BalestraWeb: efficient online evaluation of drug–target interactions

• DOI: 10.1093/bioinformatics/btu599
• Publication Date: 2014-09-06T04:48:38Z
• Authors: Murat Can Cobanoglu; Zoltán N. Oltvai; D. Lansing Taylor; Ivet Bahar
• Keywords: DrugBank; Cheminformatics; Drug repositioning; Drug-drug interaction; Python

Abstract Summary: BalestraWeb is an online server that allows users to instantly make predictions about the potential occurrence of interactions between any given drug–target pair, or predict most likely interaction partners drug target listed in DrugBank. It also permits identify similar drugs targets based on their patterns. Outputs help develop hypotheses repurposing as well side effects. Availability and implementation: accessible at http://balestra.csb.pitt.edu/ . The tool built using a probabilistic matrix factorization method DrugBank v3, latent variable models are trained GraphLab collaborative filtering toolkit. implemented Python, Flask, NumPy SciPy. Contact: [e-mail]