The vitamin D receptor is a common target for various drugs, and is of great interest due to the protective function that this vitamin exerts on the body. The presence of single nucleotide polymorphisms (SNPs) in this receptor can affect the binding of the drug, which makes its analysis important. Through chemoinformatic studies, Perturbation Theory Machine Learning Information Fusion (PTMLIF) models that analyze this interaction can be established, for which the drug data set was downloaded from the public databases ChEMBL and NCBI (National Center for Biotechnology Information) and was subsequently performed the fusion of information. The database included 26064 trials with 47 different properties and 376 SNPs. In the present study, the deviations of the reference drug with respect to the perturbation operators were measured. The best model obtained showed values of Sp = 72.62%, Sn = 89.54% and Ac = 83.85% for training and Sp = 74.78% Sn = 90.88% and Ac = 85.31% for validation for a given application domain.
Previous Article in event
Previous Article in congress
Next Article in event
Next Article in congress
PTMLIF Model of ChEMBL preclinical assays of vit D derivatives vs. Single nucleotide polymorphism (SNP) data
Published:
12 June 2020
by MDPI
in MOL2NET'20, Conference on Molecular, Biomed., Comput. & Network Science and Engineering, 6th ed.
congress CHEMBIOMOL-06: Chem. Biol. & Med. Chem. Workshop, Bilbao-Rostock, Germany-Galveston, Texas, USA, 2020
https://doi.org/10.3390/mol2net-06-06859
(registering DOI)
Abstract:
Keywords: vitamin D; VDR; PTMLIF
![Top](/images/top.png?version=d2a1072bcb778c072486fad356669189)