Clear Search sequence regions


Sizes of these terms reflect their relevance to your search.

Combinatorial therapy is a promising strategy for combating complex diseases by improving the efficacy and reducing the side effects. To facilitate the identification of drug combinations in pharmacology, we proposed a new computational model, termed PDC-SGB, to predict effective drug combinations by integrating biological, chemical and pharmacological information based on a stochastic gradient boosting algorithm. To begin with, a set of 352 golden positive samples were collected from the public drug combination database. Then, a set of 732 dimensional feature vector involving biological, chemical and pharmaceutical information was constructed for each drug combination to describe its properties. To avoid overfitting, the maximum relevance & minimum redundancy (mRMR) method was performed to extract useful ones by removing redundant subsets. Based on the selected features, the three different type of classification algorithms were employed to build the drug combination prediction models. Our results demonstrated that the model based on the stochastic gradient boosting algorithm yield out the best performance. Furthermore, it is indicated that the feature patterns of therapy had powerful ability to discriminate effective drug combinations from non-effective ones. By analyzing various features, it is shown that the enriched features occurred frequently in golden positive samples can help predict novel drug combinations. Copyright © 2017 Elsevier Ltd. All rights reserved.

Citation

Qian Xu, Yi Xiong, Hao Dai, Kotni Meena Kumari, Qin Xu, Hong-Yu Ou, Dong-Qing Wei. PDC-SGB: Prediction of effective drug combinations using a stochastic gradient boosting algorithm. Journal of theoretical biology. 2017 Mar 21;417:1-7

Expand section icon Mesh Tags

Expand section icon Substances


PMID: 28099868

View Full Text