KCRR: a nonlinear machine learning with a modified genomic similarity matrix improved the genomic prediction efficiency

Nowadays, advances in high-throughput sequencing benefit the increasing application of genomic prediction (GP) in breeding programs. In this research, we designed a Cosine kernel-based KRR named KCRR to perform GP. This paper assessed the prediction accuracies of 12 traits with various heritability and genetic architectures from four populations using the genomic best linear unbiased prediction (GBLUP), BayesB, support vector regression (SVR), and KCRR. On the whole, KCRR performed stably for all traits of multiple species, indicating that the hypothesis of KCRR had the potential to be adapted to a wide range of genetic architectures. Moreover, we defined a modified genomic similarity matrix named Cosine similarity matrix (CS matrix). The results indicated that the accuracies between GBLUP_kinship and GBLUP_CS almost unanimously for all traits, but the computing efficiency has increased by an average of 20 times. Our research will be a significant promising strategy in future GP.

Automated summary

The study introduced a novel cosine kernel-based KRR model, KCRR, for genomic prediction (GP) in breeding programs. KCRR showed stable performance across multiple species, suggesting its potential for diverse genetic architectures. Additionally, a modified genomic similarity matrix called Cosine similarity matrix (CS matrix) was defined, which significantly improved computing efficiency without compromising prediction accuracy when compared to traditional methods like GBLUP. This research presents a promising strategy for future genomic prediction.