Screen-VarCal: An Interpretable Probabilistic Framework for Recalibrating ACMG Rule-Based Variant Classification in Preventive Medicine
Bibliographic record
Abstract
Abstract Motivation hole-genome sequencing (WGS) is increasingly used for preventive genomics, yet rule-based ACMG engines such as InterVar were tuned for high pre-test probability diagnostics. In screening contexts, these heuristics can inflate pathogenic/likely pathogenic (P/LP) calls, prompting unnecessary follow-up. We sought an interpretable, data-driven recalibration tailored to proactive use. Results Across 20 WGS cases, InterVar flagged 109 variants as P/LP; only 18 (16.5%) were concordant with ClinVar P/LP assertions. The remaining 83.5% were largely absent from Clin-Var (n=68) or mapped to benign/likely benign (n=13). Nearly all flagged variants (96%) were heterozygous, predominantly in autosomal recessive genes (e.g., FAM20C, MTMR2 ), indicating a dominant carrier inflation effect; recurrent loci (e.g., ATXN3, FAM20C ) further amplified yield. We introduce Screen-VarCal , an interpretable probabilistic framework that combines logistic regression with isotonic adjustment to align InterVar outputs with observed ClinVar P/LP distributions. Screen-VarCal reduced false positives by ∼ 60% while retaining all ClinVar-concordant findings and yields calibrated probabilities with coefficients that transparently link ACMG evidence categories (PVS/PS/PM/PP/BS/BP) and zygosity to risk.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.018 | 0.066 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.003 |
| Bibliometrics | 0.005 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.002 |
| Open science | 0.004 | 0.003 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.008 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".