Computational Analysis of LOX1 Inhibition Identifies Descriptors Responsible for Binding Selectivity

Chrysoula Gousiadou*, Irene Kouskoumvekaki

*Corresponding author for this work

    Research output: Contribution to journalJournal articleResearchpeer-review

    191 Downloads (Pure)

    Abstract

    Lipoxygenases are a family of cytosolic, peripheral membrane enzymes, which catalyze the hydroperoxidation of polyunsaturated fatty acids and are implicated in the pathogenesis of major human diseases. Over the years, a substantial number of scientific reports have introduced inhibitors active against one or another subtype of the enzyme, but the selectivity issue has proved to be a major challenge for drug design. In the present work, we assembled a dataset of 317 structurally diverse molecules hitherto reported as active against 15S-LOX1, 12S-LOX1, and 15S-LOX2 and identified, using supervised machine learning, a set of structural descriptors responsible for the binding selectivity toward the enzyme 15S-LOX1. We subsequently incorporated these descriptors in the training of QSAR models for LOX1 activity and selectivity. The best performing classifiers are two stacked models that include an ensemble of support vector machine, random forest, and k-nearest neighbor algorithms. These models not only can predict LOX1 activity/inactivity but also can discriminate with high accuracy between molecules that exhibit selective activity toward either one of the isozymes 15S-LOX1 and 12S-LOX1.
    Original languageEnglish
    JournalACS Omega
    Volume3
    Issue number2
    Pages (from-to)2261-2272
    DOIs
    Publication statusPublished - 2018

    Bibliographical note

    This is an open access article published under an ACS AuthorChoice License

    Cite this