Figure 6
Overall pipeline of machine-learning-based approaches. For a given pathway, these methods filter the multi-omics data to keep only genes belonging to the pathway. Next, these methods classify each sample using the expression data and assess the accuracy using the area under the receiver operating characteristic curve (AUC). The P-value of the pathway is calculated by comparing the obtained AUC to its empirical distribution constructed under the null.

Overall pipeline of machine-learning-based approaches. For a given pathway, these methods filter the multi-omics data to keep only genes belonging to the pathway. Next, these methods classify each sample using the expression data and assess the accuracy using the area under the receiver operating characteristic curve (AUC). The P-value of the pathway is calculated by comparing the obtained AUC to its empirical distribution constructed under the null.

Close
This Feature Is Available To Subscribers Only

Sign In or Create an Account

Close

This PDF is available to Subscribers Only

View Article Abstract & Purchase Options

For full access to this pdf, sign in to an existing account, or purchase an annual subscription.

Close