Study of drug-drug combinations based on molecular descriptors and physicochemical properties

Author(s): Bing Niu, Zhihao Xing, Manman Zhao, Haizhong Huo, Guohua Huang, Fuxue Chen, Qiang Su, Yin Lu, Meng Wang, Jing Yang, Lei Chen, Ling Tang, Linfeng Zheng

Journal Name: Combinatorial Chemistry & High Throughput Screening
Accelerated Technologies for Biotechnology, Bioassays, Medicinal Chemistry and Natural Products Research

Volume 19 , Issue 2 , 2016

Become EABM
Become Reviewer


In the present study, molecular descriptors and physicochemical properties were used to encode drug molecules. Based on this molecular representation method, Random forest was applied to construct a drug-drug combination network. After feature selection, an optimal features subset was built, which described the main factors of drugs in our prediction. As a result, the selected features can be clustered into three categories: elemental analysis, chemistry, and geometric features. And all of the three types features are essential elements of the drug-drug combination network. The final prediction model achieved a Matthew's correlation coefficient (MCC) of 0.5335 and an overall prediction accuracy of 88.79% for the 10-fold cross-validation test.

Keywords: Physicochemical properties, mRMR, drug-drug combinations, random forest, feature selection.

Rights & PermissionsPrintExport Cite as

Article Details

Year: 2016
Page: [153 - 160]
Pages: 8
DOI: 10.2174/1386207319666151110122931
Price: $65

Article Metrics

PDF: 33
PRC: 1