Get access

PON-P: Integrated predictor for pathogenicity of missense variants

Authors

  • Ayodeji Olatubosun,

    1. Institute of Biomedical Technology, University of Tampere, Tampere, Finland
    2. BioMediTech, Tampere, Finland
    Search for more papers by this author
  • Jouni Väliaho,

    1. Institute of Biomedical Technology, University of Tampere, Tampere, Finland
    2. BioMediTech, Tampere, Finland
    Search for more papers by this author
  • Jani Härkönen,

    1. Institute of Biomedical Technology, University of Tampere, Tampere, Finland
    Search for more papers by this author
  • Janita Thusberg,

    1. Institute of Biomedical Technology, University of Tampere, Tampere, Finland
    Current affiliation:
    1. Buck Institute for Research on Aging, 8001 Redwood Blvd., Novato, CA 94945
    Search for more papers by this author
  • Mauno Vihinen

    Corresponding author
    1. Institute of Biomedical Technology, University of Tampere, Tampere, Finland
    2. BioMediTech, Tampere, Finland
    3. Department of Experimental Medical Science, Lund University, Lund, Sweden
    • Department of Experimental Medical Science, Lund University, BMC D11, SE-221 84 Lund, Sweden.
    Search for more papers by this author

  • Communicated by Barend Mons

  • This article is dedicated to the memory of Ayodeji Olatubosun who passed away during its completion.

Abstract

High-throughput sequencing data generation demands the development of methods for interpreting the effects of genomic variants. Numerous computational methods have been developed to assess the impact of variations because experimental methods are unable to cope with both the speed and volume of data generation. To harness the strength of currently available predictors, the Pathogenic-or-Not-Pipeline (PON-P) integrates five predictors to predict the probability that nonsynonymous variations affect protein function and may consequently be disease related. Random forest methodology-based PON-P shows consistently improved performance in cross-validation tests and on independent test sets, providing ternary classification and statistical reliability estimate of results. Applied to missense variants in a melanoma cancer cell line, PON-P predicts variants in 17 genes to affect protein function. Previous studies implicate nine of these genes in the pathogenesis of various forms of cancer. PON-P may thus be used as a first step in screening and prioritizing variants to determine deleterious ones for further experimentation. Hum Mutat 33:1166–1174, 2012. © 2012 Wiley Periodicals, Inc.

Get access to the full text of this article

Ancillary