A neural network for phenotyping <i>Fusarium</i>‐damaged kernels (FDKs) in wheat and its impact on genomic selection accuracy
Bibliographic record
Abstract
Abstract Fusarium head blight (FHB) remains one of the most destructive diseases in wheat. Primarily caused by the mycotoxigenic fungi Fusarium graminearum , FHB results in both widespread yield loss and deoxynivalenol (DON) contamination of wheat grain. Phenotyping for Fusarium‐ damaged kernels (FDKs) is the most efficient estimate of resistance to DON accumulation outside of performing costly and time‐consuming laboratory assays. However, manual phenotyping for FDKs can be tedious and highly subjective to observers. This study developed and tested an open‐access, easy‐to‐use, and effective method for phenotyping FDKs using a neural network capable of analyzing cell phone camera images. Quantitative genetic analysis of FDK data generated by our trained neural network found that the trait had a broad sense heritability of 0.48, and its phenotypic and genetic correlations with DON were 0.41 and 0.58, respectively. To determine if our neural network‐derived FDK data could be useful in a modern breeding scenario, we included it in a multi‐trait genomic selection (GS) model and evaluated the model's ability to predict DON. We found that including FDK data generated by our trained neural network on the test set during GS model training more than doubled GS accuracy, but the highest accuracy was obtained using conventional FDK data. Although further training is needed to improve the capabilities of our neural network, initial testing shows encouraging results and demonstrates the possibility of providing an automated and objective phenotyping method for FDKs that could be widely deployed to support FHB resistance breeding efforts.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 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 teacher head, 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".