Hakime Moghadam - Database Research Group (DBRG), Control and Intelligent Processing Center of Excellence (CIPCE), School of Electri-cal and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran;
Masoud Rahgozar - Database Research Group (DBRG), Control and Intelligent Processing Center of Excellence (CIPCE), School of Electri-cal and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran;
Sajjad Gharaghani - Laboratory of Chemoinformatics & Drug Design (LCD), Institute of Biochemistry and Biophysics, University of Tehran, Tehran, Iran;

Prediction of drug-disease interactions is one of the existing fields in drug repositioning. Drug repositioning which makes use of known drugs to new indications has turned into a challenging topic in pharmaceutical science. To predict unknown drug-disease interactions, there are diverse data sources and multiple side information available to us which can help have more accurate and reliable results. This information can be collectively mined using data fusion methods. In this paper, we have proposed a computational methods, namely Average Similarity Fusion (ASF) which integrate various data sources and side information related to drugs or diseases in order to predict novel drug indications. Generally, the purpose of the present study has been to investigate the effect of side information of drugs and diseases as well as data fusion in prediction of drug-disease interactions. To this purpose, the method was validated against a well-established drug-disease gold-standard dataset. Comparisons with some existing methods revealed that our proposed method (ASF) outperformed and is competitive in performance.

Data fusion, drug-disease interaction prediction, kernel fusion, support vector machine