Identification of immune microenvironment subtypes and signature genes for Alzheimer's disease diagnosis and risk prediction based on explainable machine learning

Predictive value of machine learning for in-hospital mortality risk in acute myocardial infarction: A systematic review and meta-analysis

BACKGROUND

Machine learning (ML) models have been constructed to predict the risk of in-hospital mortality in patients with myocardial infarction (MI). Due to diverse ML models and modeling variables, along with the significant imbalance in data, the predictive accuracy of these models remains controversial.

OBJECTIVE

This study aimed to review the accuracy of ML in predicting in-hospital mortality risk in MI patients and to provide evidence-based advices for the development or updating of clinical tools.

METHODS

PubMed, Embase, Cochrane, and Web of Science databases were searched, up to June 4, 2024. PROBAST and ChAMAI checklist are utilized to assess the risk of bias in the included studies. Since the included studies constructed models based on severely unbalanced datasets, subgroup analyses were conducted by the type of dataset (balanced data, unbalanced data, model type).

RESULTS

This meta-analysis included 32 studies. In the validation set, the pooled C-index, sensitivity, and specificity of prediction models based on balanced data were 0.83 (95 % CI: 0.795-0.866), 0.81 (95 % CI: 0.79-0.84), and 0.82 (95 % CI: 0.78-0.86), respectively. In the validation set, the pooled C-index, sensitivity, and specificity of ML models based on imbalanced data were 0.815 (95 % CI: 0.789-0.842), 0.66 (95 % CI: 0.60-0.72), and 0.84 (95 % CI: 0.83-0.85), respectively.

CONCLUSIONS

ML models such as LR, SVM, and RF exhibit high sensitivity and specificity in predicting in-hospital mortality in MI patients. However, their sensitivity is not superior to well-established scoring tools. Mitigating the impact of imbalanced data on ML models remains challenging.

Alzheimer's Disease and Frontotemporal Dementia: A Review of Pathophysiology and Therapeutic Approaches

Alzheimer's disease (AD) is a devastating form of dementia, with the number of affected individuals rising sharply. The main hallmarks of the disease include amyloid-beta plaque deposits and neurofibrillary tangles consisting of hyperphosphorylated tau protein, besides other pathological features that contribute to the disease's complexity. The causes of sporadic AD are multifactorial and mostly age-related and involve risk factors such as diabetes and cardiovascular or cerebrovascular disorders. Frontotemporal dementia (FTD) is another type of dementia characterized by a spectrum of behaviors, memory, and motor abnormalities and associated with abnormal depositions of protein aggregation, including tau protein. Currently approved medications are symptomatic, and no disease-modifying therapy is available to halt the disease progression. Therefore, the development of multi-targeted therapeutic approaches could hold promise for the treatment of AD and other neurodegenerative disorders, including tauopathies. In this article, we will discuss the pathophysiology of AD and FTD, the proposed hypotheses, and current therapeutic approaches, highlighting the development of novel drug candidates and the progress of clinical trials in this field of research.

Molecular mechanisms of MAPK9, BAX, and TFEB proteins: Genetic correlations between oxidative stress and autophagy pathways in Alzheimer's disease

Alzheimer's disease (AD) is a complex neurodegenerative disease whose pathological mechanisms involve dysregulation of oxidative stress and autophagy pathways. MAPK9, BAX and TFEB were used as key proteins. Wayne analysis was used to identify genes associated with autophagy and oxidative stress, and protein-protein interaction (PPI) networks were constructed to study the associations between key genes. The key genes were mined by machine learning algorithm and prognostic marker models were constructed. The immune characteristics of AD were investigated by gene collection enrichment analysis (GSEA) and immunoresponse pathway enrichment analysis, and the clinical application potential was evaluated by drug prediction and molecular docking analysis. Finally, Mendelian randomization (MR) analysis was used to verify the causal relationship between key genes and AD. The results showed that we successfully identified several genes associated with Alzheimer's disease, including MAPK9, BAX, and TFEB. GSEA analysis showed their active involvement in the immune response, indicating the importance of immune function in AD. Drug prediction models reveal potential therapeutic targets for these key genes.

Current methods in explainable artificial intelligence and future prospects for integrative physiology

Explainable artificial intelligence (XAI) is gaining importance in physiological research, where artificial intelligence is now used as an analytical and predictive tool for many medical research questions. The primary goal of XAI is to make AI models understandable for human decision-makers. This can be achieved in particular through providing inherently interpretable AI methods or by making opaque models and their outputs transparent using post hoc explanations. This review introduces XAI core topics and provides a selective overview of current XAI methods in physiology. It further illustrates solved and discusses open challenges in XAI research using existing practical examples from the medical field. The article gives an outlook on two possible future prospects: (1) using XAI methods to provide trustworthy AI for integrative physiological research and (2) integrating physiological expertise about human explanation into XAI method development for useful and beneficial human-AI partnerships.

Natural Killer Cells in Alzheimer's Disease: From Foe to Friend

The neuroinflammatory aspect of Alzheimer's disease (AD) has been largely focused on microglia, the innate immune cells of the brain; however, recent evidence increasingly points to the importance of multiple alterations in the systemic immune response during disease development. Natural killer (NK) cells are also components of innate immunity, whose role in AD pathogenesis has been sporadically investigated and often conflicting results have been reported. Recent clinical trial has suggested the potential beneficial effects of AD immunotherapy based on ex vivo-expanded, genetically unmodified, NK cells. This has led to increased interest in understanding the function of these cells in the central nervous system in both physiological and pathological contexts such as AD. Considering that AD is predominantly a disease of the elderly population, in this review, we summarized the current state of knowledge on the physiological changes that occur in the NK cell compartment during the normal aging process and the pathophysiological alterations that occur throughout the AD continuum that could potentially explain the therapeutic efficacy of these cells.

A comprehensive bioinformatics analysis identifies mitophagy biomarkers and potential Molecular mechanisms in hypertensive nephropathy

Mitophagy, the selective removal of damaged mitochondria, plays a critical role in kidney diseases, but its involvement in hypertensive nephropathy (HTN) is not well understood. To address this gap, we investigated mitophagy-related genes in HTN, identifying potential biomarkers for diagnosis and treatment. Transcriptome datasets from the Gene Expression Omnibus database were analyzed, resulting in the identification of seven mitophagy related differentially expressed genes (MR-DEGs), namely PINK1, ULK1, SQSTM1, ATG5, ATG12, MFN2, and UBA52. Further, we explored the correlation between MR-DEGs, immune cells, and inflammatory factors. The identified genes demonstrated a strong correlation with Mast cells, T-cells, TGFβ3, IL13, and CSF3. Machine learning techniques were employed to screen important genes, construct diagnostic models, and evaluate their accuracy. Consensus clustering divided the HTN patients into two mitophagy subgroups, with Subgroup 2 showing higher levels of immune cell infiltration and inflammatory factors. The functions of their proteins primarily involve complement, coagulation, lipids, and vascular smooth muscle contraction. Single-cell RNA sequencing revealed that mitophagy was most significant in proximal tubule cells (PTC) in HTN patients. Pseudotime analysis of PTC confirmed the expression changes observed in the transcriptome. Intercellular communication analysis suggested that mitophagy might regulate PTC's participation in intercellular crosstalk. Notably, specific transcription factors such as HNF4A, PPARA, and STAT3 showed strong correlations with mitophagy-related genes in PTC, indicating their potential role in modulating PTC function and influencing the onset and progression of HTN. This study offers a comprehensive analysis of mitophagy in HTN, enhancing our understanding of the pathogenesis, diagnosis, and treatment of HTN.

Predicting Radiation Esophagitis in Patients Undergoing Synchronous Boost Radiotherapy Post-Breast-Conserving Surgery

This study constructed a predictive model for occurrence of radiation esophagitis during breast-cancer radiotherapy. 308 breast-cancer patients were analyzed. Lasso regression identified crucial variables that were further integrated into a radiation esophagitis risk score, which was used to segregate patients into high- and low-risk groups. A nomogram model was designed for clinical applicability. Training and validations were performed to assess robustness and generalizability of proposed models, employing C-index, AUCs, calibration curves, and decision curves. SHAP algorithm was used for model interpretation, offering insights into the major contributory factors. Seven significant variables were identified by Lasso regression. C-indexes of nomograms of individual clinical variables and risk score were 0.795 and 0.784, respectively, exhibiting strong predictive ability. In internal validation, AUCs for risk score, nomogram, and logistic models were 0.784, 0.795, and 0.812, respectively. Calibration curves showed a close fit between predicted and observed outcomes across models. Decision curve analysis indicated logistic model's superior clinical utility when the risk threshold was above 0.2. SHAP interpretation emphasized radiation dose, pruritus, molecular type, and hepatic dysfunction as top contributory factors for radiation esophagitis. Models based on interpretable machine learning offer an intuitive tool to assess risk of radiation esophagitis in breast-cancer radiotherapy.

Comparison of Deep Learning and Traditional Machine Learning Models for Predicting Mild Cognitive Impairment Using Plasma Proteomic Biomarkers

Mild cognitive impairment (MCI) is a clinical condition characterized by a decline in cognitive ability and progression of cognitive impairment. It is often considered a transitional stage between normal aging and Alzheimer's disease (AD). This study aimed to compare deep learning (DL) and traditional machine learning (ML) methods in predicting MCI using plasma proteomic biomarkers. A total of 239 adults were selected from the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort along with a pool of 146 plasma proteomic biomarkers. We evaluated seven traditional ML models (support vector machines (SVMs), logistic regression (LR), naïve Bayes (NB), random forest (RF), k-nearest neighbor (KNN), gradient boosting machine (GBM), and extreme gradient boosting (XGBoost)) and six variations of a deep neural network (DNN) model-the DL model in the H2O package. Least Absolute Shrinkage and Selection Operator (LASSO) selected 35 proteomic biomarkers from the pool. Based on grid search, the DNN model with an activation function of "Rectifier With Dropout" with 2 layers and 32 of 35 selected proteomic biomarkers revealed the best model with the highest accuracy of 0.995 and an F1 Score of 0.996, while among seven traditional ML methods, XGBoost was the best with an accuracy of 0.986 and an F1 Score of 0.985. Several biomarkers were correlated with the APOE-ε4 genotype, polygenic hazard score (PHS), and three clinical cerebrospinal fluid biomarkers (Aβ42, tTau, and pTau). Bioinformatics analysis using Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) revealed several molecular functions and pathways associated with the selected biomarkers, including cytokine-cytokine receptor interaction, cholesterol metabolism, and regulation of lipid localization. The results showed that the DL model may represent a promising tool in the prediction of MCI. These plasma proteomic biomarkers may help with early diagnosis, prognostic risk stratification, and early treatment interventions for individuals at risk for MCI.

Chemokines in neurodegenerative diseases

Neurodegeneration and neuroinflammation disorders are mainly the result of the deposition of various proteins, such as α-synuclein, amyloid-β and prions, which lead to the initiation and activation of inflammatory responses. Different chemokines are involved in the infiltration and movement of inflammatory leukocytes into the central nervous system (CNS) that express chemokine receptors. Dysregulation of several members of chemokines has been shown in the CNS, cerebrospinal fluid and peripheral blood of patients who have neurodegenerative disorders. Upon infiltration of various cells, they produce many inflammatory mediators such as cytokines. Besides them, some CNS-resident cells, such as neurons and astrocytes, are also involved in the pathogenesis of neurodegeneration by producing chemokines. In this review, we summarize the role of chemokines and their related receptors in the pathogenesis of neurodegeneration and neuroinflammation disorders, including multiple sclerosis, Parkinson's disease and Alzheimer's disease. Therapeutic strategies targeting chemokines or their related receptors are also discussed in this article.

Insights into the Correlation and Immune Crosstalk Between COVID-19 and Sjögren's Syndrome Keratoconjunctivitis Sicca via Weighted Gene Coexpression Network Analysis and Machine Learning

Background: Although autoimmune complications of COVID-19 have aroused concerns, there is no consensus on its ocular complications. Sjögren's syndrome is an autoimmune disease accompanied by the ocular abnormality keratoconjunctivitis sicca (SS-KCS), which may be influenced by COVID-19. Thereby, we explored the possible interaction between COVID-19 and SS-KCS, and we aimed to elucidate the potential correlated mechanism. Methods: Differentially expressed genes (DEGs) in COVID-19 and SS-KCS transcriptome data obtained from the gene expression omnibus database were identified, and COVID-19-related genes were screened using weighted gene coexpression network analysis. Common genes were verified using four machine-learning diagnostic predictors. The clinical relationship between the two common hub genes of COVID-19 was analyzed. Finally, the immune cell types infiltrating the microenvironment in the COVID-19 dataset were analyzed using CIBERSORT, and the interrelation between key genes and differentially infiltrating immune cells was verified via Pearson correlation. Results: Ten potential primary hub mRNAs were screened by intersecting the COVID-19 DEGs, SS-KCS DEGs, and WGCNA genes. After a multifaceted evaluation using four mainstream machine-learning diagnostic predictors, the most accurate and sensitive random forest model identified CR1 and TAP2 as the common hub genes of COVID-19 and SS-KCS. Together with the clinical information on COVID-19, the expression of CR1 and TAP2 was significantly correlated with the status and severity of COVID-19. CR1 and TAP2 were significantly positively correlated with M0 and M2 macrophages, neutrophils, and CD4+ memory resting T cells and negatively correlated with activated NK cells, monocytes, and CD8+ T cells. Conclusions: We validated the hub genes associated with both COVID-19 and SS-KCS, and we investigated the immune mechanisms underlying their interaction, which may help in the early prediction, identification, diagnosis, and management of SARS-CoV-2 infection-related SS-KCS syndrome or many other immune-related complications in the long COVID period.

Potential molecular mechanisms of tobacco smoke exposure in Alzheimer's disease

BACKGROUND

Smoking is detrimental to health, with tobacco use being a critical factor in the development of various neurodegenerative diseases, including Alzheimer's disease (AD), which progressively impairs brain function and poses a significant threat to public health. This study aims to examine the potential genetic alterations induced by smoking that are associated with AD and to investigate the underlying regulatory mechanisms. The research will provide theoretical foundations for targeted prevention and treatment strategies for AD.

METHODS

This study analyzed datasets from the Gene Expression Omnibus (GEO) and the Comparative Toxicogenomics Database (CTD) to identify genes affected by tobacco smoke exposure and those altered in patients with AD relative to normal controls. We conducted Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses using OmicShare tools to screen for key pathways. Key genes were identified by constructing protein-protein interaction networks (PPI) in the STRING database with the aid of CytoHubba. Additionally, the binding activity of the proteins encoded by these key genes to nicotine, the main component of tobacco, was analyzed using molecular docking techniques. Finally, the analytical results were verified using Quantitative Real-Time Polymerase Chain Reaction.

RESULTS

The CTD identified 12,164 CE-related genes affected by tobacco smoke exposure. A comparison of these datasets yielded 94 common genes that were both influenced by tobacco and differentially expressed across all brain regions. The GO and KEGG pathway enrichment analyses showed that these common differentially expressed genes (DEGs) were predominantly enriched in the Wnt/β-catenin and PI3K-AKT signaling pathways. The DEGs' PPI network, constructed using the STRING database, highlighted key genes such as HSP90AB1, SOS2, MAGI1, and YWHAZ. Molecular docking studies demonstrated that nicotine binds effectively to the protein structures of these key genes, primarily through amino acid residues such as Ser and Glu. Experimental validation showed that HSP90AB1 and YWHAZ exhibited notable expression discrepancies under varying concentrations of cigarette smoke extract (CSE) treatments, particularly demonstrating a pronounced down-regulation trend at elevated concentrations.

CONCLUSION

The study indicates that tobacco may impact the function of transmembrane transporter proteins and contribute to the development of AD by affecting key genes such as HSP90AB1 and YWHAZ, as well as signaling pathways like PI3K-AKT.

ERBB3-related gene PBX1 is associated with prognosis in patients with HER2-positive breast cancer

BACKGROUND

HER2-positive breast cancer (BC) is a subtype of breast cancer. Increased ERBB3 expression has been implicated as a potential cause of resistance to other HER-targeted therapies. Our study aimed to screen and validate prognostic markers associated with ERBB3 expression by bioinformatics and affecting the prognosis of HER2 staging.

METHODS

Analyzing differences in ERBB3-related groups. ERBB3 expression-related differentially expressed genes (DEGs) were identified and intersected with survival status-related DEGs to obtain intersected genes. Three algorithms, LASSO, RandomForest and XGBoost were combined to identify the signature genes. we construct risk models and generate ROC curves for prediction. Furthermore, we delve into the immunological traits, correlations, and expression patterns of signature genes by conducting a comprehensive analysis that encompasses immune infiltration analysis, correlation analysis, and differential expression analysis.

RESULTS

Significant variability in ERBB3 expression and prognosis in high and low ERBB3 expression groups. Twenty-five candidate DEGs were identified by intersecting ERBB3-related DEGs with survival-related DEGs. Utilizing three distinct machine learning algorithms, we identified three signature genes-PBX1, IGHM, and CXCL13-that exhibited significant diagnostic value within the diagnostic model. In addition, the risk model had better prognostic and predictive effects, and the immune infiltration analysis showed that IGHM, CXCL13 might affect the proliferation of BC cells through immune cells. Functional studies demonstrated that interference with PBX1 inhibited the proliferation, migration, and epithelial-mesenchymal transition process of HER2-positive BC cells.

CONCLUSION

PBX1, IGHM and CXCL13 are associated with the expression level of the ERBB3 and are prognostic markers for HER2-positive in BC, which may play an important role in the development and progression of BC.

Unraveling the copper-death connection: Decoding COVID-19's immune landscape through advanced bioinformatics and machine learning approaches

This study aims to analyze Coronavirus Disease 2019 (COVID-19)-associated copper-death genes using the Gene Expression Omnibus (GEO) dataset and machine learning, exploring their immune microenvironment correlation and underlying mechanisms. Utilizing GEO, we analyzed the GSE217948 dataset with control samples. Differential expression analysis identified 16 differentially expressed copper-death genes, and Cell type Identification By Estimating Relative Subsets Of RNA Transcripts (CIBERSORT) quantified immune cell infiltration. Gene classification yielded two copper-death clusters, with Weighted Gene Co-expression Network Analysis (WGCNA) identifying key module genes. Machine learning models (random forest, Support Vector Machine (SVM), Generalized Linear Model (GLM), eXtreme Gradient Boosting (XGBoost)) selected 6 feature genes validated by the GSE213313 dataset. Ferredoxin 1 (FDX1) emerged as the top gene, corroborated by Area Under the Curve (AUC) analysis. Gene Set Enrichment Analysis (GSEA) and Gene Set Variation Analysis (GSVA) revealed enriched pathways in T cell receptor, natural killer cytotoxicity, and Peroxisome Proliferator-Activated Receptor (PPAR). We uncovered differentially expressed copper-death genes and immune infiltration differences, notably CD8 T cells and M0 macrophages. Clustering identified modules with potential implications for COVID-19. Machine learning models effectively predicted COVID-19 risk, with FDX1's pivotal role validated. FDX1's high expression was associated with immune pathways, suggesting its role in COVID-19 pathogenesis. This comprehensive approach elucidated COVID-19-related copper-death genes, their immune context, and risk prediction potential. FDX1's connection to immune pathways offers insights into COVID-19 mechanisms and therapy.

The STAT1-SLC31A1 axis: Potential regulation of cuproptosis in diabetic retinopathy

BACKGROUND

By identifying molecular biological markers linked to cuproptosis in diabetic retinopathy (DR), new pathobiological pathways and more accessible diagnostic markers can be developed.

METHODS

The datasets related to DR were acquired from the Gene Expression Omnibus database, while genes associated with cuproptosis were sourced from previously published compilations. Consensus clustering was conducted to delineate distinct DR subclasses. Feature genes were identified utilizing weighted correlation network analysis (WGCNA). Additionally, two machine-learning algorithms were employed to refine the selection of feature genes. Finally, we conducted preliminary validation experiments to ascertain the involvement of cuproptosis in DR development and the transcriptional regulation of critical genes using both the streptozotocin-induced diabetic mouse model and the high glucose-induced BV2 model.

RESULTS

In the STZ-induced diabetic mouse retinas, a decrease in the expression of cuproptosis signature proteins (FDX1, DLAT, and NDUFS8) suggested the occurrence of cuproptosis in DR. Subsequently, the expression of eight cuproptosis differential genes was validated through the STZ-induced diabetes and oxygen-induced retinopathy (OIR) models, with the key gene SLC31A1 showing upregulation in both models and dataset species. Further analyses, including weighted gene co-expression network analysis, GSVA, and immune infiltration analysis, indicated a close correlation between cuproptosis and microglia function. Additionally, validation in an in vitro model of microglia indicated the occurrence of cuproptosis in microglia under high glucose conditions, alongside abnormal expression of STAT1 with SLC31A1.

CONCLUSION

Our findings suggest that STAT1/SLC31A1 may pave the way for a deeper comprehension of the mechanistic basis of DR and offer potential therapeutic avenues.

Comparing the Artificial Intelligence Detection Models to Standard Diagnostic Methods and Alternative Models in Identifying Alzheimer's Disease in At-Risk or Early Symptomatic Individuals: A Scoping Review

Alzheimer's disease (AD) and other neurodegenerative illnesses place a heavy strain on the world's healthcare systems, particularly among the aging population. With a focus on research from January 2022 to September 2023, this scoping review, which adheres to Preferred Reporting Items for Systematic Reviews and Meta-Analysis extension for Scoping Reviews (PRISMA-Scr) criteria, examines the changing landscape of artificial intelligence (AI) applications for early AD detection and diagnosis. Forty-four carefully chosen articles were selected from a pool of 2,966 articles for the qualitative synthesis. The research reveals impressive advancements in AI-driven approaches, including neuroimaging, genomics, cognitive tests, and blood-based biomarkers. Notably, AI models focusing on deep learning (DL) algorithms demonstrate outstanding accuracy in early AD identification, often even before the onset of clinical symptoms. Multimodal approaches, which combine information from various sources, including neuroimaging and clinical assessments, provide comprehensive insights into the complex nature of AD. The study also emphasizes the critical role that blood-based and genetic biomarkers play in strengthening AD diagnosis and risk assessment. When combined with clinical or imaging data, genetic variations and polygenic risk scores help to improve prediction models. In a similar vein, blood-based biomarkers provide non-invasive instruments for detecting metabolic changes linked to AD. Cognitive and functional evaluations, which include neuropsychological examinations and assessments of daily living activities, serve as essential benchmarks for monitoring the course of AD and directing treatment interventions. When these evaluations are included in machine learning models, the diagnosis accuracy is improved, and treatment monitoring is made more accessible. In addition, including methods that support model interpretability and explainability helps in the thorough understanding and valuable implementation of AI-driven insights in clinical contexts. This review further identifies several gaps in the research landscape, including the need for diverse, high-quality datasets to address data heterogeneity and improve model generalizability. Practical implementation challenges, such as integrating AI systems into clinical workflows and clinician adoption, are highlighted as critical barriers to real-world application. Moreover, ethical considerations, particularly surrounding data privacy and informed consent, must be prioritized as AI adoption in healthcare accelerates. Performance metrics (e.g., sensitivity, specificity, and area under the curve (AUC)) for AI-based approaches are discussed, with a need for clearer reporting and comparative analyses. Addressing these limitations, alongside methodological clarity and critical evaluation of biases, would strengthen the credibility of AI applications in AD detection. By expanding its scope, this study highlights areas for improvement and future opportunities in early detection, aiming to bridge the gap between innovative AI technologies and practical clinical utility.

Explainable Machine Learning Models for Brain Diseases: Insights from a Systematic Review

In recent years, Artificial Intelligence (AI) methods, specifically Machine Learning (ML) models, have been providing outstanding results in different areas of knowledge, with the health area being one of its most impactful fields of application. However, to be applied reliably, these models must provide users with clear, simple, and transparent explanations about the medical decision-making process. This systematic review aims to investigate the use and application of explainability in ML models used in brain disease studies. A systematic search was conducted in three major bibliographic databases, Web of Science, Scopus, and PubMed, from January 2014 to December 2023. A total of 133 relevant studies were identified and analyzed out of a total of 682 found in the initial search, in which the explainability of ML models in the medical context was studied, identifying 11 ML models and 12 explainability techniques applied in the study of 20 brain diseases.

Identification of Autophagy-Related Candidate Genes in the Early Diagnosis of Alzheimer's Disease and Exploration of Potential Molecular Mechanisms

This study aimed to identify autophagy-related candidate genes for the early diagnosis of Alzheimer's disease (AD) and elucidate their potential molecular mechanisms. Differentially expressed genes (DEGs) and phenotype-associated significant module genes were obtained using the "limma" package and weighted gene co-expression network analysis (WGCNA) based on hippocampal tissue datasets from AD patients and control samples. The intersection between the list of autophagy-related genes (ATGs), DEGs, and module genes was further investigated to obtain AD-autophagy-related differential expression genes (ATDEGs). Subsequently, the least absolute shrinkage and selection operator (LASSO) algorithm was utilized to identify hub genes, and a second intersection was performed with important module genes from the protein-protein interaction (PPI) network to obtain co-hub genes. Finally, a diagnostic model was constructed by receiver operating characteristic (ROC) analysis to determine the candidate genes with high diagnostic efficacy in the external validation set. Moreover, immune infiltration analysis was performed on AD patient brain tissues and explore the correlation between candidate genes and immune cells. We further analyzed the expression level of candidate genes in the SH-SY5Y cells with Aβ25-35 (25 µM). Among the 17 identified AD-ATDEGs, ATP6V1E1 stood out with area under the curve (AUC) values of 0.869, 0.817, and 0.714 in the external validation set, underscoring its high diagnostic efficacy in both hippocampal and peripheral blood contexts for AD patients. Meanwhile, ATP6V1E1 expression was positively correlated with effector memory CD4 + T cells, while negatively correlated with natural killer T cells and activated CD4 + T cells. Results from quantitative PCR (qPCR) and immunofluorescence assays indicated a reduction in ATP6V1E1 expression, aligning with our database analysis findings. In summary, ATP6V1E1 as a candidate gene provides a new perspective for the early identification and pathogenesis of AD.

Radiomics-based machine learning model to phenotype hip involvement in ankylosing spondylitis: a pilot study

Objectives

Hip involvement is an important reason of disability in patients with ankylosing spondylitis (AS). Unveiling the potential phenotype of hip involvement in AS remains an unmet need to understand its biological mechanisms and improve clinical decision-making. Radiomics, a promising quantitative image analysis method that had been successfully used to describe the phenotype of a wide variety of diseases, while it was less reported in AS. The objective of this study was to investigate the feasibility of radiomics-based approach to profile hip involvement in AS.

Methods

A total of 167 patients with AS was included. Radiomic features were extracted from pelvis MRI after image preprocessing and feature engineering. Then, we performed unsupervised machine learning method to derive radiomics-based phenotypes. The validation and interpretation of derived phenotypes were conducted from the perspectives of clinical backgrounds and MRI characteristics. The association between derived phenotypes and radiographic outcomes was evaluated by multivariable analysis.

Results

1321 robust radiomic features were extracted and four biologically distinct phenotypes were derived. According to patient clinical backgrounds, phenotype I (38, 22.8%) and II (34, 20.4%) were labelled as high-risk while phenotype III (24, 14.4%) and IV (71, 42.5%) were at low risk for hip involvement. Consistently, the high-risk phenotypes were associated with higher prevalence of MRI-detected lesion than the low-risk. Moreover, phenotype I had significant acute inflammation signs than phenotype II, while phenotype IV was enthesitis-predominant. Importantly, the derived phenotypes were highly predictive of radiographic outcomes of patients, as the high-risk phenotypes were 3 times more likely to have radiological hip lesion than the low-risk [27 (58.7%) vs 16 (28.6%); adjusted odds ratio (OR) 2.95 (95% CI 1.10, 7.92)].

Conclusion

We confirmed for the first time, the clinical actionability of profiling hip involvement in AS by radiomics method. Four distinct phenotypes of hip involvement in AS were identified and importantly, the high-risk phenotypes could predict structural damage of hip involvement in AS.

Platelet Metabolites as Candidate Biomarkers in Sepsis Diagnosis and Management Using the Proposed Explainable Artificial Intelligence Approach

Background: Sepsis is characterized by an atypical immune response to infection and is a dangerous health problem leading to significant mortality. Current diagnostic methods exhibit insufficient sensitivity and specificity and require the discovery of precise biomarkers for the early diagnosis and treatment of sepsis. Platelets, known for their hemostatic abilities, also play an important role in immunological responses. This study aims to develop a model integrating machine learning and explainable artificial intelligence (XAI) to identify novel platelet metabolomics markers of sepsis. Methods: A total of 39 participants, 25 diagnosed with sepsis and 14 control subjects, were included in the study. The profiles of platelet metabolites were analyzed using quantitative 1H-nuclear magnetic resonance (NMR) technology. Data were processed using the synthetic minority oversampling method (SMOTE)-Tomek to address the issue of class imbalance. In addition, missing data were filled using a technique based on random forests. Three machine learning models, namely extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and kernel tree boosting (KTBoost), were used for sepsis prediction. The models were validated using cross-validation. Clinical annotations of the optimal sepsis prediction model were analyzed using SHapley Additive exPlanations (SHAP), an XAI technique. Results: The results showed that the KTBoost model (0.900 accuracy and 0.943 AUC) achieved better performance than the other models in sepsis diagnosis. SHAP results revealed that metabolites such as carnitine, glutamate, and myo-inositol are important biomarkers in sepsis prediction and intuitively explained the prediction decisions of the model. Conclusion: Platelet metabolites identified by the KTBoost model and XAI have significant potential for the early diagnosis and monitoring of sepsis and improving patient outcomes.

Spatial cell interplay networks of regulatory T cells predict recurrence in patients with operable non-small cell lung cancer

BACKGROUND

The interplay between regulatory T cells (Tregs) and neighboring cells, which is pivotal for anti-tumor immunity and closely linked to patient prognosis, remains to be fully elucidated.

METHODS

Tissue microarrays of 261 operable NSCLC patients were stained by multiplex immunofluorescence (mIF) assay, and the interaction between Tregs and neighboring cells in the tumor microenvironment (TME) was evaluated. Employing various machine learning algorithms, we developed a spatial immune signature to predict the prognosis of NSCLC patients. Additionally, we explored the interplay between programmed death-1/programmed death ligand-1 (PD-1/PD-L1) interactions and their relationship with Tregs.

RESULTS

Survival analysis indicated that the interplay between Tregs and neighboring cells in the invasive margin (IM) and tumor center was associated with recurrence in NSCLC patients. We integrated the intersection of the three algorithms to identify four crucial spatial immune features [P(CD8+Treg to CK) in IM, P(CD8+Treg to CD4) in IM, N(CD4+Treg to CK) in IM, N(CD4+Tcon to CK) in IM] and employed these characteristics to establish SIS, an independent prognosticator of recurrence in NSCLC patients [HR = 2.34, 95% CI (1.53, 3.58), P < 0.001]. Furthermore, analysis of cell interactions demonstrated that a higher number of Tregs contributed to higher PD-L1+ cells surrounded by PD-1+ cells (P < 0.001) with shorter distances (P = 0.004).

CONCLUSION

We dissected the cell interplay network within the TME, uncovering the spatial architecture and intricate interactions between Tregs and neighboring cells, along with their impact on the prognosis of NSCLC patients.

Overcoming treatment-resistant depression with machine-learning based tools: a study protocol combining EEG and clinical data to personalize glutamatergic and brain stimulation interventions (SelecTool Project)

Treatment-Resistant Depression (TRD) poses a substantial health and economic challenge, persisting as a major concern despite decades of extensive research into novel treatment modalities. The considerable heterogeneity in TRD's clinical manifestations and neurobiological bases has complicated efforts toward effective interventions. Recognizing the need for precise biomarkers to guide treatment choices in TRD, herein we introduce the SelecTool Project. This initiative focuses on developing (WorkPlane 1/WP1) and conducting preliminary validation (WorkPlane 2/WP2) of a computational tool (SelecTool) that integrates clinical data, neurophysiological (EEG) and peripheral (blood sample) biomarkers through a machine-learning framework designed to optimize TRD treatment protocols. The SelecTool project aims to enhance clinical decision-making by enabling the selection of personalized interventions. It leverages multi-modal data analysis to navigate treatment choices towards two validated therapeutic options for TRD: esketamine nasal spray (ESK-NS) and accelerated repetitive Transcranial Magnetic Stimulation (arTMS). In WP1, 100 subjects with TRD will be randomized to receive either ESK-NS or arTMS, with comprehensive evaluations encompassing neurophysiological (EEG), clinical (psychometric scales), and peripheral (blood samples) assessments both at baseline (T0) and one month post-treatment initiation (T1). WP2 will utilize the data collected in WP1 to train the SelecTool algorithm, followed by its application in a second, out-of-sample cohort of 20 TRD subjects, assigning treatments based on the tool's recommendations. Ultimately, this research seeks to revolutionize the treatment of TRD by employing advanced machine learning strategies and thorough data analysis, aimed at unraveling the complex neurobiological landscape of depression. This effort is expected to provide pivotal insights that will promote the development of more effective and individually tailored treatment strategies, thus addressing a significant void in current TRD management and potentially reducing its profound societal and economic burdens.

Identification and experimental validation of m7G-related molecular subtypes, immune signature, and feature genes in Alzheimer's disease

Background

Studies has shown that N7-methylguanosine (m7G) modification plays a critical role in neurological diseases. However, the exact role and association of m7G with the immune microenvironment in Alzheimer's disease (AD) remain largely unknown and unexplored.

Methods

The study datasets comprised 667 AD samples and 503 control samples selected from eight datasets in the Gene Expression Omnibus database; m7G regulator genes were obtained from previous literature. The AD subtypes were identified by consensus clustering analysis according to m7G regulator genes. The clinical characteristics, immune infiltration, and biological functions of the AD subgroups were evaluated. A combination of different types of machine-learning algorithms were used for the identification of AD genes. We also assessed and validated the diagnostic performance of the identified genes via qRT-PCR, immunofluorescence, and immunohistochemical analyses.

Results

Two AD distinct subgroups, namely cluster A and cluster B, were identified. Cluster A had poor pathological progression and immune infiltration, representing a high-risk subgroup for AD. The differentially expressed genes of cluster A were enriched in immune and synapse-related pathways, suggesting that these genes probably contribute to AD progression by regulating immune-related pathways. Additionally, five feature genes (AEBP1, CARTPT, AK5, NPTX2, and COPG2IT1) were identified, which were used to construct a nomogram model with good ability to predict AD. The animal experiment analyses further confirmed that these feature genes were associated with AD development.

Conclusion

To the best of our knowledge, this is the first study to reveal close correlations among m7G RNA modification, the immune microenvironment, and the pathogenesis of AD. We also identified five feature genes associated with AD, further contributing to our understanding of the underlying mechanisms and potential therapeutic targets for AD.

Analysis and experimental validation of necroptosis-related molecular classification, immune signature and feature genes in Alzheimer's disease

Necroptosis, a programmed cell death pathway, has been demonstrated to be activated in Alzheimer's disease (AD). However, the precise role of necroptosis and its correlation with immune cell infiltration in AD remains unclear. In this study, we conducted non-negative matrix factorization clustering analysis to identify three subtypes of AD based on necroptosis-relevant genes. Notably, these subtypes exhibited varying necroptosis scores, clinical characteristics and immune infiltration signatures. Cluster B, characterized by high necroptosis scores, showed higher immune cell infiltration and was associated with a more severe pathology, potentially representing a high-risk subgroup. To identify potential biomarkers for AD within cluster B, we employed two machine learning algorithms: the least absolute shrinkage and selection operator regression and Random Forest. Subsequently, we identified eight feature genes (CARTPT, KLHL35, NRN1, NT5DC3, PCYOX1L, RHOQ, SLC6A12, and SLC38A2) that were utilized to develop a diagnosis model with remarkable predictive capacity for AD. Moreover, we conducted validation using bulk RNA-seq, single-nucleus RNA-seq, and in vivo experiments to confirm the expression of these feature genes. In summary, our study identified a novel necroptosis-related subtype of AD and eight diagnostic biomarkers, explored the roles of necroptosis in AD progression and shed new light for the clinical diagnosis and treatment of this disease.

A review and analysis of key biomarkers in Alzheimer's disease

Alzheimer's disease (AD) is a progressive neurodegenerative disorder that affects over 50 million elderly individuals worldwide. Although the pathogenesis of AD is not fully understood, based on current research, researchers are able to identify potential biomarker genes and proteins that may serve as effective targets against AD. This article aims to present a comprehensive overview of recent advances in AD biomarker identification, with highlights on the use of various algorithms, the exploration of relevant biological processes, and the investigation of shared biomarkers with co-occurring diseases. Additionally, this article includes a statistical analysis of key genes reported in the research literature, and identifies the intersection with AD-related gene sets from databases such as AlzGen, GeneCard, and DisGeNet. For these gene sets, besides enrichment analysis, protein-protein interaction (PPI) networks utilized to identify central genes among the overlapping genes. Enrichment analysis, protein interaction network analysis, and tissue-specific connectedness analysis based on GTEx database performed on multiple groups of overlapping genes. Our work has laid the foundation for a better understanding of the molecular mechanisms of AD and more accurate identification of key AD markers.

Cathepsin B serves as a potential prognostic biomarker and correlates with ferroptosis in rheumatoid arthritis

BACKGROUND

Rheumatoid arthritis (RA) is a long-term, systemic, and progressive autoimmune disorder. It has been established that ferroptosis, a type of iron-dependent lipid peroxidation cell death, is closely associated with RA. Fibroblast-like synoviocytes (FLS) are the main drivers of RA joint destruction, and they possess a high concentration of endoplasmic reticulum structure. Therefore, targeting ferroptosis and RA-FLS may be a potential treatment for RA.

METHODS

Four machine learning algorithms were utilized to detect the essential genes linked to RA, and an XGBoost model was created based on the identified genes. SHAP values were then used to visualize the factors that affect the development and progression of RA, and to analyze the importance of individual features in predicting the outcomes. Moreover, WGCNA and PPI were employed to identify the key genes related to RA, and CIBERSORT was used to analyze the correlation between the chosen genes and immune cells. Finally, the findings were validated through in vitro cell experiments, such as CCK-8 assay, lipid peroxidation assay, iron assay, GSH assay, and Western blot.

RESULTS

Bioinformatics and machine learning were employed to identify cathepsin B (CTSB) as a potential biomarker for RA. CTSB is highly expressed in RA patients and has been found to have a positive correlation with macrophages M2, neutrophils, and T cell follicular helper cells, and a negative correlation with CD8 T cells, monocytes, Tregs, and CD4 memory T cells. To investigate the effect of CTSB on RA-FLS from RA patients, the CTSB inhibitor CA-074Me was used and it was observed to reduce the proliferation and migration of RA-FLS, as indicated by the accumulation of lipid ROS and ferrous ions, and induce ferroptosis in RA-FLS.

CONCLUSIONS

This study identified CTSB, a gene associated with ferroptosis, as a potential biomarker for diagnosing and managing RA. Moreover, CA-074Me, a CTSB inhibitor, was observed to cause ferroptosis and reduce the migratory capacity of RA-FLS.

Targeting GM2 Ganglioside Accumulation in Dementia: Current Therapeutic Approaches and Future Directions

Dementia in neurodegenerative diseases, such as Alzheimer's disease (AD), Parkinson's disease (PD), and dementia with Lewy bodies (DLB) is a progressive neurological condition affecting millions worldwide. The amphiphilic molecule GM2 gangliosides are abundant in the human brain and play important roles in neuronal development, intercellular recognition, myelin stabilization, and signal transduction. GM2 ganglioside's degradation requires hexosaminidase A (HexA), a heterodimer composed of an α subunit encoded by HEXA and a β subunit encoded by HEXB. The hydrolysis of GM2 also requires a non-enzymatic protein, the GM2 activator protein (GM2-AP), encoded by GM2A. Pathogenic mutations of HEXA, HEXB, and GM2A are responsible for autosomal recessive diseases known as GM2 gangliosidosis, caused by the excessive intralysosomal accumulation of GM2 gangliosides. In AD, PD and DLB, GM2 ganglioside accumulation is reported to facilitate Aβ and α-synuclein aggregation into toxic oligomers and plaques through activation of downstream signaling pathways, such as protein kinase C (PKC) and oxidative stress factors. This review explored the potential role of GM2 ganglioside alteration in toxic protein aggregations and its related signaling pathways leading to neurodegenerative diseases. Further review explored potential therapeutic approaches, which include synthetic and phytomolecules targeting GM2 ganglioside accumulation in the brain, holding a promise for providing new and effective management for dementia.

Aberrant Expressions of PSMD14 in Tumor Tissue are the Potential Prognostic Biomarkers for Hepatocellular Carcinoma after Curative Resection

Introduction

Hepatocellular carcinoma (HCC) has a high mortality rate, with curative resection being the primary treatment. However, HCC patients have a large possibility of recurrence within 5 years after curative resection.

Methods

Thus, identifying biomarkers to predict recurrence is crucial. In our study, we analyzed data from CCLE, GEO, and TCGA, identifying eight oncogenes associated with HCC. Subsequently, the expression of 8 genes was tested in 5 cases of tumor tissues and the adjacent non-tumor tissues. Then ATP6AP1, PSMD14 and HSP90AB1 were selected to verify the expression in 63 cases of tumor tissues and the adjacent non-tumor tissues. The results showed that ATP6AP1, PSMD14, HSP90AB1 were generally highly expressed in tumor tissues. A five-year follow-up of the 63 clinical cases, combined with Kaplan-Meier Plotter's relapse-free survival (RFS) analysis, found a significant correlation between PSMD14 expression and recurrence in HCC patients. Subsequently, we analyzed the PSMD14 mutations and found that the PSMD14 gene mutations can lead to a shorter disease-free survival time for HCC patients.

Results

The results of enrichment analysis indicated that the differentially expressed genes related to PSMD14 are mainly enriched in the signal release pathway.

Conclusion

In conclusion, our research showed that PSMD14 might be related to recurrence in HCC patients, and the expression of PSMD14 in tumor tissue might be a potential prognostic biomarker after tumor resection in HCC patients.

Machine learning identification and immune infiltration of disulfidptosis-related Alzheimer's disease molecular subtypes

BACKGROUND

Alzheimer's disease (AD) is a common neurodegenerative disorder. Disulfidptosis is a newly discovered form of programmed cell death that holds promise as a therapeutic strategy for various disorders. However, the functional roles of disulfidptosis-related genes (DRGs) in AD remain unknown.

METHODS

Microarray data and clinical information from patients with AD and healthy controls were downloaded from the Gene Expression Omnibus database. A thorough examination of DRG expression and immune characteristics in both groups was performed. Based on the identified DRGs, we performed an unsupervised clustering analysis to categorize the AD samples into various disulfidptosis-related molecular clusters. Weighted gene co-expression network analysis was performed to select hub genes specific to disulfidptosis-related AD clusters. The performances of various machine learning models were compared to determine the optimal predictive model. The predictive ability of the optimal model was assessed using nomogram analysis and five external datasets.

RESULTS

Eight DRGs showed differential expression between the AD and control samples. Two different molecular clusters were identified. The immune cell infiltration analysis revealed distinct differences in the immune microenvironment of the two clusters. The support vector machine model showed the highest performance, and a panel of five signature genes was identified, which showed excellent performance on the external validation datasets. The nomogram analysis also showed high accuracy in predicting AD.

CONCLUSION

We identified disulfidptosis-related molecular clusters in AD and established a novel risk model to assess the likelihood of developing AD. These findings revealed a complex association between disulfidptosis and AD, which may aid in identifying potential therapeutic targets for this debilitating disorder.

Identification of key lipid metabolism-related genes in Alzheimer's disease

BACKGROUND

Alzheimer's disease (AD) represents profound degenerative conditions of the brain that cause significant deterioration in memory and cognitive function. Despite extensive research on the significant contribution of lipid metabolism to AD progression, the precise mechanisms remain incompletely understood. Hence, this study aimed to identify key differentially expressed lipid metabolism-related genes (DELMRGs) in AD progression.

METHODS

Comprehensive analyses were performed to determine key DELMRGs in AD compared to controls in GSE122063 dataset from Gene Expression Omnibus. Additionally, the ssGSEA algorithm was utilized for estimating immune cell levels. Subsequently, correlations between key DELMRGs and each immune cell were calculated specifically in AD samples. The key DELMRGs expression levels were validated via two external datasets. Furthermore, gene set enrichment analysis (GSEA) was utilized for deriving associated pathways of key DELMRGs. Additionally, miRNA-TF regulatory networks of the key DELMRGs were constructed using the miRDB, NetworkAnalyst 3.0, and Cytoscape software. Finally, based on key DELMRGs, AD samples were further segmented into two subclusters via consensus clustering, and immune cell patterns and pathway differences between the two subclusters were examined.

RESULTS

Seventy up-regulated and 100 down-regulated DELMRGs were identified. Subsequently, three key DELMRGs (DLD, PLPP2, and PLAAT4) were determined utilizing three algorithms [(i) LASSO, (ii) SVM-RFE, and (iii) random forest]. Specifically, PLPP2 and PLAAT4 were up-regulated, while DLD exhibited downregulation in AD cerebral cortex tissue. This was validated in two separate external datasets (GSE132903 and GSE33000). The AD group exhibited significantly altered immune cell composition compared to controls. In addition, GSEA identified various pathways commonly associated with three key DELMRGs. Moreover, the regulatory network of miRNA-TF for key DELMRGs was established. Finally, significant differences in immune cell levels and several pathways were identified between the two subclusters.

CONCLUSION

This study identified DLD, PLPP2, and PLAAT4 as key DELMRGs in AD progression, providing novel insights for AD prevention/treatment.

Identification of metabolism-related subtypes and feature genes in Alzheimer's disease

BACKGROUND

Owing to the heterogeneity of Alzheimer's disease (AD), its pathogenic mechanisms are yet to be fully elucidated. Evidence suggests an important role of metabolism in the pathophysiology of AD. Herein, we identified the metabolism-related AD subtypes and feature genes.

METHODS

The AD datasets were obtained from the Gene Expression Omnibus database and the metabolism-relevant genes were downloaded from a previously published compilation. Consensus clustering was performed to identify the AD subclasses. The clinical characteristics, correlations with metabolic signatures, and immune infiltration of the AD subclasses were evaluated. Feature genes were screened using weighted correlation network analysis (WGCNA) and processed via Gene Ontology and Kyoto Encyclopedia of Genes and Genomes pathway analyses. Furthermore, three machine-learning algorithms were used to narrow down the selection of the feature genes. Finally, we identified the diagnostic value and expression of the feature genes using the AD dataset and quantitative reverse-transcription polymerase chain reaction (qRT-PCR) analysis.

RESULTS

Three AD subclasses were identified, namely Metabolism Correlated (MC) A (MCA), MCB, and MCC subclasses. MCA contained signatures associated with high AD progression and may represent a high-risk subclass compared with the other two subclasses. MCA exhibited a high expression of genes related to glycolysis, fructose, and galactose metabolism, whereas genes associated with the citrate cycle and pyruvate metabolism were downregulated and associated with high immune infiltration. Conversely, MCB was associated with citrate cycle genes and exhibited elevated expression of immune checkpoint genes. Using WGCNA, 101 metabolic genes were identified to exhibit the strongest association with poor AD progression. Finally, the application of machine-learning algorithms enabled us to successfully identify eight feature genes, which were employed to develop a nomogram model that could bring distinct clinical benefits for patients with AD. As indicated by the AD datasets and qRT-PCR analysis, these genes were intimately associated with AD progression.

CONCLUSION

Metabolic dysfunction is associated with AD. Hypothetical molecular subclasses of AD based on metabolic genes may provide new insights for developing individualized therapy for AD. The feature genes highly correlated with AD progression included GFAP, CYB5R3, DARS, KIAA0513, EZR, KCNC1, COLEC12, and TST.

Identification of mitochondrial related signature associated with immune microenvironment in Alzheimer's disease

BACKGROUND

Alzheimer's disease (AD) is the most common neurodegenerative disease. Mitochondrial dysfunction and immune responses are important factors in the pathogenesis of AD, but their crosstalk in AD has not been studied. In this study, the independent role and interaction of mitochondria-related genes and immune cell infiltration in AD were investigated using bioinformatics methods.

METHODS

The datasets of AD were obtained from NCBI Gene Expression Omnibus (GEO), and the data of mitochondrial genes was from MitoCarta3.0 database. Subsequently, differential expression genes (DEGs) screening and GSEA functional enrichment analysis were performed. The intersection of DEGs and mitochondrial related genes was used to obtain MitoDEGs. The MitoDEGs most relevant to AD were determined by Least absolute shrinkage and selection operator and multiple support vector machine recursive feature elimination, as well as protein-protein interactions (PPI) network and random forest. The infiltration of 28 kinds of immune cells in AD was analyzed by ssGSEA, and the relationship between hub MitoDEGs and the proportion of immune infiltration was studied. The expression levels of hub MitoDEGs were verified in cell models and AD mice, and the role of OPA1 in mitochondrial damage and neuronal apoptosis was investigated.

RESULTS

The functions and pathways of DEGs were significantly enriched in AD, including immune response activation, IL1R pathway, mitochondrial metabolism, oxidative damage response and electron transport chain-oxphos system in mitochondria. Hub MitoDEGs closely related to AD were obtained based on PPI network, random forest and two machine learning algorithms. Five hub MitoDEGs associated with neurological disorders were identified by biological function examination. The hub MitoDEGs were found to be correlated with memory B cell, effector memory CD8 T cell, activated dendritic cell, natural killer T cell, type 17 T helper cell, Neutrophil, MDSC, plasmacytoid dendritic cell. These genes can also be used to predict the risk of AD and have good diagnostic efficacy. In addition, the mRNA expression levels of BDH1, TRAP1, OPA1, DLD in cell models and AD mice were consistent with the results of bioinformatics analysis, and expression levels of SPG7 showed a downward trend. Meanwhile, OPA1 overexpression alleviated mitochondrial damage and neuronal apoptosis induced by Aβ1-42.

CONCLUSIONS

Five potential hub MitoDEGs most associated with AD were identified. Their interaction with immune microenvironment may play a crucial role in the occurrence and prognosis of AD, which provides a new insight for studying the potential pathogenesis of AD and exploring new targets.

Combined analysis of single-cell and bulk RNA sequencing reveals the expression patterns of circadian rhythm disruption in the immune microenvironment of Alzheimer's disease

Background

Circadian rhythm disruption (CRD) represents a critical contributor to the pathogenesis of Alzheimer's disease (AD). Nonetheless, how CRD functions within the AD immune microenvironment remains to be illustrated.

Methods

Circadian rhythm score (CRscore) was utilized to quantify the microenvironment status of circadian disruption in a single-cell RNA sequencing dataset derived from AD. Bulk transcriptome datasets from public repository were employed to validate the effectiveness and robustness of CRscore. A machine learning-based integrative model was applied for constructing a characteristic CRD signature, and RT-PCR analysis was employed to validate their expression levels.

Results

We depicted the heterogeneity in B cells, CD4⁺ T cells, and CD8⁺ T cells based on the CRscore. Furthermore, we discovered that CRD might be strongly linked to the immunological and biological features of AD, as well as the pseudotime trajectories of major immune cell subtypes. Additionally, cell-cell interactions revealed that CRD was critical in the alternation of ligand-receptor pairs. Bulk sequencing analysis indicated that the CRscore was found to be a reliable predictive biomarker in AD patients. The characteristic CRD signature, which included 9 circadian-related genes (CRGs), was an independent risk factor that accurately predicted the onset of AD. Meanwhile, abnormal expression of several characteristic CRGs, including GLRX, MEF2C, PSMA5, NR4A1, SEC61G, RGS1, and CEBPB, was detected in neurons treated with Aβ1-42 oligomer.

Conclusion

Our study revealed CRD-based cell subtypes in the AD microenvironment at single-cell level and proposed a robust and promising CRD signature for AD diagnosis. A deeper knowledge of these mechanisms may provide novel possibilities for incorporating "circadian rhythm-based anti-dementia therapies" into the treatment protocols of individualized medicine.