Abstract
LightGBM is an ensemble model of decision trees for classification and regression prediction. We demonstrate its utility in genomic selection-assisted breeding with a large dataset of inbred and hybrid maize lines. LightGBM exhibits superior performance in terms of prediction precision, model stability, and computing efficiency through a series of benchmark tests. We also assess the factors that are essential to ensure the best performance of genomic selection prediction by taking complex scenarios in crop hybrid breeding into account. LightGBM has been implemented as a toolbox, CropGBM, encompassing multiple novel functions and analytical modules to facilitate genomically designed breeding in crops.
Highlights
The rapid advancement of genotyping technology has promoted the integration of genomic prediction into modern breeding programs for both animals and crops [1,2,3,4,5]
As a set of non-redundant features is crucial for Machine learning (ML) to avoid dimension explosion, 32,559 haplotypic tag single-nucleotide polymorphisms (SNPs) evenly distributed in the genome were used as genotype features (Methods)
LightGBM is an ensemble learning framework, which adopts the strategy of leaf-wise tree growth to construct decision trees and features ultrafast efficiency in coping with large dataset
Summary
The rapid advancement of genotyping technology has promoted the integration of genomic prediction into modern breeding programs for both animals and crops [1,2,3,4,5]. As most traits subject to selective breeding are determined by quantitative trait loci (QTLs), genomic selection (GS) has been validated as an effective approach utilizing whole-genome variations to build genomic prediction models without prior characterization of trait-associated genes [8, 9]. Among existing GS tools, ridge regression BLUP (rrBLUP) is a state-of-the-art method that uses a linear mixed-effect model to deduce the genomic kinship of breeding materials and marker effects for phenotype prediction [10].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
