Chen Hailin, Zhang Heng, Zhang Zuping, Cao Yiqin, Tang Wenliang
School of Software, East China Jiaotong University, Nanchang 330013, China.
School of Information Engineering, East China Jiaotong University, Nanchang 330013, China.
Comput Math Methods Med. 2015;2015:130620. doi: 10.1155/2015/130620. Epub 2015 Apr 12.
Mining potential drug-disease associations can speed up drug repositioning for pharmaceutical companies. Previous computational strategies focused on prior biological information for association inference. However, such information may not be comprehensively available and may contain errors. Different from previous research, two inference methods, ProbS and HeatS, were introduced in this paper to predict direct drug-disease associations based only on the basic network topology measure. Bipartite network topology was used to prioritize the potentially indicated diseases for a drug. Experimental results showed that both methods can receive reliable prediction performance and achieve AUC values of 0.9192 and 0.9079, respectively. Case studies on real drugs indicated that some of the strongly predicted associations were confirmed by results in the Comparative Toxicogenomics Database (CTD). Finally, a comprehensive prediction of drug-disease associations enables us to suggest many new drug indications for further studies.
挖掘潜在的药物-疾病关联可以加快制药公司的药物重新定位。以前的计算策略侧重于利用先前的生物学信息进行关联推断。然而，此类信息可能无法全面获取，并且可能包含错误。与先前的研究不同，本文引入了两种推断方法ProbS和HeatS，仅基于基本的网络拓扑度量来预测直接的药物-疾病关联。使用二分网络拓扑对药物潜在指示的疾病进行优先级排序。实验结果表明，这两种方法都能获得可靠的预测性能，AUC值分别达到0.9192和0.9079。对真实药物的案例研究表明，一些预测强烈的关联在比较毒理基因组学数据库（CTD）中得到了结果证实。最后，对药物-疾病关联的全面预测使我们能够提出许多新的药物适应症以供进一步研究。
