Introduction

To date most medical tests derived by applying classification methods to high-dimensional molecular data are hardly used in clinical practice. This is partly because the prediction error resulting when applying them to external data is usually much higher than internal error as evaluated through within-study validation procedures. We suggest the use of addon normalization and addon batch effect removal techniques in this context to reduce systematic differences between external data and the original dataset with the aim to improve prediction performance.We evaluate the impact of addon normalization and seven batch effect removal methods on cross-study prediction performance for several common classifiers using a large collection of microarray gene expression datasets, showing that some of these techniques reduce prediction error.All investigated addon methods are implemented in our R package bapred.hornung@ibe.med.uni-muenchen.de.Supplementary data are available at Bioinformatics online.

Publications

  1. Improving cross-study prediction through addon batch effect adjustment or addon normalization.
    Cite this
    Hornung R, Causeur D, Bernau C, Boulesteix AL, 2017-02-01 - Bioinformatics (Oxford, England)
  2. Combining location-and-scale batch effect adjustment with data cleaning by latent factor adjustment.
    Cite this
    Hornung R, Boulesteix AL, Causeur D, 2016-01-01 - BMC bioinformatics

Credits

  1. Roman Hornung
    Developer

    Department of Medical Informatics, Biometry and Epidemiology, Germany

  2. David Causeur
    Developer

    Applied Mathematics Department, Agrocampus Ouest, France

  3. Christoph Bernau
    Developer

    Leibniz Supercomputing Center, Garching, Germany

  4. Anne-Laure Boulesteix
    Investigator

    Department of Medical Informatics, Biometry and Epidemiology, Germany

Community Ratings

UsabilityEfficiencyReliabilityRated By
0 user
Sign in to rate
Summary
AccessionBT001415
Tool TypeApplication
Category
PlatformsLinux/Unix
TechnologiesR
User InterfaceTerminal Command Line
Download Count0
Country/RegionGermany
Submitted ByAnne-Laure Boulesteix