Empirical Data Analysis for Training Population Selection in Wheat Breeding
Bibliographic record
Abstract
The Genomic Assisted Breeding lab, in collaboration with Agriculture and Agri-Food Canada at the Swift Current Research and Development Center, evaluated various genomic plant breeding methods using data from an ongoing wheat breeding program. The study aimed to test the efficacy of these methods, compare state-of-the-art training set (TRS) optimization techniques, assess the impact of historical and parental data on the TRS, and evaluate the accuracy of additive and non-additive genomic prediction models. Results indicated that the Mean Coefficient of Determination generally outperformed the Average Relationship (AvgRel), except in optimal cases where AvgRel excelled. The optimal optimization method varied by model, supporting the ”no-free-lunch” theorem in statistic, and further tests with different TRS sizes are necessary to determine the best method. All optimization methods surpassed random sampling, but the breeder-proposed TRS performed worse than random sampling, highlighting the sophistication of our optimization approaches. Adding parental and historical data did not improve prediction accuracy, probably due to decreased similarity between the TRS and the test set or different environmental effects. However, for the 2021 lines, accuracy improved when adding parental lines measured in the same year. The study also found that Reproducing Kernel Hilbert Space regression outperformed traditional parametric models and other non-additive models like Random Forest.
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 | 0.032 | 0.092 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".