PREreviews of “EMT network-based feature selection improves prognosis prediction in lung adenocarcinoma” | PREreview

Skip to preprint details Skip to PREreviews

EMT network-based feature selection improves prognosis prediction in lung adenocarcinoma

by Borong Shao, Maria M Bjaanæs, Helland Åslaug, Christof Schütte, and Tim Conrad

Posted: September 6, 2018
Server: bioRxiv
DOI: 10.1101/410472

Abstract

Various feature selection algorithms have been proposed to identify cancer prognostic biomarkers. In recent years, however, their reproducibility is criticized. The performance of feature selection algorithms is shown to be affected by the datasets, underlying networks and evaluation metrics. One of the causes is the curse of dimensionality, which makes it hard to select the features that generalize well on independent data. Even the integration of biological networks does not mitigate this issue because the networks are large and many of their components are not relevant for the phenotype of interest. With the availability of multi-omics data, integrative approaches are being developed to build more robust predictive models. In this scenario, the higher data dimensions create greater challenges.

We proposed a phenotype relevant network-based feature selection (PRNFS) framework and demonstrated its advantages in lung cancer prognosis prediction. We constructed cancer prognosis relevant networks based on epithelial mesenchymal transition (EMT) and integrated them with different types of omics data for feature selection. With less than 2.5% of the total dimensionality, we obtained EMT prognostic signatures that achieved remarkable prediction performance (average AUC values >0.8), very significant sample stratifications, and meaningful biological interpretations. In addition to finding EMT signatures from different omics data levels, we combined these single-omics signatures into multi-omics signatures, which improved sample stratifications significantly. Both single- and multi-omics EMT signatures were tested on independent multi-omics lung cancer datasets and significant sample stratifications were obtained.

Read the preprint

1 Rapid PREreview

by Yan Zhou

Where can I fill out a Rapid PREreview?

We’ve recently replaced Rapid PREreviews with Structured PREreviews.

You can write a Structured PREreview now.

We’ll be updating older Rapid PREreviews like these soon.

Aggregated Rapid PREreviews
Question	Yes	Unsure	N/A	No
Are the findings novel?	100%	0%	0%	0%
Are the results likely to lead to future research?	100%	0%	0%	0%
Is sufficient detail provided to allow reproduction of the study?	100%	0%	0%	0%
Are the methods and statistics appropriate for the analysis?	100%	0%	0%	0%
Are the principal conclusions supported by the data and analysis?	100%	0%	0%	0%
Does the manuscript discuss limitations?	100%	0%	0%	0%
Have the authors adequately discussed ethical concerns?	0%	100%	0%	0%
Does the manuscript include new data?	100%	0%	0%	0%
Are the data used in the manuscript available?	0%	100%	0%	0%
Is the code used in the manuscript available?	0%	100%	0%	0%
Would you recommend this manuscript to others?	100%	0%	0%	0%
Do you recommend this manuscript for peer review?	100%	0%	0%	0%

2 PREreviews

Write a PREreview Request a PREreview

PREreview by Yan Zhou

Authored by Yan Zhou

This study finds EMT signatures from different omics data levels.

Read the PREreview by Yan Zhou
PREreview by Daniela Saderi

Authored by Daniela Saderi

Live-streamed preprint Journal Club on "EMT network-based feature selection improves prognosis prediction in lung adenocarcinoma" – October 23, 2018
This is a review of the bioRxiv preprint "EMT network-based feature selection improves prognosis prediction in lung adenocarcinoma" by Borong Shao,…
Read the PREreview by Daniela Saderi