|
OlegV. Tinkov, Veniamin
Yu. Grigorev, Lyudmila D. Grigoreva
QSAR
analysis of HDAC6 inhibitors
Abstract
Histone deacetylase inhibitors are the most
important class of drugs for the treatment of oncologies and other diseases due
to their effect on cell growth, differentiation and apoptosis. Among the known
eighteen histone deacetylases, Histone deacetylase 6 (HDAC6), which is involved
in oncogenesis, cell survival, and cancer cell metastasis, is of high
importance. Using 2D molecular descriptors RDKit, simplex descriptors, as well
as methods of Random Forest (RF), Gradient Boosting (GBM), Support vectors
(SVM), a number of adequate classification models of Quantitative
Structure–Activity Relationship (QSAR) are proposed. For the models constructed
using simplex descriptors, a structural interpretation was carried out, which
made it possible to describe molecular fragments that increase and decrease the
activity of HDAC6 inhibitors. The results of the structural interpretation were
used for the rational molecular design of potential HDAC6 inhibitors, for which
ADMET properties were also evaluated. Models built using 2D RDKit descriptors
are freely available on the github platform (https://github.com/ovttiras/HDAC6-inhibitors).
Key words: histone deacetylase 6 inhibitors, QSAR, molecular
descriptors, machine learning, structural interpretation
Copyright (C) Chemistry Dept., Moscow State University, 2002
|
|
