domains / families / science / biomarker-discovery

biomarker-discovery

separate

Selects biomarker features from high-dimensional omics data using Boruta all-relevant selection, mRMR, LASSO/elastic-net, and stability selection, while controlling the leakage, irreproducibility, and correlated-feature traps that make most published signatures fail to replicate. Use when identifying candidate biomarkers, deciding between an all-relevant and a minimal-optimal selector, or judging whether a selected gene set is reproducible. For unbiased performance estimation of the resulting model see machine-learning/model-validation; for interpreting a trained model see machine-learning/prediction-explanation.

When to use

• identifying candidate biomarkers
• deciding between all-relevant and minimal-optimal selector
• judging whether a selected gene set is reproducible
• feature selection from high-dimensional omics data
• quantifying stability of selected features
• using Boruta all-relevant selection
• using mRMR, LASSO, or elastic-net
• controlling leakage and correlated-feature traps

When not to use

• unbiased performance estimation of the resulting model
• interpreting a trained model

Skill page

Source