Data from: Applications of random forest feature selection for fine-scale genetic population assignment
Genetic population assignment used to inform wildlife management and conservation efforts requires panels of highly informative genetic markers and sensitive assignment tests. We explored the utility of machine-learning algorithms (random forest, regularized random forest, and guided regularized ran...
Main Authors: | , , , , , , |
---|---|
Language: | unknown |
Published: |
2017
|
Subjects: | |
Online Access: | http://nbn-resolving.org/urn:nbn:nl:ui:13-4v-kwh8 https://easy.dans.knaw.nl/ui/datasets/id/easy-dataset:98388 |
id |
ftdans:oai:easy.dans.knaw.nl:easy-dataset:98388 |
---|---|
record_format |
openpolar |
spelling |
ftdans:oai:easy.dans.knaw.nl:easy-dataset:98388 2023-07-02T03:31:42+02:00 Data from: Applications of random forest feature selection for fine-scale genetic population assignment Sylvester, Emma V.A. Bentzen, Paul Bradbury, Ian R. Clément, Marie Pearce, Jon Horne, John Beiko, Robert G. 2017-07-27T17:40:10.000+02:00 http://nbn-resolving.org/urn:nbn:nl:ui:13-4v-kwh8 https://easy.dans.knaw.nl/ui/datasets/id/easy-dataset:98388 unknown doi:10.5061/dryad.93h33/1 doi:10.5061/dryad.93h33/2 doi:10.1111/eva.12524 http://nbn-resolving.org/urn:nbn:nl:ui:13-4v-kwh8 doi:10.5061/dryad.93h33 https://easy.dans.knaw.nl/ui/datasets/id/easy-dataset:98388 OPEN_ACCESS: The data are archived in Easy, they are accessible elsewhere through the DOI https://dans.knaw.nl/en/about/organisation-and-policy/legal-information/DANSLicence.pdf Life sciences medicine and health care 2017 ftdans https://doi.org/10.5061/dryad.93h33/110.5061/dryad.93h33/210.1111/eva.1252410.5061/dryad.93h33 2023-06-13T13:25:06Z Genetic population assignment used to inform wildlife management and conservation efforts requires panels of highly informative genetic markers and sensitive assignment tests. We explored the utility of machine-learning algorithms (random forest, regularized random forest, and guided regularized random forest) compared with FST ranking for selection of single nucleotide polymorphisms (SNP) for fine-scale population assignment. We applied these methods to an unpublished SNP dataset for Atlantic salmon (Salmo salar) and a published SNP data set for Alaskan Chinook salmon (Oncorhynchus tshawytscha). In each species, we identified the minimum panel size required to obtain a self-assignment accuracy of at least 90% using each method to create panels of 50-700 markers Panels of SNPs identified using random forest-based methods performed up to 7.8 and 11.2 percentage points better than FST-selected panels of similar size for the Atlantic salmon and Chinook salmon data, respectively. Self-assignment accuracy ≥90% was obtained with panels of 670 and 384 SNPs for each dataset, respectively, a level of accuracy never reached for these species using FST-selected panels. Our results demonstrate a role for machine-learning approaches in marker selection across large genomic datasets to improve assignment for management and conservation of exploited populations. Other/Unknown Material Atlantic salmon Salmo salar Data Archiving and Networked Services (DANS): EASY (KNAW - Koninklijke Nederlandse Akademie van Wetenschappen) |
institution |
Open Polar |
collection |
Data Archiving and Networked Services (DANS): EASY (KNAW - Koninklijke Nederlandse Akademie van Wetenschappen) |
op_collection_id |
ftdans |
language |
unknown |
topic |
Life sciences medicine and health care |
spellingShingle |
Life sciences medicine and health care Sylvester, Emma V.A. Bentzen, Paul Bradbury, Ian R. Clément, Marie Pearce, Jon Horne, John Beiko, Robert G. Data from: Applications of random forest feature selection for fine-scale genetic population assignment |
topic_facet |
Life sciences medicine and health care |
description |
Genetic population assignment used to inform wildlife management and conservation efforts requires panels of highly informative genetic markers and sensitive assignment tests. We explored the utility of machine-learning algorithms (random forest, regularized random forest, and guided regularized random forest) compared with FST ranking for selection of single nucleotide polymorphisms (SNP) for fine-scale population assignment. We applied these methods to an unpublished SNP dataset for Atlantic salmon (Salmo salar) and a published SNP data set for Alaskan Chinook salmon (Oncorhynchus tshawytscha). In each species, we identified the minimum panel size required to obtain a self-assignment accuracy of at least 90% using each method to create panels of 50-700 markers Panels of SNPs identified using random forest-based methods performed up to 7.8 and 11.2 percentage points better than FST-selected panels of similar size for the Atlantic salmon and Chinook salmon data, respectively. Self-assignment accuracy ≥90% was obtained with panels of 670 and 384 SNPs for each dataset, respectively, a level of accuracy never reached for these species using FST-selected panels. Our results demonstrate a role for machine-learning approaches in marker selection across large genomic datasets to improve assignment for management and conservation of exploited populations. |
author |
Sylvester, Emma V.A. Bentzen, Paul Bradbury, Ian R. Clément, Marie Pearce, Jon Horne, John Beiko, Robert G. |
author_facet |
Sylvester, Emma V.A. Bentzen, Paul Bradbury, Ian R. Clément, Marie Pearce, Jon Horne, John Beiko, Robert G. |
author_sort |
Sylvester, Emma V.A. |
title |
Data from: Applications of random forest feature selection for fine-scale genetic population assignment |
title_short |
Data from: Applications of random forest feature selection for fine-scale genetic population assignment |
title_full |
Data from: Applications of random forest feature selection for fine-scale genetic population assignment |
title_fullStr |
Data from: Applications of random forest feature selection for fine-scale genetic population assignment |
title_full_unstemmed |
Data from: Applications of random forest feature selection for fine-scale genetic population assignment |
title_sort |
data from: applications of random forest feature selection for fine-scale genetic population assignment |
publishDate |
2017 |
url |
http://nbn-resolving.org/urn:nbn:nl:ui:13-4v-kwh8 https://easy.dans.knaw.nl/ui/datasets/id/easy-dataset:98388 |
genre |
Atlantic salmon Salmo salar |
genre_facet |
Atlantic salmon Salmo salar |
op_relation |
doi:10.5061/dryad.93h33/1 doi:10.5061/dryad.93h33/2 doi:10.1111/eva.12524 http://nbn-resolving.org/urn:nbn:nl:ui:13-4v-kwh8 doi:10.5061/dryad.93h33 https://easy.dans.knaw.nl/ui/datasets/id/easy-dataset:98388 |
op_rights |
OPEN_ACCESS: The data are archived in Easy, they are accessible elsewhere through the DOI https://dans.knaw.nl/en/about/organisation-and-policy/legal-information/DANSLicence.pdf |
op_doi |
https://doi.org/10.5061/dryad.93h33/110.5061/dryad.93h33/210.1111/eva.1252410.5061/dryad.93h33 |
_version_ |
1770271082711875584 |