Combining Bayesian and Frequentist Inference for Laboratory-Specific Performance Guarantees in Copy Number Variation Detection

2026-04-15

AI Summary

This study addresses the challenges in clinically validating copy number variation (CNV) detection from targeted amplicon sequencing, where performance is hindered by amplification artifacts, heterogeneity from protocol mismatches, and limited sample sizes. The authors propose a hybrid framework integrating Bayesian and frequentist inference: Bayesian posterior functionals are employed to assess performance, with squared loss modeled via a Gamma distribution to construct admissible intervals achieving valid frequentist coverage. Innovatively, the method incorporates a label-free mechanism to exclude CNV-positive outliers, small-sample regularization, and a log-model-evidence–based stratification strategy to effectively mitigate non-exchangeable noise. Evaluated on two amplicon panels, the approach achieves single-digit mean absolute coverage error across all genes under both protocol-matched and mismatched conditions, substantially outperforming conventional Bayesian methods—for instance, reducing ERBB2 error by over 60%.

Technology Category

Machine Learning: Calibration & Uncertainty QuantificationComputer Vision: Learning & Optimization for CVReasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty

Application Category

Search and Retrieval-Augmented AI: Web evaluation methodologies and metricsWeb Mining and Content Analysis: Robustness and generalizability of Web mining methodsEconomics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Targeted amplicon panels are widely used in oncology diagnostics, but providing per-gene performance guarantees for copy number variant (CNV) detection remains challenging due to amplification artifacts, process-mismatch heterogeneity, and limited validation sample sizes. While Bayesian CNV callers naturally quantify per-sample uncertainty, translating this into the frequentist population-level guarantees required for clinical validation, coverage rates, false-positive bounds, and minimum detectable copy-number changes, is a fundamentally different inferential problem. We show empirically that even robust Bayesian credible intervals, including coarsened posteriors and sandwich-adjusted intervals, are severely miscalibrated on panels with small amplicon counts per gene. To address this, we propose a hybrid framework that evaluates Bayesian posterior functionals on validation samples and models the resulting squared losses with a Gamma distribution, yielding tolerance intervals with valid frequentist coverage. Three components make the method practical under real-world constraints: (1) imputation that removes the influence of true CNV-positive samples without requiring known ground truth, (2) regularization to address small sample variability, and (3) evidence-based stratification on the log model evidence to accommodate non-exchangeable noise profiles arising from process mismatch. Evaluated on two targeted amplicon panels using leave-one-out cross-validation, the proposed method achieves single-digit mean absolute coverage error across all genes under both process-matched and unmatched conditions, whereas Bayesian comparators exhibit mean absolute errors exceeding 60\% on clinically relevant genes such as ERBB2.

Problem

• copy number variation
• performance guarantees
• targeted amplicon panels
• frequentist coverage
• clinical validation

Innovation

• Bayesian-frequentist hybrid
• copy number variation detection
• tolerance intervals
• amplicon panel diagnostics
• coverage calibration