Evaluating feature-selection stability in next-generation proteomics
Journal of Bioinformatics and Computational Biology · 2016-10 · 14 (05) · 1650029
DOI: 10.1142/s0219720016500293 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Bioinformatics and Computational Biology, online erschienen am 03.11.2016. Verfasst von Wilson Wen Bin Goh und 1 weiteren Autor:innen. Beteiligte Einrichtung: 1 School of Pharmaceutical Science and Technology, Tianjin University, 92 Weijin Road, Tianjin 300072, China. Hauptthemen laut MEDLINE: Algorithms. Die Arbeit wurde bisher 60-mal zitiert (Crossref) und nennt 33 Literaturangaben.
Abstract (Originalsprache)
Identifying reproducible yet relevant features is a major challenge in biological research. This is well documented in genomics data. Using a proposed set of three reliability benchmarks, we find that this issue exists also in proteomics for commonly used feature-selection methods, e.g. [Formula: see text]-test and recursive feature elimination. Moreover, due to high test variability, selecting the top proteins based on [Formula: see text]-value ranks — even when restricted to high-abundance proteins — does not improve reproducibility. Statistical testing based on networks are believed to be more robust, but this does not always hold true: The commonly used hypergeometric enrichment that tests for enrichment of protein subnets performs abysmally due to its dependence on unstable protein pre-selection steps. We demonstrate here for the first time the utility of a novel suite of network-based algorithms called ranked-based network algorithms (RBNAs) on proteomics. These have originally been introduced and tested extensively on genomics data. We show here that they are highly stable, reproducible and select relevant features when applied to proteomics data. It is also evident from these results that use of statistical feature testing on protein expression data should be executed with due caution. Careless use of networks does not resolve poor-performance issues, and can even mislead. We recommend augmenting statistical feature-selection methods with concurrent analysis on stability and reproducibility to improve the quality of the selected features prior to experimental validation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- 1 School of Pharmaceutical Science and Technology, Tianjin University, 92 Weijin Road, Tianjin 300072, China.
- 2 Department of Computer Science, National University of Singapore, 13 Computing Drive, Singapore 117417 Singapore.
Zitieren
APA
Goh, W. W., & Wong, L. (2016). Evaluating feature-selection stability in next-generation proteomics. Journal of Bioinformatics and Computational Biology, 14(05), 1650029. https://doi.org/10.1142/s0219720016500293
Vancouver
Goh WW, Wong L. Evaluating feature-selection stability in next-generation proteomics. Journal of Bioinformatics and Computational Biology. 2016;14(05):1650029. doi:10.1142/s0219720016500293
BibTeX
@article{Goh2016,
author = {Goh, Wilson Wen Bin and Wong, Limsoon},
title = {Evaluating feature-selection stability in next-generation proteomics},
journal = {Journal of Bioinformatics and Computational Biology},
year = {2016},
volume = {14},
number = {05},
pages = {1650029},
doi = {10.1142/s0219720016500293}
}
EUVIMED