Department of Computational Medicine and Bioinformatics, Michigan Medicine, University of Michigan, Ann Arbor, MI, USA.
Department of Electrical Engineering and Computer Science (EECS) - CSE Division, University of Michigan, Ann Arbor, MI, USA.
Commun Biol. 2023 Apr 11;6(1):397. doi: 10.1038/s42003-023-04783-5.
Combination treatment has multiple advantages over traditional monotherapy in clinics, thus becoming a target of interest for many high-throughput screening (HTS) studies, which enables the development of machine learning models predicting the response of new drug combinations. However, most existing models have been tested only within a single study, and these models cannot generalize across different datasets due to significantly variable experimental settings. Here, we thoroughly assessed the transferability issue of single-study-derived models on new datasets. More importantly, we propose a method to overcome the experimental variability by harmonizing dose-response curves of different studies. Our method improves the prediction performance of machine learning models by 184% and 1367% compared to the baseline models in intra-study and inter-study predictions, respectively, and shows consistent improvement in multiple cross-validation settings. Our study addresses the crucial question of the transferability in drug combination predictions, which is fundamental for such models to be extrapolated to new drug combination discovery and clinical applications that are de facto different datasets.
联合治疗在临床上比传统的单药治疗具有多种优势，因此成为许多高通量筛选 (HTS) 研究的目标，这使得开发用于预测新药组合反应的机器学习模型成为可能。然而，大多数现有模型仅在单个研究中进行了测试，由于实验设置的显著差异，这些模型不能跨不同数据集进行泛化。在这里，我们彻底评估了单研究模型在新数据集上的可转移性问题。更重要的是，我们提出了一种通过协调不同研究的剂量反应曲线来克服实验变异性的方法。与基线模型相比，我们的方法分别将机器学习模型在研究内和研究间预测中的预测性能提高了 184%和 1367%，并在多个交叉验证设置中显示出一致的改进。我们的研究解决了药物组合预测中可转移性的关键问题，这对于将此类模型推广到新的药物组合发现和临床应用（实际上是不同的数据集）至关重要。
