GRASP: GRAPH-BASED RESIDUE NEIGHBORHOOD STRATEGY TO PREDICT BINDING SITES

Charles Abreu Santana; Sabrina de Azevedo Silveira; João Pedro Areias de Moraes; Sandro Izidoro; Raquel Minardi; António J. M. Ribeiro; Jonathan D. Tyzack; Neera Borkakoti; Janet M. Thornton

All Papers

Submission

Paper Title

GRASP: GRAPH-BASED RESIDUE NEIGHBORHOOD STRATEGY TO PREDICT BINDING SITES

Authors

Charles Abreu Santana
Sabrina de Azevedo Silveira
João Pedro Areias de Moraes
Sandro Izidoro
Raquel Minardi
António J. M. Ribeiro
Jonathan D. Tyzack
Neera Borkakoti
Janet M. Thornton

Modality

Xpress presentation

Subject area

Structural Bioinformatics

Publishing Date

26/04/2022

Country of Publishing

Brasil

Language of Publishing

Inglês

Paper Page

https://www.even3.com.br/anais/xmeetingxp2021/420197-grasp--graph-based-residue-neighborhood-strategy-to-predict-binding-sites

ISBN

978-65-5941-645-5

Keywords

proteins, binding site, machine learning, graph

Summary

Proteins are pivotal macromolecules involved in several biological processes important for the cell life cycle. Often protein activity is performed through physicochemical interactions between the protein and other molecules called ligands. These ligands comprise organic compounds, metal ions, nucleic acids or even other proteins, which attach to the protein so that its activity is properly performed. The region on the protein in which these interactions take place is called binding sites. The identification and characterization of these regions is crucial to determine the function of a protein, which is one of the necessary steps in areas such as the design and development of new drugs. Due to experimental issues, since detecting protein–ligand-binding sites experimentally is time-consuming and expensive, the location of these regions may not be trivial, requiring the support of automatic methods to assist in their identification. In this work we propose Graph-based Residue neighborhood Strategy to Predict binding sites (GRaSP), a residue centric method to predict ligand-binding site residues. GRaSP models the residue environment as a graph at atomic level, enriching these graphs with physicochemical properties, and using them as input for a supervised learning strategy. From experiments using databases of different protein structures, GRaSP proved to be robust, presenting compatible or better results in relation to the tools already consolidated in the literature. GRaSP ranked second when compared against pocket-centric methods, which is a significant result, as it was not devised to predict pockets. Furthermore, due to the simple and informative modeling provided by the graphs, the algorithm proved to be efficient. While already consolidated methods take around 5 hours of processing for protein structures with approximately 300 residues, the GRASP is able to process them in an average time of 20 seconds.

Title of the Event: X-Meeting XPerience 2021
Title of the Proceedings of the event: X-Meeting presentations
Name of the Publisher: Even3
Means of Dissemination: Meio Digital

How to cite

SANTANA, Charles Abreu et al.. GRASP: GRAPH-BASED RESIDUE NEIGHBORHOOD STRATEGY TO PREDICT BINDING SITES.. In: X-Meeting presentations. Anais...São Paulo(SP) AB3C, 2021. Available in: https//www.even3.com.br/anais/xmeetingxp2021/420197-GRASP--GRAPH-BASED-RESIDUE-NEIGHBORHOOD-STRATEGY-TO-PREDICT-BINDING-SITES. Access in: 04/07/2025