@article{d3f317acce0940b7b8eb44b177247285,
title = "The impact of collisions on the ability to detect rare mutant alleles using Barcode-Type Next-Generation Sequencing Techniques",
abstract = "Barcoding techniques are used to reduce error from next-generation sequencing, with applications ranging from understanding tumor subclone populations to detecting circulating tumor DNA. Collisions occur when more than one sample molecule is tagged by the same unique identifier (UID) and can result in failure to detect very-low-frequency mutations and error in estimating mutation frequency. Here, we created computer models of barcoding technique, with and without amplification bias introduced by the UID, and analyzed the effect of collisions for a range of mutant allele frequencies (1e−6 to 0.2), number of sample molecules (10 000 to 1e7), and number of UIDs (410 - 414). Inability to detect rare mutant alleles occurred in 0% to 100% of simulations, depending on collisions and number of mutant molecules. Collisions also introduced error in estimating mutant allele frequency resulting in underestimation of minor allele frequency. Incorporating an understanding of the effect of collisions into experimental design can allow for optimization of the number of sample molecules and number of UIDs to minimize the negative impact on rare mutant detection and mutant frequency estimation.",
keywords = "Barcoding, Collision, Mutation detection, Next-generation sequencing, UID",
author = "Canzoniero, {Jenna Van Liere} and Karen Cravero and Park, {Ben Ho}",
note = "Funding Information: FUNDING: The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: This work was supported by the Avon Foundation (B.H.P.), NIH P30 CA006973, the Sandy Garcia Charitable Foundation, the Commonwealth Foundation, the Santa Fe Foundation, the Breast Cancer Research Foundation, the Mike and Diane Canney Foundation, the Marcie and Ellen Foundation, and the Helen Golde Trust. The funding bodies played no role in the design of the study, collection, analysis or interpretation of data, or in the writing of the manuscript. Funding Information: The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: This work was supported by the Avon Foundation (B.H.P.), NIH P30 CA006973, the Sandy Garcia Charitable Foundation, the Commonwealth Foundation, the Santa Fe Foundation, the Breast Cancer Research Foundation, the Mike and Diane Canney Foundation, the Marcie and Ellen Foundation, and the Helen Golde Trust. The funding bodies played no role in the design of the study, collection, analysis or interpretation of data, or in the writing of the manuscript. Publisher Copyright: {\textcopyright} The Author(s) 2017.",
year = "2017",
doi = "10.1177/1176935117719236",
language = "English (US)",
volume = "16",
journal = "Cancer Informatics",
issn = "1176-9351",
publisher = "Libertas Academica Ltd.",
}