Genomic selection of agronomic and seed quality traits in hybrid Brassica napus L. based on parametric and machine learning methods
Bibliographic record
Abstract
Various GS models obtained high prediction accuracy in agronomic and seed quality traits in canola with an appropriate TP, a key component that affects prediction accuracy in GS. Abstract Genomic selection (GS) has become a useful tool in plant breeding with advantages in shortening the breeding cycle and improving cost efficiencies. Various factors that affect the prediction accuracy on Brassica napus L. were examined based on a mixed population consisting of 91 parental genotypes and 345 F1 hybrids. Based on rrBLUP, the prediction of hybrid performance using a training population (TP) of 91 parental genotypes produced a prediction accuracy that varied between 1 to 2 % on seed yield (YLD) and 23 to 24 % on seed protein content (SPC). Whereas, a mixed TP of 91 genotypes consisting of both parental and hybrid genotypes performed drastically better (28 % for YLD and 45 % for SPC). The prediction accuracy increased as the mixed TP size increased to 262 (38 % for YLD and 58 % for SPC). Marker density effects were investigated, and the medium-coverage-marker set (16,855 SNPs) performed the best. Model performance of various Bayesian models was compared with rrBLUP and GBLUP. The prediction accuracy based on GBLUP was slightly lower than the Bayesian models on YLD and plant height (HT), but equal with BayesA on SPC, seed oil content (SOC) and seed glucosinolate content (GSL). Lastly, three machine learning algorithms all showed strong robustness in predicting all five traits, with the lowest prediction produced on YLD (69 to 72 %) and the highest on GSL (84 to 87 %). Taken together, this research offers valuable information in implementing GS in hybrid breeding of B. napus.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".