domains / families / science / omics-classifiers

omics-classifiers

separate

Builds diagnostic and prognostic classifiers on omics feature matrices with regularized logistic regression, random forest, and gradient-boosted trees, handling the p>>n regime, batch shortcut learning, class imbalance, and probability calibration. Use when building a classifier from expression, methylation, or variant data, choosing an algorithm for high-dimensional small-n data, or diagnosing a suspiciously perfect AUC. For unbiased evaluation see machine-learning/model-validation; for feature selection see machine-learning/biomarker-discovery; for time-to-event outcomes see machine-learning/survival-analysis.

When to use

• building a classifier from expression, methylation, or variant data
• choosing an algorithm for high-dimensional small-n data
• diagnosing a suspiciously perfect AUC
• handling batch shortcut learning
• managing class imbalance
• probability calibration

When not to use

• unbiased evaluation
• feature selection
• time-to-event outcomes

Skill page

Source