Dataset Information

Prediction of effective drug combinations by chemical interaction, protein interaction and target enrichment of KEGG pathways.

ABSTRACT: Drug combinatorial therapy could be more effective in treating some complex diseases than single agents due to better efficacy and reduced side effects. Although some drug combinations are being used, their underlying molecular mechanisms are still poorly understood. Therefore, it is of great interest to deduce a novel drug combination by their molecular mechanisms in a robust and rigorous way. This paper attempts to predict effective drug combinations by a combined consideration of: (1) chemical interaction between drugs, (2) protein interactions between drugs' targets, and (3) target enrichment of KEGG pathways. A benchmark dataset was constructed, consisting of 121 confirmed effective combinations and 605 random combinations. Each drug combination was represented by 465 features derived from the aforementioned three properties. Some feature selection techniques, including Minimum Redundancy Maximum Relevance and Incremental Feature Selection, were adopted to extract the key features. Random forest model was built with its performance evaluated by 5-fold cross-validation. As a result, 55 key features providing the best prediction result were selected. These important features may help to gain insights into the mechanisms of drug combinations, and the proposed prediction model could become a useful tool for screening possible drug combinations.

SUBMITTER: Chen L

PROVIDER: S-EPMC3780555 | biostudies-literature | 2013

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Prediction of effective drug combinations by chemical interaction, protein interaction and target enrichment of KEGG pathways.

Chen Lei L Li Bi-Qing BQ Zheng Ming-Yue MY Zhang Jian J Feng Kai-Yan KY Cai Yu-Dong YD

BioMed research international 20130905

Drug combinatorial therapy could be more effective in treating some complex diseases than single agents due to better efficacy and reduced side effects. Although some drug combinations are being used, their underlying molecular mechanisms are still poorly understood. Therefore, it is of great interest to deduce a novel drug combination by their molecular mechanisms in a robust and rigorous way. This paper attempts to predict effective drug combinations by a combined consideration of: (1) chemica ...[more]

PMID: 24083237

Similar Datasets

Project description:An effective anti-tumor immune response requires the coordinated action of the innate and adaptive phases of the immune system. Critical processes include the activation of dendritic cells to present antigens, produce cytokines including type I interferons, and express multiple costimulatory ligands; induction of a productive T cell response within lymph nodes; migration of activated T cells to the tumor microenvironment in response to chemokines and homing receptor expression; and having effector T cells gain access to antigen-expressing tumor cells and maintain sufficient functionality to destroy them. However, tumors can become adept at escaping the immune response, developing multiple mechanisms to disrupt key processes. In general, tumors can be assigned into two different, major groups depending on whether the tumor there is an 'inflamed' or 'non-inflamed' tumor microenvironment. Improvements in our understanding of the interactions between the immune system and cancer have resulted in the development of various strategies to improve the immune-mediated control of tumors in both sub-groups. Categories of major immunotherapeutic intervention include methods to increase the frequency of tumor antigen-specific effector T cells in the circulation, strategies to block or uncouple a range of immune suppressive mechanisms within the tumor microenvironment, and tactics to induce de novo immune inflammation within the tumor microenvironment. The latter may be particularly important for eliciting immune recognition of non-inflamed tumor phenotypes. The premise put forth in this review is that synergistic therapeutic effects in vivo may be derived from combination therapies taken from distinct "bins" based on these mechanisms of action. Early data in both preclinical and some clinical studies provide support for this model. We also suggest that optimal application of these combinations may be aided by appropriate patient selection based on predictive biomarkers.

Dataset Information

Prediction of effective drug combinations by chemical interaction, protein interaction and target enrichment of KEGG pathways.

Publications

Prediction of effective drug combinations by chemical interaction, protein interaction and target enrichment of KEGG pathways.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets