Next Article in Journal
Structural Characterization of Lithium and Sodium Bulky Bis(silyl)amide Complexes
Next Article in Special Issue
Evolution of In Silico Strategies for Protein-Protein Interaction Drug Discovery
Previous Article in Journal
Detecting Differential Transcription Factor Activity from ATAC-Seq Data
Previous Article in Special Issue
Accurate Estimation of the Standard Binding Free Energy of Netropsin with DNA
Article

Fingerprint-Based Machine Learning Approach to Identify Potent and Selective 5-HT2BR Ligands

1
Department of Medicinal Chemistry, Institute of Pharmacology, Polish Academy of Sciences, 12 Smętna Street, 31-343 Krakow, Poland
2
Medicinal Chemistry Research Group, Research Centre for Natural Sciences, Hungarian Academy of Sciences, Magyar tudósok krt. 2, H1117 Budapest, Hungary
3
Grupo de Investigación “BioFarma” USC, Centro de Investigación CIMUS, Planta 3ª, Avd. de Barcelona s/n, 15782 Santiago de Compostela, Spain
*
Authors to whom correspondence should be addressed.
Academic Editor: F. Javier Luque
Molecules 2018, 23(5), 1137; https://doi.org/10.3390/molecules23051137
Received: 16 April 2018 / Revised: 5 May 2018 / Accepted: 7 May 2018 / Published: 10 May 2018
(This article belongs to the Special Issue Frontiers in Computational Chemistry for Drug Discovery)
The identification of subtype-selective GPCR (G-protein coupled receptor) ligands is a challenging task. In this study, we developed a computational protocol to find compounds with 5-HT2BR versus 5-HT1BR selectivity. Our approach employs the hierarchical combination of machine learning methods, docking, and multiple scoring methods. First, we applied machine learning tools to filter a large database of druglike compounds by the new Neighbouring Substructures Fingerprint (NSFP). This two-dimensional fingerprint contains information on the connectivity of the substructural features of a compound. Preselected subsets of the database were then subjected to docking calculations. The main indicators of compounds’ selectivity were their different interactions with the secondary binding pockets of both target proteins, while binding modes within the orthosteric binding pocket were preserved. The combined methodology of ligand-based and structure-based methods was validated prospectively, resulting in the identification of hits with nanomolar affinity and ten-fold to ten thousand-fold selectivities. View Full-Text
Keywords: target selectivity; G-protein coupled receptor; 5-HT2BR; chemical fingerprint target selectivity; G-protein coupled receptor; 5-HT2BR; chemical fingerprint
Show Figures

Graphical abstract

MDPI and ACS Style

Rataj, K.; Kelemen, Á.A.; Brea, J.; Loza, M.I.; Bojarski, A.J.; Keserű, G.M. Fingerprint-Based Machine Learning Approach to Identify Potent and Selective 5-HT2BR Ligands. Molecules 2018, 23, 1137. https://doi.org/10.3390/molecules23051137

AMA Style

Rataj K, Kelemen ÁA, Brea J, Loza MI, Bojarski AJ, Keserű GM. Fingerprint-Based Machine Learning Approach to Identify Potent and Selective 5-HT2BR Ligands. Molecules. 2018; 23(5):1137. https://doi.org/10.3390/molecules23051137

Chicago/Turabian Style

Rataj, Krzysztof, Ádám A. Kelemen, José Brea, María I. Loza, Andrzej J. Bojarski, and György M. Keserű. 2018. "Fingerprint-Based Machine Learning Approach to Identify Potent and Selective 5-HT2BR Ligands" Molecules 23, no. 5: 1137. https://doi.org/10.3390/molecules23051137

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop