A positive and unlabeled learning framework based on extreme learning machine for drug-drug interactions discovery
A positive and unlabeled learning framework based on extreme learning machine for drug-drug interactions discovery
复制标题
基于极限学习机的积极且无标签的药物相互作用发现学习框架
DOI：
10.1007/s12652-018-0960-7
复制
发表时间：
2018
影响因子：
--
通讯作者：
Deyang Chen
中科院分区：
文献类型：
--
作者：
Xin Bi;He Ma;Jianhua Li;Yuliang Ma;Deyang Chen
药物相互作用（Drug-drug interactions，DDI）在大多数情况下会导致药物不良反应（Adverse Drug Reactions，ADRs），极大地增加了医疗成本，并可能导致医疗疏忽甚至死亡事故。许多研究者将二元分类方法引入到DDI发现任务中，以避免昂贵且低效的实验。然而，我们发现，没有DDI标签的药物-药物对不能简单地被视为阴性样品在实践中，因为未观察到的DDI可能会发现从未标记的对。因此，不同于传统的阳性-阴性分类，本文将DDI发现视为阳性-未标记学习（PU学习）问题，其中每个药物-药物对要么是阳性样本（标记为DDI），要么是未标记样本（标记为非DDI）。我们提出了一个基于极端学习机（ELM）的PU学习框架PU-ELM，它由两个部分组成，即可靠的否定提取和分类器学习。为了提高可靠否定集的质量，提出了一种可靠否定集提取方法OC-ELM-RN（One-Class ELM for Reliable Negative extraction）。在学习模块中，我们首先将半监督学习策略应用于PU-ELM（简称PU-ELM-SS），以获得极快的学习速度，然后提出一种基于熵的加权学习方法PU-ELM-EW（PU-ELM with Entropy Weighted learning），以提高PU的学习性能。在具有不同设置的合成数据集上进行了广泛的实验。我们还将PU-ELM应用于真实世界的药物数据集。结果表明，PU-ELM实现了更好的DDI发现能力相比，国家的最先进的方法。
Drug-drug interactions (DDIs) lead to Adverse Drug Reactions (ADRs) in most cases, which increase medical costs tremendously, and may cause medical negligence or even fatal accidents. Many researchers introduce binary classification methods into DDIs discovery task to avoid expensive and inefficient experimental trials. However, we find that drug-drug pairs without DDI labels cannot be simply viewed as negative samples in practice, since unobserved DDIs may be discovered from unlabeled pairs. Therefore, different from traditional positive-negative classification, in this paper, we treat DDIs discovery as a positive-unlabeled learning (PU learning) problem, in which each drug-drug pair is either a positive sample (labeled as DDI) or an unlabeled one (labeled as non-DDI). We propose a PU learning framework based on Extreme Learning Machine (ELM) named PU-ELM, which consists of two components, namely reliable negative extraction and classifier learning. To improve the quality of reliable negative set, we propose a negative extraction method named OC-ELM-RN (One-Class ELM for Reliable Negative extraction). As to the learning module, we first apply the semi-supervised learning strategy in PU-ELM (denoted as PU-ELM-SS) to achieve extremely fast learning speed, and then we propose an entropy based weighted learning method named PU-ELM-EW (PU-ELM with Entropy Weighted learning) to improve the PU learning performance. Extensive experiments are conducted on a synthetic dataset with varied settings. We also apply PU-ELM to a real-world drug dataset. The results indicate that PU-ELM achieves better DDIs discovery ability compared with state-of-the-art methods.