BENDER DB: a database of protein binding sites across neglected disease proteomes.
5 affiliations
- 1Department of Computer Science, Universidade Federal de Viçosa, Peter Henry Rolfs Av, Viçosa, Brazil. [email protected].
- 2School of Computing and Information Systems, University of Melbourne, Swanston St, Melbourne, Australia.
- 3Department of Biochemistry and Molecular Biology, Universidade Federal de Viçosa, Peter Henry Rolfs Av, Viçosa, Brazil.
- 4Institute of Technological Sciences, Universidade Federal de Itajubá, Irmã Ivone Drumond St, Itabira, Brazil.
- 5Department of Computer Science, Universidade Federal de Viçosa, Peter Henry Rolfs Av, Viçosa, Brazil.
Abstract
Identifying binding sites is crucial for expanding our knowledge of various biological processes, supporting drug discovery, and repositioning strategies, particularly in the early research phases of target hopping. This is especially important for neglected diseases, which predominantly impact vulnerable populations in developing regions. To address this, we created BENDER DB, a database designed to map predicted protein binding sites within the proteomes of pathogens associated with neglected diseases. Utilizing AlphaFold-predicted structures, BENDER DB integrates results from five leading binding site prediction tools, resulting in over one million binding sites across over 100,000 proteins from 10 different proteomes. BENDER DB offers unique features, such as integrating multiple predictors, interactive visualization tools, and comprehensive graphical representations, allowing for a detailed visual comparative analysis of different prediction methods and the predicted binding sites. We combined the computational approaches to offer a consensus of binding site predictions, leveraging the strengths of multiple techniques. Additionally, we introduce BENDER AI, a meta-predictor that integrates the outputs of the individual predictors into a unified, consensus-based binding site classification. By combining the five methods, BENDER AI provides a high-confidence classification that achieved an MCC of 0.64 and an AUC of 0.89, offering reliable predictions that minimize false positives while remaining competitive with the best individual predictors. By consolidating these results, BENDER DB enables detailed comparative analyses of prediction methods and integrates interactive visualization tools to provide users with an intuitive platform for binding site exploration. The database aims to accelerate drug discovery efforts, particularly in underdeveloped regions, by providing a robust and detailed resource for studying protein binding sites. BENDER DB is available at https://benderdb.ufv.br .
Related
- RNAffinityDB: a curated database of experimental RNA–protein binding affinities
- ProPepBA: a binding affinity database for canonical and chemically modified protein–peptide interactions
- Tau is an m6A-associated RNA binding protein that causes RNA dysregulation in disease
- ARIEL: an openly accessible database of experimental RNA–ligand binding affinities paired with 3D structures
- An advanced LLM-powered article extraction pipeline delivers a database of buffers for protein studies and protein expression conditions.
BibTeX
@article{paiva2026bender,
title = {{BENDER DB: a database of protein binding sites across neglected disease proteomes.}},
author = {Vinícius A Paiva and Douglas E V Pires and Gustavo C Bressan and Sandro C Izidoro and Sabrina A Silveira},
journal = {BMC bioinformatics},
year = {2026},
month = aug,
doi = {10.1186/s12859-026-06590-1},
url = {https://europepmc.org/article/MED/42972226},
note = {CC BY},
}
RIS
TY - JOUR
TI - BENDER DB: a database of protein binding sites across neglected disease proteomes.
AU - Vinícius A Paiva
AU - Douglas E V Pires
AU - Gustavo C Bressan
AU - Sandro C Izidoro
AU - Sabrina A Silveira
PY - 2026
DA - 2026/08/05
JO - BMC bioinformatics
DO - 10.1186/s12859-026-06590-1
UR - https://europepmc.org/article/MED/42972226
AB - Identifying binding sites is crucial for expanding our knowledge of various biological processes, supporting drug discovery, and repositioning strategies, particularly in the early research phases of target hopping. This is especially important for neglected diseases, which predominantly impact vulnerable populations in developing regions. To address this, we created BENDER DB, a database designed to map predicted protein binding sites within the proteomes of pathogens associated with neglected diseases. Utilizing AlphaFold-predicted structures, BENDER DB integrates results from five leading binding site prediction tools, resulting in over one million binding sites across over 100,000 proteins from 10 different proteomes. BENDER DB offers unique features, such as integrating multiple predictors, interactive visualization tools, and comprehensive graphical representations, allowing for a detailed visual comparative analysis of different prediction methods and the predicted binding sites. We combined the computational approaches to offer a consensus of binding site predictions, leveraging the strengths of multiple techniques. Additionally, we introduce BENDER AI, a meta-predictor that integrates the outputs of the individual predictors into a unified, consensus-based binding site classification. By combining the five methods, BENDER AI provides a high-confidence classification that achieved an MCC of 0.64 and an AUC of 0.89, offering reliable predictions that minimize false positives while remaining competitive with the best individual predictors. By consolidating these results, BENDER DB enables detailed comparative analyses of prediction methods and integrates interactive visualization tools to provide users with an intuitive platform for binding site exploration. The database aims to accelerate drug discovery efforts, particularly in underdeveloped regions, by providing a robust and detailed resource for studying protein binding sites. BENDER DB is available at https://benderdb.ufv.br .
SN - 1471-2105
ER -