Construction and analysis of a joint diagnosis model of random forest and artificial neural network for heart failure

DEPDC1B, CDCA2, APOBEC3B, and TYMS are potential hub genes and therapeutic targets for diagnosing dialysis patients with heart failure

Introduction

Heart failure (HF) has a very high prevalence in patients with maintenance hemodialysis (MHD). However, there is still a lack of effective and reliable HF diagnostic markers and therapeutic targets for patients with MHD.

Methods

In this study, we analyzed transcriptome profiles of 30 patients with MHD by high-throughput sequencing. Firstly, the differential genes between HF group and control group of patients with MHD were screened. Secondly, HF-related genes were screened by WGCNA, and finally the genes intersecting the two were selected as candidate genes. Machine learning was used to identify hub gene and construct a nomogram model, which was verified by ROC curve and RT-qPCR. In addition, we further explored potential mechanism and function of hub genes in HF of patients with MHD through GSEA, immune cell infiltration analysis, drug analysis and establishment of molecular regulatory network.

Results

Totally 23 candidate genes were screened out by overlapping 673 differentially expressed genes (DEGs) and 147 key module genes, of which four hub genes (DEPDC1B, CDCA2, APOBEC3B and TYMS) were obtained by two machine learning algorithms. Through GSEA analysis, it was found that the four genes were closely related to ribosome, cell cycle, ubiquitin-mediated proteolysis. We constructed a ceRNA regulatory network, and found that 4 hub genes (TYMS, CDCA2 and DEPDC1B) might be regulated by 4 miRNAs (hsa-miR-1297, hsa-miR-4465, hsa-miR-27a-3p, hsa-miR-129-5p) and 21 lncRNAs (such as HCP5, CAS5, MEG3, HCG18). 24 small molecule drugs were predicted based on TYMS through DrugBank website. Finally, qRT-PCR experiments showed that the expression trend of biomarkers was consistent with the results of transcriptome sequencing.

Discussion

Overall, our results reveal the molecular mechanism of HF in patients with MHD and provide insights into potential diagnostic markers and therapeutic targets.

Identification of Key Genes Mediated by N6-Methyladenosine Methyltransferase METTL3 in Ischemic Stroke via Bioinformatics Analysis and Experiments

The N6-methyladenosine (m6A) methyltransferase METTL3 has been demonstrated to function in mediating m6A modification, but its role in ischemic stroke (IS) has not been fully elucidated. This study aimed to explore the downstream mechanism of METTL3-mediated m6A modification in IS. GSE16561 and GSE22255 were downloaded from the Gene Expression Omnibus database for analysis of differentially expressed genes (DEGs), and it was found that METTL3 mRNA was downregulated in IS. Then quantitative real-time polymerase chain reaction was used to verify the downregulation of METTL3 mRNA in the peripheral blood of IS patients and the cortexes of transient middle cerebral artery occlusion mice. By combining DEGs with the m6A-downregulated genes in GSE142386 which performed methylated RNA immunoprecipitation sequencing (MeRIP-seq) on METTL3-deficient and control endothelial cells, a total of 131 genes were identified as the METTL3-mediated m6A-modified genes in IS. Kyoto Encyclopedia of Genes and Genomes pathway enrichment analysis showed that the genes were mainly involved in cytokine-cytokine receptor interaction, MAPK signaling pathway and NF-kappa B signaling pathway. CTSS and SBK1 were further screened as the key METTL3-mediated m6A-modified genes by random forest model and PCR validation. The ROC curve analysis showed that the combination with CTSS and SBK1 was of good diagnostic value for IS, with the AUC of 0.810, sensitivity of 0.780, and specificity of 0.773. Overall, we found that METTL3-mediated m6A modification may influence the occurrence and development of IS by participating in inflammation-related biological processes, and two key m6A-modified genes mediated by METTL3 (CTSS and SBK1) can be used as diagnostic biomarkers for IS.

Comprehensive analysis of molecular mechanisms underlying kidney stones: gene expression profiles and potential diagnostic markers

Background

The study aimed to investigate the molecular mechanisms underlying kidney stones by analyzing gene expression profiles. They focused on identifying differentially expressed genes (DEGs), performing gene set enrichment analysis (GSEA), weighted gene co-expression network analysis (WGCNA), functional enrichment analysis, and screening optimal feature genes using various machine learning algorithms.

Methods

Data from the GSE73680 dataset, comprising normal renal papillary tissues and Randall's Plaque (RP) tissues, were downloaded from the GEO database. DEGs were identified using the limma R package, followed by GSEA and WGCNA to explore functional modules. Functional enrichment analysis was conducted using KEGG and Disease Ontology. Various machine learning algorithms were used for screening the most suitable feature genes, which were then assessed for their expression and diagnostic significance through Wilcoxon rank-sum tests and ROC curves. GSEA and correlation analysis were performed on optimal feature genes, and immune cell infiltration was assessed using the CIBERSORT algorithm.

Results

412 DEGs were identified, with 194 downregulated and 218 upregulated genes in kidney stone samples. GSEA revealed enriched pathways related to metabolic processes, immune response, and disease states. WGCNA identified modules correlated with kidney stones, particularly the yellow module. Functional enrichment analysis highlighted pathways involved in metabolism, immune response, and disease pathology. Through machine learning algorithms, KLK1 and MMP10 were identified as optimal feature genes, significantly upregulated in kidney stone samples, with high diagnostic value. GSEA further elucidated their biological functions and pathway associations.

Conclusion

The study comprehensively analyzed gene expression profiles to uncover molecular mechanisms underlying kidney stones. KLK1 and MMP10 were identified as potential diagnostic markers and key players in kidney stone progression. Functional enrichment analysis provided insights into their roles in metabolic processes, immune response, and disease pathology. These results contribute significantly to a better understanding of kidney stone pathogenesis and may inform future diagnostic and therapeutic strategies.

Evaluating ChatGPT platform in delivering heart failure educational material: A comparison with the leading national cardiology institutes

BACKGROUND

Patient education plays a crucial role in improving the quality of life for patients with heart failure. As artificial intelligence continues to advance, new chatbots are emerging as valuable tools across various aspects of life. One prominent example is ChatGPT, a widely used chatbot among the public. Our study aims to evaluate the readability of ChatGPT answers for common patients' questions about heart failure.

METHODS

We performed a comparative analysis between ChatGPT responses and existing heart failure educational materials from top US cardiology institutes. Validated readability calculators were employed to assess and compare the reading difficulty and grade level of the materials. Furthermore, blind assessment using The Patient Education Materials Assessment Tool (PEMAT) was done by four advanced heart failure attendings to evaluate the readability and actionability of each resource.

RESULTS

Our study revealed that responses generated by ChatGPT were longer and more challenging to read compared to other materials. Additionally, these responses were written at a higher educational level (undergraduate and 9-10th grade), similar to those from the Heart Failure Society of America. Despite achieving a competitive PEMAT readability score (75 %), surpassing the American Heart Association score (68 %), ChatGPT's actionability score was the lowest (66.7 %) among all materials included in our study.

CONCLUSION

Despite its current limitations, artificial intelligence chatbots has the potential to revolutionize the field of patient education especially given theirs ongoing improvements. However, further research is necessary to ensure the integrity and reliability of these chatbots before endorsing them as reliable resources for patient education.

Exploring the predictive values of SERP4 and FRZB in dilated cardiomyopathy based on an integrated analysis

BACKGROUND AND OBJECTIVE

The aim of this study was to investigate potential hub genes for dilated cardiomyopathy (DCM).

METHODS

Five DCM-related microarray datasets were downloaded from the Gene Expression Omnibus (GEO). Differentially expressed genes (DEGs) were used for identification. Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment, disease ontology, gene ontology annotation and protein-protein interaction (PPI) network analysis were then performed, while a random forest was constructed to explore central genes. Artificial neural networks were used to compare with known genes and to develop new diagnostic models. 240 population blood samples were collected and expression of hub genes was verified in these samples using RT-PCR and demonstrated by Nomogram.

RESULTS

After differential analysis, 33 genes were statistically significant (adjusted P < 0.05). Functional enrichment of these differential genes resulted in 85 Gene Ontology (GO) functions identified and 6 pathways enriched for the KEGG pathway. PPI networks and molecular complex assays identified 10 hub genes (adjusted P < 0.05). Random forest identified SMOC2 and SFRP4 as the most important, followed by FCER1G and FRZB. NeuraHF models (SMOC2, SFRP4, FCER1G and FRZB) were selected by artificial neural network model and had better diagnostic efficacy for the onset of DCM, compared with the traditional KG-DCM models (MYH7, ACTC1, TTN and LMNA). Finally, SFRP4 and FRZB were expressed higher in DCM verified by RT-PCR and as a factor for DCM identified by Nomogram.

CONCLUSIONS

We performed an integrated analysis and identified SFRP4 and FRZB as a new factor for DCM. But the exact mechanism still needs further experimental verification.

Identification and Analysis of Potential Biomarkers Associated with Neutrophil Extracellular Traps in Cervicitis

Early diagnosis of cervicitis is important. Previous studies have found that neutrophil extracellular traps (NETs) play pro-inflammatory and anti-inflammatory roles in many diseases, suggesting that they may be involved in the inflammation of the uterine cervix and NETs-related genes may serve as biomarkers of cervicitis. However, what NETs-related genes are associated with cervicitis remains to be determined. Transcriptome analysis was performed using samples of exfoliated cervical cells from 15 patients with cervicitis and 15 patients without cervicitis as the control group. First, the intersection of differentially expressed genes (DEGs) and neutrophil extracellular trap-related genes (NETRGs) were taken to obtain genes, followed by functional enrichment analysis. We obtained hub genes through two machine learning algorithms. We then performed Artificial Neural Network (ANN) and nomogram construction, confusion matrix, receiver operating characteristic (ROC), gene set enrichment analysis (GSEA), and immune cell infiltration analysis. Moreover, we constructed ceRNA network, mRNA-transcription factor (TF) network, and hub genes-drug network. We obtained 19 intersecting genes by intersecting 1398 DEGs and 136 NETRGs. 5 hub genes were obtained through 2 machine learning algorithms, namely PKM, ATG7, CTSG, RIPK3, and ENO1. Confusion matrix and ROC curve evaluation ANN model showed high accuracy and stability. A nomogram containing the 5 hub genes was established to assess the disease rate in patients. The correlation analysis revealed that the expression of ATG7 was synergistic with RIPK3. The GSEA showed that most of the hub genes were related to ECM receptor interactions. It was predicted that the ceRNA network contained 2 hub genes, 3 targeted miRNAs, and 27 targeted lnRNAs, and that 5 mRNAs were regulated by 28 TFs. In addition, 36 small molecule drugs that target hub genes may improve the treatment of cervicitis. In this study, five hub genes (PKM, ATG7, CTSG, RIPK3, ENO1) provided new directions for the diagnosis and treatment of patients with cervicitis.

m6A RNA methylation modification is involved in the disease course of heart failure

We explored N6-methyladenosine (m6A) RNA methylation as one of the gene regulatory mechanisms in heart failure (HF) biology. Understanding the different physiological mechanisms will facilitate the prevention and individualized treatment of HF. The Gene Expression Omnibus (GEO) database served as the source of the data. In GSE116250, differential analysis between ischemic cardiomyopathy (ICM), dilated cardiomyopathy (DCM) and controls yielded differentially expressed m6A regulators. Differential analysis between HF and controls in GSE131296 identifies m6A-modified genes and then performs enrichment analysis. Protein-protein interaction (PPI) network analysis was performed for the differentially expressed ICM- or DCM-associated genes in GSE116250 and GSE55296, respectively. Finally, the diagnostic genes for ICM and DCM were predicted using receiver operating characteristic (ROC) curve. YTHDC1, HNRNPC and HNRNPA2B1 were significantly downregulated in GSE116250 in DCM and ICM compared with controls. A total of 195 genes were identified in GSE131296 as subject to m6A alteration. These genes may play a role in HF through the MAPK signaling pathway and p53 signaling pathway. PPI network analysis identified CCL5, CXCR4 and CCL2 as key genes for ICM and IL-6 as a key gene for DCM. Through ROC curves, we identified m6A-modified APLP1, KLF2 as potential diagnostic genes for ICM, and m6A-modified FGF7, FREM1 and C14orf132 as potential diagnostic genes for DCM. Our findings support m6A modifying mechanisms in HF etiology that contribute to the treatment of HF. Thus, our data suggest that m6A methylation may be an interesting target for therapeutic intervention.

Identifying the risk of depression in a large sample of adolescents: An artificial neural network based on random forest

BACKGROUND

This study aims to develop an artificial neural network (ANN) prediction model incorporating random forest (RF) screening ability for predicting the risk of depression in adolescents and identifies key risk factors to provide a new approach for primary care screening of depression among adolescents.

METHODS

The data were from a large cross-sectional study conducted in China from July to September 2021, enrolling 8635 adolescents aged 10-17 with their parents. We used the Patient health questionnaire (PHQ-9) to rate adolescent depression symptoms, using scales and single-item questions to collect demographic information and other variables. Initial model variables screening used the RF importance assessment, followed by building prediction model using the screened variables through the ANN.

RESULTS

The rate of depression symptoms in adolescents was 24.6%, and the depression risk prediction model was built based on 70% of the training set and 30% of the test set. Ten variables were included in the final prediction model with a model accuracy of 85.03%, AUC of 0.892, specificity of 89.79%, and sensitivity of 70.81%. The top 10 significant factors of depression risk were adolescent rumination, adolescent self-esteem, adolescent mobile phone addiction, peer victimization, care in parenting styles, overprotection in parenting styles, academic pressure, conflict in parent-child relationship, parental rumination, and relationship between parents.

CONCLUSIONS

The ANN model based on the RF effectively identifies depression risk in adolescents and provides a methodological reference for large-scale primary screening. Cross-sectional studies and single-item scales limit further improvements in model accuracy.

Identification of potential therapeutic targets for plaque vulnerability based on an integrated analysis

BACKGROUND AND AIMS

This study aimed to explore potential hub genes and pathways of plaque vulnerability and to investigate possible therapeutic targets for acute coronary syndrome (ACS).

METHODS AND RESULTS

Four microarray datasets were downloaded from the Gene Expression Omnibus (GEO) database. Differentially expressed genes (DEGs), weighted gene coexpression networks (WGCNA) and immune cell infiltration analysis (IIA) were used to identify the genes for plaque vulnerability. Then, Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment, Disease Ontology, Gene Ontology annotation and protein-protein interaction (PPI) network analyses were performed to explore the hub genes. Random forest and artificial neural networks were constructed for validation. Furthermore, the CMap and Herb databases were employed to explore possible therapeutic targets. A total of 168 DEGs with an adjusted P < 0.05 and approximately 1974 IIA genes were identified in GSE62646. Three modules were detected and associated with CAD-Class, including 891 genes that can be found in GSE90074. After removing duplicates, 114 hub genes were used for functional analysis. GO functions identified 157 items, and 6 pathways were enriched for the KEGG pathway at adjusted P < 0.05 (false discovery rate, FDR set at < 0.05). Random forest and artificial neural network models were built based on the GSE48060 and GSE34822 datasets, respectively, to validate the previous hub genes. Five genes (GZMA, GZMB, KLRB1, KLRD1 and TRPM6) were selected, and only two of them (GZMA and GZMB) were screened as therapeutic targets in the CMap and Herb databases.

CONCLUSION

We performed a comprehensive analysis and validated GZMA and GZMB as a target for plaque vulnerability, which provides a therapeutic strategy for the prevention of ACS. However, whether it can be used as a predictor in blood samples requires further experimental verification.

The influence of climate and human factors on a regional heat island in the Zhengzhou metropolitan area, China

The development of urbanization and the establishment of metropolitan areas causes the urban heat island to cross the original single-city scale and form a regional heat island (RHI) with a larger influence range. Due to the decreasing distance between cities, there is an urgent need to reevaluate RHI for urban agglomerations, considering all cities instead of a conventional single-city perspective. The impact of climatic conditions and human factors on heat islands still lacks a general method and framework for systematic evaluation. Therefore, we used land and night light data as background conditions to study the diurnal and seasonal changes of heat islands in the Zhengzhou metropolitan area, China. Pearson correlation analysis and random forest regression analysis were then used to explore the influence of climatic conditions and human factors on RHI and its internal relationship. We found that the daytime RHI had strong spatial heterogeneity and seasonal differences from 2001 to 2020. The daytime RHI was stronger than nighttime in spring, summer, and autumn, and the nighttime RHI was stronger than daytime in winter. From spring to winter, RHI increased first and then decreased during the daytime, while the opposite was observed at night. In this study, temperature has a greater effect on daytime RHI; CO2 and NL have a greater effect on nighttime RHI. There was strong spatial heterogeneity in the effects of climatic conditions and human factors on the RHI, with climatic conditions contributing more to the daytime RHI in the northern mountainous areas, while human factors had a greater impact on the nighttime RHI in the main urban areas of each location. The results of this study highlight more targeted and informed strategies for RHI mitigation in the Zhengzhou metropolitan area and provide helpful insights into RHI evaluation in other urban agglomerations.

Investigating the progression of preeclampsia through a comprehensive analysis of genes associated with per- and polyfluoroalkyl substances

Per- and Polyfluoroalkyl Substances (PFAS) are synthetic chemicals utilized in the production of various products that possess water and dirt-repellent properties. Exposure to PFAS has been linked to numerous diseases, such as cancer and preeclampsia (PE). However, whether PFAS contributes to the advancement of PE remains uncertain. In this study, we conducted an extensive bioinformatics analysis using the Comparative Toxicogenomics Database (CTD) and Gene Expression Omnibus (GEO) databases, leading us to discover a connection between PE and four specific PFAS. Moreover, further examination revealed that six genes associated with PFAS exhibited significant diagnostic potential for individuals with PE. By employing receiver operating characteristic (ROC) curves, our PFAS-related gene-based nomogram model demonstrated outstanding predictive efficacy for diagnosing PE. Immune infiltration analysis showed that six PFAS-related genes were significantly associated with the level of immune cell infiltration. The expression of PFAS-related genes in PE patients was confirmed by collecting clinical samples. This research has offered fresh perspectives on comprehending the impact of PFAS on PE, drawing attention to the connection between environmental factors and the risks and development of PE.

Experimental validation and comprehensive analysis of m6A methylation regulators in intervertebral disc degeneration subpopulation classification

Intervertebral disc degeneration (IVDD) is one of the most prevalent causes of chronic low back pain. The role of m6A methylation modification in disc degeneration (IVDD) remains unclear. We investigated immune-related m6A methylation regulators as IVDD biomarkers through comprehensive analysis and experimental validation of m6A methylation regulators in disc degeneration. The training dataset was downloaded from the GEO database and analysed for differentially expressed m6A methylation regulators and immunological features, the differentially regulators were subsequently validated by a rat IVDD model and RT-qPCR. Further screening of key m6A methylation regulators based on machine learning and LASSO regression analysis. Thereafter, a predictive model based on key m6A methylation regulators was constructed for training sets, which was validated by validation set. IVDD patients were then clustered based on the expression of key m6A regulators, and the expression of key m6A regulators and immune infiltrates between clusters was investigated to determine immune markers in IVDD. Finally, we investigated the potential role of the immune marker in IVDD through enrichment analysis, protein-to-protein network analysis, and molecular prediction. By analysising of the training set, we revealed significant differences in gene expression of five methylation regulators including RBM15, YTHDC1, YTHDF3, HNRNPA2B1 and ALKBH5, while finding characteristic immune infiltration of differentially expressed genes, the result was validated by PCR. We then screen the differential m6A regulators in the training set and identified RBM15 and YTHDC1 as key m6A regulators. We then used RBM15 and YTHDC1 to construct a predictive model for IVDD and successfully validated it in the training set. Next, we clustered IVDD patients based on the expression of RBM15 and YTHDC1 and explored the immune infiltration characteristics between clusters as well as the expression of RBM15 and YTHDC1 in the clusters. YTHDC1 was finally identified as an immune biomarker for IVDD. We finally found that YTHDC1 may influence the immune microenvironment of IVDD through ABL1 and TXK. In summary, our results suggest that YTHDC1 is a potential biomarker for the development of IVDD and may provide new insights for the precise prevention and treatment of IVDD.

Construction of a diagnostic model based on random forest and artificial neural network for peri-implantitis

OBJECTIVES

This study aimed to reveal critical genes regulating peri-implantitis during its development and construct a diagnostic model by using random forest (RF) and artificial neural network (ANN).

METHODS

GSE-33774, GSE106090, and GSE57631 datasets were obtained from the GEO database. The GSE33774 and GSE106090 datasets were analyzed for differential expression and functional enrichment. The protein-protein interaction networks (PPI) and RF screened vital genes. A diagnostic model for peri-implantitis was established using ANN and validated on the GSE33774 and GSE57631 datasets. A transcription factor-gene interaction network and a transcription factor-micro-RNA (miRNA) regulatory network were also established.

RESULTS

A total of 124 differentially expressed genes (DEGs) involved in the regulation of peri-implantitis were screened. Enrichment analysis showed that DEGs were mainly associated with immune receptor activity and cytokine receptor activity and were mainly involved in processes such as leukocyte and neutrophil migration. The PPI and RF screened six essential genes, namely, CD38, CYBB, FCGR2A, SELL, TLR4, and CXCL8. The receiver operating characteristic curve (ROC) indicated that the ANN model had an excellent diagnostic performance. FOXC1, GATA2, and NF-κB1 may be essential transcription factors in peri-implantitis, and hsa-miR-204 may be a key miRNA.

CONCLUSIONS

The diagnostic model of peri-implantitis constructed by RF and ANN has high confidence, and CD38, CYBB, FCGR2A, SELL, TLR4, and CXCL8 are potential diagnostic markers. FOXC1, GATA2, and NF-κB1 may be essential transcription factors in peri-implantitis, and hsa-miR-204 plays a vital role as a critical miRNA.

An assessment system for clinical and biological interpretability in ulcerative colitis

Ulcerative colitis (UC) is a serious inflammatory bowel disease (IBD) with high morbidity and mortality worldwide. As the traditional diagnostic techniques have various limitations in the practice and diagnosis of early ulcerative colitis, it is necessary to develop new diagnostic models from molecular biology to supplement the existing methods. In this study, we developed a machine learning-based synthesis to construct an artificial intelligence diagnostic model for ulcerative colitis, and the correctness of the model is verified using an external independent dataset. According to the significantly expressed genes related to the occurrence of UC in the model, an unsupervised quantitative ulcerative colitis related score (UCRScore) based on principal coordinate analysis was established. The UCRScore is not only highly generalizable across UC bulk cohorts at different stages, but also highly generalizable across single-cell datasets, with the same effect in terms of cell numbers, activation pathways and mechanisms. As an important role of screening genes in disease occurrence, based on connectivity map analysis, 5 potential targeting molecular compounds were identified, which can be used as an additional supplement to the therapeutic of UC. Overall, this study provides a potential tool for differential diagnosis and assessment of bio-pathological changes in UC at the macroscopic level, providing an opportunity to optimize the diagnosis and treatment of UC.

Identification of diagnostic model in heart failure with myocardial fibrosis and conduction block by integrated gene co-expression network analysis

BACKGROUND

Despite the advancements in heart failure(HF) research, the early diagnosis of HF continues to be a challenging issue in clinical practice. This study aims to investigate the genes related to myocardial fibrosis and conduction block, with the goal of developing a diagnostic model for early treatment of HF in patients.

METHOD

The gene expression profiles of GSE57345, GSE16499, and GSE9128 were obtained from the Gene Expression Omnibus (GEO) database. After merging the expression profile data and adjusting for batch effects, differentially expressed genes (DEGs) associated with conduction block and myocardial fibrosis were identified. Gene Ontology (GO) resources, Kyoto Encyclopedia of Genes and Genomes (KEGG) resources, and gene set enrichment analysis (GSEA) were utilized for functional enrichment analysis. A protein-protein interaction network (PPI) was constructed using a string database. Potential key genes were selected based on the bioinformatics information mentioned above. SVM and LASSO were employed to identify hub genes and construct the module associated with HF. The mRNA levels of TAC mice and external datasets (GSE141910 and GSE59867) are utilized for validating the diagnostic model. Additionally, the study explores the relationship between the diagnostic model and immune cell infiltration.

RESULTS

A total of 395 genes exhibiting differential expression were identified. Functional enrichment analysis revealed that these specific genes primarily participate in biological processes and pathways associated with the constituents of the extracellular matrix (ECM), immune system processes, and inflammatory responses. We identified a diagnostic model consisting of 16 hub genes, and its predictive performance was validated using external data sets and a transverse aortic coarctation (TAC) mouse model. In addition, we observed significant differences in mRNA expression of 7 genes in the TAC mouse model. Interestingly, our study also unveiled a correlation between these model genes and immune cell infiltration.

CONCLUSIONS

We identified sixteen key genes associated with myocardial fibrosis and conduction block, as well as diagnostic models for heart failure. Our findings have significant implications for the intensive management of individuals with potential genetic variants associated with heart failure, especially in the context of advancing cell-targeted therapy for myocardial fibrosis.

Integrated Bioinformatics Analysis Reveals Diagnostic Biomarkers and Immune Cell Infiltration Characteristics of Solar Lentigines

Background

Solar lentigines (SLs), serving as a prevalent characteristic of skin photoaging, present as cutaneous aberrant pigmentation. However, the underlying pathogenesis remains unclear and there is a dearth of reliable diagnostic biomarkers.

Objective

The aim of this study was to identify diagnostic biomarkers for SLs and reveal its immunological features.

Methods

In this study, gene expression profiling datasets (GSE192564 and GSE192565) of SLs were obtained from the GEO database. The GSE192564 was used as the training group for screening of differentially expressed genes (DEGs) and subsequent depth analysis. Gene set enrichment analysis (GSEA) was employed to explore the biological states associated with SLs. The weighted gene co-expression network analysis (WGCNA) was employed to identify the significant modules and hub genes. Then, the feature genes were further screened by the overlapping of hub genes and up-regulated differential genes. Subsequently, an artificial neural network was constructed for identifying SLs samples. The GSE192565 was used as the test group for validation of feature genes expression level and the model's classification performance. Furthermore, we conducted immune cell infiltration analysis to reveal the immune infiltration landscape of SLs.

Results

The 9 feature genes were identified as diagnostic biomarkers for SLs in this study. And an artificial neural network based on diagnostic biomarkers was successfully constructed for identification of SLs. GSEA highlighted potential role of immune system in pathogenesis of SLs. SLs samples had a higher proportion of several immune cells, including activated CD8 T cell, dendritic cell, myeloid-derived suppressor cell and so on. And diagnostic biomarkers exhibited a strong relationship with the infiltration of most immune cells.

Conclusion

Our study identified diagnostic biomarkers for SLs and explored its immunological features, enhancing the comprehension of its pathogenesis.

Characterizing the metabolic divide: distinctive metabolites differentiating CAD-T2DM from CAD patients

OBJECTIVE

To delineate the metabolomic differences in plasma samples between patients with coronary artery disease (CAD) and those with concomitant CAD and type 2 diabetes mellitus (T2DM), and to pinpoint distinctive metabolites indicative of T2DM risk.

METHOD

Plasma samples from CAD and CAD-T2DM patients across three centers underwent comprehensive metabolomic and lipidomic analyses. Multivariate logistic regression was employed to discern the relationship between the identified metabolites and T2DM risk. Characteristic metabolites' metabolic impacts were further probed through hepatocyte cellular experiments. Subsequent transcriptomic analyses elucidated the potential target sites explaining the metabolic actions of these metabolites.

RESULTS

Metabolomic analysis revealed 192 and 95 significantly altered profiles in the discovery (FDR < 0.05) and validation (P < 0.05) cohorts, respectively, that were associated with T2DM risk in univariate logistic regression. Further multivariate regression analyses identified 22 characteristic metabolites consistently associated with T2DM risk in both cohorts. Notably, pipecolinic acid and L-pipecolic acid, lysine derivatives, exhibited negative association with CAD-T2DM and influenced cellular glucose metabolism in hepatocytes. Transcriptomic insights shed light on potential metabolic action sites of these metabolites.

CONCLUSIONS

This research underscores the metabolic disparities between CAD and CAD-T2DM patients, spotlighting the protective attributes of pipecolinic acid and L-pipecolic acid. The comprehensive metabolomic and transcriptomic findings provide novel insights into the mechanism research, prophylaxis and treatment of comorbidity of CAD and T2DM.

Identification and exploration of aging-related subtypes and distinctive role of SERPINE1 in heart failure based on single-cell and bulk RNA sequencing data

Aging is a major risk factor for heart failure (HF) and is the leading cause of death worldwide. Currently, the nature of the relationship between aging and HF is not entirely clear. Herein, this study aimed to explore new diagnostic biomarkers, molecular typing and therapeutic strategies for HF by investigating the biological significance of aging-related genes in HF. A total of 157 differentially expressed genes (DEGs) were screened totally between HF and normal samples, and functional enrichment analysis of DEGs revealed the strong association of HF progression with aging, immune processes and metabolism. Six HF-specific aging-related genes were further identified, and a diagnostic model was developed and validated for good diagnostic efficacy. In addition, we collected blood samples from 10 normal controls and 10 HF patients for RT-qPCR analysis to verify the bioinformation. We also identified two aging-associated subtypes with distinctly different immune infiltration and metabolic microenvironment. Further single-cell sequencing analysis conducted in the study identified SERPINE1 as a key gene in HF. The distinctive role of SERPINE1 fibroblasts was revealed, including three main findings: (I) fibroblasts had a higher proportion and expression of SERPINE1 levels in HF; (II) the ligand-receptor pair MDK-LRP1 made the most contributions in high interactions with other cell types in SERPINE1 fibroblasts; and (III) SERPINE1 fibroblasts were associated with the interaction of extracellular matrix and receptor and may be regulated by the transcription factor EGR1. In conclusion, this study highlights the importance of aging-related genes in diagnosing HF and regulating immune infiltration. We also identified different HF subtypes and a potentially crucial gene, which may provide a better understanding of the molecular-level mechanisms of aging-related HF and aid in developing effective therapeutic strategies.

Current Insights and Future Directions in the Treatment of Heart Failure with Preserved Ejection Fraction

Heart failure is a clinical syndrome associated with poor quality of life, substantial healthcare resource utilization, and premature mortality, in large part related to high rates of hospitalizations. The clinical manifestations of heart failure are similar regardless of the ejection fraction. Unlike heart failure with reduced ejection fraction, there are few therapeutic options for treating heart failure with preserved ejection fraction. Molecular therapies that have shown reduced mortality and morbidity in heart failure with reduced ejection have not been proven to be effective for patients with heart failure and preserved ejection fraction. The study of pathophysiological processes involved in the production of heart failure with preserved ejection fraction is the basis for identifying new therapeutic means. In this narrative review, we intend to synthesize the existing therapeutic means, but also those under research (metabolic and microRNA therapy) for the treatment of heart failure with preserved ejection fraction.

Identification and validation of key biomarkers associated with macrophages in nonalcoholic fatty liver disease based on hdWGCNA and machine learning

BACKGROUND

NAFLD has attracted increasing attention because of its high prevalence and risk of progression to cirrhosis or even hepatocellular carcinoma. Therefore, research into the root causes and molecular indicators of NAFLD is crucial.

METHODS

We analyzed scRNA-seq data and RNA-seq data from normal and NAFLD liver samples. We utilized hdWGCNA to find module-related genes associated with the phenotype. Multiple machine learning algorithms were used to validate the model diagnostics and further screen for genes that are characteristic of NAFLD. The NAFLD mouse model was constructed using the MCD diet to validate the diagnostic effect of the genes.

RESULTS

We identified a specific macrophage population called NASH-macrophages by single-cell sequencing analysis. Cell communication analysis and Pseudo-time trajectory analysis revealed the specific role and temporal distribution of NASH-macrophages in NAFLD. The hdWGCNA screening yielded 30 genes associated with NASH-macrophages, and machine learning algorithms screened and obtained two genes characterizing NAFLD. The immune infiltration indicated that these genes were highly associated with macrophages. Notably, we verified by RT-qPCR, IHC, and WB that MAFB and CX3CR1 are highly expressed in the MCD mouse model and may play important roles.

CONCLUSIONS

Our study revealed a macrophage population that is closely associated with NAFLD. Using hdWGCNA analysis and multiple machine learning algorithms, we identified two NAFLD signature genes that are highly correlated with macrophages. Our findings may provide potential feature markers and therapeutic targets for NAFLD.

Fusing WGCNA and Machine Learning for Immune-Related Gene Prognostic Index in Lung Adenocarcinoma: Precision Prognosis, Tumor Microenvironment Profiling, and Biomarker Discovery

Background

The objective is to create an IRGPI (Immune-related genes prognostic index), which could predict the survival and effectiveness of immune checkpoint inhibitor (ICI) treatment for lung adenocarcinoma (LUAD).

Methods

By applying weighted gene co-expression network analysis (WGCNA), we ascertained 13 genes associated with immune functions. An IRGPI was constructed using four genes through multicox regression, and its validity was assessed in the GEO dataset. Next, we explored the immunological and molecular attributes and advantages of ICI treatment in subcategories delineated by IRGPI. The model genes were also validated by the random forest tree, and functional experiments were conducted to validate it.

Results

The IRGPI relied on the genes CD79A, IL11, CTLA-4, and CD27. Individuals categorized as low-risk exhibited significantly improved overall survival in comparison to those classified as high-risk. Extensive findings indicated that the low-risk category exhibited associations with immune pathways, significant infiltration of CD8 T cells, M1 macrophages, and CD4 T cells, a reduced rate of gene mutations, and improved sensitivity to ICI therapy. Conversely, the higher-risk group displayed metabolic signals, elevated frequencies of TP53, KRAS, and KEAP1 mutations, escalated levels of NK cells, M0, and M2 macrophage infiltration, and a diminished response to ICI therapy. Additionally, our study unveiled that the downregulation of IL11 effectively impedes the proliferation and migration of lung carcinoma cells, while also inducing cell cycle arrest.

Conclusion

IRGPI is a biomarker with significant potential for predicting the effectiveness of ICI treatment in LUAD patients and is closely related to the microenvironment and clinicopathological characteristics.

The relationship between symptom perception and fear of progression in patients with chronic heart failure: a multiple mediation analysis

AIMS

Studies have shown that symptom perception is associated with fear of progression (FOP) in many diseases and regulated by psychological factors. Whether the association also occurs in patients with chronic heart failure (HF) remains unclear, as do the specific mechanisms involved. This study aimed to explore the multiple mediation effects of self-care confidence and mental resilience on the relationship between symptom perception and FOP in Chinese patients with chronic HF.

METHODS AND RESULTS

A cross-sectional study was conducted on 247 patients with chronic HF recruited from two hospitals in Yangzhou, China. The sociodemographic and clinical data and self-reported questionnaires including heart failure somatic perception, fear of progression, self-care confidence, and mental resilience were collected. Data analysis relating to correlations and mediating effects was carried out by SPSS 26.0 and PROCESS v3.3 macro. Fear of progression was positively correlated with symptom perception (r = 0.599, P < 0.01), but negatively correlated with self-care confidence (r = -0.663, P < 0.01), mental resilience-strength (r = -0.521, P < 0.01), and mental resilience-toughness (r = -0.596, P < 0.01). The relationship between symptom perception and FOP was mediated by self-care confidence [effect = 0.095, 95% confidence interval (CI) (0.054-0.142)] and mental resilience-toughness [effect = 0.033, 95% CI (0.006-0.074)], respectively, and together in serial [effect = 0.028, 95% CI (0.011-0.050)]. The proportion of the mediating effect accounting for the total effect was 31.0%.

CONCLUSION

Self-care confidence and mental resilience-toughness were multiple mediators of the association between symptom perception and FOP in patients with chronic HF. Interventions targeted at strengthening self-care confidence and mental resilience may be beneficial for the reduction of FOP, especially with regard to toughness.

Prediction of the risk of cytopenia in hospitalized HIV/AIDS patients using machine learning methods based on electronic medical records

Background

Cytopenia is a frequent complication among HIV-infected patients who require hospitalization. It can have a negative impact on the treatment outcomes for these patients. However, by leveraging machine learning techniques and electronic medical records, a predictive model can be developed to evaluate the risk of cytopenia during hospitalization in HIV patients. Such a model is crucial for designing a more individualized and evidence-based treatment strategy for HIV patients.

Method

The present study was conducted on HIV patients who were admitted to Guangxi Chest Hospital between June 2016 and October 2021. We extracted a total of 66 clinical features from the electronic medical records and employed them to train five machine learning prediction models (artificial neural network [ANN], adaptive boosting [AdaBoost], k-nearest neighbour [KNN] and support vector machine [SVM], decision tree [DT]). The models were tested using 20% of the data. The performance of the models was evaluated using indicators such as the area under the receiver operating characteristic curve (AUC). The best predictive models were interpreted using the shapley additive explanation (SHAP).

Result

The ANN models have better predictive power. According to the SHAP interpretation of the ANN model, hypoproteinemia and cancer were the most important predictive features of cytopenia in HIV hospitalized patients. Meanwhile, the lower hemoglobin-to-RDW ratio (HGB/RDW), low-density lipoprotein cholesterol (LDL-C) levels, CD4+ T cell counts, and creatinine clearance (Ccr) levels increase the risk of cytopenia in HIV hospitalized patients.

Conclusion

The present study constructed a risk prediction model for cytopenia in HIV patients during hospitalization with machine learning and electronic medical record information. The prediction model is important for the rational management of HIV hospitalized patients and the personalized treatment plan setting.

Construction of diagnostic and prognostic models based on gene signatures of nasopharyngeal carcinoma by machine learning methods

Background

Diagnostic models based on gene signatures of nasopharyngeal carcinoma (NPC) were constructed by random forest (RF) and artificial neural network (ANN) algorithms. Least absolute shrinkage and selection operator (Lasso)-Cox regression was used to select and build prognostic models based on gene signatures. This study contributes to the early diagnosis and treatment, prognosis, and molecular mechanisms associated with NPC.

Methods

Two gene expression datasets were downloaded from the Gene Expression Omnibus (GEO) database, and differentially expressed genes (DEGs) associated with NPC were identified by gene expression differential analysis. Subsequently, significant DEGs were identified by a RF algorithm. ANN were used to construct a diagnostic model for NPC. The performance of the diagnostic model was evaluated by area under the curve (AUC) values using a validation set. Lasso-Cox regression examined gene signatures associated with prognosis. Overall survival (OS) and disease-free survival (DFS) prediction models were constructed and validated from The Cancer Genome Atlas (TCGA) database and the International Cancer Genome Consortium (ICGC) database.

Results

A total of 582 DEGs associated with NPC were identified, and 14 significant genes were identified by the RF algorithm. A diagnostic model for NPC was successfully constructed using ANN, and the validity of the model was confirmed on the training set AUC =0.947 [95% confidence interval (CI): 0.911-0.969] and the validation set AUC =0.864 (95% CI: 0.828-0.901). The 24-gene signatures associated with prognosis were identified by Lasso-Cox regression, and prediction models for OS and DFS of NPC were constructed on the training set. Finally, the ability of the model was validated on the validation set.

Conclusions

Several potential gene signatures associated with NPC were identified, and a high-performance predictive model for early diagnosis of NPC and a prognostic prediction model with robust performance were successfully developed. The results of this study provide valuable references for early diagnosis, screening, treatment and molecular mechanism research of NPC in the future.

Pyroptosis patterns influence the clinical outcome and immune microenvironment characterization in HPV-positive head and neck squamous cell carcinoma

BACKGROUND

Head and neck squamous cell carcinoma (HNSCC) is a heterogeneous tumor with diverse molecular pathological profiles. Recent studies have suggested the vital role of pyroptosis in tumor microenvironment. However, the expression patterns of pyroptosis in HPV-positive HNSCC are still unclear.

METHODS

Unsupervised clustering analysis was used to identify the pyroptosis patterns based on the RNA-sequencing data of 27 pyroptosis-related genes (PRGs) in HPV-positive HNSCC samples. Random forest classifier and artificial neural network were performed to screen the signature genes associated with pyroptosis, which were verified in two independent external cohorts and qRT-PCR experiment. Principal component analysis was used to develop a scoring system, namely Pyroscore.

RESULTS

The expression variations of 27 PRGs in HPV-positive HNSCC patients were analyzed from genomic and transcriptional domains. Two pyroptosis-related subtypes with distinct clinical outcomes, enrichment pathways and immune characteristics were identified. Next, six signature genes (GZMB, LAG3, NKG7, PRF1, GZMA and GZMH) associated with pyroptosis were selected for prognostic prediction. Further, a Pyroscore system was constructed to determine the level of pyroptosis in each patient. A low Pyroscore was featured by better survival time, increased immune cell infiltration, higher expression of immune checkpoint molecules and T cell-inflamed genes, as well as elevated mutational burden. The Pyroscore was also related to the sensitivity of chemotherapeutic agents.

CONCLUSIONS

The pyroptosis-related signature genes and Pyroscore system may be reliable predictors of prognosis and serve as mediators of immune microenvironment in patients with HPV-positive HNSCC.

An artificial neural network model to diagnose non-obstructive azoospermia based on RNA-binding protein-related genes

Non-obstructive azoospermia (NOA) is a severe form of male infertility, but its pathological mechanisms and diagnostic biomarkers remain obscure. Since the dysregulation of RNA-binding proteins (RBPs) had nonnegligible effects on spermatogenesis, we aimed to investigate the functions and diagnosis values of RBPs in NOA. 58 testicular samples (control = 11, NOA = 47) from Gene Expression Omnibus (GEO) were set as the training cohort. Three public datasets, containing GSE45885 (control = 4, NOA = 27), GSE45887 (control = 4, NOA = 16), and GSE145467 (control = 10, NOA = 10), and 44 clinical samples from the local hospital (control = 27, NOA = 17) were used for validation. Through a series of bioinformatical analyses and machine learning algorithms, including genomic difference detection, protein-protein interaction network analysis, LASSO, SVM-RFE, and Boruta, DDX20 and NCBP2 were determined as significant predictors of NOA. Single-cell RNA sequencing of 432 testicular cell samples from NOA patients indicated that DDX20 and NCBP2 were associated with spermatogenesis (false discovery rate < 0.05). Based on the transcriptome expressions of DDX20 and NCBP2, we constructed multiple diagnosis models using logistic regression, random forest, and artificial neural network (ANN). The ANN model exhibited the most reliable predictive performance in the training cohort (AUC = 0.840), GSE45885 (AUC = 0.731), GSE45887 (AUC = 0.781), GSE145467 (AUC = 0.850), and local cohort (AUC = 0.623). Totally, an ANN diagnosis model based on RBP DDX20 and NCBP2 was developed and externally validated in NOA, functioning as a promising tool in clinical practice.

Identification MNS1, FRZB, OGN, LUM, SERP1NA3 and FCN3 as the potential immune-related key genes involved in ischaemic cardiomyopathy by random forest and nomogram

The immune molecular mechanisms involved in ischaemic cardiomyopathy (ICM) have not been fully elucidated. The current study aimed to elucidate the immune cell infiltration pattern of the ICM and identify key immune-related genes that participate in the pathologic process of the ICM. The differentially expressed genes (DEGs) were identified from two datasets (GSE42955 combined with GSE57338) and the top 8 key DEGs related to ICM were screened using random forest and used to construct the nomogram model. Moreover, the "CIBERSORT" software package was used to determine the proportion of infiltrating immune cells in the ICM. A total of 39 DEGs (18 upregulated and 21 downregulated) were identified in the current study. Four upregulated DEGs, including MNS1, FRZB, OGN, and LUM, and four downregulated DEGs, SERP1NA3, RNASE2, FCN3 and SLCO4A1, were identified by the random forest model. The nomogram constructed based on the above 8 key genes suggested a diagnostic value of up to 99% to distinguish the ICM from healthy participants. Meanwhile, most of the key DEGs presented prominent interactions with immune cell infiltrates. The RT-qPCR results suggested that the expression levels of MNS1, FRZB, OGN, LUM, SERP1NA3 and FCN3 between the ICM and control groups were consistent with the bioinformatic analysis results. These results suggested that immune cell infiltration plays a critical role in the occurrence and progression of ICM. Several key immune-related genes, including the MNS1, FRZB, OGN, LUM, SERP1NA3 and FCN3 genes, are expected to be reliable serum markers for the diagnosis of ICM and potential molecular targets for ICM immunotherapy.

Identification of m6A regulator-mediated RNA methylation modification patterns and key immune-related genes involved in atrial fibrillation

The role of m6A in the regulation of the immune microenvironment in atrial fibrillation (AF) remains unclear. This study systematically evaluated the RNA modification patterns mediated by differential m6A regulators in 62 AF samples, identified the pattern of immune cell infiltration in AF and identified several immune-related genes associated with AF. A total of six key differential m6A regulators between healthy subjects and AF patients were identified by the random forest classifier. Three distinct RNA modification patterns (m6A cluster-A, -B and -C) among AF samples were identified based on the expression of 6 key m6A regulators. Differential infiltrating immune cells and HALLMARKS signaling pathways between normal and AF samples as well as among samples with three distinct m6A modification patterns were identified. A total of 16 overlapping key genes were identified by weighted gene coexpression network analysis (WGCNA) combined with two machine learning methods. The expression levels of the NCF2 and HCST genes were different between controls and AF patient samples as well as among samples with the distinct m6A modification patterns. RT-qPCR also proved that the expression of NCF2 and HCST was significantly increased in AF patients compared with control participants. These results suggested that m6A modification plays a key role in the complexity and diversity of the immune microenvironment of AF. Immunotyping of patients with AF will help to develop more accurate immunotherapy strategies for those with a significant immune response. The NCF2 and HCST genes may be novel biomarkers for the accurate diagnosis and immunotherapy of AF.

Machine learning-based integration develops biomarkers initial the crosstalk between inflammation and immune in acute myocardial infarction patients

Great strides have been made in past years toward revealing the pathogenesis of acute myocardial infarction (AMI). However, the prognosis did not meet satisfactory expectations. Considering the importance of early diagnosis in AMI, biomarkers with high sensitivity and accuracy are urgently needed. On the other hand, the prevalence of AMI worldwide has rapidly increased over the last few years, especially after the outbreak of COVID-19. Thus, in addition to the classical risk factors for AMI, such as overwork, agitation, overeating, cold irritation, constipation, smoking, and alcohol addiction, viral infections triggers have been considered. Immune cells play pivotal roles in the innate immunosurveillance of viral infections. So, immunotherapies might serve as a potential preventive or therapeutic approach, sparking new hope for patients with AMI. An era of artificial intelligence has led to the development of numerous machine learning algorithms. In this study, we integrated multiple machine learning algorithms for the identification of novel diagnostic biomarkers for AMI. Then, the possible association between critical genes and immune cell infiltration status was characterized for improving the diagnosis and treatment of AMI patients.

The Core-Targeted RRM2 Gene of Berberine Hydrochloride Promotes Breast Cancer Cell Migration and Invasion via the Epithelial-Mesenchymal Transition

Berberine hydrochloride (BBR) could inhibit the proliferation, migration, and invasion of various cancer cells. As the only enzyme for the de novo synthesis of ribonucleotides, RRM2 is closely related to the development of tumorigenesis. However, not much is currently known about the functional roles of RRM2 in breast cancer (BRCA), and whether BBR regulates the migration and invasion of BRCA cells by regulating the expression of RRM2 remains to be determined. We study the effects of BBR on BRCA cell proliferation in vitro and tumorigenesis in vivo by using colony formation assays, EdU assays, and xenograft models. Transcriptome sequencing, the random forest algorithm, and KEGG analysis were utilized to explore the therapeutic target genes and relative pathways. The expression of RRM2 in BRCA patients was analyzed with The Cancer Genome Atlas (TCGA) dataset, the GEPIA website tool, the Gene Expression Omnibus (GEO) database, and the UALCAN database. The survival probability of BRCA patients could be predicted by survival curve and nomogram analysis. Molecular docking was used to explore the affinity between BBR and potential targets. Gain- and loss-of-function methods were employed to explore the biological process in RRM2 participants. We comprehensively investigated the pharmacological characteristics of BBR on BRCA cell lines and discovered that BBR could inhibit the proliferation of BRCA cells in vitro and in vivo. Combining transcriptome sequencing and KEGG analysis, we found that BBR mainly affected the biological behavior of BRCA cells via HIF-1α and AMPK signal pathways. Additionally, by using bioinformatics and molecular docking, we demonstrated that RRM2 plays an oncogenic role in BRCA samples and that it acts as the hub gene of BBR on BRCA cells. Knockdown and overexpression studies indicated that RRM2 promoted BRCA cell migration as well as invasion in vitro by affecting the epithelial-to-mesenchymal transition (EMT). Our study demonstrated the significance of BBR regulating HIF-1α and AMPK signaling pathways in BRCA cells. Moreover, we revealed the carcinogenic role and potential mechanism of RRM2 as a core regulatory factor of BBR in BRCA in controlling BRCA invasion, migration, and EMT, suggesting that RRM2 may be a therapeutic target and prognostic biomarker for BRCA therapy.

Comprehensive molecular analyses of an autoimmune-related gene predictive model and immune infiltrations using machine learning methods in moyamoya disease

Background: Growing evidence suggests the links between moyamoya disease (MMD) and autoimmune diseases. However, the molecular mechanism from genetic perspective remains unclear. This study aims to clarify the potential roles of autoimmune-related genes (ARGs) in the pathogenesis of MMD. Methods: Two transcription profiles (GSE157628 and GSE141025) of MMD were downloaded from GEO databases. ARGs were obtained from the Gene and Autoimmune Disease Association Database (GAAD) and DisGeNET databases. Differentially expressed ARGs (DEARGs) were identified using "limma" R packages. GO, KEGG, GSVA, and GSEA analyses were conducted to elucidate the underlying molecular function. There machine learning methods (LASSO logistic regression, random forest (RF), support vector machine-recursive feature elimination (SVM-RFE)) were used to screen out important genes. An artificial neural network was applied to construct an autoimmune-related signature predictive model of MMD. The immune characteristics, including immune cell infiltration, immune responses, and HLA gene expression in MMD, were explored using ssGSEA. The miRNA-gene regulatory network and the potential therapeutic drugs for hub genes were predicted. Results: A total of 260 DEARGs were identified in GSE157628 dataset. These genes were involved in immune-related pathways, infectious diseases, and autoimmune diseases. We identified six diagnostic genes by overlapping the three machine learning algorithms: CD38, PTPN11, NOTCH1, TLR7, KAT2B, and ISG15. A predictive neural network model was constructed based on the six genes and presented with great diagnostic ability with area under the curve (AUC) = 1 in the GSE157628 dataset and further validated by GSE141025 dataset. Immune infiltration analysis showed that the abundance of eosinophils, natural killer T (NKT) cells, Th2 cells were significant different between MMD and controls. The expression levels of HLA-A, HLA-B, HLA-C, HLA-DMA, HLA-DRB6, HLA-F, and HLA-G were significantly upregulated in MMD. Four miRNAs (mir-26a-5p, mir-1343-3p, mir-129-2-3p, and mir-124-3p) were identified because of their interaction at least with four hub DEARGs. Conclusion: Machine learning was used to develop a reliable predictive model for the diagnosis of MMD based on ARGs. The uncovered immune infiltration and gene-miRNA and gene-drugs regulatory network may provide new insight into the pathogenesis and treatment of MMD.

Integrated analysis of WGCNA and machine learning identified diagnostic biomarkers in dilated cardiomyopathy with heart failure

The etiologies and pathogenesis of dilated cardiomyopathy (DCM) with heart failure (HF) remain to be defined. Thus, exploring specific diagnosis biomarkers and mechanisms is urgently needed to improve this situation. In this study, three gene expression profiling datasets (GSE29819, GSE21610, GSE17800) and one single-cell RNA sequencing dataset (GSE95140) were obtained from the Gene Expression Omnibus (GEO) database. GSE29819 and GSE21610 were combined into the training group, while GSE17800 was the test group. We used the weighted gene co-expression network analysis (WGCNA) and identified fifteen driver genes highly associated with DCM with HF in the module. We performed the least absolute shrinkage and selection operator (LASSO) on the driver genes and then constructed five machine learning classifiers (random forest, gradient boosting machine, neural network, eXtreme gradient boosting, and support vector machine). Random forest was the best-performing classifier established on five Lasso-selected genes, which was utilized to select out NPPA, OMD, and PRELP for diagnosing DCM with HF. Moreover, we observed the up-regulation mRNA levels and robust diagnostic accuracies of NPPA, OMD, and PRELP in the training group and test group. Single-cell RNA-seq analysis further demonstrated their stable up-regulation expression patterns in various cardiomyocytes of DCM patients. Besides, through gene set enrichment analysis (GSEA), we found TGF-β signaling pathway, correlated with NPPA, OMD, and PRELP, was the underlying mechanism of DCM with HF. Overall, our study revealed NPPA, OMD, and PRELP serving as diagnostic biomarkers for DCM with HF, deepening the understanding of its pathogenesis.

Machine learning links different gene patterns of viral infection to immunosuppression and immune-related biomarkers in severe burns

Introduction

Viral infection, typically disregarded, has a significant role in burns. However, there is still a lack of biomarkers and immunotherapy targets related to viral infections in burns.

Methods

Virus-related genes (VRGs) that were extracted from Gene Oncology (GO) database were included as hallmarks. Through unsupervised consensus clustering, we divided patients into two VRGs molecular patterns (VRGMPs). Weighted gene co-expression network analysis (WGCNA) was performed to study the relationship between burns and VRGs. Random forest (RF), least absolute shrinkage and selection operator (LASSO) regression, and logistic regression were used to select key genes, which were utilized to construct prognostic signatures by multivariate logistic regression. The risk score of the nomogram defined high- and low-risk groups. We compared immune cells, immune checkpoint-related genes, and prognosis between the two groups. Finally, we used network analysis and molecular docking to predict drugs targeting CD69 and SATB1. Expression of CD69 and SATB1 was validated by qPCR and microarray with the blood sample from the burn patient.

Results

We established two VRGMPs, which differed in monocytes, neutrophils, dendritic cells, and T cells. In WGCNA, genes were divided into 14 modules, and the black module was correlated with VRGMPs. A total of 65 genes were selected by WGCNA, STRING, and differential expression analysis. The results of GO enrichment analysis were enriched in Th1 and Th2 cell differentiation, B cell receptor signaling pathway, alpha-beta T cell activation, and alpha-beta T cell differentiation. Then the 2-gene signature was constructed by RF, LASSO, and LOGISTIC regression. The signature was an independent prognostic factor and performed well in ROC, calibration, and decision curves. Further, the expression of immune cells and checkpoint genes differed between high- and low-risk groups. CD69 and SATB1 were differentially expressed in burns.

Discussion

This is the first VRG-based signature (including 2 key genes validated by qPCR) for predicting survival, and it could provide vital guidance to achieve optimized immunotherapy for immunosuppression in burns.

Identification of hub genes and transcription factor regulatory network for heart failure using RNA-seq data and robust rank aggregation analysis

Background

Heart failure (HF) is the end stage of various cardiovascular diseases with a high mortality rate. Novel diagnostic and therapeutic biomarkers for HF are urgently required. Our research aims to identify HF-related hub genes and regulatory networks using bioinformatics and validation assays.

Methods

Using four RNA-seq datasets in the Gene Expression Omnibus (GEO) database, we screened differentially expressed genes (DEGs) of HF using Removal of Unwanted Variation from RNA-seq data (RUVSeq) and the robust rank aggregation (RRA) method. Then, hub genes were recognized using the STRING database and Cytoscape software with cytoHubba plug-in. Furthermore, reliable hub genes were validated by the GEO microarray datasets and quantitative reverse transcription polymerase chain reaction (qRT-PCR) using heart tissues from patients with HF and non-failing donors (NFDs). In addition, R packages “clusterProfiler” and “GSVA” were utilized for enrichment analysis. Moreover, the transcription factor (TF)–DEG regulatory network was constructed by Cytoscape and verified in a microarray dataset.

Results

A total of 201 robust DEGs were identified in patients with HF and NFDs. STRING and Cytoscape analysis recognized six hub genes, among which ASPN, COL1A1, and FMOD were confirmed as reliable hub genes through microarray datasets and qRT-PCR validation. Functional analysis showed that the DEGs and hub genes were enriched in T-cell-mediated immune response and myocardial glucose metabolism, which were closely associated with myocardial fibrosis. In addition, the TF–DEG regulatory network was constructed, and 13 significant TF–DEG pairs were finally identified.

Conclusion

Our study integrated different RNA-seq datasets using RUVSeq and the RRA method and identified ASPN, COL1A1, and FMOD as potential diagnostic biomarkers for HF. The results provide new insights into the underlying mechanisms and effective treatments of HF.

Metabolic reprogramming enables the auxiliary diagnosis of breast cancer by automated breast volume scanner

Breast cancer is the leading cause of female cancer-related deaths worldwide. New technologies with enhanced sensitivity and specificity for early diagnosis and monitoring of postoperative recurrence are in critical demand. Automatic breast full volume scanning system (ABVS) is an emerging technology used as an alternative imaging method for breast cancer screening. Despite its improved detection rate of malignant tumors, ABVS cannot accurately stage breast cancer preoperatively in 30–40% of cases. As a major hallmark of breast cancer, the characteristic metabolic reprogramming may provide potential biomarkers as an auxiliary method for ABVS.

Objective

The objective of this study was to identify differential metabolomic signatures between benign and malignant breast tumors and among different subtypes of breast cancer patients based on untargeted metabolomics and improve breast cancer detection rate by combining key metabolites and ABVS.

Methods

Untargeted metabolomics approach was used to profile serum samples from 70 patients with different subtypes of breast cancer and benign breast tumor to determine specific metabolomic profiles through univariate and multivariate statistical data analysis.

Results

Metabolic profiles correctly distinguished benign and malignant breast tumors patients, and a total of 791 metabolites were identified. There were 54 different metabolites between benign and malignant breast tumors and 17 different metabolites between invasive and non-invasive breast cancer. Notably, the missed diagnosis rate of ABVS could be reduced by differential metabolite analysis. Moreover, the diagnostic performance analyses of combined metabolites (pelargonic acid, N-acetylasparagine, and cysteine-S-sulfate) with ABVS performance gave a ROC area under the curve of 0.967 (95% CI: 0.926, 0.993).

Conclusions

Our study identified metabolic features both in benign and malignant breast tumors and in invasive and non-invasive breast cancer. Combined ultrasound ABVS and a panel of differential serum metabolites could further improve the accuracy of preoperative diagnosis of breast cancer and guide surgical therapy.

Identification of energy metabolism-related biomarkers for risk prediction of heart failure patients using random forest algorithm

OBJECTIVE

Energy metabolism plays a crucial role in the improvement of heart dysfunction as well as the development of heart failure (HF). The current study is designed to identify energy metabolism-related diagnostic biomarkers for predicting the risk of HF due to myocardial infarction.

METHODS

Transcriptome sequencing data of HF patients and non-heart failure (NF) people (GSE66360 and GSE59867) were obtained from gene expression omnibus (GEO) database. Energy metabolism-related differentially expressed genes (DEGs) were screened between HF and NF samples. The subtyping consistency analysis was performed to enable the samples to be grouped. The immune infiltration level among subtypes was assessed by single sample gene set enrichment analysis (ssGSEA). Random forest algorithm (RF) and support vector machine (SVM) were applied to identify diagnostic biomarkers, and the receiver operating characteristic curves (ROC) was plotted to validate the accuracy. Predictive nomogram was constructed and validated based on the result of the RF. Drug screening and gene-miRNA network were analyzed to predict the energy metabolism-related drugs and potential molecular mechanism.

RESULTS

A total of 22 energy metabolism-related DEGs were identified between HF and NF patients. The clustering analysis showed that HF patients could be classified into two subtypes based on the energy metabolism-related genes, and functional analyses demonstrated that the identified DEGs among two clusters were mainly involved in immune response regulating signaling pathway and lipid and atherosclerosis. ssGSEA analysis revealed that there were significant differences in the infiltration levels of immune cells between two subtypes of HF patients. Random-forest and support vector machine algorithm eventually identified ten diagnostic markers (MEF2D, RXRA, PPARA, FOXO1, PPARD, PPP3CB, MAPK14, CREB1, MEF2A, PRMT1) for risk prediction of HF patients, and the proposed nomogram resulted in good predictive performance (GSE66360, AUC = 0.91; GSE59867, AUC = 0.84) and the clinical usefulness in HF patients. More importantly, 10 drugs and 15 miRNA were predicted as drug target and hub miRNA that associated with energy metabolism-related genes, providing further information on clinical HF treatment.

CONCLUSION

This study identified ten energy metabolism-related diagnostic markers using random forest algorithm, which may help optimize risk stratification and clinical treatment in HF patients.

Construction of a neural network diagnostic model and investigation of immune infiltration characteristics for Crohn’s disease

Objective: Crohn’s disease (CD), a chronic recurrent illness, is a type of inflammatory bowel disease whose incidence and prevalence rates are gradually increasing. However, there is no universally accepted criterion for CD diagnosis. The aim of this study was to create a diagnostic prediction model for CD and identify immune cell infiltration features in CD.

Methods: In this study, gene expression microarray datasets were obtained from the Gene Expression Omnibus (GEO) database. Then, we identified differentially expressed genes (DEGs) between 178 CD and 38 control cases. Enrichment analysis of DEGs was also performed to explore the biological role of DEGs. Moreover, the “randomForest” package was applied to select core genes that were used to create a neural network model. Finally, in the training cohort, we used CIBERSORT to evaluate the immune landscape between the CD and normal groups.

Results: The results of enrichment analysis revealed that these DEGs may be involved in biological processes associated with immunity and inflammatory responses. Moreover, the top 3 hub genes in the protein-protein interaction network were IL-1β, CCL2, and CXCR2. The diagnostic model allowed significant discrimination with an area under the ROC curve of 0.984 [95% confidence interval: 0.971–0.993]. A validation cohort (GSE36807) was utilized to ensure the reliability and applicability of the model. In addition, the immune infiltration analysis indicated nine different immune cell types were significantly different between the CD and healthy control groups.

Conclusion: In summary, this study offers a novel insight into the diagnosis of CD and provides potential biomarkers for the precise treatment of CD.

Development and validation of immune-based biomarkers and deep learning models for Alzheimer’s disease

Background: Alzheimer’s disease (AD) is the most common form of dementia in old age and poses a severe threat to the health and life of the elderly. However, traditional diagnostic methods and the ATN diagnostic framework have limitations in clinical practice. Developing novel biomarkers and diagnostic models is necessary to complement existing diagnostic procedures.

Methods: The AD expression profile dataset GSE63060 was downloaded from the NCBI GEO public database for preprocessing. AD-related differentially expressed genes were screened using a weighted co-expression network and differential expression analysis, and functional enrichment analysis was performed. Subsequently, we screened hub genes by random forest, analyzed the correlation between hub genes and immune cells using ssGSEA, and finally built an AD diagnostic model using an artificial neural network and validated it.

Results: Based on the random forest algorithm, we screened a total of seven hub genes from AD-related DEGs, based on which we confirmed that hub genes play an essential role in the immune microenvironment and successfully established a novel diagnostic model for AD using artificial neural networks, and validated its effectiveness in the publicly available datasets GSE63060 and GSE97760.

Conclusion: Our study establishes a reliable model for screening and diagnosing AD that provides a theoretical basis for adding diagnostic biomarkers for the AD gene.

Establishment and Analysis of a Combined Diagnostic Model of Alzheimer's Disease With Random Forest and Artificial Neural Network

Alzheimer's disease (AD) is a neurodegenerative condition that causes cognitive decline over time. Because existing diagnostic approaches for AD are limited, improving upon previously established diagnostic models based on genetic biomarkers is necessary. Firstly, four AD gene expression datasets were collected from the Gene Expression Omnibus (GEO) database. Two datasets were used to establish diagnostic models, and the other two datasets were used to verify the model effect. We merged GSE5281 with GSE44771 as the training dataset and found 120 DEGs. Then, we used random forest (RF) to screen 6 key genes (KLF15, MAFF, ITPKB, SST, DDIT4, and NRXN3) as being critical for separating AD and normal samples. The weights of these key genes were measured, and a diagnostic model was created using an artificial neural network (ANN). The area under the curve (AUC) of the model is 0.953, while the accuracy is 0.914. In the final step, two validation datasets were utilized to assess AUC performance. In GSE109887, our model had an AUC of 0.854, and in GSE132903, it had an AUC of 0.810. To summarize, we successfully identified key gene biomarkers and developed a new AD diagnostic model.

Construction of Novel Gene Signature-Based Predictive Model for the Diagnosis of Acute Myocardial Infarction by Combining Random Forest With Artificial Neural Network

Background

Acute myocardial infarction (AMI) is one of the most common causes of mortality around the world. Early diagnosis of AMI contributes to improving prognosis. In our study, we aimed to construct a novel predictive model for the diagnosis of AMI using an artificial neural network (ANN), and we verified its diagnostic value via constructing the receiver operating characteristic (ROC).

Methods

We downloaded three publicly available datasets (training sets GSE48060, GSE60993, and GSE66360) from Gene Expression Omnibus (GEO) database, and differentially expressed genes (DEGs) were identified between 87 AMI and 78 control samples. We applied the random forest (RF) and ANN algorithms to further identify novel gene signatures and construct a model to predict the possibility of AMI. Besides, the diagnostic value of our model was further validated in the validation sets GSE61144 (7 AMI patients and 10 controls), GSE34198 (49 AMI patients and 48 controls), and GSE97320 (3 AMI patients and 3 controls).

Results

A total of 71 DEGs were identified, of which 68 were upregulated and 3 were downregulated. Firstly, 11 key genes in 71 DEGs were screened with RF classifier for the classification of AMI and control samples. Then, we calculated the weight of each key gene using ANN. Furthermore, the diagnostic model was constructed and named neuralAMI, with significant predictive power (area under the curve [AUC] = 0.980). Finally, our model was validated with the independent datasets GSE61144 (AUC = 0.900), GSE34198 (AUC = 0.882), and GSE97320 (AUC = 1.00).

Conclusion

Machine learning was used to develop a reliable predictive model for the diagnosis of AMI. The results of our study provide potential gene biomarkers for early disease screening.

A Joint Model of Random Forest and Artificial Neural Network for the Diagnosis of Endometriosis

Endometriosis (EM), an estrogen-dependent inflammatory disease with unknown etiology, affects thousands of childbearing-age couples, and its early diagnosis is still very difficult. With the rapid development of sequencing technology in recent years, the accumulation of many sequencing data makes it possible to screen important diagnostic biomarkers from some EM-related genes. In this study, we utilized public datasets in the Gene Expression Omnibus (GEO) and Array-Express database and identified seven important differentially expressed genes (DEGs) (COMT, NAA16, CCDC22, EIF3E, AHI1, DMXL2, and CISD3) through the random forest classifier. Among these DEGs, AHI1, DMXL2, and CISD3 have never been reported to be associated with the pathogenesis of EMs. Our study indicated that these three genes might participate in the pathogenesis of EMs through oxidative stress, epithelial–mesenchymal transition (EMT) with the activation of the Notch signaling pathway, and mitochondrial homeostasis, respectively. Then, we put these seven DEGs into an artificial neural network to construct a novel diagnostic model for EMs and verified its diagnostic efficacy in two public datasets. Furthermore, these seven DEGs were included in 15 hub genes identified from the constructed protein–protein interaction (PPI) network, which confirmed the reliability of the diagnostic model. We hope the diagnostic model can provide novel sights into the understanding of the pathogenesis of EMs and contribute to the clinical diagnosis and treatment of EMs.

Construction and evaluation of an integrated predictive model for chronic kidney disease based on the random forest and artificial neural network approaches

Chronic kidney disease (CKD) is recognized as a serious global health problem due to its high prevalence and all-cause mortality. The aim of this research was to identify critical biomarkers and construct an integrated model for the early prediction of CKD. By using existing RNA-seq data and clinical information from CKD patients from the Gene Expression Omnibus (GEO) database, we applied a computational technique that combined the random forest (RF) and artificial neural network (ANN) approaches to identify gene biomarkers and construct an early diagnostic model. We generated ROC curves to compare the model with other markers and evaluated the associations of selected genes with various clinical properties of CKD. Moreover, we highlighted two biomarkers involved in energy metabolism pathways: pyruvate dehydrogenase kinase 4 (PDK4) and zinc finger protein 36 (ZFP36). The downregulation of the identified key genes was subsequently confirmed in both unilateral ureteral obstruction (UUO) and ischemia reperfusion injury (IRI) mouse models, accompanied by decreased energy metabolism. In vitro experiments and single-cell sequencing analysis proved that these key genes were related to the energy metabolism of proximal tubule cells and were involved in the development of CKD. Overall, we constructed a composite prediction model and discovered key genes that might be used as biomarkers and therapeutic targets for CKD.

The Novel Methylation Biomarker NPY5R Sensitizes Breast Cancer Cells to Chemotherapy

Breast cancer (BC) is the most common tumor in women, and the molecular mechanism underlying its pathogenesis remains unclear. In this study, we aimed to investigate gene modules related to the phenotypes of BC, and identify representative candidate biomarkers for clinical prognosis of BC patients. Using weighted gene co-expression network analysis, we here identified NPY5R as a hub gene in BC. We further found that NPY5R was frequently downregulated in BC tissues compared with adjacent tumor-matched control tissues, due to its aberrant promoter CpG methylation which was confirmed by methylation analysis and treatment with demethylation agent. Higher expression of NPY5R was closely associated with better prognosis for BC patients. Gene set enrichment analysis showed that transcriptome signatures concerning apoptosis and cell cycle were critically enriched in specimens with elevated NPY5R. Ectopic expression of NPY5R significantly curbed breast tumor cell growth, induced cell apoptosis and G2/M arrest. Moreover, NPY5R also promoted the sensitivity of BC cells to doxorubicin. Mechanistically, we found that NPY5R restricted STAT3 signaling pathway activation through interacting with IL6, which may be responsible for the antitumor activity of NPY5R. Collectively, our findings indicate that NPY5R functions as a tumor suppressor but was frequently downregulated in BC.