Multi-Trait Regressor Stacking Increased Genomic Prediction Accuracy of Sorghum Grain Composition
, J. Lucas Boatwright 1,2, Kathleen Jordan 1, Richard Boyles 2,3 and Stephen Kresovich 1,2Round 1
Reviewer 1 Report
It was a real pleasure for me to go through this manuscript. It reads very well, indicative of the serious that authors put in its preparation. More importantly, the experimental design and the statistical methods are adequate and clearly presented.
Stacking ensemble methods are gaining ground in predictive analysis techniques such as machine learning to improve the overall accuracy of the predictors. Here, authors successfully implemented a stacking method for genomic prediction using a Bayesian approach. As expected, the stacking method (Bayesian multi-output regressor stacking) outperformed the single trait single environment models, since a stacking method by essence takes advantage of the correct predictions made by each single predictor.
Author Response
Dear reviewer,
Thank you for your reviews and comments. We appreciate the time taken and effort made to improve our manuscript. We hope you all the best as well.
Sincerely,
Sirjan sapkota
Reviewer 2 Report
See attached file.
Comments for author File: 
Comments.pdf
Author Response
Dear Reviewer,
Thank you for your comments and suggestions. Please see the response in the file attached.
Sincerely,
Sirjan
Author Response File: 
Author Response.docx
Round 2
Reviewer 2 Report
The authors have addressed all my previous concerns and should be accepted as is.
