Format

Send to

Choose Destination
Comput Math Methods Med. 2015;2015:275045. doi: 10.1155/2015/275045. Epub 2015 May 19.

Matrix Factorization-Based Prediction of Novel Drug Indications by Integrating Genomic Space.

Author information

1
Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China.
2
Beijing University of Chinese Medicine, Beijing 100029, China.

Abstract

There has been rising interest in the discovery of novel drug indications because of high costs in introducing new drugs. Many computational techniques have been proposed to detect potential drug-disease associations based on the creation of explicit profiles of drugs and diseases, while seldom research takes advantage of the immense accumulation of interaction data. In this work, we propose a matrix factorization model based on known drug-disease associations to predict novel drug indications. In addition, genomic space is also integrated into our framework. The introduction of genomic space, which includes drug-gene interactions, disease-gene interactions, and gene-gene interactions, is aimed at providing molecular biological information for prediction of drug-disease associations. The rationality lies in our belief that association between drug and disease has its evidence in the interactome network of genes. Experiments show that the integration of genomic space is indeed effective. Drugs, diseases, and genes are described with feature vectors of the same dimension, which are retrieved from the interaction data. Then a matrix factorization model is set up to quantify the association between drugs and diseases. Finally, we use the matrix factorization model to predict novel indications for drugs.

PMID:
26078775
PMCID:
PMC4452507
DOI:
10.1155/2015/275045
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Hindawi Limited Icon for PubMed Central
Loading ...
Support Center