By using the expression profiles and survival data of ATF/CREB genes, the full TCGA set was employed as the training dataset and the full ICGC set as the test dataset. The ATF/CREB family genes model was developed using the training dataset and validated using the full and test datasets. The Lasso and Cox regression (“glmnet” and “survival” packages) were employed to examine the link between pyroptosis-related genes and overall survival rate. The Lasso model was developed using cross-validation to ensure reliability. By applying the penalty parameter (λ), we identified six genes that were associated with survival and used them to construct a multivariate Cox regression model. Using a forward-backward Cox regression technique, the optimal set of genes was chosen and used to predict survival. Kaplan-Meier (KM) analysis was conducted to generate survival curves for both the training and testing sets. The risk score was computed using the following equation.
\documentclass[12pt]{minimal}
\usepackage{wasysym}
\usepackage[substack]{amsmath}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage[mathscr]{eucal}
\usepackage{mathrsfs}
\DeclareFontFamily{T1}{linotext}{}
\DeclareFontShape{T1}{linotext}{m}{n} {linotext }{}
\DeclareSymbolFont{linotext}{T1}{linotext}{m}{n}
\DeclareSymbolFontAlphabet{\mathLINOTEXT}{linotext}
\begin{document}
$${\rm{Risks}}\ {\rm{core}}\,{\rm{=}}\,\mathop \sum \limits_{{\rm{i=1}}}^{\rm{n}} {\rm{coefi\times{Xi}}}$$
\end{document}