Genomic Prediction of Leaf Rust Resistance in Arabica Coffee Plants

A study by Ithalo Coelho de Sousa used genomic data from 245 Arabica coffee plants genotyped for 137 markers to predict resistance to orange rust. Machine learning algorithms, including Decision Trees and their refinements, Artificial Neural Networks, and Bayesian Generalized Linear Regression, were compared for prediction accuracy and marker importance identification. The refinements identified an average of 9.3 important markers located in quantitative trait loci regions associated with disease resistance.

Use Cases

• Comparing the performance of Decision Tree-based models against Bayesian and Neural Network methods for genomic prediction.
• Identifying genetic markers most important for predicting resistance to orange rust in Arabica coffee.
• Validating genomic selection methodologies using a dataset of 137 markers across 245 coffee plants.

Strengths

• Dataset size is specified with 245 coffee plants and 137 genetic markers.
• Results include a concrete metric for marker importance, with an average of 9.3 key markers found in known QTL regions.
• Methodology compares multiple machine learning and statistical approaches, including Decision Trees, Random Forest, Boosting, GBLASSO, and ANN.

Limitations

• Row count and column-level documentation are unknown; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.
• Data may reflect bias inherent to the specific study and platform (paperswithcode).

Provenance

Source

Ithalo Coelho de Sousa via paperswithcode.

Collection Method

Genomic data collection from Arabica coffee plants, likely for research purposes.