Rapid detection of identity-by-descent tracts for mega-scale datasets. Shemirani, R., Belbin, G. M, Avery, C. L, Kenny, E. E, Gignoux, C. R, & Ambite, J. L. Nat Commun, 12(1):3546, Jun, 2021. ![Rapid detection of identity-by-descent tracts for mega-scale datasets [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex The ability to identify segments of genomes identical-by-descent (IBD) is a part of standard workflows in both statistical and population genetics. However, traditional methods for finding local IBD across all pairs of individuals scale poorly leading to a lack of adoption in very large-scale datasets. Here, we present iLASH, an algorithm based on similarity detection techniques that shows equal or improved accuracy in simulations compared to current leading methods and speeds up analysis by several orders of magnitude on genomic datasets, making IBD estimation tractable for millions of individuals. We apply iLASH to the PAGE dataset of 52,000 multi-ethnic participants, including several founder populations with elevated IBD sharing, identifying IBD segments in 3 minutes per chromosome compared to over 6 days for a state-of-the-art algorithm. iLASH enables efficient analysis of very large-scale datasets, as we demonstrate by computing IBD across the UK Biobank ( 500,000 individuals), detecting 12.9 billion pairwise connections.
@article{Shemirani:2021wk,
abstract = {The ability to identify segments of genomes identical-by-descent (IBD) is a part of standard workflows in both statistical and population genetics. However, traditional methods for finding local IBD across all pairs of individuals scale poorly leading to a lack of adoption in very large-scale datasets. Here, we present iLASH, an algorithm based on similarity detection techniques that shows equal or improved accuracy in simulations compared to current leading methods and speeds up analysis by several orders of magnitude on genomic datasets, making IBD estimation tractable for millions of individuals. We apply iLASH to the PAGE dataset of ~52,000 multi-ethnic participants, including several founder populations with elevated IBD sharing, identifying IBD segments in ~3 minutes per chromosome compared to over 6 days for a state-of-the-art algorithm. iLASH enables efficient analysis of very large-scale datasets, as we demonstrate by computing IBD across the UK Biobank (~500,000 individuals), detecting 12.9 billion pairwise connections.},
author = {Shemirani, Ruhollah and Belbin, Gillian M and Avery, Christy L and Kenny, Eimear E and Gignoux, Christopher R and Ambite, Jos{\'e} Luis},
date-added = {2021-06-15 23:00:14 -0400},
date-modified = {2021-06-15 23:00:14 -0400},
doi = {10.1038/s41467-021-22910-w},
journal = {Nat Commun},
journal-full = {Nature communications},
month = {Jun},
number = {1},
pages = {3546},
pmid = {34112768},
url = {https://pubmed.ncbi.nlm.nih.gov/34112768/},
pst = {epublish},
title = {Rapid detection of identity-by-descent tracts for mega-scale datasets},
volume = {12},
year = {2021},
bdsk-url-1 = {https://doi.org/10.1038/s41467-021-22910-w}}
Downloads: 0
{"_id":"ehnvsTKhhgcNKTMvo","bibbaseid":"shemirani-belbin-avery-kenny-gignoux-ambite-rapiddetectionofidentitybydescenttractsformegascaledatasets-2021","author_short":["Shemirani, R.","Belbin, G. M","Avery, C. L","Kenny, E. E","Gignoux, C. R","Ambite, J. L."],"bibdata":{"bibtype":"article","type":"article","abstract":"The ability to identify segments of genomes identical-by-descent (IBD) is a part of standard workflows in both statistical and population genetics. However, traditional methods for finding local IBD across all pairs of individuals scale poorly leading to a lack of adoption in very large-scale datasets. Here, we present iLASH, an algorithm based on similarity detection techniques that shows equal or improved accuracy in simulations compared to current leading methods and speeds up analysis by several orders of magnitude on genomic datasets, making IBD estimation tractable for millions of individuals. We apply iLASH to the PAGE dataset of 52,000 multi-ethnic participants, including several founder populations with elevated IBD sharing, identifying IBD segments in 3 minutes per chromosome compared to over 6 days for a state-of-the-art algorithm. iLASH enables efficient analysis of very large-scale datasets, as we demonstrate by computing IBD across the UK Biobank ( 500,000 individuals), detecting 12.9 billion pairwise connections.","author":[{"propositions":[],"lastnames":["Shemirani"],"firstnames":["Ruhollah"],"suffixes":[]},{"propositions":[],"lastnames":["Belbin"],"firstnames":["Gillian","M"],"suffixes":[]},{"propositions":[],"lastnames":["Avery"],"firstnames":["Christy","L"],"suffixes":[]},{"propositions":[],"lastnames":["Kenny"],"firstnames":["Eimear","E"],"suffixes":[]},{"propositions":[],"lastnames":["Gignoux"],"firstnames":["Christopher","R"],"suffixes":[]},{"propositions":[],"lastnames":["Ambite"],"firstnames":["José","Luis"],"suffixes":[]}],"date-added":"2021-06-15 23:00:14 -0400","date-modified":"2021-06-15 23:00:14 -0400","doi":"10.1038/s41467-021-22910-w","journal":"Nat Commun","journal-full":"Nature communications","month":"Jun","number":"1","pages":"3546","pmid":"34112768","url":"https://pubmed.ncbi.nlm.nih.gov/34112768/","pst":"epublish","title":"Rapid detection of identity-by-descent tracts for mega-scale datasets","volume":"12","year":"2021","bdsk-url-1":"https://doi.org/10.1038/s41467-021-22910-w","bibtex":"@article{Shemirani:2021wk,\n\tabstract = {The ability to identify segments of genomes identical-by-descent (IBD) is a part of standard workflows in both statistical and population genetics. However, traditional methods for finding local IBD across all pairs of individuals scale poorly leading to a lack of adoption in very large-scale datasets. Here, we present iLASH, an algorithm based on similarity detection techniques that shows equal or improved accuracy in simulations compared to current leading methods and speeds up analysis by several orders of magnitude on genomic datasets, making IBD estimation tractable for millions of individuals. We apply iLASH to the PAGE dataset of ~52,000 multi-ethnic participants, including several founder populations with elevated IBD sharing, identifying IBD segments in ~3 minutes per chromosome compared to over 6 days for a state-of-the-art algorithm. iLASH enables efficient analysis of very large-scale datasets, as we demonstrate by computing IBD across the UK Biobank (~500,000 individuals), detecting 12.9 billion pairwise connections.},\n\tauthor = {Shemirani, Ruhollah and Belbin, Gillian M and Avery, Christy L and Kenny, Eimear E and Gignoux, Christopher R and Ambite, Jos{\\'e} Luis},\n\tdate-added = {2021-06-15 23:00:14 -0400},\n\tdate-modified = {2021-06-15 23:00:14 -0400},\n\tdoi = {10.1038/s41467-021-22910-w},\n\tjournal = {Nat Commun},\n\tjournal-full = {Nature communications},\n\tmonth = {Jun},\n\tnumber = {1},\n\tpages = {3546},\n\tpmid = {34112768},\n\turl = {https://pubmed.ncbi.nlm.nih.gov/34112768/},\n\tpst = {epublish},\n\ttitle = {Rapid detection of identity-by-descent tracts for mega-scale datasets},\n\tvolume = {12},\n\tyear = {2021},\n\tbdsk-url-1 = {https://doi.org/10.1038/s41467-021-22910-w}}\n\n","author_short":["Shemirani, R.","Belbin, G. M","Avery, C. L","Kenny, E. E","Gignoux, C. R","Ambite, J. L."],"key":"Shemirani:2021wk","id":"Shemirani:2021wk","bibbaseid":"shemirani-belbin-avery-kenny-gignoux-ambite-rapiddetectionofidentitybydescenttractsformegascaledatasets-2021","role":"author","urls":{"Paper":"https://pubmed.ncbi.nlm.nih.gov/34112768/"},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/network/files/ATqGzmCTsrzAKzFAt","dataSources":["u6mkjCfDH8rbab6NJ","kPBc6iWGZmNjbuDDH","5JKhyMHuXACi7SoYs","u2FapfsC5Fb8utfsp","QAF6SGgDqRToQqywH","Lsm8pmGSv2KvYKbGa","JQebczwRZR8K3iCti","W3Ty4goQyWTLZwBCW","FXh5xBxZTSBk6n5vm","sthuNp53GwPCpZwwp","cH26r8A5bLLvrATPs","N4uyhMmECtMCQ4yxr","LEpdJHKSrq7efm57x","85sbTviwdTd4xQPNB","opp9uStnmKS3oQje8","Dkg7n26tgpZo9AL8u","4YqezFvdyhXuFZPL5","d7LXuMvui3p9KMQuk","M3cm7WzF5gdELQkoy"],"keywords":[],"search_terms":["rapid","detection","identity","descent","tracts","mega","scale","datasets","shemirani","belbin","avery","kenny","gignoux","ambite"],"title":"Rapid detection of identity-by-descent tracts for mega-scale datasets","year":2021}