AUTHOR=Song Jian-Kun , Zhang Ying , Fei Xiao-Ya , Chen Yi-Ran , Luo Ying , Jiang Jing-Si , Ru Yi , Xiang Yan-Wei , Li Bin , Luo Yue , Kuai Le 

TITLE=Classification and biomarker gene selection of pyroptosis-related gene expression in psoriasis using a random forest algorithm

JOURNAL=Frontiers in Genetics

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2022.850108

DOI=10.3389/fgene.2022.850108

ISSN=1664-8021

ABSTRACT=Background: Psoriasis is a chronic and immune-mediated skin disorder that currently has no cure. Pyroptosis has been illustrated to be involved in the pathogenesis and progression of psoriasis. However, the role of pyroptosis in psoriasis remains elusive.
Methods: The RNA-seq data of psoriasis patients were collected from the GEO database, and the differential pyroptosis-related genes (PRGs) between psoriasis and normal were obtained. A principal component analysis (PCA) was conducted subsequently to determine if PRGs could distinguish the samples. PRGs and immune cell correlation were performed as well. Subsequently, a novel diagnostic model consisting of PRGs for psoriasis was constructed by random forest (ntree=400). A ROC analysis was used to evaluate the classification performance in internal and external validation. Consensus clustering analysis was used to investigate whether there is a difference in biological functions within PRGs-based subtypes. Finally, the expression of the kernel PRGs were validated by qRT-PCR in vivo.
Results: We identified a total of 39 PRGs, which could distinguish psoriasis samples compared with normal samples. T cell CD4 memory activated and Mast cells resting were correlated with PRGs. Ten PRGs comprising IL-1β, AIM2, CASP5, DHX9, CASP4, CYCS, CASP1, GZMB, CHMP2B, and CASP8 were subsequently screened by a random forest diagnostic model. ROC analysis revealed that our model has good diagnostic performance in internal validation (AUC=0.930 [95% CI 0.877–0.984]), as well as in external validation (mean AUC=0.852). Next, PRGs subtype indicated differences in metabolic process, and MAPK signaling pathway. Last, the qRT- PCR results demonstrated the apparent dysregulation of PRGs in psoriasis, especially AIM2 and GZMB.
Conclusion: In summary, pyroptosis may play a crucial role in psoriasis and can provide new insights into the diagnosis and underlying mechanisms of psoriasis.