What question did this study set out to answer?

The aim is to assess various regression models for their effectiveness in predicting the significance of SNPs from genetic data.

Predictive Modelling for Genetic Data Significance: An Experimental Study

View Full Paper

Ask AI

Bookmark

Authors

Experimental study evaluates regression models for predicting SNP significance in genetic data, suggesting optimal methods for GWAS.

The aim is to assess various regression models for their effectiveness in predicting the significance of SNPs from genetic data.
Evaluated seven regression models including Random Forest and XGBoost.
Used transformed P-values on a logarithmic scale as targets for regression.
Applied Bonferroni and False Discovery Rate corrections to establish significance thresholds.
Measured model performance using metrics like mean squared error and R-squared.
Random Forest achieved the highest predictive accuracy among all models tested.
Extra Trees Regressor also showed strong performance in predicting SNP significance.
XGBoost and CatBoost demonstrated the capability to capture complex SNP interactions.
Overall, tree-based ensemble methods outperformed traditional regression approaches.

Yelure et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark