As with other pharma companies, we maintain production QSAR models of ADMET end points and update them regularly. Here, for six ADMET end points, we examine the predictions of test set molecules on multiple versions of random forest models spanning a period of 10 years. For any given end point, the predictions for the majority of molecules are similar for all model versions. However, for a small minority of molecules, the prediction shifts substantially over the span of a few versions. For most molecules that shift, the prediction becomes more accurate at later times. This Perspective investigates metrics that can help indicate which molecules will shift substantially in prediction and when the shift will occur.

中文翻译：

---

生产 ADMET 模型中预测的稳定性作为版本的函数：预测发生变化的原因和时间

与其他制药公司一样，我们维护 ADMET 端点的生产 QSAR 模型并定期更新它们。在这里，对于六个 ADMET 端点，我们检查了测试集分子对跨越 10 年的多个版本的随机森林模型的预测。对于任何给定的终点，大多数分子的预测对于所有模型版本都是相似的。然而，对于少数分子，预测在几个版本的跨度上发生了显着变化。对于大多数发生变化的分子，预测在以后变得更加准确。这个观点研究了可以帮助指示哪些分子在预测中会发生重大变化以及何时发生变化的指标。