Taba: A Tool to Analyze the Binding Affinity.

da Silva, Amauri Duarte; Bitencourt-Ferreira, Gabriela; de Azevedo, Walter Filgueira

da Silva, Amauri Duarte; Bitencourt-Ferreira, Gabriela; de Azevedo, Walter Filgueira.

Afiliação

da Silva AD; Laboratory of Computational Systems Biology, Pontifical Catholic University of Rio Grande do Sul (PUCRS), Ipiranga Avenue, 6681 Partenon, 90619-900, Porto Alegre/RS, Brazil.
Bitencourt-Ferreira G; Specialization Program in Bioinformatics, Pontifical Catholic University of Rio Grande do Sul (PUCRS), Ipiranga Avenue, 6681 Partenon, 90619-900, Porto Alegre/RS, Brazil.
de Azevedo WF; Laboratory of Computational Systems Biology, Pontifical Catholic University of Rio Grande do Sul (PUCRS), Ipiranga Avenue, 6681 Partenon, 90619-900, Porto Alegre/RS, Brazil.

J Comput Chem ; 41(1): 69-73, 2020 01 05.

Article em En | MEDLINE | ID: mdl-31410856

RESUMO

Evaluation of ligand-binding affinity using the atomic coordinates of a protein-ligand complex is a challenge from the computational point of view. The availability of crystallographic structures of complexes with binding affinity data opens the possibility to create machine-learning models targeted to a specific protein system. Here, we describe a new methodology that combines a mass-spring system approach with supervised machine-learning techniques to predict the binding affinity of protein-ligand complexes. The combination of these techniques allows exploring the scoring function space, generating a model targeted to a protein system of interest. The new model shows superior predictive performance when compared with classical scoring functions implemented in the programs Molegro Virtual Docker, AutoDock4, and AutoDock Vina. We implemented this methodology in a new program named Taba. Taba is implemented in Python and available to download under the GNU license at https://github.com/azevedolab/taba. © 2019 Wiley Periodicals, Inc.

Assuntos

Proteínas/química; Software; Ligantes; Aprendizado de Máquina; Modelos Moleculares; Termodinâmica

Palavras-chave

binding affinity; drug design; machine learning; protein-ligand interactions; scoring function

Texto completo

Adicionar na Minha BVS

Imprimir

XML

PubMed Links

Buscar no Google

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Software / Proteínas Tipo de estudo: Prognostic_studies Idioma: En Revista: J Comput Chem Assunto da revista: QUIMICA Ano de publicação: 2020 Tipo de documento: Article País de afiliação: Brasil País de publicação: Estados Unidos

Texto completo

Adicionar na Minha BVS

Imprimir

XML

PubMed Links

Buscar no Google