Meng-Jie Zhang, Ting-Ting Xue, Xiao-Ya Fei, Ying Zhang, Ying Luo, Yi Ru, Jing-Si Jiang, Jian-Kun Song, Le Kuai, Yue Luo, Rui-Ping Wang, Bin Li
{"title":"基于随机森林算法的银屑病血管生成相关基因和分子亚型鉴定","authors":"Meng-Jie Zhang, Ting-Ting Xue, Xiao-Ya Fei, Ying Zhang, Ying Luo, Yi Ru, Jing-Si Jiang, Jian-Kun Song, Le Kuai, Yue Luo, Rui-Ping Wang, Bin Li","doi":"10.1093/cei/uxae052","DOIUrl":null,"url":null,"abstract":"<p><p>Psoriasis is a chronic immune-mediated recurrent skin disease causing systemic damage. Increased angiogenesis has been reported to participate in the progression of psoriasis. However, angiogenesis-related genes (ARGs) in psoriasis have not been systematically elucidated. Therefore, we aim to identify potential biomarkers and subtypes using two algorithmsr. Transcriptome sequencing data of patients with psoriasis were obtained, in which differentially expressed genes were assessed by principal component analysis. A diagnostic model was developed using random forest algorithm and validated by receiver operating characteristic (ROC) curves. Subsequently, we performed consensus clustering to calculate angiogenesis-associated molecular subtypes of psoriasis. Additionally, a correlation analysis was conducted between ARGs and immune cell infiltration. Finally, validation of potential ARG genes was performed by quantitative real-time PCR (qRT-PCR). We identified 29 differentially expressed ARGs, including 13 increased and 16 decreased. Ten ARGs, CXCL8, ANG, EGF, HTATIP2, ANGPTL4, TNFSF12, RHOB, PML, FOXO4, and EMCN were subsequently sifted by the diagnostic model based on a random forest algorithm. Analysis of the ROC curve (area under the curve [AUC] = 1.0) indicated high diagnostic performance in internal validation. The correlation analysis suggested that CXCL8 has a high positive correlation with neutrophil (R =0.8, P < 0.0001) and interleukins pathway (R = 0.79, P < 0.0001). Furthermore, two ARG-mediated subtypes were obtained, indicating potential heterogeneity. Finally, the qRT-PCR demonstrated that the mRNA expression levels of CXCL8 and ANGPTL4 were elevated in psoriasis patients, with a reduced expression of EMCN observed. The current paper indicated potential ARG-related biomarkers of psoriasis, including CXCL8, ANGPTL4, and EMCN, with two molecular subtypes.</p>","PeriodicalId":10268,"journal":{"name":"Clinical and experimental immunology","volume":" ","pages":"199-212"},"PeriodicalIF":3.4000,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11482546/pdf/","citationCount":"0","resultStr":"{\"title\":\"Identification of angiogenesis-related genes and molecular subtypes for psoriasis based on random forest algorithm.\",\"authors\":\"Meng-Jie Zhang, Ting-Ting Xue, Xiao-Ya Fei, Ying Zhang, Ying Luo, Yi Ru, Jing-Si Jiang, Jian-Kun Song, Le Kuai, Yue Luo, Rui-Ping Wang, Bin Li\",\"doi\":\"10.1093/cei/uxae052\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Psoriasis is a chronic immune-mediated recurrent skin disease causing systemic damage. Increased angiogenesis has been reported to participate in the progression of psoriasis. However, angiogenesis-related genes (ARGs) in psoriasis have not been systematically elucidated. Therefore, we aim to identify potential biomarkers and subtypes using two algorithmsr. Transcriptome sequencing data of patients with psoriasis were obtained, in which differentially expressed genes were assessed by principal component analysis. A diagnostic model was developed using random forest algorithm and validated by receiver operating characteristic (ROC) curves. Subsequently, we performed consensus clustering to calculate angiogenesis-associated molecular subtypes of psoriasis. Additionally, a correlation analysis was conducted between ARGs and immune cell infiltration. Finally, validation of potential ARG genes was performed by quantitative real-time PCR (qRT-PCR). We identified 29 differentially expressed ARGs, including 13 increased and 16 decreased. Ten ARGs, CXCL8, ANG, EGF, HTATIP2, ANGPTL4, TNFSF12, RHOB, PML, FOXO4, and EMCN were subsequently sifted by the diagnostic model based on a random forest algorithm. Analysis of the ROC curve (area under the curve [AUC] = 1.0) indicated high diagnostic performance in internal validation. The correlation analysis suggested that CXCL8 has a high positive correlation with neutrophil (R =0.8, P < 0.0001) and interleukins pathway (R = 0.79, P < 0.0001). Furthermore, two ARG-mediated subtypes were obtained, indicating potential heterogeneity. Finally, the qRT-PCR demonstrated that the mRNA expression levels of CXCL8 and ANGPTL4 were elevated in psoriasis patients, with a reduced expression of EMCN observed. The current paper indicated potential ARG-related biomarkers of psoriasis, including CXCL8, ANGPTL4, and EMCN, with two molecular subtypes.</p>\",\"PeriodicalId\":10268,\"journal\":{\"name\":\"Clinical and experimental immunology\",\"volume\":\" \",\"pages\":\"199-212\"},\"PeriodicalIF\":3.4000,\"publicationDate\":\"2024-10-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11482546/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Clinical and experimental immunology\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1093/cei/uxae052\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"IMMUNOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Clinical and experimental immunology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1093/cei/uxae052","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"IMMUNOLOGY","Score":null,"Total":0}
Identification of angiogenesis-related genes and molecular subtypes for psoriasis based on random forest algorithm.
Psoriasis is a chronic immune-mediated recurrent skin disease causing systemic damage. Increased angiogenesis has been reported to participate in the progression of psoriasis. However, angiogenesis-related genes (ARGs) in psoriasis have not been systematically elucidated. Therefore, we aim to identify potential biomarkers and subtypes using two algorithmsr. Transcriptome sequencing data of patients with psoriasis were obtained, in which differentially expressed genes were assessed by principal component analysis. A diagnostic model was developed using random forest algorithm and validated by receiver operating characteristic (ROC) curves. Subsequently, we performed consensus clustering to calculate angiogenesis-associated molecular subtypes of psoriasis. Additionally, a correlation analysis was conducted between ARGs and immune cell infiltration. Finally, validation of potential ARG genes was performed by quantitative real-time PCR (qRT-PCR). We identified 29 differentially expressed ARGs, including 13 increased and 16 decreased. Ten ARGs, CXCL8, ANG, EGF, HTATIP2, ANGPTL4, TNFSF12, RHOB, PML, FOXO4, and EMCN were subsequently sifted by the diagnostic model based on a random forest algorithm. Analysis of the ROC curve (area under the curve [AUC] = 1.0) indicated high diagnostic performance in internal validation. The correlation analysis suggested that CXCL8 has a high positive correlation with neutrophil (R =0.8, P < 0.0001) and interleukins pathway (R = 0.79, P < 0.0001). Furthermore, two ARG-mediated subtypes were obtained, indicating potential heterogeneity. Finally, the qRT-PCR demonstrated that the mRNA expression levels of CXCL8 and ANGPTL4 were elevated in psoriasis patients, with a reduced expression of EMCN observed. The current paper indicated potential ARG-related biomarkers of psoriasis, including CXCL8, ANGPTL4, and EMCN, with two molecular subtypes.
期刊介绍:
Clinical & Experimental Immunology (established in 1966) is an authoritative international journal publishing high-quality research studies in translational and clinical immunology that have the potential to transform our understanding of the immunopathology of human disease and/or change clinical practice.
The journal is focused on translational and clinical immunology and is among the foremost journals in this field, attracting high-quality papers from across the world. Translation is viewed as a process of applying ideas, insights and discoveries generated through scientific studies to the treatment, prevention or diagnosis of human disease. Clinical immunology has evolved as a field to encompass the application of state-of-the-art technologies such as next-generation sequencing, metagenomics and high-dimensional phenotyping to understand mechanisms that govern the outcomes of clinical trials.