Format

Send to

Choose Destination
Biochem Biophys Res Commun. 2017 Dec 9;494(1-2):305-310. doi: 10.1016/j.bbrc.2017.10.035. Epub 2017 Oct 7.

Supervised machine learning techniques to predict binding affinity. A study for cyclin-dependent kinase 2.

Author information

1
Laboratory of Computational Systems Biology, School of Sciences - Pontifical Catholic University of Rio Grande do Sul (PUCRS), Av. Ipiranga, 6681, Porto Alegre, RS 90619-900, Brazil; Graduate Program in Cellular and Molecular Biology, Pontifical Catholic University of Rio Grande do Sul (PUCRS), Av. Ipiranga, 6681, Porto Alegre, RS 90619-900, Brazil.
2
Laboratory of Computational Systems Biology, School of Sciences - Pontifical Catholic University of Rio Grande do Sul (PUCRS), Av. Ipiranga, 6681, Porto Alegre, RS 90619-900, Brazil.
3
Laboratory of Computational Systems Biology, School of Sciences - Pontifical Catholic University of Rio Grande do Sul (PUCRS), Av. Ipiranga, 6681, Porto Alegre, RS 90619-900, Brazil; Graduate Program in Cellular and Molecular Biology, Pontifical Catholic University of Rio Grande do Sul (PUCRS), Av. Ipiranga, 6681, Porto Alegre, RS 90619-900, Brazil. Electronic address: walter@azevedolab.net.

Abstract

Here we report the development of a machine-learning model to predict binding affinity based on the crystallographic structures of protein-ligand complexes. We used an ensemble of crystallographic structures (resolution better than 1.5 Å resolution) for which half-maximal inhibitory concentration (IC50) data is available. Polynomial scoring functions were built using as explanatory variables the energy terms present in the MolDock and PLANTS scoring functions. Prediction performance was tested and the supervised machine learning models showed improvement in the prediction power, when compared with PLANTS and MolDock scoring functions. In addition, the machine-learning model was applied to predict binding affinity of CDK2, which showed a better performance when compared with AutoDock4, AutoDock Vina, MolDock, and PLANTS scores.

KEYWORDS:

Bioinformatics; CDK2; Docking; Drug design; Kinase; Machine learning

PMID:
29017921
DOI:
10.1016/j.bbrc.2017.10.035
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center