An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers

Missense pathogenicity predictors such as AlphaMissense are increasingly used in clinical variant interpretation, yet they are trained on germline labels dominated by loss-of-function (LOF) variants. Using an openly licensed, reproducible benchmark of 768 Cancer Gene Census genes scored with 49 predictors (labels from CIViC, COSMIC, cancerhotspots, ClinVar and gnomAD), we show that 42 of 49 tools (86%) score oncogene, gain-of-function (GOF) variants worse than tumour-suppressor variants. This under-scoring is mechanistically characterized: missed drivers occupy low-conservation, solvent-exposed, non-destabilizing positions (phyloP 2.51 versus 7.89; relative solvent accessibility 0.671 versus 0.185; gene-clustered p = 4.8×10⁻²⁰ and 2.3×10⁻³⁵), and, counter-intuitively, the unsupervised and protein-language models now entering clinical use are the most affected. Per-gene oncogenic thresholds span 0.07–0.99, so a single global cut-off is mis-calibrated for most genes; we provide a per-gene calibration map. A cancer-calibrated stack (OncoCal) modestly improves discrimination over the best single tool (AUROC ≈ 0.93 versus 0.87), rescues drivers such as JAK2 V617F (0.334→0.57), and generalizes to independent deep mutational scanning data. We provide an openly licensed framework to interpret and recalibrate these tools in the somatic setting rather than a replacement predictor.