Estimating population genetic parameters and comparing model goodness-of-fit using DNA sequences with error
- Human Genetics Center, School of Public Health, The University of Texas Health Science Center at Houston, Houston, Texas 77030, USA
Abstract
It is known that sequencing error can bias estimation of evolutionary or population genetic parameters. This problem is more prominent in deep resequencing studies because of their large sample size n, and a higher probability of error at each nucleotide site. We propose a new method based on the composite likelihood of the observed SNP configurations to infer population mutation rate θ = 4Neμ, population exponential growth rate R, and error rate ɛ, simultaneously. Using simulation, we show the combined effects of the parameters, θ, n, ɛ, and R on the accuracy of parameter estimation. We compared our maximum composite likelihood estimator (MCLE) of θ with other θ estimators that take into account the error. The results show the MCLE performs well when the sample size is large or the error rate is high. Using parametric bootstrap, composite likelihood can also be used as a statistic for testing the model goodness-of-fit of the observed DNA sequences. The MCLE method is applied to sequence data on the ANGPTL4 gene in 1832 African American and 1045 European American individuals.
Footnotes
-
↵1 Corresponding author.
E-mail Xiaoming.Liu{at}uth.tmc.edu; fax (713) 500-0900.
-
[Supplemental material is available online at http://www.genome.org. Java programs for calculating MCLE of θ, R, and ɛ are freely available at http://sites.google.com/site/jpopgen/.]
-
Article published online before print. Article and publication date are at http://www.genome.org/cgi/doi/10.1101/gr.097543.109.
-
- Received June 18, 2009.
- Accepted October 8, 2009.
- Copyright © 2010 by Cold Spring Harbor Laboratory Press
