagnostic prowess for NSOI. Additionally, the relationship between these hub PMGs and relevant clinical parameters was thoroughly investigated. To corroborate our findings, we analyzed expression data from datasets GSE58331 and GSE105149, focusing on the seven PMGs identified as potentially crucial to NSOI pathology. Our investigation unveiled seven PMGs (ENTPD1, POLR2K, NPR2, PDE6D, PDE6H, PDE4B, and ALLC) as intimately connected to NSOI. Functional analyses shed light on their involvement in processes such as peroxisome targeting sequence binding, seminiferous tubule development, and ciliary transition zone organization. Importantly, the diagnostic capabilities of these PMGs demonstrated promising efficacy in distinguishing NSOI from non-affected states. Through rigorous bioinformatics analyses, this study unveils seven PMGs as novel biomarker candidates for NSOI, elucidating their potential roles in the disease's pathogenesis. These discoveries not only enhance our understanding of NSOI at the molecular level but also pave the way for innovative approaches to monitor and study its progression, offering a beacon of hope for individuals afflicted by this enigmatic condition.

A machine learning-based diagnostic model for myocardial infarction patients: Analysis of neutrophil extracellular traps-related genes and eQTL Mendelian randomization.

To identify neutrophil extracellular trap (NET)-associated gene features in the blood of patients with myocardial infarction (MI) using bioinformatics and machine learning, with the aim of exploring potential diagnostic utility in atherosclerosis. The datasets GSE66360 and GSE48060 were downloaded from the Gene Expression Omnibus (GEO) public database. GSE66360 was used as the training set, and GSE48060 was used as an independent validation set. Differential genes related to NETs were screened using R software. Machine learning was performed based on the differential expression of NET-related genes across different samples. The advantages and disadvantages of 4 machine learning algorithms (Random Forest [RF], Extreme Gradient Boosting [XGBoost, XGB], Generalized Linear Models [GLM], and Support Vector Machine-Recursive Feature Elimination [SVM-RFE]) were compared, and the optimal method was used to screen feature genes and construct diagnostic models, which were then validated in the external validation dataset. Correlations between feature genes and immune cells were analyzed, and samples were reclustered based on the expression of feature genes. Differences in downstream molecular mechanisms and immune responses were explored for different clusters. Weighted Gene Co-expression Network Analysis was performed on different clusters, and disease-related NET genes were extracted, followed by Gene Ontology and Kyoto Encyclopedia of Genes and Genomes analysis. Finally, Mendelian randomization was employed to further investigate the causal relationship between the expression of model genes and the occurrence of MI. Forty-seven NET-related differential genes were obtained, and after comparing the 4 machine learning methods, support vector machine was used to screen ATG7, MMP9, interleukin 6 (IL6), DNASE1, and PDE4B as key genes for the construction of diagnostic models. The diagnostic value of the model was validated in an independent external validation dataset. These five genes showed strong correlations with neutrophils. Different sample clusters also demonstrated differential enrichment in pathways such as nitrogen metabolism, complement and coagulation cascades, cytokine-cytokine receptor interaction, renin-angiotensin system, and steroid biosynthesis. The Mendelian randomization results demonstrate a causal relationship between the expression of ATG7 and the incidence of myocardial infarction. The feature genes ATG7, MMP9, IL6, DNASE1, and PDE4B, identified using bioinformatics, may serve as potential diagnostic biomarkers and therapeutic targets for Myocardial infarction. Specifically, the expression of ATG7 could potentially be a significant factor in the occurrence of MI.

Toxicity prediction and classification of Gunqile-7 with small sample based on transfer learning method

Drug-induced diseases are the most important component of iatrogenic disease. It is the duty of doctors to provide a reasonable and safe dose of medication. Gunqile-7 is a Mongolian medicine with analgesic and anti-inflammatory effects. As a foreign substance in the body, even with reasonable medication, it may produce varying degrees of adverse reactions or toxic side effects. Since the cost of collecting Gunqile-7 for pharmacological animal trials is high and the data sample is small, this paper employs transfer learning and data augmentation methods to study the toxicity of Gunqile-7. More specifically, to reduce the necessary number of training samples, the data augmentation approach is employed to extend the data set. Then, the transfer learning method and one-dimensional convolutional neural network are utilized to train the network. In addition, we use the support vector machine-recursive feature elimination method for feature selection to reduce features that have adverse effects on model predictions. Furthermore, due to the important role of the pre-trained model of transfer learning, we select a quantitative toxicity prediction model as the pre-trained model, which is consistent with the purpose of this paper. Lastly, the experimental results demonstrate the efficiency of the proposed method. Our method can improve accuracy by up to 9 percentage points compared to the method without transfer learning on a small sample set.

Improve the accuracy of FT-NIR for determination of zearalenone content in wheat by using the characteristic wavelength optimization algorithm

The research contributes a unique method to achieve high-precision quantification of zearalenone (ZEN) in wheat, significantly improving accuracy in the analysis. Fourier transform near infrared spectroscopy (FT-NIR) was employed to capture the spectral information of wheat with different mildew degrees. Three feature selection models, competitive adaptive reweighted sampling (CARS), support vector machine-recursive feature elimination (SVM-RFE), and multiple feature-spaces ensemble-least absolute shrinkage and selection operator (MFE-LASSO) were introduced to processed pre-processed near-infrared spectral data and established partial least squares (PLS) regression according to the selected features. The outcomes indicated that the optimal generalization performance was achieved by the PLS model optimized through the MFE-LASSO model. The root mean square error of prediction (RMSEP) was 18.6442 μg·kg-1, coefficient of predictive determination (RP2) was 0.9545, and relative percent deviation (RPD) was 4.3198. According to the results, it is feasible to construct a stoichiometric model for the quantitative determination of ZEN in wheat by using FT-NIR combined with feature selection algorithm, and this method can also be extended to the detection of various molds in other cereals in the future.

Integrating machine learning and nontargeted plasma lipidomics to explore lipid characteristics of premetabolic syndrome and metabolic syndrome.

To identify plasma lipid characteristics associated with premetabolic syndrome (pre-MetS) and metabolic syndrome (MetS) and provide biomarkers through machine learning methods. Plasma lipidomics profiling was conducted using samples from healthy individuals, pre-MetS patients, and MetS patients. Orthogonal partial least squares-discriminant analysis (OPLS-DA) models were employed to identify dysregulated lipids in the comparative groups. Biomarkers were selected using support vector machine recursive feature elimination (SVM-RFE), random forest (rf), and least absolute shrinkage and selection operator (LASSO) regression, and the performance of two biomarker panels was compared across five machine learning models. In the OPLS-DA models, 50 and 89 lipid metabolites were associated with pre-MetS and MetS patients, respectively. Further machine learning identified two sets of plasma metabolites composed of PS(38:3), DG(16:0/18:1), and TG(16:0/14:1/22:6), TG(16:0/18:2/20:4), and TG(14:0/18:2/18:3), which were used as biomarkers for the pre-MetS and MetS discrimination models in this study. In the initial lipidomics analysis of pre-MetS and MetS, we identified relevant lipid features primarily linked to insulin resistance in key biochemical pathways. Biomarker panels composed of lipidomics components can reflect metabolic changes across different stages of MetS, offering valuable insights for the differential diagnosis of pre-MetS and MetS.

Identification of diagnostic markers for moyamoya disease by combining bulk RNA-sequencing analysis and machine learning

Moyamoya disease (MMD) remains a chronic progressive cerebrovascular disease with unknown etiology. A growing number of reports describe the development of MMD relevant to infection or autoimmune diseases. Identifying biomarkers of MMD is to understand the pathogenesis and development of novel targeted therapy and may be the key to improving the patient’s outcome. Here, we analyzed gene expression from two GEO databases. To identify the MMD biomarkers, the weighted gene co-expression network analysis (WGCNA) and the differential expression analyses were conducted to identify 266 key genes. The KEGG and GO analyses were then performed to construct the protein interaction (PPI) network. The three machine-learning algorithms of support vector machine-recursive feature elimination (SVM-RFE), random forest and least absolute shrinkage and selection operator (LASSO) were used to analyze the key genes and take intersection to construct MMD diagnosis based on the four core genes found (ACAN, FREM1, TOP2A and UCHL1), with highly accurate AUCs of 0.805, 0.903, 0.815, 0.826. Gene enrichment analysis illustrated that the MMD samples revealed quite a few differences in pathways like one carbon pool by folate, aminoacyl-tRNA biosynthesis, fat digestion and absorption and fructose and mannose metabolism. In addition, the immune infiltration profile demonstrated that ACAN expression was associated with mast cells resting, FREM1 expression was associated with T cells CD4 naive, TOP2A expression was associated with B cells memory, UCHL1 expression was associated with mast cells activated. Ultimately, the four key genes were verified by qPCR. Taken together, our study analyzed the diagnostic biomarkers and immune infiltration characteristics of MMD, which may shed light on the potential intervention targets of moyamoya disease patients

CD6 and CCR7 as Genetic Biomarkers in Evaluating Intracranial Aneurysm Rupture Risk.

This study used bioinformatics combined with statistical methods to identify plasma biomarkers that can predict intracranial aneurysm (IA) rupture and provide a strong theoretical basis for the search for new IA rupture prevention methods. We downloaded gene expression profiles in the GSE36791 and GSE122897 datasets from the Gene Expression Omnibus (GEO) database. Data were normalized using the "sva" R package and differentially expressed genes (DEGs) were identified using the "limma" R package. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analyses were used for DEG function analysis. Univariate logistic regression analysis, least absolute shrinkage and selection operator (LASSO) regression modeling, and the support vector machine recursive feature elimination (SVM-RFE) algorithm were used to identify key biomarker genes. Data from GSE122897 and GSE13353 were extracted to verify our findings. Eight co-DEG mRNAs were identified in the GSE36791 and GSE122897 datasets. Genes associated with inflammatory responses were clustered in the co-DEG mRNAs in IAs. CD6 and C-C chemokine receptor 7 (CCR7) were identified as key genes associated with IA. CD6 and CCR7 were upregulated in patients with IA and their expression levels were positively correlated. There were significant differences in the infiltration of immune cells between IAs and normal vascular wall tissues (p < 0.05). A predictive nomogram was designed using this two-gene signature. Binary transformation of CD6 and CCR7 was performed according to the cut-off value to construct the receiver-operating characteristic (ROC) curve and showed a strong predictive ability of the CD6-CCR7 gene signature (p < 0.01; area under the curve (AUC): 0.90; 95% confidence interval (CI): 0.88-0.92). Furthermore, validation of this two-gene signature using the GSE122897 and GSE13353 datasets proved it to be valuable for clinical application. The identified two-gene signature (CD6-CCR7) for evaluating the risk of IA rupture demonstrated good clinical application value.

Bioinformatics analysis identifies a key gene HLA_DPA1 in severe influenza-associated immune infiltration

BackgroundSevere influenza is a serious global health issue that leads to prolonged hospitalization and mortality on a significant scale. The pathogenesis of this infectious disease is poorly understood. Therefore, this study aimed to identify the key genes associated with severe influenza patients necessitating invasive mechanical ventilation.MethodsThe current study utilized two publicly accessible gene expression profiles (GSE111368 and GSE21802) from the Gene Expression Omnibus database. The research focused on identifying the genes exhibiting differential expression between severe and non-severe influenza patients. We employed three machine learning algorithms, namely the Least Absolute Shrinkage and Selection Operator regression model, Random Forest, and Support Vector Machine-Recursive Feature Elimination, to detect potential key genes. The key gene was further selected based on the diagnostic performance of the target genes substantiated in the dataset GSE101702. A single-sample gene set enrichment analysis algorithm was applied to evaluate the participation of immune cell infiltration and their associations with key genes.ResultsA total of 44 differentially expressed genes were recognized; among them, we focused on 10 common genes, namely PCOLCE2, HLA_DPA1, LOC653061, TDRD9, MPO, HLA_DQA1, MAOA, S100P, RAP1GAP, and CA1. To ensure the robustness of our findings, we employed overlapping LASSO regression, Random Forest, and SVM-RFE algorithms. By utilizing these algorithms, we were able to pinpoint the aforementioned 10 genes as potential biomarkers for distinguishing between both cases of influenza (severe and non-severe). However, the gene HLA_DPA1 has been recognized as a crucial factor in the pathological condition of severe influenza. Notably, the validation dataset revealed that this gene exhibited the highest area under the receiver operating characteristic curve, with a value of 0.891. The use of single-sample gene set enrichment analysis has provided valuable insights into the immune responses of patients afflicted with severe influenza that have further revealed a categorical correlation between the expression of HLA_DPA1 and lymphocytes.ConclusionThe findings indicated that the HLA_DPA1 gene may play a crucial role in the immune-pathological condition of severe influenza and could serve as a promising therapeutic target for patients infected with severe influenza.

Accumulation mechanism of metabolite markers identified by machine learning between Qingyuan and Xiushui counties in Polygonatum cyrtonema Hua

Polygonatum cyrtonema Hua is a traditional Chinese medicinal plant acclaimed for its therapeutic potential in diabetes and various chronic diseases. Its rhizomes are the main functional parts rich in secondary metabolites, such as flavonoids and saponins. But their quality varies by region, posing challenges for industrial and medicinal application of P. cyrtonema. In this study, 482 metabolites were identified in P. cyrtonema rhizome from Qingyuan and Xiushui counties. Cluster analysis showed that samples between these two regions had distinct secondary metabolite profiles. Machine learning methods, specifically support vector machine-recursive feature elimination and random forest, were utilized to further identify metabolite markers including flavonoids, phenolic acids, and lignans. Comparative transcriptomics and weighted gene co-expression analysis were performed to uncover potential candidate genes including CHI, UGT1, and PcOMT10/11/12/13 associated with these compounds. Functional assays using tobacco transient expression system revealed that PcOMT10/11/12/13 indeed impacted metabolic fluxes of the phenylpropanoid pathway and phenylpropanoid-related metabolites such as chrysoeriol-6,8-di-C-glucoside, syringaresinol-4'-O-glucopyranosid, and 1-O-Sinapoyl-D-glucose. These findings identified metabolite markers between these two regions and provided valuable genetic insights for engineering the biosynthesis of these compounds.