[论文解读] PADME: A Deep Learning-based Framework for Drug-Target Interaction Prediction

Qingyuan Feng, Evgenia V. Dueva+2 more|arXiv (Cornell University)|Jul 25, 2018

Computational Drug Discovery Methods参考文献 52被引用 81

一句话总结

PADME 是一个深度神经网络框架，通过将分子图卷积用于化合物并结合蛋白质描述子来预测实值药物–靶标相互作用（DTI）强度，解决冷靶点和冷药物问题，并在多个数据集上优于基线。

ABSTRACT

In silico drug-target interaction (DTI) prediction is an important and challenging problem in biomedical research with a huge potential benefit to the pharmaceutical industry and patients. Most existing methods for DTI prediction including deep learning models generally have binary endpoints, which could be an oversimplification of the problem, and those methods are typically unable to handle cold-target problems, i.e., problems involving target protein that never appeared in the training set. Towards this, we contrived PADME (Protein And Drug Molecule interaction prEdiction), a framework based on Deep Neural Networks, to predict real-valued interaction strength between compounds and proteins without requiring feature engineering. PADME takes both compound and protein information as inputs, so it is capable of solving cold-target (and cold-drug) problems. To our knowledge, we are the first to combine Molecular Graph Convolution (MGC) for compound featurization with protein descriptors for DTI prediction. We used multiple cross-validation split schemes and evaluation metrics to measure the performance of PADME on multiple datasets, including the ToxCast dataset, and PADME consistently dominates baseline methods. The results of a case study, which predicts the binding affinity between various compounds and androgen receptor (AR), suggest PADME's potential in drug development. The scalability of PADME is another advantage in the age of Big Data.

研究动机与目标

• 将 DTI 预测从二元端点推进到实值相互作用强度。
• 在不进行特征工程的情况下实现对冷靶点和冷药物情景的处理。
• 将分子图卷积用于化合物与蛋白质描述子整合于一个统一框架。
• 在多个数据集和交叉验证方案上评估 PADME，以展示鲁棒性和可扩展性。

提出的方法

• 使用分子图卷积对化合物结构进行特征化，无需手工特征。
• 将化合物表示与蛋白质描述子作为输入输入到深度神经网络。
• 预测实值的相互作用强度，而非二元标签。
• 使用多个跨数据集的分割和评估指标在数据集上进行评估（如 ToxCast）。
• 展示一个案例研究，预测化合物与雄激素受体（AR）之间的结合亲和力。

实验结果

研究问题

• RQ1 PADME 能否在不进行特征工程的情况下预测实值 DTI 分数？
• RQ2 该框架能否有效应对冷靶点和冷药物情景？
• RQ3 PADME 相较于基线方法在多个数据集和 CV 方案中的表现如何？
• RQ4 PADME 是否可扩展到大数据并支持实际药物开发工作流程？
• RQ5 在如 AR 结合亲和力预测等案例研究中，PADME 的潜力如何？

主要发现

• PADME 在多个数据集和交叉验证方案中对基线方法持续占优。
• 该框架可以在不需要特征工程的情况下处理冷靶点和冷药物问题。
• 关于雄激素受体（AR）结合亲和力的案例研究展示了 PADME 在药物开发中的潜力。
• PADME 提供适用于 DTI 预测大数据设定的可扩展性。