Using the Pearson’s correlation coefficient as the sole metric to measure the accuracy of quantitative trait prediction: is it sufficient?

How to evaluate the accuracy of quantitative trait prediction is crucial to choose the best model among several possible choices in plant breeding. Pearson’s correlation coefficient (PCC), serving as a metric for quantifying the strength of the linear association between two variables, is widely use...

Full description

Saved in:
Bibliographic Details
Main Authors: Shouhui Pan, Zhongqiang Liu, Yanyun Han, Dongfeng Zhang, Xiangyu Zhao, Jinlong Li, Kaiyi Wang
Format: Article
Language:English
Published: Frontiers Media S.A. 2024-12-01
Series:Frontiers in Plant Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpls.2024.1480463/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846128992677003264
author Shouhui Pan
Shouhui Pan
Zhongqiang Liu
Zhongqiang Liu
Yanyun Han
Yanyun Han
Dongfeng Zhang
Dongfeng Zhang
Xiangyu Zhao
Xiangyu Zhao
Jinlong Li
Jinlong Li
Kaiyi Wang
Kaiyi Wang
author_facet Shouhui Pan
Shouhui Pan
Zhongqiang Liu
Zhongqiang Liu
Yanyun Han
Yanyun Han
Dongfeng Zhang
Dongfeng Zhang
Xiangyu Zhao
Xiangyu Zhao
Jinlong Li
Jinlong Li
Kaiyi Wang
Kaiyi Wang
author_sort Shouhui Pan
collection DOAJ
description How to evaluate the accuracy of quantitative trait prediction is crucial to choose the best model among several possible choices in plant breeding. Pearson’s correlation coefficient (PCC), serving as a metric for quantifying the strength of the linear association between two variables, is widely used to evaluate the accuracy of the quantitative trait prediction models, and generally performs well in most circumstances. However, PCC may not always offer a comprehensive view of predictive accuracy, especially in cases involving nonlinear relationships or complex dependencies in machine learning-based methods. It has been found that many papers on quantitative trait prediction solely use PCC as a single metric to evaluate the accuracy of their models, which is insufficient and limited from a formal perspective. This study addresses this crucial issue by presenting a typical example and conducting a comparative analysis of PCC and nine other evaluation metrics using four traditional methods and four machine learning-based methods, thereby contributing to the improvement of practical applicability and reliability of plant quantitative trait prediction models. It is recommended to employ PCC in conjunction with other evaluation metrics in a targeted manner based on specific application scenarios to reduce the likelihood of drawing misleading conclusions.
format Article
id doaj-art-cb98cda2e0114c2b827c66340549854b
institution Kabale University
issn 1664-462X
language English
publishDate 2024-12-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Plant Science
spelling doaj-art-cb98cda2e0114c2b827c66340549854b2024-12-10T11:05:46ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2024-12-011510.3389/fpls.2024.14804631480463Using the Pearson’s correlation coefficient as the sole metric to measure the accuracy of quantitative trait prediction: is it sufficient?Shouhui Pan0Shouhui Pan1Zhongqiang Liu2Zhongqiang Liu3Yanyun Han4Yanyun Han5Dongfeng Zhang6Dongfeng Zhang7Xiangyu Zhao8Xiangyu Zhao9Jinlong Li10Jinlong Li11Kaiyi Wang12Kaiyi Wang13Information Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaNational Engineering Research Center for Information Technology in Agriculture, Beijing, ChinaInformation Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaNational Engineering Research Center for Information Technology in Agriculture, Beijing, ChinaInformation Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaNational Engineering Research Center for Information Technology in Agriculture, Beijing, ChinaInformation Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaNational Engineering Research Center for Information Technology in Agriculture, Beijing, ChinaInformation Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaNational Engineering Research Center for Information Technology in Agriculture, Beijing, ChinaInformation Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaNational Engineering Research Center for Information Technology in Agriculture, Beijing, ChinaInformation Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaNational Engineering Research Center for Information Technology in Agriculture, Beijing, ChinaHow to evaluate the accuracy of quantitative trait prediction is crucial to choose the best model among several possible choices in plant breeding. Pearson’s correlation coefficient (PCC), serving as a metric for quantifying the strength of the linear association between two variables, is widely used to evaluate the accuracy of the quantitative trait prediction models, and generally performs well in most circumstances. However, PCC may not always offer a comprehensive view of predictive accuracy, especially in cases involving nonlinear relationships or complex dependencies in machine learning-based methods. It has been found that many papers on quantitative trait prediction solely use PCC as a single metric to evaluate the accuracy of their models, which is insufficient and limited from a formal perspective. This study addresses this crucial issue by presenting a typical example and conducting a comparative analysis of PCC and nine other evaluation metrics using four traditional methods and four machine learning-based methods, thereby contributing to the improvement of practical applicability and reliability of plant quantitative trait prediction models. It is recommended to employ PCC in conjunction with other evaluation metrics in a targeted manner based on specific application scenarios to reduce the likelihood of drawing misleading conclusions.https://www.frontiersin.org/articles/10.3389/fpls.2024.1480463/fullgenomic selectionquantitative trait predictionPearson’s correlation coefficientevaluation metricregression prediction
spellingShingle Shouhui Pan
Shouhui Pan
Zhongqiang Liu
Zhongqiang Liu
Yanyun Han
Yanyun Han
Dongfeng Zhang
Dongfeng Zhang
Xiangyu Zhao
Xiangyu Zhao
Jinlong Li
Jinlong Li
Kaiyi Wang
Kaiyi Wang
Using the Pearson’s correlation coefficient as the sole metric to measure the accuracy of quantitative trait prediction: is it sufficient?
Frontiers in Plant Science
genomic selection
quantitative trait prediction
Pearson’s correlation coefficient
evaluation metric
regression prediction
title Using the Pearson’s correlation coefficient as the sole metric to measure the accuracy of quantitative trait prediction: is it sufficient?
title_full Using the Pearson’s correlation coefficient as the sole metric to measure the accuracy of quantitative trait prediction: is it sufficient?
title_fullStr Using the Pearson’s correlation coefficient as the sole metric to measure the accuracy of quantitative trait prediction: is it sufficient?
title_full_unstemmed Using the Pearson’s correlation coefficient as the sole metric to measure the accuracy of quantitative trait prediction: is it sufficient?
title_short Using the Pearson’s correlation coefficient as the sole metric to measure the accuracy of quantitative trait prediction: is it sufficient?
title_sort using the pearson s correlation coefficient as the sole metric to measure the accuracy of quantitative trait prediction is it sufficient
topic genomic selection
quantitative trait prediction
Pearson’s correlation coefficient
evaluation metric
regression prediction
url https://www.frontiersin.org/articles/10.3389/fpls.2024.1480463/full
work_keys_str_mv AT shouhuipan usingthepearsonscorrelationcoefficientasthesolemetrictomeasuretheaccuracyofquantitativetraitpredictionisitsufficient
AT shouhuipan usingthepearsonscorrelationcoefficientasthesolemetrictomeasuretheaccuracyofquantitativetraitpredictionisitsufficient
AT zhongqiangliu usingthepearsonscorrelationcoefficientasthesolemetrictomeasuretheaccuracyofquantitativetraitpredictionisitsufficient
AT zhongqiangliu usingthepearsonscorrelationcoefficientasthesolemetrictomeasuretheaccuracyofquantitativetraitpredictionisitsufficient
AT yanyunhan usingthepearsonscorrelationcoefficientasthesolemetrictomeasuretheaccuracyofquantitativetraitpredictionisitsufficient
AT yanyunhan usingthepearsonscorrelationcoefficientasthesolemetrictomeasuretheaccuracyofquantitativetraitpredictionisitsufficient
AT dongfengzhang usingthepearsonscorrelationcoefficientasthesolemetrictomeasuretheaccuracyofquantitativetraitpredictionisitsufficient
AT dongfengzhang usingthepearsonscorrelationcoefficientasthesolemetrictomeasuretheaccuracyofquantitativetraitpredictionisitsufficient
AT xiangyuzhao usingthepearsonscorrelationcoefficientasthesolemetrictomeasuretheaccuracyofquantitativetraitpredictionisitsufficient
AT xiangyuzhao usingthepearsonscorrelationcoefficientasthesolemetrictomeasuretheaccuracyofquantitativetraitpredictionisitsufficient
AT jinlongli usingthepearsonscorrelationcoefficientasthesolemetrictomeasuretheaccuracyofquantitativetraitpredictionisitsufficient
AT jinlongli usingthepearsonscorrelationcoefficientasthesolemetrictomeasuretheaccuracyofquantitativetraitpredictionisitsufficient
AT kaiyiwang usingthepearsonscorrelationcoefficientasthesolemetrictomeasuretheaccuracyofquantitativetraitpredictionisitsufficient
AT kaiyiwang usingthepearsonscorrelationcoefficientasthesolemetrictomeasuretheaccuracyofquantitativetraitpredictionisitsufficient