A Stacking Ensemble Learning Framework for Genomic Prediction

Machine learning (ML) is perhaps the most useful tool for the interpretation of large genomic datasets. However, the performance of a single machine learning method in genomic selection (GS) is currently unsatisfactory. To improve the genomic predictions, we constructed a stacking ensemble learning...

Full description

Bibliographic Details
Published in:Frontiers in Genetics
Main Authors: Mang Liang, Tianpeng Chang, Bingxing An, Xinghai Duan, Lili Du, Xiaoqiao Wang, Jian Miao, Lingyang Xu, Xue Gao, Lupei Zhang, Junya Li, Huijiang Gao
Format: Article
Language:English
Published: Frontiers Media S.A. 2021-03-01
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fgene.2021.600040/full
_version_ 1852731871767560192
author Mang Liang
Tianpeng Chang
Bingxing An
Xinghai Duan
Lili Du
Xiaoqiao Wang
Jian Miao
Lingyang Xu
Xue Gao
Lupei Zhang
Junya Li
Huijiang Gao
author_facet Mang Liang
Tianpeng Chang
Bingxing An
Xinghai Duan
Lili Du
Xiaoqiao Wang
Jian Miao
Lingyang Xu
Xue Gao
Lupei Zhang
Junya Li
Huijiang Gao
author_sort Mang Liang
collection DOAJ
container_title Frontiers in Genetics
description Machine learning (ML) is perhaps the most useful tool for the interpretation of large genomic datasets. However, the performance of a single machine learning method in genomic selection (GS) is currently unsatisfactory. To improve the genomic predictions, we constructed a stacking ensemble learning framework (SELF), integrating three machine learning methods, to predict genomic estimated breeding values (GEBVs). The present study evaluated the prediction ability of SELF by analyzing three real datasets, with different genetic architecture; comparing the prediction accuracy of SELF, base learners, genomic best linear unbiased prediction (GBLUP) and BayesB. For each trait, SELF performed better than base learners, which included support vector regression (SVR), kernel ridge regression (KRR) and elastic net (ENET). The prediction accuracy of SELF was, on average, 7.70% higher than GBLUP in three datasets. Except for the milk fat percentage (MFP) traits, of the German Holstein dairy cattle dataset, SELF was more robust than BayesB in all remaining traits. Therefore, we believed that SEFL has the potential to be promoted to estimate GEBVs in other animals and plants.
format Article
id doaj-art-e7a7b1fab9e34cc2bbb5aebb8efc3b48
institution Directory of Open Access Journals
issn 1664-8021
language English
publishDate 2021-03-01
publisher Frontiers Media S.A.
record_format Article
spelling doaj-art-e7a7b1fab9e34cc2bbb5aebb8efc3b482025-08-19T21:08:17ZengFrontiers Media S.A.Frontiers in Genetics1664-80212021-03-011210.3389/fgene.2021.600040600040A Stacking Ensemble Learning Framework for Genomic PredictionMang LiangTianpeng ChangBingxing AnXinghai DuanLili DuXiaoqiao WangJian MiaoLingyang XuXue GaoLupei ZhangJunya LiHuijiang GaoMachine learning (ML) is perhaps the most useful tool for the interpretation of large genomic datasets. However, the performance of a single machine learning method in genomic selection (GS) is currently unsatisfactory. To improve the genomic predictions, we constructed a stacking ensemble learning framework (SELF), integrating three machine learning methods, to predict genomic estimated breeding values (GEBVs). The present study evaluated the prediction ability of SELF by analyzing three real datasets, with different genetic architecture; comparing the prediction accuracy of SELF, base learners, genomic best linear unbiased prediction (GBLUP) and BayesB. For each trait, SELF performed better than base learners, which included support vector regression (SVR), kernel ridge regression (KRR) and elastic net (ENET). The prediction accuracy of SELF was, on average, 7.70% higher than GBLUP in three datasets. Except for the milk fat percentage (MFP) traits, of the German Holstein dairy cattle dataset, SELF was more robust than BayesB in all remaining traits. Therefore, we believed that SEFL has the potential to be promoted to estimate GEBVs in other animals and plants.https://www.frontiersin.org/articles/10.3389/fgene.2021.600040/fullensemble learningstackinggenomic predictionmachine learningprediction accuracy
spellingShingle Mang Liang
Tianpeng Chang
Bingxing An
Xinghai Duan
Lili Du
Xiaoqiao Wang
Jian Miao
Lingyang Xu
Xue Gao
Lupei Zhang
Junya Li
Huijiang Gao
A Stacking Ensemble Learning Framework for Genomic Prediction
ensemble learning
stacking
genomic prediction
machine learning
prediction accuracy
title A Stacking Ensemble Learning Framework for Genomic Prediction
title_full A Stacking Ensemble Learning Framework for Genomic Prediction
title_fullStr A Stacking Ensemble Learning Framework for Genomic Prediction
title_full_unstemmed A Stacking Ensemble Learning Framework for Genomic Prediction
title_short A Stacking Ensemble Learning Framework for Genomic Prediction
title_sort stacking ensemble learning framework for genomic prediction
topic ensemble learning
stacking
genomic prediction
machine learning
prediction accuracy
url https://www.frontiersin.org/articles/10.3389/fgene.2021.600040/full
work_keys_str_mv AT mangliang astackingensemblelearningframeworkforgenomicprediction
AT tianpengchang astackingensemblelearningframeworkforgenomicprediction
AT bingxingan astackingensemblelearningframeworkforgenomicprediction
AT xinghaiduan astackingensemblelearningframeworkforgenomicprediction
AT lilidu astackingensemblelearningframeworkforgenomicprediction
AT xiaoqiaowang astackingensemblelearningframeworkforgenomicprediction
AT jianmiao astackingensemblelearningframeworkforgenomicprediction
AT lingyangxu astackingensemblelearningframeworkforgenomicprediction
AT xuegao astackingensemblelearningframeworkforgenomicprediction
AT lupeizhang astackingensemblelearningframeworkforgenomicprediction
AT junyali astackingensemblelearningframeworkforgenomicprediction
AT huijianggao astackingensemblelearningframeworkforgenomicprediction
AT mangliang stackingensemblelearningframeworkforgenomicprediction
AT tianpengchang stackingensemblelearningframeworkforgenomicprediction
AT bingxingan stackingensemblelearningframeworkforgenomicprediction
AT xinghaiduan stackingensemblelearningframeworkforgenomicprediction
AT lilidu stackingensemblelearningframeworkforgenomicprediction
AT xiaoqiaowang stackingensemblelearningframeworkforgenomicprediction
AT jianmiao stackingensemblelearningframeworkforgenomicprediction
AT lingyangxu stackingensemblelearningframeworkforgenomicprediction
AT xuegao stackingensemblelearningframeworkforgenomicprediction
AT lupeizhang stackingensemblelearningframeworkforgenomicprediction
AT junyali stackingensemblelearningframeworkforgenomicprediction
AT huijianggao stackingensemblelearningframeworkforgenomicprediction