Additional file 2 of Ridge regression and deep learning models for genome-wide selection of complex traits in New Mexican Chile peppers

Supplementary Material 2: Additional file 2. Table S1. Genomic prediction accuracy across different ridge regression and deep learning models for 10 iterations and 10-fold cross validations for subset of markers derived from linkage disequilibrium (LD) coefficients and 14,922 SNP loci for first pod date. Table S2. Genomic prediction accuracy across different ridge regression and deep learning models for 10 iterations and 10-fold cross validations for subset of markers derived from linkage disequilibrium (LD) coefficients and 14,922 SNP loci for flowering time. Table S3. Genomic prediction accuracy across different ridge regression and deep learning models for 10 iterations and 10-fold cross validations for subset of markers derived from linkage disequilibrium (LD) coefficients and 14,922 SNP loci for mature green yield. Table S4. Genomic prediction accuracy across different ridge regression and deep learning models for 10 iterations and 10-fold cross validations for subset of markers derived from linkage disequilibrium (LD) coefficients and 14,922 SNP loci for plant height. Table S5. Genomic prediction accuracy across different ridge regression and deep learning models for 10 iterations and 10-fold cross validations for subset of markers derived from linkage disequilibrium (LD) coefficients and 14,922 SNP loci for plant width. Table S6. Genomic prediction accuracy across different ridge regression and deep learning models for 10 iterations and 10-fold cross validations for subset of markers derived from linkage disequilibrium (LD) coefficients and 14,922 SNP loci for mature red yield. Table S7. Genomic prediction accuracy across different ridge regression and deep learning models for 10 iterations and 10-fold cross validations for subset of markers derived from linkage disequilibrium (LD) coefficients and 14,922 SNP loci for ten pod weight. Table S8. Genomic prediction accuracy across different ridge regression and deep learning models for 10 iterations and 10-fold cross validations for subset of markers derived from linkage disequilibrium (LD) coefficients and 14,922 SNP loci for total yield per plant.