School of Computer Science and Engineering, Central South University, Changsha 410083, China.
Bioinformatics. 2023 Aug 1;39(8). doi: 10.1093/bioinformatics/btad478.
Understanding drug-response differences in cancer treatments is one of the most challenging aspects of personalized medicine. Recently, graph neural networks (GNNs) have become state-of-the-art methods in many graph representation learning scenarios in bioinformatics. However, building an optimal handcrafted GNN model for a particular drug sensitivity dataset requires manual design and fine-tuning of the hyperparameters for the GNN model, which is time-consuming and requires expert knowledge.
In this work, we propose AutoCDRP, a novel framework for automated cancer drug-response predictor using GNNs. Our approach leverages surrogate modeling to efficiently search for the most effective GNN architecture. AutoCDRP uses a surrogate model to predict the performance of GNN architectures sampled from a search space, allowing it to select the optimal architecture based on evaluation performance. Hence, AutoCDRP can efficiently identify the optimal GNN architecture by exploring the performance of all GNN architectures in the search space. Through comprehensive experiments on two benchmark datasets, we demonstrate that the GNN architecture generated by AutoCDRP surpasses state-of-the-art designs. Notably, the optimal GNN architecture identified by AutoCDRP consistently outperforms the best baseline architecture from the first epoch, providing further evidence of its effectiveness.
理解癌症治疗中药物反应的差异是个性化医疗最具挑战性的方面之一。最近，图神经网络（GNN）在生物信息学中的许多图表示学习场景中已成为最先进的方法。然而，为特定的药物敏感性数据集构建最佳的手工 GNN 模型需要手动设计和微调 GNN 模型的超参数，这既耗时又需要专业知识。
在这项工作中，我们提出了 AutoCDRP，这是一种使用 GNN 进行自动化癌症药物反应预测的新框架。我们的方法利用替代模型来有效地搜索最有效的 GNN 架构。AutoCDRP 使用替代模型来预测从搜索空间中采样的 GNN 架构的性能，从而可以根据评估性能选择最佳架构。因此，AutoCDRP 可以通过探索搜索空间中所有 GNN 架构的性能来有效地识别最佳 GNN 架构。通过在两个基准数据集上的综合实验，我们证明了由 AutoCDRP 生成的 GNN 架构优于最先进的设计。值得注意的是，AutoCDRP 确定的最佳 GNN 架构始终优于第一个时期的最佳基线架构，进一步证明了其有效性。
