MANORAA: A machine learning platform to guide protein-ligand design by anchors and influential distances.
Structure
; 30(1): 181-189.e5, 2022 01 06.
Article
em En
| MEDLINE
| ID: mdl-34614393
ABSTRACT
The MANORAA platform uses structure-based approaches to provide information on drug design originally derived from mapping tens of thousands of amino acids on a grid. In-depth analyses of the pockets, frequently occurring atoms, influential distances, and active-site boundaries are used for the analysis of active sites. The algorithms derived provide model equations that can predict whether changes in distances, such as contraction or expansion, will result in improved binding affinity. The algorithm is confirmed using kinetic studies of dihydrofolate reductase (DHFR), together with two DHFR-TS crystal structures. Empirical analyses of 881 crystal structures involving 180 ligands are used to interpret protein-ligand binding affinities. MANORAA links to major biological databases for web-based analysis of drug design. The frequency of atoms inside the main protease structures, including those from SARS-CoV-2, shows how the rigid part of the ligand can be used as a probe for molecular design (http//manoraa.org).
Palavras-chave
Texto completo:
1
Base de dados:
MEDLINE
Assunto principal:
Proteínas
/
Biologia Computacional
/
Bases de Dados de Proteínas
/
Aprendizado de Máquina
/
Domínios Proteicos
Tipo de estudo:
Prognostic_studies
Limite:
Humans
Idioma:
En
Ano de publicação:
2022
Tipo de documento:
Article