The determination of the relationship between a pair of individuals is a fundamental application of genetics. The most accurate methods for relationship estimation rely on precise, localized estimates of genetic sharing between individuals. Earlier methods have generated these estimates from high-density genetic marker data. We performed relationship estimation using whole-genome sequence data for 1490 known pairwise relationships among 258 individuals in 30 families along with 46 population samples as controls. Our results demonstrate that complexities specific to whole-genome sequencing result in regions of the genome that are prone to false-positive estimates of genetic sharing. We provide a map of these spurious IBD regions and introduce new methods, implemented in the software package ERSA 2.0, to control for spurious IBD. We show that ERSA 2.0 provides a 5\% to 15\% increase in relationship detection power for distant relationships with whole-genome sequence data relative to high-density genetic marker data.
%0 Journal Article
%1 li2014relationship
%A Li, Hong
%A Glusman, Gustavo
%A Hu, Hao
%A Shankaracharya, Juan Caballero
%A Hubley, Robert
%A Witherspoon, David
%A Guthery, Stephen L.
%A Mauldin, Denise E.
%A Jorde, Lynn B.
%A Hood, Leroy
%A Roach, Jared C.
%A Huff, Chad D.
%D 2014
%I Public Library of Science
%J PLoS Genet
%K methods relationship_estimation IBD
%N 1
%P e1004144
%R 10.1371/journal.pgen.1004144
%T Relationship Estimation from Whole-Genome Sequence Data
%U http://dx.doi.org/10.1371%2Fjournal.pgen.1004144
%V 10
%X The determination of the relationship between a pair of individuals is a fundamental application of genetics. The most accurate methods for relationship estimation rely on precise, localized estimates of genetic sharing between individuals. Earlier methods have generated these estimates from high-density genetic marker data. We performed relationship estimation using whole-genome sequence data for 1490 known pairwise relationships among 258 individuals in 30 families along with 46 population samples as controls. Our results demonstrate that complexities specific to whole-genome sequencing result in regions of the genome that are prone to false-positive estimates of genetic sharing. We provide a map of these spurious IBD regions and introduce new methods, implemented in the software package ERSA 2.0, to control for spurious IBD. We show that ERSA 2.0 provides a 5\% to 15\% increase in relationship detection power for distant relationships with whole-genome sequence data relative to high-density genetic marker data.
@article{li2014relationship,
abstract = {The determination of the relationship between a pair of individuals is a fundamental application of genetics. The most accurate methods for relationship estimation rely on precise, localized estimates of genetic sharing between individuals. Earlier methods have generated these estimates from high-density genetic marker data. We performed relationship estimation using whole-genome sequence data for 1490 known pairwise relationships among 258 individuals in 30 families along with 46 population samples as controls. Our results demonstrate that complexities specific to whole-genome sequencing result in regions of the genome that are prone to false-positive estimates of genetic sharing. We provide a map of these spurious IBD regions and introduce new methods, implemented in the software package ERSA 2.0, to control for spurious IBD. We show that ERSA 2.0 provides a 5\% to 15\% increase in relationship detection power for distant relationships with whole-genome sequence data relative to high-density genetic marker data.},
added-at = {2014-02-16T17:28:20.000+0100},
author = {Li, Hong and Glusman, Gustavo and Hu, Hao and Shankaracharya, Juan Caballero and Hubley, Robert and Witherspoon, David and Guthery, Stephen L. and Mauldin, Denise E. and Jorde, Lynn B. and Hood, Leroy and Roach, Jared C. and Huff, Chad D.},
biburl = {https://www.bibsonomy.org/bibtex/26604da01485623829eb49af990adb92b/peter.ralph},
doi = {10.1371/journal.pgen.1004144},
interhash = {fea3349709476fccaff6040c3f73aeb1},
intrahash = {6604da01485623829eb49af990adb92b},
journal = {PLoS Genet},
keywords = {methods relationship_estimation IBD},
month = {01},
number = 1,
pages = {e1004144},
publisher = {Public Library of Science},
timestamp = {2015-01-20T22:35:53.000+0100},
title = {Relationship Estimation from Whole-Genome Sequence Data},
url = {http://dx.doi.org/10.1371%2Fjournal.pgen.1004144},
volume = 10,
year = 2014
}