@article{ref1,
title="Statistical method to compare massive parallel sequencing pipelines",
journal="BMC bioinformatics",
year="2017",
author="Elsensohn, M.H. and Leblay, N. and Dimassi, S. and Campan-Fournier, A. and Labalme, A. and Roucher-Boulez, F. and Sanlaville, D. and Lesca, G. and Bardel, C. and Roy, P.",
volume="18",
number="1",
pages="e139-e139",
abstract="BACKGROUND: Today, sequencing is frequently carried out by Massive Parallel Sequencing (MPS) that cuts drastically sequencing time and expenses. Nevertheless, Sanger sequencing remains the main validation method to confirm the presence of variants. The analysis of MPS data involves the development of several bioinformatic tools, academic or commercial. We present here a statistical method to compare MPS pipelines and test it in a comparison between an academic (BWA-GATK) and a commercial pipeline (TMAP-NextGENe), with and without reference to a gold standard (here, Sanger sequencing), on a panel of 41 genes in 43 epileptic patients. This method used the number of variants to fit log-linear models for pairwise agreements between pipelines. To assess the heterogeneity of the margins and the odds ratios of agreement, four log-linear models were used: a full model, a homogeneous-margin model, a model with single odds ratio for all patients, and a model with single intercept. Then a log-linear mixed model was fitted considering the biological variability as a random effect. <br><br>RESULTS: Among the 390,339 base-pairs sequenced, TMAP-NextGENe and BWA-GATK found, on average, 2253.49 and 1857.14 variants (single nucleotide variants and indels), respectively. Against the gold standard, the pipelines had similar sensitivities (63.47% vs. 63.42%) and close but significantly different specificity (99.57% vs. 99.65%; p  Keywords: Pipeline transportation   Keywords: Pipeline transportation<p /> <p>Language: en</p>",
language="en",
issn="1471-2105",
doi="10.1186/s12859-017-1552-9",
url="http://dx.doi.org/10.1186/s12859-017-1552-9"
}