English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Recently, several classifiers that combine primary tumor data, like geneexpression data, and secondary data sources, such as protein-proteininteraction networks, have been proposed for predicting outcome in breastcancer. In these approaches, new composite features are typically constructedby aggregating the expression levels of several genes. The secondary datasources are employed to guide this aggregation. Although many studies claimthat these approaches improve classification performance over single geneclassifiers, the gain in performance is difficult to assess. This stems mainlyfrom the fact that different breast cancer data sets and validation proceduresare employed to assess the performance. Here we address these issues byemploying a large cohort of six breast cancer data sets as benchmark set and byperforming an unbiased evaluation of the classification accuracies of thedifferent approaches. Contrary to previous claims, we find that compositefeature classifiers do not outperform simple single gene classifiers. Weinvestigate the effect of (1) the number of selected features; (2) the specificgene set from which features are selected; (3) the size of the training set and(4) the heterogeneity of the data set on the performance of composite featureand single gene classifiers. Strikingly, we find that randomization ofsecondary data sources, which destroys all biological information in thesesources, does not result in a deterioration in performance of composite featureclassifiers. Finally, we show that when a proper correction for gene set sizeis performed, the stability of single gene sets is similar to the stability ofcomposite feature sets. Based on these results there is currently no reason toprefer prognostic classifiers based on composite features over single geneclassifiers for predicting outcome in breast cancer.

A critical evaluation of network and pathway based classifiers for outcome prediction in breast cancer