Identification and Immune Characteristics Study of Pyroptosis‑Related Genes in Endometriosis

Su, Zhe; Su, Wenjing; Li, Chenglong; Ding, Peihui; Lao, Kaixue; Li, Yiqian; Wang, Yanlin

doi:10.1007/s10528-023-10583-7

Cited by 1 publication

(1 citation statement)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RF is an ensemble learning method based on decision trees that is commonly used for the prediction of classification or regression [15]. Support vector machine recursive feature elimination (SVM-RFE) is a widely used supervised machine learning protocol for classification and regression that is used to find the best variables by deleting SVM-generated eigenvectors.…”

Section: Machine Learningmentioning

confidence: 99%

Combined scRNA-Seq and bulk RNA-Seq analysis suggests that ITGB2 has potential as a prognostic factor for the immune microenvironment of gastric cancer tumours and as an indicator of tumour microenvironment remodelling.

Yu,

Huang,

Wang

et al. 2024

Preprint

View full text Add to dashboard Cite

Background: The prognostic management of gastric cancer remains a major challenge for clinicians. In recent years, correlation studies of immune infiltration in gastric cancers, such as stomachadenocarcinoma (STAD)have attracted much attention. However, the correlation between the expression of the immune factor ITGB2 and the malignant features of immune infiltration and gastric cancer has rarely been reported. Methods: Batch RNA-seq and single-cell RNA sequencing (scRNA-seq) data were combined to screen for differentially expressed genes using software packages and machine learning. Data from the TCGA and five GEO databases were used to investigate the expression levels of ITGB2 in patients with STAD, and the correlation between ITGB2 expression levels and gastric cancer progression was explored and validated. Tumour-infiltrating immune cells were sorted and sequenced at the single-cell level to analyse differences in the expression of ITGB2. Several algorithms were used to analyse the correlation between ITGB2 and immune infiltration in patients with STAD. The study predicted chemotherapy and immunotherapy responses for subgroups with high and low expression of ITGB2. Additionally, LASSO regression models were employed to identify prognostic features based on ITGB2-derived molecules. Results: This study revealed that increased levels of ITGB2 were linked to worse clinical outcomes and prognosis in STAD patients. Bioinformaticanalysis revealed that ITGB2 is involved in leukocyte migration, cytokine activation, and other pathways. Additionally, ITGB2 was positively correlated with the infiltration of most immune cells, immunomodulators, and chemokines. Moreover, gastric cancer patients with high levels of ITGB2 had better responses to immunotherapy. Finally, a machine learning algorithm, LASSO regression, was used to identify prognostic features based on molecules derived from ITGB2. The algorithm demonstrated satisfactory prognostic predictive ability in both the training and validation cohorts. Conclusion: ITGB2 expression is a promising potential immune-related biomarker for STAD and can be used to identify patients who may benefit from immunotherapy.

show abstract

Section: Machine Learningmentioning

confidence: 99%