Phenotypic POLE Variant Classification Identifies Patients Who May Have Favorable Prognosis and Benefit from Immunotherapy

Abstract

Pathogenic POLE mutations (pPOLE) undermine mismatch error correction by polymerase ε during DNA replication, and the resulting somatic ultramutation predicts response to immunotherapy. Beyond frequently recurrent alleles, historical pPOLE classification has been largely based on exonuclease domain localization. A POLE-specific phenotypic classification model was developed, encompassing tumor mutational burden (TMB), mutational signatures, germline frequency, and consideration of comutation with other POLE mutations to identify pPOLE. This model was applied to >490,000 samples and identified 29 predicted pPOLE, including 16 not previously reported. A total of 748 tumors (0.2%) had one or more pPOLE, most commonly in endometrial and colorectal cancers, although pPOLE were observed in many additional cancer types. pPOLE were associated with ultramutation [median TMB, 186.3 mutations per megabase (mut/Mb)] across tumor types. Concurrent pPOLE and microsatellite instability were more common than previously appreciated and produced a synergistic TMB impact, with medians of 135.7 mut/Mb for pPOLE/microsatellite stable samples compared with 325.6 mut/Mb for pPOLE/microsatellite instability-high samples. Comutation analysis in endometrial and colorectal cancers highlighted associations with homologous recombination pathway gene mutations that were predominantly monoallelic passengers that are unlikely to predict response to therapies targeting DNA repair deficiencies. pPOLE have been incorporated into treatment guidelines for several malignancies and are an important predictor of immunotherapy response. This study provides biological insight to guide classification and clinical management of patients with tumors harboring pPOLE.