This mode is used to perform univariate feature selection with fold change. We compare each feature individually for evidence of differential expression in the two prediction classes. If the fold change is more than a threshold , then the feature is selected as an informative biomarker.

It is implemented by org.bdval.DiscoverWithFoldChange.java.

Mode Parameters

The following options are available in this mode

Flag Arguments Required Description
--ratiorationoThe fold change ratio used as threshold. Default is 2 fold changes.
--output-gene-listn/anoWrite features to the output in the tissueinfo gene list format.
--report-max-probesreport-max-probesnoRestrict output to the top ranked probes. This option works in conjunction with the ratio and can further restrict the output.