Identification of lysosome-related hub genes as potential biomarkers and immune infiltrations of moyamoya disease by multiple bioinformatics methods and machine-learning strategies.

Background: Moyamoya disease (MMD), characterized by chronic cerebrovascular pathology, poses a rare yet significant clinical challenge, associated with elevated rates of mortality and disability. Despite intensive research endeavors, the exact biomarkers driving its pathogenesis remain enigmatic. Methods: The expression patterns of GSE189993 and GSE141022 were retrieved from the Gene Expression Omnibus (GEO) repository to procure differentially expressed genes (DEGs) between samples afflicted with MMD and those under control conditions. The Least Absolute Shrinkage and Selection Operator (LASSO), Support Vector Machine with Recursive Feature Elimination (SVM-RFE), and Random Forest (RF) algorithms were employed for identifying candidate diagnostic genes associated with MMD. Subsequently, these candidate genes underwent validation in an independent cohort (GSE157628). The CMAP database was ultimately employed to forecast drugs pertinent to MMD for clinical translation. Results: A collective of 240 DEGs were discerned. Functional enrichment scrutiny unveiled the enrichment of the cholesterol metabolism pathway, salmonella infection pathway, and allograft rejection pathway within the MMD cohort. EPDR1, DENND3, and NCSTN emerged as discerned diagnostic biomarkers for MMD. The CMAP database was ultimately employed to scrutinize the ten most auspicious pharmaceutical compounds for managing MMD. Finally, after validation through in vitro experiments, EPDR1, DENND3, and NCSTN were identified as the key genes. Conclusion: EPDR1, DENND3, and NCSTN have emerged as potential novel biomarkers for MMD. The involvement of T lymphocytes, neutrophilic granulocytes, dendritic cells, natural killer cells, and plasma cells could be pivotal in the pathogenesis and advancement of MMD.

Identification of CFH and FHL2 as biomarkers for idiopathic pulmonary fibrosis.

Background: Idiopathic pulmonary fibrosis (IPF) is a fatal disease of unknown etiology with a poor prognosis, characterized by a lack of effective diagnostic and therapeutic interventions. The role of immunity in the pathogenesis of IPF is significant, yet remains inadequately understood. This study aimed to identify potential key genes in IPF and their relationship with immune cells by integrated bioinformatics analysis and verify by in vivo and in vitro experiments. Methods: Gene microarray data were obtained from the Gene Expression Omnibus (GEO) for differential expression analysis. The differentially expressed genes (DEGs) were identified and subjected to functional enrichment analysis. By utilizing a combination of three machine learning algorithms, specific genes associated with idiopathic pulmonary fibrosis (IPF) were pinpointed. Then their diagnostic significance and potential co-regulators were elucidated. We further analyzed the correlation between key genes and immune infiltrating cells via single-sample gene set enrichment analysis (ssGSEA). Subsequently, a single-cell RNA sequencing data (scRNA-seq) was used to explore which cell types expressed key genes in IPF samples. Finally, a series of in vivo and in vitro experiments were conducted to validate the expression of candidate genes by western blot (WB), quantitative real-time PCR (qRT-PCR), and immunohistochemistry (IHC) analysis. Results: A total of 647 DEGs of IPF were identified based on two datasets, including 225 downregulated genes and 422 upregulated genes. They are closely related to biological functions such as cell migration, structural organization, immune cell chemotaxis, and extracellular matrix. CFH and FHL2 were identified as key genes with diagnostic accuracy for IPF by three machine learning algorithms. Analysis using ssGSEA revealed a significant association of both CFH and FHL2 with diverse immune cells, such as B cells and NK cells. Further scRNA-seq analysis indicated CFH and FHL2 were specifically upregulated in human IPF tissues, which was confirmed by in vitro and in vivo experiments. Conclusion: In this study, CFH and FHL2 have been identified as novel potential biomarkers for IPF, with potential diagnostic utility in future clinical applications. Subsequent investigations into the functions of these genes in IPF and their interactions with immune cells may enhance comprehension of the disease's pathogenesis and facilitate the identification of therapeutic targets.

The Diagnostic Features of Peripheral Blood Biomarkers in Identifying Osteoarthritis Individuals: Machine Learning Strategies and Clinical Evidence.

BACKGROUND: People with osteoarthritis place a huge burden on society. Early diagnosis is essential to prevent disease progression and to select the best treatment strategy more effectively. In this study, the aim was to examine the diagnostic features and clinical value of peripheral blood biomarkers for osteoarthritis. OBJECTIVE: The goal of this project was to investigate the diagnostic features of peripheral blood and immune cell infiltration in osteoarthritis (OA). METHODS: Two eligible datasets (GSE63359 and GSE48556) were obtained from the GEO database to discern differentially expressed genes (DEGs). The machine learning strategy was employed to filtrate diagnostic biomarkers for OA. Additional verification was implemented by collecting clinical samples of OA. The CIBERSORT website estimated relative subsets of RNA transcripts to evaluate the immune-inflammatory states of OA. The link between specific DEGs and clinical immune-inflammatory markers was found by correlation analysis. RESULTS: Overall, 67 robust DEGs were identified. The nuclear receptor subfamily 2 group C member 2 (NR2C2), transcription factor 4 (TCF4), stromal antigen 1 (STAG1), and interleukin 18 receptor accessory protein (IL18RAP) were identified as effective diagnostic markers of OA in peripheral blood. All four diagnostic markers showed significant increases in expression in OA. Analysis of immune cell infiltration revealed that macrophages are involved in the occurrence of OA. Candidate diagnostic markers were correlated with clinical immune-inflammatory indicators of OA patients. CONCLUSION: We highlight that DEGs associated with immune inflammation (NR2C2, TCF4, STAG1, and IL18RAP) may be potential biomarkers for peripheral blood in OA, which are also associated with clinical immune-inflammatory indicators.

Identification of biomarkers differentiating Alzheimer's disease from other neurodegenerative diseases by integrated bioinformatic analysis and machine-learning strategies.

Background: Alzheimer's disease (AD) is the most common neurodegenerative disease, imposing huge mental and economic burdens on patients and society. The specific molecular pathway(s) and biomarker(s) that distinguish AD from other neurodegenerative diseases and reflect the disease progression are still not well studied. Methods: Four frontal cortical datasets of AD were integrated to conduct differentially expressed genes (DEGs) and functional gene enrichment analyses. The transcriptional changes after the integrated frontal cortical datasets subtracting the cerebellar dataset of AD were further compared with frontal cortical datasets of frontotemporal dementia and Huntingdon's disease to identify AD-frontal-associated gene expression. Integrated bioinformatic analysis and machine-learning strategies were applied for screening and determining diagnostic biomarkers, which were further validated in another two frontal cortical datasets of AD by receiver operating characteristic (ROC) curves. Results: Six hundred and twenty-six DEGs were identified as AD frontal associated, including 580 downregulated genes and 46 upregulated genes. The functional enrichment analysis revealed that immune response and oxidative stress were enriched in AD patients. Decorin (DCN) and regulator of G protein signaling 1 (RGS1) were screened as diagnostic biomarkers in distinguishing AD from frontotemporal dementia and Huntingdon's disease of AD. The diagnostic effects of DCN and RGS1 for AD were further validated in another two datasets of AD: the areas under the curve (AUCs) reached 0.8148 and 0.8262 in GSE33000, and 0.8595 and 0.8675 in GSE44770. There was a better value for AD diagnosis when combining performances of DCN and RGS1 with the AUCs of 0.863 and 0.869. Further, DCN mRNA level was correlated to CDR (Clinical Dementia Rating scale) score (r = 0.5066, p = 0.0058) and Braak staging (r = 0.3348, p = 0.0549). Conclusion: DCN and RGS1 associated with the immune response may be useful biomarkers for diagnosing AD and distinguishing the disease from frontotemporal dementia and Huntingdon's disease. DCN mRNA level reflects the development of the disease.

Comprehensive bioinformatics and machine learning analysis identify VCAN as a novel biomarker of hepatitis B virus-related liver fibrosis.

Hepatitis B virus (HBV) infection remains the leading cause of liver fibrosis (LF) worldwide, especially in China. Identification of decisive diagnostic biomarkers for HBV-associated liver fibrosis (HBV-LF) is required to prevent chronic hepatitis B (CHB) from progressing to liver cancer and to more effectively select the best treatment strategy. We obtained 43 samples from CHB patients without LF and 81 samples from CHB patients with LF (GSE84044 dataset). Among these, 173 differentially expressed genes (DEGs) were identified. Functional analysis revealed that these DEGs predominantly participated in immune-, extracellular matrix-, and metabolism-related processes. Subsequently, we integrated four algorithms (LASSO regression, SVM-RFE, RF, and WGCNA) to determine diagnostic biomarkers for HBV-LF. These analyses and receive operating characteristic curves identified the genes for phosphatidic acid phosphatase type 2C (PPAP2C) and versican (VCAN) as potentially valuable diagnostic biomarkers for HBV-LF. Single-sample gene set enrichment analysis (ssGSEA) further confirmed the immune landscape of HBV-LF. The two diagnostic biomarkers also significantly correlated with infiltrating immune cells. The potential regulatory mechanisms of VCAN underlying the occurrence and development of HBV-LF were also analyzed. These collective findings implicate VCAN as a novel diagnostic biomarker for HBV-LF, and infiltration of immune cells may critically contribute to the occurrence and development of HBV-LF.

Identification of diagnostic signatures associated with immune infiltration in Alzheimer's disease by integrating bioinformatic analysis and machine-learning strategies.

Objective: As a chronic neurodegenerative disorder, Alzheimer's disease (AD) is the most common form of progressive dementia. The purpose of this study was to identify diagnostic signatures of AD and the effect of immune cell infiltration in this pathology. Methods: The expression profiles of GSE109887, GSE122063, GSE28146, and GSE1297 were downloaded from the Gene Expression Omnibus (GEO) database to obtain differentially expressed genes (DEGs) between AD and control brain samples. Functional enrichment analysis was performed to reveal AD-associated biological functions and key pathways. Besides, we applied the Least Absolute Shrinkage Selection Operator (LASSO) and support vector machine-recursive feature elimination (SVM-RFE) analysis to screen potential diagnostic feature genes in AD, which were further tested in AD brains of the validation cohort (GSE5281). The discriminatory ability was then assessed by the area under the receiver operating characteristic curves (AUC). Finally, the CIBERSORT algorithm and immune cell infiltration analysis were employed to assess the inflammatory state of AD. Results: A total of 49 DEGs were identified. The functional enrichment analysis revealed that leukocyte transendothelial migration, cytokine receptor interaction, and JAK-STAT signaling pathway were enriched in the AD group. MAF basic leucine zipper transcription factor F (MAFF), ADCYAP1, and ZFP36L1 were identified as the diagnostic biomarkers of AD with high discriminatory ability (AUC = 0.850) and validated in AD brains (AUC = 0.935). As indicated from the immune cell infiltration analysis, naive B cells, plasma cells, activated/resting NK cells, M0 macrophages, M1 macrophages, resting CD4+ T memory cells, resting mast cells, memory B cells, and resting/activated dendritic cells may participate in the development of AD. Additionally, all diagnostic signatures presented different degrees of correlation with different infiltrating immune cells. Conclusion: MAFF, ADCYAP1, and ZFP36L1 may become new candidate biomarkers of AD, which were closely related to the pathogenesis of AD. Moreover, the immune cells mentioned above may play crucial roles in disease occurrence and progression.

Revealing Potential Spinal Cord Injury Biomarkers and Immune Cell Infiltration Characteristics in Mice.

Spinal cord injury (SCI) is a disabling condition with significant morbidity and mortality. Currently, no effective SCI treatment exists. This study aimed to identify potential biomarkers and characterize the properties of immune cell infiltration during this pathological event. To eliminate batch effects, we concurrently analyzed two mouse SCI datasets (GSE5296, GSE47681) from the GEO database. First, we identified differentially expressed genes (DEGs) using linear models for microarray data (LIMMA) and performed functional enrichment studies on those DEGs. Next, we employed bioinformatics and machine-learning methods to identify and define the characteristic genes of SCI. Finally, we validated them using immunofluorescence and qRT-PCR. Additionally, this study assessed the inflammatory status of SCI by identifying cell types using CIBERSORT. Furthermore, we investigated the link between key markers and infiltrating immune cells. In total, we identified 561 robust DEGs. We identified Rab20 and Klf6 as SCI-specific biomarkers and demonstrated their significance using qRT-PCR in the mouse model. According to the examination of immune cell infiltration, M0, M1, and M2 macrophages, along with naive CD8, dendritic cell-activated, and CD4 Follicular T cells may have a role in the progression of SCI. Therefore, Rab20 and Klf6 could be accessible targets for diagnosing and treating SCI. Moreover, as previously stated, immune cell infiltration may significantly impact the development and progression of SCI.

Identification of Diagnostic Signatures and Immune Cell Infiltration Characteristics in Rheumatoid Arthritis by Integrating Bioinformatic Analysis and Machine-Learning Strategies.

Background: Rheumatoid arthritis (RA) refers to an autoimmune rheumatic disease that imposes a huge burden on patients and society. Early RA diagnosis is critical to preventing disease progression and selecting optimal therapeutic strategies more effectively. In the present study, the aim was at examining RA's diagnostic signatures and the effect of immune cell infiltration in this pathology. Methods: Gene Expression Omnibus (GEO) database provided three datasets of gene expressions. Firstly, this study adopted R software for identifying differentially expressed genes (DEGs) and conducting functional correlation analyses. Subsequently, we integrated bioinformatic analysis and machine-learning strategies for screening and determining RA's diagnostic signatures and further verify by qRT-PCR. The diagnostic values were assessed through receiver operating characteristic (ROC) curves. Moreover, this study employed cell-type identification by estimating relative subsets of RNA transcript (CIBERSORT) website for assessing the inflammatory state of RA, and an investigation was conducted on the relationship of diagnostic signatures and infiltrating immune cells. Results: On the whole, 54 robust DEGs received the recognition. Lymphocyte-specific protein 1 (LSP1), Granulysin (GNLY), and Mesenchymal homobox 2 (MEOX2) (AUC = 0.955) were regarded as RA's diagnostic markers and showed their statistically significant difference by qRT-PCR. As indicated from the immune cell infiltration analysis, resting NK cells, neutrophils, activated NK cells, T cells CD8, memory B cells, and M0 macrophages may be involved in the development of RA. Additionally, all diagnostic signatures might be different degrees of correlation with immune cells. Conclusions: In conclusion, LSP1, GNLY, and MEOX2 are likely to be available in terms of diagnosing and treating RA, and the infiltration of immune cells mentioned above may critically impact RA development and occurrence.

[Progress of classification algorithms for motor imagery electroencephalogram signals].

Motor imagery (MI), motion intention of the specific body without actual movements, has attracted wide attention in fields as neuroscience. Classification algorithms for motor imagery electroencephalogram (MI-EEG) signals are able to distinguish different MI tasks based on the physiological information contained by the EEG signals, especially the features extracted from them. In recent years, there have been some new advances in classification algorithms for MI-EEG signals in terms of classifiers versus machine learning strategies. In terms of classifiers, traditional machine learning classifiers have been improved by some researchers, deep learning and Riemannian geometry classifiers have been widely applied as well. In terms of machine learning strategies, ensemble learning, adaptive learning, and transfer learning strategies have been utilized to improve classification accuracies or reach other targets. This paper reviewed the progress of classification algorithms for MI-EEG signals, summarized and evaluated the existing classifiers and machine learning strategies, to provide new ideas for developing classification algorithms with higher performance.

Confocal Laser Microscopy for in vivo Intraoperative Application: Diagnostic Accuracy of Investigator and Machine Learning Strategies.

BACKGROUND: Confocal laser microscopy (CLM) is one of the optical techniques that are promising methods of intraoperative in vivo real-time tissue examination based on tissue fluorescence. However, surgeons might struggle interpreting CLM images intraoperatively due to different tissue characteristics of different tissue pathologies in clinical reality. Deep learning techniques enable fast and consistent image analysis and might support intraoperative image interpretation. The objective of this study was to analyze the diagnostic accuracy of newly trained observers in the evaluation of normal colon and peritoneal tissue and colon cancer and metastasis, respectively, and to compare it with that of convolutional neural networks (CNNs). METHODS: Two hundred representative CLM images of the normal and malignant colon and peritoneal tissue were evaluated by newly trained observers (surgeons and pathologists) and CNNs (VGG-16 and Densenet121), respectively, based on tissue dignity. The primary endpoint was the correct detection of the normal and cancer/metastasis tissue measured by sensitivity and specificity of both groups. Additionally, positive predictive values (PPVs) and negative predictive values (NPVs) were calculated for the newly trained observer group. The interobserver variability of dignity evaluation was calculated using kappa statistic. The F1-score and area under the curve (AUC) were used to evaluate the performance of image recognition of the CNNs' training scenarios. RESULTS: Sensitivity and specificity ranged between 0.55 and 1.0 (pathologists: 0.66-0.97; surgeons: 0.55-1.0) and between 0.65 and 0.96 (pathologists: 0.68-0.93; surgeons: 0.65-0.96), respectively. PPVs were 0.75 and 0.90 in the pathologists' group and 0.73-0.96 in the surgeons' group, respectively. NPVs were 0.73 and 0.96 for pathologists' and between 0.66 and 1.00 for surgeons' tissue analysis. The overall interobserver variability was 0.54. Depending on the training scenario, cancer/metastasis tissue was classified with an AUC of 0.77-0.88 by VGG-16 and 0.85-0.89 by Densenet121. Transfer learning improved performance over training from scratch. CONCLUSIONS: Newly trained investigators are able to learn CLM images features and interpretation rapidly, regardless of their clinical experience. Heterogeneity in tissue diagnosis and a moderate interobserver variability reflect the clinical reality more realistic. CNNs provide comparable diagnostic results as clinical observers and could improve surgeons' intraoperative tissue assessment.