首页|University of Bari 'Aldo Moro' Reports Findings in Artificial Intelligence (Expl ainable artificial intelligence for genotype-to-phenotype prediction in plant br eeding: a case study with a dataset from an almond germplasm collection)
University of Bari 'Aldo Moro' Reports Findings in Artificial Intelligence (Expl ainable artificial intelligence for genotype-to-phenotype prediction in plant br eeding: a case study with a dataset from an almond germplasm collection)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
New research on Artificial Intelligenc e is the subject of a report. According to news reporting originating from Bari, Italy, by NewsRx correspondents, research stated, "Advances in DNA sequencing r evolutionized plant genomics and significantly contributed to the study of genet ic diversity. However, predicting phenotypes from genomic data remains a challen ge, particularly in the context of plant breeding." Our news editors obtained a quote from the research from the University of Bari ‘Aldo Moro', "Despite significant progress, accurately predicting phenotypes fro m high-dimensional genomic data remains a challenge, particularly in identifying the key genetic factors influencing these predictions. This study aims to bridg e this gap by integrating explainable artificial intelligence (XAI) techniques w ith advanced machine learning models. This approach is intended to enhance both the predictive accuracy and interpretability of genotype-to-phenotype models, th ereby improving their reliability and supporting more informed breeding decision s. This study compares several ML methods for genotype-to-phenotype prediction, using data available from an almond germplasm collection. After preprocessing an d feature selection, regression models are employed to predict almond shelling f raction. Best predictions were obtained by the Random Forest method (correlation = 0.727 ? 0.020, an = 0.511 ? 0.025, and an RMSE = 7.746 ? 0.199). Notably, the application of the SHAP (SHapley Additive exPlanations) values algorithm to exp lain the results highlighted several genomic regions associated with the trait, including one, having the highest feature importance, located in a gene potentia lly involved in seed development. Employing explainable artificial intelligence algorithms enhances model interpretability, identifying genetic polymorphisms as sociated with the shelling percentage."
NETL
NSTL
