Support Vector Machine Recursive Feature Research Articles

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.

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

BackgroundThe 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.MethodsAn 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.ResultsA 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.ConclusionThe 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.

Exploration of the shared diagnostic genes and mechanisms between periodontitis and primary Sjögren’s syndrome by integrated comprehensive bioinformatics analysis and machine learning

BackgroundAccumulating evidence has showed a bidirectional link between periodontitis (PD) and primary Sjögren’s syndrome (pSS), but the mechanisms of their occurrence remain unclear. Hence, this study aimed to investigate the shared diagnostic genes and potential mechanisms between PD and pSS using bioinformatics methods. MethodsGene expression data for PD and pSS were acquired from the Gene Expression Omnibus (GEO) database. Differential expression genes (DEGs) analysis and weighted gene co-expression network analysis (WGCNA) were utilized to search common genes. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis were conducted to explore biological functions. Three machine learning algorithms (least absolute shrinkage and selection operator (LASSO), support vector machine recursive feature elimination (SVM-RFE), and random forest (RF)) were used to further identify shared diagnostic genes, and these genes were assessed via receiver operating characteristic (ROC) curves in discovery and validation datasets. CIBERSORT was employed for immune cell infiltration analysis. Transcription factors (TFs)-genes and miRNAs-genes regulatory networks were conducted by NetworkAnalyst. Finally, relevant drug targets were predicted by DSigDB. ResultsBased on DEGs, 173 overlapping genes were obtained and primarily enriched in immune- and inflammation-related pathways. WGCNA revealed 34 common disease-related genes, which were enriched in similar biological pathways. Intersecting the DEGs with WGCNA results yielded 22 candidate genes. Moreover, three machine learning algorithms identified three shared genes (CSF2RB, CXCR4, and LYN) between PD and pSS, and these genes demonstrated good diagnostic performance (AUC>0.85) in both discovery and validation datasets. The immune cell infiltration analysis showed significant dysregulation in several immune cell populations. Regulatory network analysis highlighted that WRNIP1 and has-mir-155-5p might be pivotal co-regulators of the three shared gene expressions. Finally, the top 10 potential gene-targeted drugs were screened. ConclusionCSF2RB, CXCR4, and LYN may serve as potential biomarkers for the concurrent diagnosis of PD and pSS. Additionally, we identified common molecular mechanisms, TFs, miRNAs, and candidate drugs between PD and pSS, which may provide novel insights and targets for future research on the pathogenesis, diagnosis, and therapy of both diseases.

Identification and Validation of Aging Related Genes Signature in Chronic Obstructive Pulmonary Disease

Purpose Chronic Obstructive Pulmonary Disease (COPD) is regarded as an accelerated aging disease. Aging-related genes in COPD are still poorly understood. Method Data set GSE76925 was obtained from the Gene Expression Omnibus (GEO) database. The “limma” package identified the differentially expressed genes. The weighted gene co-expression network analysis (WGCNA) constructes co-expression modules and detect COPD-related modules. The least absolute shrinkage and selection operator (LASSO) and the support vector machine recursive feature elimination (SVM-RFE) algorithms were chosen to identify the hub genes and the diagnostic ability. Three external datasets were used to identify differences in the expression of hub genes. Real-time reverse transcription polymerase chain reaction (RT-qPCR) was used to verify the expression of hub genes. Result We identified 15 differentially expressed genes associated with aging (ARDEGs). The SVM-RFE and LASSO algorithms pinpointed four potential diagnostic biomarkers. Analysis of external datasets confirmed significant differences in PIK3R1 expression. RT-qPCR results indicated decreased expression of hub genes. The ROC curve demonstrated that PIK3R1 exhibited strong diagnostic capability for COPD. Conclusion We identified 15 differentially expressed genes associated with aging. Among them, PIK3R1 showed differences in external data sets and RT-qPCR results. Therefore, PIK3R1 may play an essential role in regulating aging involved in COPD.

Identification of diagnostic biomarkers of rheumatoid arthritis based on machine learning-assisted comprehensive bioinformatics and its correlation with immune cells

BackgroundRheumatoid arthritis (RA) is a chronic systemic autoimmune disease characterized by inflammatory cell infiltration, which can lead to chronic disability, joint destruction and loss of function. At present, the pathogenesis of RA is still unclear. The purpose of this study is to explore the potential biomarkers and immune molecular mechanisms of rheumatoid arthritis through machine learning-assisted bioinformatics analysis, in order to provide reference for the early diagnosis and treatment of RA disease. MethodsRA gene chips were screened from the public gene GEO database, and batch correction of different groups of RA gene chips was performed using Strawberry Perl. DEGs were obtained using the limma package of R software, and functional enrichment analysis such as gene ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG), disease ontology (DO), and gene set (GSEA) were performed. Three machine learning methods, least absolute shrinkage and selection operator regression (LASSO), support vector machine recursive feature elimination (SVM-RFE) and random forest tree (Random Forest), were used to identify potential biomarkers of RA. The validation group data set was used to verify and further confirm its expression and diagnostic value. In addition, CIBERSORT algorithm was used to evaluate the infiltration of immune cells in RA and control samples, and the correlation between confirmed RA diagnostic biomarkers and immune cells was analyzed. ResultsThrough feature screening, 79 key DEGs were obtained, mainly involving virus response, Parkinson's pathway, dermatitis and cell junction components. A total of 29 hub genes were screened by LASSO regression, 34 hub genes were screened by SVM-RFE, and 39 hub genes were screened by Random Forest. Combined with the three algorithms, a total of 12 hub genes were obtained. Through the expression and diagnostic value verification in the validation group data set, 7 genes that can be used as diagnostic biomarkers for RA were preliminarily confirmed. At the same time, the correlation analysis of immune cells found that γδT cells, CD4+ memory activated T cells, activated dendritic cells and other immune cells were positively correlated with multiple RA diagnostic biomarkers, CD4+ naive T cells, regulatory T cells and other immune cells were negatively correlated with multiple RA diagnostic biomarkers. ConclusionsThe results of novel characteristic gene analysis of RA showed that KYNU, EVI2A, CD52, C1QB, BATF, AIM2 and NDC80 had good diagnostic and clinical value for the diagnosis of RA, and were closely related to immune cells. Therefore, these seven DEGs may become new diagnostic markers and immunotherapy markers for RA.

Discrete Space Deep Reinforcement Learning Algorithm Based on Support Vector Machine Recursive Feature Elimination

Algorithms for training agents with experience replay have advanced in several domains, primarily because prioritized experience replay (PER) developed from the double deep Q-network (DDQN) in deep reinforcement learning (DRL) has become a standard. PER-based algorithms have achieved significant success in the image and video domains. However, the exceptional results observed in images and videos are not as effective in many domains with simple action spaces and relatively small states, particularly in discrete action spaces with sparse rewards. Moreover, most advanced techniques may improve sampling efficiency using deep learning algorithms rather than reinforcement learning. However, there is growing evidence that deep learning algorithms cannot generalize during training. Therefore, this study proposes an algorithm suitable for discrete action space environments that uses the sample efficiency of PER based on DDQN but incorporates support vector machine recursive feature elimination (SVM-RFE) without enhancing the sampling efficiency through deep learning algorithms. The proposed algorithm exhibited considerable performance improvements in classical OpenAI Gym environments that did not use images or videos as inputs. In particular, simple discrete space environments with reflection symmetry, such as Cart–Pole, exhibited a faster and more stable learning process. These results suggest that the application of SVM-RFE, which leverages the orthogonality of support vector machines (SVMs) across learning patterns, can be appropriate when the data in the reinforcement learning environment demonstrate symmetry.

Identification and experimental validation of KMO as a critical immune-associated mitochondrial gene in unstable atherosclerotic plaque

BackgroundThe heightened risk of cardiovascular and cerebrovascular events is associated with the increased instability of atherosclerotic plaques. However, the lack of effective diagnostic biomarkers has impeded the assessment of plaque instability currently. This study was aimed to investigate and identify hub genes associated with unstable plaques through the integration of various bioinformatics tools, providing novel insights into the detection and treatment of this condition.MethodsWeighted Gene Co-expression Network Analysis (WGCNA) combined with two machine learning methods were used to identify hub genes strongly associated with plaque instability. The cell-type identification by estimating relative subsets of RNA transcripts (CIBERSORT) method was utilized to assess immune cell infiltration patterns in atherosclerosis patients. Additionally, Gene Set Variation Analysis (GSVA) was conducted to investigate the potential biological functions, pathways, and mechanisms of hub genes associated with unstable plaques. To further validate the diagnostic efficiency and expression of the hub genes, immunohistochemistry (IHC), quantitative real-time polymerase chain reaction (RT-qPCR), and enzyme-linked immunosorbent assay (ELISA) were performed on collected human carotid plaque and blood samples. Immunofluorescence co-staining was also utilized to confirm the association between hub genes and immune cells, as well as their colocalization with mitochondria.ResultsThe CIBERSORT analysis demonstrated a significant decrease in the infiltration of CD8 T cells and an obvious increase in the infiltration of M0 macrophages in patients with atherosclerosis. Subsequently, two highly relevant modules (blue and green) strongly associated with atherosclerotic plaque instability were identified. Through intersection with mitochondria-related genes, 50 crucial genes were identified. Further analysis employing least absolute shrinkage and selection operator (LASSO) logistic regression and support vector machine recursive feature elimination (SVM-RFE) algorithms revealed six hub genes significantly associated with plaque instability. Among them, NT5DC3, ACADL, SLC25A4, ALDH1B1, and MAOB exhibited positive correlations with CD8 T cells and negative correlations with M0 macrophages, while kynurenine 3-monooxygenas (KMO) demonstrated a positive correlation with M0 macrophages and a negative correlation with CD8 T cells. IHC and RT-qPCR analyses of human carotid plaque samples, as well as ELISA analyses of blood samples, revealed significant upregulation of KMO and MAOB expression, along with decreased ALDH1B1 expression, in both stable and unstable samples compared to the control samples. However, among the three key genes mentioned above, only KMO showed a significant increase in expression in unstable plaque samples compared to stable plaque samples. Furthermore, the expression patterns of KMO in human carotid unstable plaque tissues and cultured mouse macrophage cell lines were assessed using immunofluorescence co-staining techniques. Finally, lentivirus-mediated KMO silencing was successfully transduced into the aortas of high-fat-fed ApoE-/- mice, with results indicating that KMO silencing attenuated plaque formation and promoted plaque stability in ApoE-/- mice.ConclusionsThe results suggest that KMO, a mitochondria-targeted gene associated with macrophage cells, holds promise as a valuable diagnostic biomarker for assessing the instability of atherosclerotic plaques.

Adipocytes impact on gastric cancer progression: Prognostic insights and molecular features.

Adipocytes, especially adipocytes within tumor tissue known as cancer-associated adipocytes, have been increasingly recognized for their pivotal role in the tumor microenvironment of gastric cancer (GC). Their influence on tumor progression and patient prognosis has sparked significant interest in recent research. The main objectives of this study were to investigate adipocyte infiltration, assess its correlation with clinical pathological features, develop a prognostic prediction model based on independent prognostic factors, evaluate the impact of adipocytes on immune cell infiltration and tumor invasiveness in GC, and identify and validate genes associated with high adipocyte expression, exploring their potential diagnostic and prognostic value. To explore the relationship between increased adipocytes within tumor tissue and prognosis in GC patients as well as the associated mechanisms and potential biomarkers, using public databases and clinical data. Using mRNA microarray datasets from the Gene Expression Omnibus database and clinical samples from Jiangsu Provincial Hospital, survival and regression analyses were conducted to determine the relevant prognostic factors in GC. Feature gene selection was performed using least absolute shrinkage and selection operator and support vector machine recursive feature elimination algorithms, followed by differential gene expression analysis, gene ontology, pathway analysis, and Gene Set Enrichment Analysis. Immune cell infiltration was analyzed using the CIBERSORT algorithm. Tumor adipocyte infiltration correlated with poor prognosis in GC, leading to the development of a highly accurate and discriminative prognostic prediction model. Key genes, ADH1B, SFRP1, PLAC9, and FABP4, were identified as associated with high adipocyte expression in GC. The diagnostic and prognostic potential of these identified genes was validated using independent datasets. Downregulation of immune cells was observed in GC with high adipocyte expression. GC with high intratumoral adipocyte expression demonstrated aggressive tumor biology and a poorer prognosis. The genes ADH1B, SFRP1, PLAC9, and FABP4 have been identified as holding diagnostic and prognostic significance in GC. These findings strongly support the use of adipocyte expression as a valuable indicator of tumor invasiveness and anticipated patient outcomes in GC.

An novel effective and safe model for the diagnosis of nonalcoholic fatty liver disease in China: gene excavations, clinical validations, and mechanism elucidation

BackgroundNon-alcoholic fatty liver disease (NAFLD) is one of the most common chronic liver diseases. NAFLD leads to liver fibrosis and hepatocellular carcinoma, and it also has systemic effects associated with metabolic diseases, cardiovascular diseases, chronic kidney disease, and malignant tumors. Therefore, it is important to diagnose NAFLD early to prevent these adverse effects.MethodsThe GSE89632 dataset was downloaded from the Gene Expression Omnibus database, and then the optimal genes were screened from the data cohort using lasso and Support Vector Machine Recursive Feature Elimination (SVM-RFE). The ROC values of the optimal genes for the diagnosis of NAFLD were calculated. The relationship between optimal genes and immune cells was determined using the DECONVOLUTION algorithm CIBERSORT. Finally, the specificity and sensitivity of the diagnostic genes were verified by detecting the expression of the diagnostic genes in blood samples from 320 NAFLD patients and liver samples from 12 mice.ResultsThrough machine learning we identified FOSB, GPAT3, RGCC and RNF43 were the key diagnostic genes for NAFLD, and they were further demonstrated by a receiver operating characteristic curve analysis. We found that the combined diagnosis of the four genes identified NAFLD samples well from normal samples (AUC = 0.997). FOSB, GPAT3, RGCC and RNF43 were strongly associated with immune cell infiltration. We also experimentally examined the expression of these genes in NAFLD patients and NAFLD mice, and the results showed that these genes are highly specific and sensitive.ConclusionsData from both clinical and animal studies demonstrate the high sensitivity, specificity and safety of FOSB, GPAT3, RGCC and RNF43 for the diagnosis of NAFLD. The relationship between diagnostic key genes and immune cell infiltration may help to understand the development of NAFLD. The study was reviewed and approved by Ethics Committee of Tianjin Second People’s Hospital in 2021 (ChiCTR1900024415).

The therapeutic and biomarker significance of ferroptosis in chronic myeloid leukemia.

The relationship between ferroptosis and the progression and treatment of hematological tumors has been extensively studied, although its precise association with chronic myeloid leukemia (CML) remains uncertain. Multi-transcriptome sequencing data were utilized to analyze the ferroptosis level of CML samples and its correlation with the tumor microenvironment, disease progression, and treatment response. Machine learning algorithms were employed to identify diagnostic ferroptosis-related genes (FRGs). The consensus clustering algorithm was applied to identify ferroptosis-related molecular subtypes. Clinical samples were collected for sequencing to validate the results obtained from bioinformatics analysis. Cell experiments were conducted to investigate the therapeutic efficacy of induced ferroptosis in drug-resistant CML. Ferroptosis scores were significantly lower in samples from patients with CML compared to normal samples, and these scores further decreased with disease progression and non-response to treatment. Most FRGs were downregulated in CML samples. A high ferroptosis score was also associated with greater immunosuppression and increased activity of metabolic pathways. Through support vector machine recursive feature elimination (SVM-RFE), least absolute shrinkage selection operator (LASSO), and random forest (RF) algorithms, we identified five FRGs (ACSL6, SLC11A2, HMOX1, SLC38A1, AKR1C3) that have high diagnostic value. The clinical diagnostic value of these five FRGs and their effectiveness in differentiating CML from other hematological malignancies were validated using additional validation cohorts and our real-world cohort. There are significant differences in immune landscape, chemosensitivity, and immunotherapy responsiveness between the two ferroptosis-related molecular subtypes. By conducting cellular experiments, we confirmed that CML-resistant cells are more sensitive to induction of ferroptosis and can enhance the sensitivity of imatinib treatment. Our study unveils the molecular signature of ferroptosis in samples from patients with CML. FRG identified by a variety of machine learning algorithms has reliable clinical diagnostic value. Furthermore, the characterization of different ferroptosis-related molecular subtypes provides valuable insights into individual patient characteristics and can guide clinical treatment strategies. Targeting and inducing ferroptosis holds great promise as a therapeutic approach for drug-resistant CML.

Clinical serum lipidomic profiling revealed potential lipid biomarkers for early diabetic retinopathy

Diabetic retinopathy (DR) is a serious complication of diabetes featuring abnormal lipid metabolism. However, the specific lipid molecules associated with onset and progression remain unclear. We used a broad-targeted lipidomics approach to assess the lipid changes that occur before the proliferative retinopathy stage and to identify novel lipid biomarkers to distinguish between patients without DR (NDR) and with non-proliferative DR (NPDR). Targeted lipomics analysis was carried out on serum samples from patients with type I diabetes, including 20 NDRs and 20 NPDRs. The results showed that compared with the NDR group, 102 lipids in the NPDR group showed specific expressions. Four lipid metabolites including TAG58:2-FA18:1 were obtained using the Least Absolute Shrink And Selection Operator (LASSO) and Support Vector Machine Recursive Feature Elimination (SVM-RFE) methods. The four-lipid combination diagnostic models showed good predictive ability in both the discovery and validation sets, and were able to distinguish between NDR patients and NPDR patients. The identified lipid markers significantly improved diagnostic accuracy within the NPDR group. Our findings help to better understand the complexity and individual differences of DR lipid metabolism.

Coupled Multimodal Emotional Feature Analysis Based on Broad-Deep Fusion Networks in Human-Robot Interaction.

A coupled multimodal emotional feature analysis (CMEFA) method based on broad-deep fusion networks, which divide multimodal emotion recognition into two layers, is proposed. First, facial emotional features and gesture emotional features are extracted using the broad and deep learning fusion network (BDFN). Considering that the bi-modal emotion is not completely independent of each other, canonical correlation analysis (CCA) is used to analyze and extract the correlation between the emotion features, and a coupling network is established for emotion recognition of the extracted bi-modal features. Both simulation and application experiments are completed. According to the simulation experiments completed on the bimodal face and body gesture database (FABO), the recognition rate of the proposed method has increased by 1.15% compared to that of the support vector machine recursive feature elimination (SVMRFE) (without considering the unbalanced contribution of features). Moreover, by using the proposed method, the multimodal recognition rate is 21.22%, 2.65%, 1.61%, 1.54%, and 0.20% higher than those of the fuzzy deep neural network with sparse autoencoder (FDNNSA), ResNet-101 + GFK, C3D + MCB + DBN, the hierarchical classification fusion strategy (HCFS), and cross-channel convolutional neural network (CCCNN), respectively. In addition, preliminary application experiments are carried out on our developed emotional social robot system, where emotional robot recognizes the emotions of eight volunteers based on their facial expressions and body gestures.

Identification of immune-associated biomarkers of diabetes nephropathy tubulointerstitial injury based on machine learning: a bioinformatics multi-chip integrated analysis

BackgroundDiabetic nephropathy (DN) is a major microvascular complication of diabetes and has become the leading cause of end-stage renal disease worldwide. A considerable number of DN patients have experienced irreversible end-stage renal disease progression due to the inability to diagnose the disease early. Therefore, reliable biomarkers that are helpful for early diagnosis and treatment are identified. The migration of immune cells to the kidney is considered to be a key step in the progression of DN-related vascular injury. Therefore, finding markers in this process may be more helpful for the early diagnosis and progression prediction of DN.MethodsThe gene chip data were retrieved from the GEO database using the search term ' diabetic nephropathy ‘. The ' limma ' software package was used to identify differentially expressed genes (DEGs) between DN and control samples. Gene set enrichment analysis (GSEA) was performed on genes obtained from the molecular characteristic database (MSigDB. The R package ‘WGCNA’ was used to identify gene modules associated with tubulointerstitial injury in DN, and it was crossed with immune-related DEGs to identify target genes. Gene ontology (GO) enrichment analysis and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis were performed on differentially expressed genes using the ‘ClusterProfiler’ software package in R. Three methods, least absolute shrinkage and selection operator (LASSO), support vector machine recursive feature elimination (SVM-RFE) and random forest (RF), were used to select immune-related biomarkers for diagnosis. We retrieved the tubulointerstitial dataset from the Nephroseq database to construct an external validation dataset. Unsupervised clustering analysis of the expression levels of immune-related biomarkers was performed using the ‘ConsensusClusterPlus ‘R software package. The urine of patients who visited Dongzhimen Hospital of Beijing University of Chinese Medicine from September 2021 to March 2023 was collected, and Elisa was used to detect the mRNA expression level of immune-related biomarkers in urine. Pearson correlation analysis was used to detect the effect of immune-related biomarker expression on renal function in DN patients.ResultsFour microarray datasets from the GEO database are included in the analysis : GSE30122, GSE47185, GSE99340 and GSE104954. These datasets included 63 DN patients and 55 healthy controls. A total of 9415 genes were detected in the data set. We found 153 differentially expressed immune-related genes, of which 112 genes were up-regulated, 41 genes were down-regulated, and 119 overlapping genes were identified. GO analysis showed that they were involved in various biological processes including leukocyte-mediated immunity. KEGG analysis showed that these target genes were mainly involved in the formation of phagosomes in Staphylococcus aureus infection. Among these 119 overlapping genes, machine learning results identified AGR2, CCR2, CEBPD, CISH, CX3CR1, DEFB1 and FSTL1 as potential tubulointerstitial immune-related biomarkers. External validation suggested that the above markers showed diagnostic efficacy in distinguishing DN patients from healthy controls. Clinical studies have shown that the expression of AGR2, CX3CR1 and FSTL1 in urine samples of DN patients is negatively correlated with GFR, the expression of CX3CR1 and FSTL1 in urine samples of DN is positively correlated with serum creatinine, while the expression of DEFB1 in urine samples of DN is negatively correlated with serum creatinine. In addition, the expression of CX3CR1 in DN urine samples was positively correlated with proteinuria, while the expression of DEFB1 in DN urine samples was negatively correlated with proteinuria. Finally, according to the level of proteinuria, DN patients were divided into nephrotic proteinuria group (n = 24) and subrenal proteinuria group. There were significant differences in urinary AGR2, CCR2 and DEFB1 between the two groups by unpaired t test (P < 0.05).ConclusionsOur study provides new insights into the role of immune-related biomarkers in DN tubulointerstitial injury and provides potential targets for early diagnosis and treatment of DN patients. Seven different genes ( AGR2, CCR2, CEBPD, CISH, CX3CR1, DEFB1, FSTL1 ), as promising sensitive biomarkers, may affect the progression of DN by regulating immune inflammatory response. However, further comprehensive studies are needed to fully understand their exact molecular mechanisms and functional pathways in DN.

Correlation of disulfidptosis and periodontitis: New insights and clinical significance

ObjectivesThis study aims to investigate and predict the therapeutic agents associated with disulfidptosis in periodontitis. DesignThe dataset GSE10334 was downloaded from the Gene Expression Omnibus (GEO) database and used to train a least absolute shrinkage and selection operator (LASSO) regression and support vector machine recursive feature elimination (SVM–RFE) algorithm to identify genes associated with disulfidptosis in periodontitis. GSE16134 validation sets, polymerase chain reaction (PCR), and gingival immunofluorescence were used to verify the results.Single-gene Gene Set Enrichment Analysis (GSEA) was performed to explore the potential mechanisms and functions of the characterized genes. Immune infiltration and correlation analyses were performed, and competing endogenous RNA (ceRNA) networks were constructed. Effective therapeutic drugs were then predicted using the DGIdb database, and molecular docking was used to validate binding affinity. ResultsSix genes (SLC7A11, SLC3A2, RPN1, NCKAP1, LRPPRC, and NDUFS1) associated with disulfidptosis in periodontitis were obtained. Validation results from external datasets and experiments were consistent with the screening results. Single-gene GSEA analysis was mainly enriched for antigen presentation and immune-related pathways and functions.Immune infiltration and correlation analyses revealed significant regulatory relationships between these genes and plasma cells, resting dendritic cell, and activated NK cells. The ceRNA network was visualized. And ME-344, NV-128, and RILUZOLE, which have good affinity to target genes, were identified as promising agents for the treatment of periodontitis. ConclusionsSLC7A11, SLC3A2, RPN1, NCKAP1, LRPPRC, and NDUFS1 are targets associated with disulfidptosis in periodontitis, and ME-344, NV-128, and RILUZOLE are promising agents for the treatment of periodontitis.

Prediction of additional hospital days in patients undergoing cervical spine surgery with machine learning methods

Background Machine learning (ML), a subset of artificial intelligence (AI), uses algorithms to analyze data and predict outcomes without extensive human intervention. In healthcare, ML is gaining attention for enhancing patient outcomes. This study focuses on predicting additional hospital days (AHD) for patients with cervical spondylosis (CS), a condition affecting the cervical spine. The research aims to develop an ML-based nomogram model analyzing clinical and demographic factors to estimate hospital length of stay (LOS). Accurate AHD predictions enable efficient resource allocation, improved patient care, and potential cost reduction in healthcare. Methods The study selected CS patients undergoing cervical spine surgery and investigated their medical data. A total of 945 patients were recruited, with 570 males and 375 females. The mean number of LOS calculated for the total sample was 8.64 ± 3.7 days. A LOS equal to or <8.64 days was categorized as the AHD-negative group (n = 539), and a LOS > 8.64 days comprised the AHD-positive group (n = 406). The collected data was randomly divided into training and validation cohorts using a 7:3 ratio. The parameters included their general conditions, chronic diseases, preoperative clinical scores, and preoperative radiographic data including ossification of the anterior longitudinal ligament (OALL), ossification of the posterior longitudinal ligament (OPLL), cervical instability and magnetic resonance imaging T2-weighted imaging high signal (MRI T2WIHS), operative indicators and complications. ML-based models like Lasso regression, random forest (RF), and support vector machine (SVM) recursive feature elimination (SVM-RFE) were developed for predicting AHD-related risk factors. The intersections of the variables screened by the aforementioned algorithms were utilized to construct a nomogram model for predicting AHD in patients. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve and C-index were used to evaluate the performance of the nomogram. Calibration curve and decision curve analysis (DCA) were performed to test the calibration performance and clinical utility. Results For these participants, 25 statistically significant parameters were identified as risk factors for AHD. Among these, nine factors were obtained as the intersection factors of these three ML algorithms and were used to develop a nomogram model. These factors were gender, age, body mass index (BMI), American Spinal Injury Association (ASIA) scores, magnetic resonance imaging T2-weighted imaging high signal (MRI T2WIHS), operated segment, intraoperative bleeding volume, the volume of drainage, and diabetes. After model validation, the AUC was 0.753 in the training cohort and 0.777 in the validation cohort. The calibration curve exhibited a satisfactory agreement between the nomogram predictions and actual probabilities. The C-index was 0.788 (95% confidence interval: 0.73214–0.84386). On the decision curve analysis (DCA), the threshold probability of the nomogram ranged from 1 to 99% (training cohort) and 1 to 75% (validation cohort). Conclusion We successfully developed an ML model for predicting AHD in patients undergoing cervical spine surgery, showcasing its potential to support clinicians in AHD identification and enhance perioperative treatment strategies.

Identification of subclusters and prognostic genes based on GLS-associated molecular signature in ulcerative colitis

Ulcerative colitis (UC) is a chronic and recurrent inflammatory disease that affects the colon and rectum. The response to treatment varies among individuals with UC. Therefore, the aim of this study was to identify and explore potential biomarkers for different subtypes of UC and examine their association with immune cell infiltration. We obtained UC RNA sequencing data from the GEO database, which included the training set GSE92415 and the validation set GSE87473 and GSE72514. UC patients were classified based on GLS and its associated genes using consensus clustering analysis. We identified differentially expressed genes (DEGs) in different UC subtypes through a differential expression analysis of the training cohort. Machine learning algorithms, including Weighted Gene Co-Expression Network Analysis (WGCNA), Least Absolute Shrinkage and Selection Operator (LASSO), and Support Vector Machine Recursive Feature Elimination (SVM-RFE), were utilized to identify marker genes for UC. The CIBERSORT algorithm was used to determine the abundance of various immune cells in UC and their correlation with UC signature genes. Finally, we validated the expression of GLS through in vivo and ex vivo experiments. The expression of GLS was found to be elevated in patients with UC compared to normal patients. GLS and its related genes were able to classify UC patients into two subtypes, C1 and C2. The C1 subtype, as compared to the C2 subtype, showed a higher Mayo score and poorer treatment response. A total of 18 DEGs were identified in both subtypes, including 7 up-regulated and 11 down-regulated genes. Four UC signature genes (CWH43, HEPACAM2, IL24, and PCK1) were identified and their diagnostic value was validated in a separate cohort (AUC > 0.85). Furthermore, we found that UC signature biomarkers were linked to the immune cell infiltration. CWH43, HEPACAM2, IL24, and PCK1 may serve as potential biomarkers for diagnosing different subtypes of UC, which could contribute to the development of targeted molecular therapy and immunotherapy for UC.

Exploratory Study of Differentially Expressed Genes of Peripheral Blood Monocytes in Patients with Carotid Atherosclerosis.

The abundance of circulating monocytes is closely associated with the development of atherosclerosis in humans. This study aimed to further research into diagnostic biomarkers and targeted treatment of carotid atherosclerosis (CAS). We performed transcriptomics analysis through weighted gene co-expression network analysis (WGCNA) of monocytes from patients in public databases with and without CAS. Differentially expressed genes (DEGs) were screened by R package limma. Diagnostic molecules were derived by the least absolute shrinkage and selection operator (LASSO) and support vector machine recursive feature elimination (SVM-RFE) algorithms. NetworkAnalyst, miRWalk, and Star- Base databases assisted in the construction of diagnostic molecule regulatory networks. The Drug- Bank database predicted drugs targeting the diagnostic molecules. RT-PCR tested expression profiles. From 14,369 hub genes and 61 DEGs, six differentially expressed monocyte-related hub genes were significantly associated with immune cells, immune responses, monocytes, and lipid metabolism. LASSO and SVM-RFE yielded five genes for CAS prediction. RT-PCR of these genes showed HMGB1 was upregulated, and CCL3, CCL3L1, CCL4, and DUSP1 were downregulated in CAS versus controls. Then, we constructed and visualized the regulatory networks of 9 transcription factors (TFs), which significantly related to 5 diagnostic molecules. About 11 miRNAs, 19 lncRNAs, and 39 edges centered on four diagnostic molecules (CCL3, CCL4, DUSP1, and HMGB1) were constructed and displayed. Eleven potential drugs were identified, including ibrutinib, CTI-01, roflumilast etc. Conclusion: A set of five biomarkers were identified for the diagnosis of CAS and for the study of potential therapeutic targets.

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.

Identification of ion channel-related genes as diagnostic markers and potential therapeutic targets for osteoarthritis through bioinformatics and machine learning-based approaches

Background Osteoarthritis (OA) is a debilitating joint disorder characterized by the progressive degeneration of articular cartilage. Although the role of ion channels in OA pathogenesis is increasingly recognized, diagnostic markers and targeted therapies remain limited. Methods In this study, we analyzed the GSE48556 dataset to identify differentially expressed ion channel-related genes (DEGs) in OA and normal controls. We employed machine learning algorithms, least absolute shrinkage and selection operator(LASSO), and support vector machine recursive feature elimination(SVM-RFE) to select potential diagnostic markers. Then the gene set enrichment analysis (GSEA) and gene set variation analysis (GSVA) were performed to explore the potential diagnostic markers’ involvement in biological pathways. Finally, weighted gene co-expression network analysis (WGCNA) was used to identify key genes associated with OA. Results We identified a total of 47 DEGs, with the majority involved in transient receptor potential (TRP) pathways. Seven genes (CHRNA4, GABRE, HTR3B, KCNG2, KCNJ2, LRRC8C, and TRPM5) were identified as the best characteristic genes for distinguishing OA from healthy samples. We performed clustering analysis and identified two distinct subtypes of OA, C1, and C2, with differential gene expression and immune cell infiltration profiles. Then we identified three key genes (PPP1R3D, ZNF101, and LOC651309) associated with OA. We constructed a prediction model using these genes and validated it using the GSE46750 dataset, demonstrating reasonable accuracy and specificity. Conclusions Our findings provide novel insights into the role of ion channel-related genes in OA pathogenesis and offer potential diagnostic markers and therapeutic targets for the treatment of OA.