A GWAS–machine learning framework reveals protein-synthesis pathway signals for yield in Theobroma cacao after population-structure correction

Abstract Improving cacao yield, a key objective in post-domestication crop improvement, remains a primary goal for breeders, but progress is often hindered by the confounding effects of population structure. To overcome this, we analyzed 346 diverse cacao accessions using an ML-based association mapping framework (with and without population structure adjustment) and a phenotype-only ML prediction of yield. By correcting for population structure, our Bootstrap Forest-based GWAS produced SNP-importance rankings whose downstream functional summaries were enriched for ribosome/translation-related terms, and several top-ranked SNPs recurred across multiple yield components (e.g., pod index and seed number) in this panel. In parallel, Neural Networks were utilized to identify cotyledon mass and length as the most powerful predictors for total wet bean mass, providing a phenotype-only prediction example for this panel. Collectively, this study provides an ML-guided, low-density association workflow and a phenotype-only prediction example for this cacao panel, while explicitly outlining limitations related to marker density and phenotype provenance.