Chow Ryan D, Parikh Ravi B, Nathanson Katherine L
Department of Medicine, Hospital of the University of Pennsylvania, Philadelphia, PA, USA.
Division of Health Policy, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
medRxiv. 2024 Apr 7:2024.04.05.24305402. doi: 10.1101/2024.04.05.24305402.
Deep learning models for variant pathogenicity prediction can recapitulate expert-curated annotations, but their performance remains unexplored on actual disease phenotypes in a real-world setting. Here, we apply three state-of-the-art pathogenicity prediction models to classify hereditary breast cancer gene variants in the UK Biobank. Predicted pathogenic variants in , and , but not and were associated with increased breast cancer risk. We explored gene-specific score thresholds for variant pathogenicity, finding that they could improve model performance. However, when specifically tasked with classifying variants of uncertain significance, the deep learning models were generally of limited clinical utility.
用于变异致病性预测的深度学习模型可以概括专家整理的注释，但其在实际疾病表型的真实环境中的性能仍未得到探索。在这里，我们应用三种最先进的致病性预测模型对英国生物银行中的遗传性乳腺癌基因变异进行分类。预测的 、 和 中的致病性变异，但 和 中的变异与乳腺癌风险增加无关。我们探索了变异致病性的基因特异性评分阈值，发现它们可以提高模型性能。然而，当专门用于对意义不明确的变异进行分类时，深度学习模型的临床效用通常有限。
