Premium
In silico prediction of chemical mechanism of action via an improved network‐based inference method
Author(s) -
Wu Zengrui,
Lu Weiqiang,
Wu Dang,
Luo Anqi,
Bian Hanping,
Li Jie,
Li Weihua,
Liu Guixia,
Huang Jin,
Cheng Feixiong,
Tang Yun
Publication year - 2016
Publication title -
british journal of pharmacology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.432
H-Index - 211
eISSN - 1476-5381
pISSN - 0007-1188
DOI - 10.1111/bph.13629
Subject(s) - computer science , in silico , inference , drug repositioning , systems pharmacology , computational biology , benchmark (surveying) , drug , drug discovery , drug development , mechanism (biology) , node (physics) , machine learning , artificial intelligence , pharmacology , bioinformatics , medicine , biology , engineering , biochemistry , philosophy , geodesy , epistemology , structural engineering , gene , geography
Background and Purpose Deciphering chemical mechanism of action (MoA) enables the development of novel therapeutics (e.g. drug repositioning) and evaluation of drug side effects. Development of novel computational methods for chemical MoA assessment under a systems pharmacology framework would accelerate drug discovery and development with greater efficiency and low cost. Experimental Approach In this study, we proposed an improved network‐based inference method, balanced substructure‐drug‐target network‐based inference (bSDTNBI), to predict MoA for old drugs, clinically failed drugs and new chemical entities. Specifically, three parameters were introduced into network‐based resource diffusion processes to adjust the initial resource allocation of different node types, the weighted values of different edge types and the influence of hub nodes. The performance of the method was systematically validated by benchmark datasets and bioassays. Key Results High performance was yielded for bSDTNBI in both 10‐fold and leave‐one‐out cross validations. A global drug‐target network was built to explore MoA of anticancer drugs and repurpose old drugs for 15 cancer types/subtypes. In a case study, 27 predicted candidates among 56 commercially available compounds were experimentally validated to have binding affinities on oestrogen receptor α with IC 50 or EC 50 values ≤10 μM. Furthermore, two dual ligands with both agonistic and antagonistic activities ≤1 μM would provide potential lead compounds for the development of novel targeted therapy in breast cancer or osteoporosis. Conclusion and Implications In summary, bSDTNBI would provide a powerful tool for the MoA assessment on both old drugs and novel compounds in drug discovery and development.