Limits...
A network-based classification model for deriving novel drug-disease associations and assessing their molecular actions.

Oh M, Ahn J, Yoon Y - PLoS ONE (2014)

Bottom Line: The growing number and variety of genetic network datasets increases the feasibility of understanding how drugs and diseases are associated at the molecular level.These quantified scores were used as features for the prediction of novel drug-disease associations.Our classifiers using Random Forest, Multilayer Perceptron and C4.5 showed a high specificity and sensitivity (AUC score of 0.855, 0.828 and 0.797 respectively) in predicting novel drug indications, and displayed a better performance than other methods with limited drug and disease properties.

View Article: PubMed Central - PubMed

Affiliation: Department of Computer Engineering, Gachon University, Seongnam, Korea.

ABSTRACT
The growing number and variety of genetic network datasets increases the feasibility of understanding how drugs and diseases are associated at the molecular level. Properly selected features of the network representations of existing drug-disease associations can be used to infer novel indications of existing drugs. To find new drug-disease associations, we generated an integrative genetic network using combinations of interactions, including protein-protein interactions and gene regulatory network datasets. Within this network, network adjacencies of drug-drug and disease-disease were quantified using a scored path between target sets of them. Furthermore, the common topological module of drugs or diseases was extracted, and thereby the distance between topological drug-module and disease (or disease-module and drug) was quantified. These quantified scores were used as features for the prediction of novel drug-disease associations. Our classifiers using Random Forest, Multilayer Perceptron and C4.5 showed a high specificity and sensitivity (AUC score of 0.855, 0.828 and 0.797 respectively) in predicting novel drug indications, and displayed a better performance than other methods with limited drug and disease properties. Our predictions and current clinical trials overlap significantly across the different phases of drug development. We also identified and visualized the topological modules of predicted drug indications for certain types of cancers, and for Alzheimer's disease. Within the network, those modules show potential pathways that illustrate the mechanisms of new drug indications, including propranolol as a potential anticancer agent and telmisartan as treatment for Alzheimer's disease.

Show MeSH

Related in: MedlinePlus

Performance evaluation of each method.Results from the adjacency-based inference (ABI) method, the module-distance-based inference (MDBI) method, and the integrated method of ABI and MDBI (INTG) are compared.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4214731&req=5

pone-0111668-g005: Performance evaluation of each method.Results from the adjacency-based inference (ABI) method, the module-distance-based inference (MDBI) method, and the integrated method of ABI and MDBI (INTG) are compared.

Mentions: In our study, two methods were implemented for scoring the features. Figure 5 shows the AUC when each method was used alone and when both methods were used. The performance when both methods were used exceeds that when only one method was used. In Table S3, we evaluated the contribution of all features, when both methods were used. We also used the integrative genetic network, which consists of gene and protein interaction databases. Figure 6 shows the AUC of three individual networks and the integrative network. Using PPI only results in a higher AUC compared to the use of gene regulation data alone or the use of the inferred PPI alone. Additionally, using integrative networks shows a slightly better AUC for C4.5 compared to the use of PPI alone.


A network-based classification model for deriving novel drug-disease associations and assessing their molecular actions.

Oh M, Ahn J, Yoon Y - PLoS ONE (2014)

Performance evaluation of each method.Results from the adjacency-based inference (ABI) method, the module-distance-based inference (MDBI) method, and the integrated method of ABI and MDBI (INTG) are compared.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4214731&req=5

pone-0111668-g005: Performance evaluation of each method.Results from the adjacency-based inference (ABI) method, the module-distance-based inference (MDBI) method, and the integrated method of ABI and MDBI (INTG) are compared.
Mentions: In our study, two methods were implemented for scoring the features. Figure 5 shows the AUC when each method was used alone and when both methods were used. The performance when both methods were used exceeds that when only one method was used. In Table S3, we evaluated the contribution of all features, when both methods were used. We also used the integrative genetic network, which consists of gene and protein interaction databases. Figure 6 shows the AUC of three individual networks and the integrative network. Using PPI only results in a higher AUC compared to the use of gene regulation data alone or the use of the inferred PPI alone. Additionally, using integrative networks shows a slightly better AUC for C4.5 compared to the use of PPI alone.

Bottom Line: The growing number and variety of genetic network datasets increases the feasibility of understanding how drugs and diseases are associated at the molecular level.These quantified scores were used as features for the prediction of novel drug-disease associations.Our classifiers using Random Forest, Multilayer Perceptron and C4.5 showed a high specificity and sensitivity (AUC score of 0.855, 0.828 and 0.797 respectively) in predicting novel drug indications, and displayed a better performance than other methods with limited drug and disease properties.

View Article: PubMed Central - PubMed

Affiliation: Department of Computer Engineering, Gachon University, Seongnam, Korea.

ABSTRACT
The growing number and variety of genetic network datasets increases the feasibility of understanding how drugs and diseases are associated at the molecular level. Properly selected features of the network representations of existing drug-disease associations can be used to infer novel indications of existing drugs. To find new drug-disease associations, we generated an integrative genetic network using combinations of interactions, including protein-protein interactions and gene regulatory network datasets. Within this network, network adjacencies of drug-drug and disease-disease were quantified using a scored path between target sets of them. Furthermore, the common topological module of drugs or diseases was extracted, and thereby the distance between topological drug-module and disease (or disease-module and drug) was quantified. These quantified scores were used as features for the prediction of novel drug-disease associations. Our classifiers using Random Forest, Multilayer Perceptron and C4.5 showed a high specificity and sensitivity (AUC score of 0.855, 0.828 and 0.797 respectively) in predicting novel drug indications, and displayed a better performance than other methods with limited drug and disease properties. Our predictions and current clinical trials overlap significantly across the different phases of drug development. We also identified and visualized the topological modules of predicted drug indications for certain types of cancers, and for Alzheimer's disease. Within the network, those modules show potential pathways that illustrate the mechanisms of new drug indications, including propranolol as a potential anticancer agent and telmisartan as treatment for Alzheimer's disease.

Show MeSH
Related in: MedlinePlus