Identification of lysosomotropism using explainable machine learning and morphological profiling cell painting data
Loading...
Date issued
Editors
Journal Title
Journal ISSN
Volume Title
Publisher
Reuse License
Abstract
Lysosomotropism is a phenomenon of diverse pharmaceutical interests because it is a property of compounds with diverse chemical structures and primary targets. While it is primarily reported to be caused by compounds having suitable lipophilicity and basicity values, not all compounds that fulfill such criteria are in fact lysosomotropic. Here, we use morphological profiling by means of the cell painting assay (CPA) as a reliable surrogate to identify lysosomotropism. We noticed that only 35% of the compound subset with matching physicochemical properties show the lysosomotropic phenotype. Based on a matched molecular pair analysis (MMPA), no key substructures driving lysosomotropism could be identified. However, using explainable machine learning (XML), we were able to highlight that higher lipophilicity, basicity, molecular weight, and lower topological polar surface area are among the important properties that induce lysosomotropism in the compounds of this subset.
Description
Keywords
Citation
Published in
RSC medicinal chemistry, 16, Royal Society of Chemistry, Cambridge, 2024, https://doi.org/10.1039/D4MD00107A