Interpreting single-step genomic evaluation as a neural network of three layers: pedigree, genotypes, and phenotypes
Abstract The single-step approach has become the most widely-used methodology for genomic evaluations when only a subset of phenotyped individuals in the pedigree are genotyped, where the genotypes for non-genotyped individuals are imputed based on gene contents (i.e., genotypes) of genotyped indivi...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | deu |
| Published: |
BMC
2023-10-01
|
| Series: | Genetics Selection Evolution |
| Online Access: | https://doi.org/10.1186/s12711-023-00838-7 |
| _version_ | 1827725072922574848 |
|---|---|
| author | Tianjing Zhao Hao Cheng |
| author_facet | Tianjing Zhao Hao Cheng |
| author_sort | Tianjing Zhao |
| collection | DOAJ |
| description | Abstract The single-step approach has become the most widely-used methodology for genomic evaluations when only a subset of phenotyped individuals in the pedigree are genotyped, where the genotypes for non-genotyped individuals are imputed based on gene contents (i.e., genotypes) of genotyped individuals through their pedigree relationships. We proposed a new method named single-step neural network with mixed models (NNMM) to represent single-step genomic evaluations as a neural network of three sequential layers: pedigree, genotypes, and phenotypes. These three sequential layers of information create a unified network instead of two separate steps, allowing the unobserved gene contents of non-genotyped individuals to be sampled based on pedigree, observed genotypes of genotyped individuals, and phenotypes. In addition to imputation of genotypes using all three sources of information, including phenotypes, genotypes, and pedigree, single-step NNMM provides a more flexible framework to allow nonlinear relationships between genotypes and phenotypes, and for individuals to be genotyped with different single-nucleotide polymorphism (SNP) panels. The single-step NNMM has been implemented in the software package “JWAS’. |
| first_indexed | 2024-03-10T22:24:19Z |
| format | Article |
| id | doaj.art-949e8ffbb5904ba59ac1aaaf50e2e330 |
| institution | Directory Open Access Journal |
| issn | 1297-9686 |
| language | deu |
| last_indexed | 2024-03-10T22:24:19Z |
| publishDate | 2023-10-01 |
| publisher | BMC |
| record_format | Article |
| series | Genetics Selection Evolution |
| spelling | doaj.art-949e8ffbb5904ba59ac1aaaf50e2e3302023-11-19T12:09:45ZdeuBMCGenetics Selection Evolution1297-96862023-10-015511810.1186/s12711-023-00838-7Interpreting single-step genomic evaluation as a neural network of three layers: pedigree, genotypes, and phenotypesTianjing Zhao0Hao Cheng1Department of Animal Science, University of California DavisDepartment of Animal Science, University of California DavisAbstract The single-step approach has become the most widely-used methodology for genomic evaluations when only a subset of phenotyped individuals in the pedigree are genotyped, where the genotypes for non-genotyped individuals are imputed based on gene contents (i.e., genotypes) of genotyped individuals through their pedigree relationships. We proposed a new method named single-step neural network with mixed models (NNMM) to represent single-step genomic evaluations as a neural network of three sequential layers: pedigree, genotypes, and phenotypes. These three sequential layers of information create a unified network instead of two separate steps, allowing the unobserved gene contents of non-genotyped individuals to be sampled based on pedigree, observed genotypes of genotyped individuals, and phenotypes. In addition to imputation of genotypes using all three sources of information, including phenotypes, genotypes, and pedigree, single-step NNMM provides a more flexible framework to allow nonlinear relationships between genotypes and phenotypes, and for individuals to be genotyped with different single-nucleotide polymorphism (SNP) panels. The single-step NNMM has been implemented in the software package “JWAS’.https://doi.org/10.1186/s12711-023-00838-7 |
| spellingShingle | Tianjing Zhao Hao Cheng Interpreting single-step genomic evaluation as a neural network of three layers: pedigree, genotypes, and phenotypes Genetics Selection Evolution |
| title | Interpreting single-step genomic evaluation as a neural network of three layers: pedigree, genotypes, and phenotypes |
| title_full | Interpreting single-step genomic evaluation as a neural network of three layers: pedigree, genotypes, and phenotypes |
| title_fullStr | Interpreting single-step genomic evaluation as a neural network of three layers: pedigree, genotypes, and phenotypes |
| title_full_unstemmed | Interpreting single-step genomic evaluation as a neural network of three layers: pedigree, genotypes, and phenotypes |
| title_short | Interpreting single-step genomic evaluation as a neural network of three layers: pedigree, genotypes, and phenotypes |
| title_sort | interpreting single step genomic evaluation as a neural network of three layers pedigree genotypes and phenotypes |
| url | https://doi.org/10.1186/s12711-023-00838-7 |
| work_keys_str_mv | AT tianjingzhao interpretingsinglestepgenomicevaluationasaneuralnetworkofthreelayerspedigreegenotypesandphenotypes AT haocheng interpretingsinglestepgenomicevaluationasaneuralnetworkofthreelayerspedigreegenotypesandphenotypes |