Machine learning and bioinformatics-based insights into the potential targets of saponins in Paris polyphylla smith against non-small cell lung cancer

Wang, Yue; Huang, Xulong; Xian, Bin; Jiang, Huajuan; Zhou, Tao; Chen, Siyu; Wen, Feiyan; Pei, Jin

doi:10.3389/fgene.2022.1005896

Cited by 3 publications

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Exploring the diagnostic markers of essential tremor: A study based on machine learning algorithms

Gao

Liu

et al. 2023

Open Life Sciences

View full text Add to dashboard Cite

Essential tremor (ET) is a common neurological disorder with a difficult clinical diagnosis, primarily due to the lack of relevant biomarkers. The current study aims to identify possible biomarkers for ET by screening miRNAs using machine learning algorithms. In this investigation, public datasets and our own datasets were used to examine the ET disorder. The ET datasets originated from public sources. To generate our own dataset, high-throughput sequencing analyses were performed on ET and control samples from the First People’s Hospital of Yunnan Province. Functional enrichment analysis was employed to identify the potential function of differentially expressed genes (DEGs). Using datasets from the Gene Expression Omnibus database, Lasso regression analysis and support vector machine recursive feature elimination were used to screen potential diagnostic genes for ET. To identify the genes responsible for the final diagnosis, area under the curves (AUCs) of the receiver operating characteristic was examined. Finally, an ssGSEA representing an ET immune landscape was created. The sample exhibited expression profiles that corresponded with six genes in the public database. Three diagnostic genes were discovered with AUCs >0.7 that can distinguish ET from normal data: APOE, SENP6, and ZNF148. Single-gene GSEA indicated that these diagnostic genes were closely associated with the cholinergic, GABAergic, and dopaminergic synapse networks. The immune microenvironment of ET was also affected by these diagnostic genes. According to the findings, these three DEGs (APOE, SENP6, and ZNF148) may successfully differentiate between samples from ET patients and normal controls, serving as a helpful diagnostic tool. This effort provided a theoretical foundation for elucidating the pathogenesis of ET and raised hopes of overcoming the diagnostic difficulty of ET clinically.

show abstract

Exploring the diagnostic markers of essential tremor: A study based on machine learning algorithms

Gao

Liu

et al. 2023

Open Life Sciences

View full text Add to dashboard Cite

show abstract

Screening of tumor antigens and immunogenic cell death landscapes of prostate cancer for exploration of mRNA vaccine

Lin

Wang

et al. 2023

Preprint

View full text Add to dashboard Cite

Background Although the mRNA vaccine is effective against many kinds of cancers, its efficacy against prostate adenocarcinoma (PRAD) is still unclear. In this study, effective antigens of mRNA vaccine were excavated from the perspective of immunogenic cell death (ICD), and ICD subtypes of PRAD were further distinguished to establish an ICD landscape, thereby determining suitable vaccine recipients. Methods The Cancer Genome Atlas (TCGA) and Memorial Sloan-Kettering Cancer Center (MSKCC) databases were applied to acquire RNA-seq data and corresponding clinical data of 554 and 131 patients, respectively. GEPIA was employed to measure prognostic indices. Then comparison of genetic alterations was performed utilizing cBioPortal, and correlation of identified ICD antigens with immune infiltrating cells was analyzed employing TIMER. Moreover, ICD subtypes were identified by means of consensus cluster, and ICD landscape of PRAD was depicted utilizing graph learning-based dimensional reduction. Results In total, 4 PRAD antigens were identified in PRAD, including FUS, LMNB2, RNPC3 and ZNF700, which had association with adverse prognosis and infiltration of antigen-presenting cells (APCs). PRAD patients were classified as two ICD subtypes based on their differences in molecular, cellular and clinical features. Patients in subtype ICDS2 had immune “hot” phenotype, whereas those in ICDS1 had an immune “cold” phenotype. Furthermore, ICD modulators and immune checkpoints were also differentially expressed between two ICD subtype tumors. Finally, ICD landscape of PRAD showed substantial heterogeneity among individual patients. Conclusions FUS, LMNB2, RNPC3 and ZNF700 are identified as antigens with potential to develop anti-PRAD mRNA vaccine, particularly for patients in subtype ICDS2. In summary, the research may provide a theoretical foundation for developing mRNA vaccine against PRAD as well as determining appropriate vaccine recipients.

show abstract

Parkinson’s Disease Gene Biomarkers Screened by the LASSO and SVM Algorithms

Yang

Wang

et al. 2023

Brain Sciences

View full text Add to dashboard Cite

Parkinson’s disease (PD) is a common progressive neurodegenerative disorder. Various evidence has revealed the possible penetration of peripheral immune cells in the substantia nigra, which may be essential for PD. Our study uses machine learning (ML) to screen for potential PD genetic biomarkers. Gene expression profiles were screened from the Gene Expression Omnibus (GEO). Differential expression genes (DEGs) were selected for the enrichment analysis. A protein–protein interaction (PPI) network was built with the STRING database (Search Tool for the Retrieval of Interacting Genes), and two ML approaches, namely least absolute shrinkage and selection operator (LASSO) and support vector machine recursive feature elimination (SVM-RFE), were employed to identify candidate genes. The external validation dataset further tested the expression degree and diagnostic value of candidate biomarkers. To assess the validity of the diagnosis, we determined the receiver operating characteristic (ROC) curve. A convolution tool was employed to evaluate the composition of immune cells by CIBERSORT, and we performed correlation analyses on the basis of the training dataset. Twenty-seven DEGs were screened in the PD and control samples. Our results from the enrichment analysis showed a close association with inflammatory and immune-associated diseases. Both the LASSO and SVM algorithms screened eight and six characteristic genes. AGTR1, GBE1, TPBG, and HSPA6 are overlapping hub genes strongly related to PD. Our results of the area under the ROC (AUC), including AGTR1 (AUC = 0.933), GBE1 (AUC = 0.967), TPBG (AUC = 0.767), and HSPA6 (AUC = 0.633), suggested that these genes have good diagnostic value, and these genes were significantly associated with the degree of immune cell infiltration. AGTR1, GBE1, TPBG, and HSPA6 were identified as potential biomarkers in the diagnosis of PD and provide a novel viewpoint for further study on PD immune mechanism and therapy.

show abstract

Machine learning and bioinformatics-based insights into the potential targets of saponins in Paris polyphylla smith against non-small cell lung cancer

Cited by 3 publications

References 46 publications

Exploring the diagnostic markers of essential tremor: A study based on machine learning algorithms

Exploring the diagnostic markers of essential tremor: A study based on machine learning algorithms

Screening of tumor antigens and immunogenic cell death landscapes of prostate cancer for exploration of mRNA vaccine

Parkinson’s Disease Gene Biomarkers Screened by the LASSO and SVM Algorithms

Contact Info

Product

Resources

About