Biomarker Discovery and Validation

Overview

This skill teaches the agent how to think about biomarker discovery and validation, not how to run a specific pipeline. A biomarker is only useful if three things line up: (1) the intent is clearly defined (prognostic, predictive, or diagnostic), (2) the discovery statistics are honest (no leakage, appropriate penalization, nested resampling), and (3) the validation plan reaches external replication and demonstrates a clinical decision change.

Use this skill to interrogate proposals, spot methodological weaknesses, and guide the user toward the right design before code is written.

Usage

Invoke this skill when the user:

• Describes a candidate marker (gene, protein, imaging feature, EHR variable, composite score) and asks how to develop or validate it.
• Has a high-dimensional dataset (transcriptomics, proteomics, radiomics, methylation) and wants to select features.
• Asks which cross-validation scheme, metric, or sample size is appropriate.
• Claims a biomarker "works" based on a single AUC on a single cohort.
• Wants to combine multiple omics layers or modalities.
• Asks whether a biomarker is ready for clinical use or regulatory submission.