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

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

Volume: 19 Issue: 2

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 and Linfeng Zheng

Affiliation:

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

Abstract: 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.

Cite this article as:

Niu Bing, Xing Zhihao, Zhao Manman, Huo Haizhong, Huang Guohua, Chen Fuxue, Su Qiang, Lu Yin, Wang Meng, Yang Jing, Chen Lei, Tang Ling and Zheng Linfeng, Study of drug-drug combinations based on molecular descriptors and physicochemical properties, Combinatorial Chemistry & High Throughput Screening 2016; 19 (2) . https://dx.doi.org/10.2174/1386207319666151110122931