Skip to main content
Fig. 4 | Arthritis Research & Therapy

Fig. 4

From: Machine learning and molecular subtype analyses provide insights into PANoptosis-associated genes in rheumatoid arthritis

Fig. 4

Selection of feature genes and determination of target SPP1. A Boruta selection of 19 feature genes with importance ranking. Green represents important genes selected by Boruta algorithm after dimensionality reduction, blue represents shadowMax value, that is, the threshold value of importance score, and red represents unimportant genes after dimensionality reduction by Boruta. B SVM-RFE selection of 8 feature genes. C Coefficients were calculated for each lambda. Each line represents a gene confidence value. D LASSO regression analysis of 6 genes. The horizontal axis represents the log value of the independent variable, while the vertical axis represents the partial likelihood deviance of the log value of each independent variable. E RF selection of 8 feature genes with importance ranking. F Venn plot of the overlapping genes identified through the four machine algorithms. G Expression of SPP1 in GSE77298. H Expression of PRKG1 in GSE77298. I ROC curve of SPP1 in GSE77298. J ROC curve of PRKG1 in GSE77298

Back to article page

Arthritis Research & Therapy

ISSN: 1478-6362

Contact us