期刊
HUMAN MUTATION
卷 33, 期 8, 页码 1166-1174出版社
WILEY-HINDAWI
DOI: 10.1002/humu.22102
关键词
variation tolerance prediction; methods integration; consensus prediction; classification with reject option
资金
- Tampere Graduate Programme in Biomedicine and Biotechnology (TGPBB)
- Sigrid Juselius Foundation
- Biocenter Finland
- Competitive Research Funding of the Tampere University Hospital
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. (c) 2012 Wiley Periodicals, Inc.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据