BalestraWeb 2.0
Home  |   Tutorials  |   Theory  |   BalestraWeb 1.0

What is the BalestraWeb?
Data on protein-drug and protein-ligand interactions are rapidly accumulating in databases such as DrugBank and STITCH. These data usually reflect observed interactions, while the lack of data for a given protein-drug/ligand pair does not necessarily mean the lack of interaction. Indeed, recent studies, both computational and experimental, highlighted the promiscuity of both proteins and small molecules: many drugs have side effects i.e. they target proteins other than those known in public databases; and many proteins bind ligands other than those known, opening the way to designing repurposable drugs, new ligands, or polypharmacological treatments. There is a need for efficiently identifying such interactions and disseminating them. The BalestraWeb server addresses this need by learning probabilistic latent factor models for protein-drug/ligand interactions and enabling users to efficiently mine known interactions and predict new ones.

Input type: Drug and/or target A list of drugs/targets


Input at least one drug and/or one target

Drug group in DrugBank: Approved drugs All drugs

Query type: drug-target interaction drug-drug similarity target-target similarity

Drug 1:
DrugBank drug ID or common drug name (e.g. "Loxapine" or "DB01224").

Target 1:
UniProt ID, gene name or protein name (e.g. "P28566" or "ADA2A").

Drug 2:
DrugBank drug ID or common drug name (e.g. "Asenapine" or "DB01142").

Target 2:
UniProt ID, gene name or protein name (e.g. "P34969" or "5HT7R").

No. of predictions (1 to 100):

Display secondary Interactions: No Yes

Load examples: 


Murat Can Cobanoglu, Zoltán N. Oltvai, D. Lansing Taylor and Ivet Bahar. (2015) BalestraWeb: efficient online evaluation of drug–target interactions. Bioinformatics., 31(1), 131–133.


The BalestraWeb 2.0 server is maintained by Dr. Hongchun Li in the Bahar Lab at the Department of Computational & Systems Biology at the University of Pittsburgh, School of Medicine, and sponsored by the NIH awards #5R01GM099738-04 and #5P41GM103712-03.

For questions and comments please contact Hongchun Li.