Skip to main content
Fig. 2 | BMC Bioinformatics

Fig. 2

From: Comparison of pathway and gene-level models for cancer prognosis prediction

Fig. 2

Workflow for gene-level models. In this study, TCGA was used as the source of gene expression data. The expression data used for the gene-level models was filtered to only contain the genes mapped to the pathways considered for the pathway-level models. Nested cross validation was used to train and evaluate a Lasso-penalized Cox proportional hazards model. Cross validation was employed both for the training vs. test split and within each training fold for selection of the Lasso penalty parameter. With the selected genes and estimated parameters, we performed prediction on the test data subset by applying the Cox proportional hazards regression model that had been identified in the training data subset

Back to article page