Bivariate Poisson models with varying offsets: an application to the paired mitochondrial DNA dataset

Su Pei-Fang (), Mau Yu-Lin, Guo Yan, Li Chung-I, Liu Qi, Boice John D. and Shyr Yu
Additional contact information
Su Pei-Fang: Department of Statistics, National Cheng Kung University, Tainan 70101, Taiwan
Mau Yu-Lin: Department of Statistics, National Cheng Kung University, Tainan 70101, Taiwan
Guo Yan: Center for Quantitative Sciences, Vanderbilt University, Nashville, TN 37232, USA
Li Chung-I: Department of Statistics, National Cheng Kung University, Tainan 70101, Taiwan
Liu Qi: Center for Quantitative Sciences, Vanderbilt University, Nashville, TN 37232, USA
Boice John D.: National Council on Radiation Protection Measurements, Bethesda, MD 20814, USA
Shyr Yu: Center for Quantitative Sciences, Vanderbilt University, Nashville, TN 37232, USA

Statistical Applications in Genetics and Molecular Biology, 2017, vol. 16, issue 1, 47-58

Abstract: To assess the effect of chemotherapy on mitochondrial genome mutations in cancer survivors and their offspring, a study sequenced the full mitochondrial genome and determined the mitochondrial DNA heteroplasmic (mtDNA) mutation rate. To build a model for counts of heteroplasmic mutations in mothers and their offspring, bivariate Poisson regression was used to examine the relationship between mutation count and clinical information while accounting for the paired correlation. However, if the sequencing depth is not adequate, a limited fraction of the mtDNA will be available for variant calling. The classical bivariate Poisson regression model treats the offset term as equal within pairs; thus, it cannot be applied directly. In this research, we propose an extended bivariate Poisson regression model that has a more general offset term to adjust the length of the accessible genome for each observation. We evaluate the performance of the proposed method with comprehensive simulations, and the results show that the regression model provides unbiased parameter estimations. The use of the model is also demonstrated using the paired mtDNA dataset.

Keywords: DNA dataset; EM algorithm; offset; paired count data; sequence quality (search for similar items in EconPapers)
Date: 2017
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://doi.org/10.1515/sagmb-2016-0040 (text/html)
For access to full text, subscription to the journal or payment for the individual article is required.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:bpj:sagmbi:v:16:y:2017:i:1:p:47-58:n:5

Ordering information: This journal article can be ordered from
https://www.degruyter.com/journal/key/sagmb/html

DOI: 10.1515/sagmb-2016-0040

Access Statistics for this article

Statistical Applications in Genetics and Molecular Biology is currently edited by Michael P. H. Stumpf

More articles in Statistical Applications in Genetics and Molecular Biology from De Gruyter
Bibliographic data for series maintained by Peter Golla ().