AI Science Tracker
EN

Identifying key genes for European canker resistance in apple: machine learning and gene expression profiling of quantitative disease resistance.

NIAB, Lawrence Weaver Rd, Cambridge, CB3 0LE, UK · 1 Dec 2025 · medicine

Discovery

Identifying key genes for European canker resistance in apple: machine learning and gene expression profiling of quantitative disease resistance.

Source check: Source checked. Not independent scientific confirmation.

Finding: Twenty-six stable transcriptional predictors; 4CL/phenylpropanoid, NLR/RLK/WAK and epigenetic-regulator transcripts associated with partial resistance across six QTLs. Genotype-blocked five-fold CV on 20 full-sibling genotypes; separate expression validation in ‘Golden Delicious’ and ‘M9 EMLA’. Accuracy was 0.67 in CV and 1.00 in the two-cultivar validation table, whose small cultivar sample and limited generalizability are explicit caveats.

Technology: Random Forest variable-importance selection with genotype-blocked stability selection identified resistance-predictive transcripts from RNA-seq; expression/QTL analyses then localized candidate genes and pathways.

Publication: Preprint · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
Random Forest variable-importance selection with genotype-blocked stability selection identified resistance-predictive transcripts from RNA-seq; expression/QTL analyses then localized candidate genes and pathways.
Test and result
Twenty-six stable transcriptional predictors; 4CL/phenylpropanoid, NLR/RLK/WAK and epigenetic-regulator transcripts associated with partial resistance across six QTLs.
Limitation / still unknown
Genotype-blocked five-fold CV on 20 full-sibling genotypes; separate expression validation in ‘Golden Delicious’ and ‘M9 EMLA’. Accuracy was 0.67 in CV and 1.00 in the two-cultivar validation table, whose small cultivar sample and limited generalizability are explicit caveats.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://assets-eu.researchsquare.com/files/rs-7997107/v1/66ec742f-e758-4a1f-a763-5b34bbb1da5f.pdf · https://www.nature.com/articles/s41598-025-33478-6

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: The primary Research Square v1 (posted 2025-12-01) and the linked Scientific Reports article describe the same result: genotype-blocked Random Forest feature selection ranked 26 stable transcripts for European canker resistance; the model reached 0.67 accuracy in genotype-blocked five-fold testing (95% CI 0.55–0.77, p=0.021), and expression patterns were checked in a separate ‘Golden Delicious’/‘M9 EMLA’ dataset. The paper links candidate defense, phenylpropanoid and regulatory genes to six resistance QTLs. The independent check covers two cultivars and the authors state broader cultivar and functional validation is still needed; this is a candidate-marker result, not proof of causal resistance genes. No matching DOI or same-result record appears in the active or archived catalog; prior QTL mapping is a different result..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open in the full catalog for filters, charts and related discoveries. Browse medicine discoveries.