Transforming early pharmaceutical assessment of genotoxicity: applying statistical learning to a high throughput, multi end point in vitro micronucleus assay

Abstract

To provide a comprehensive analysis of small molecule genotoxic potential we have developed and validated an automated, high-content, high throughput, image-based in vitro Micronucleus (IVM) assay. This assay simultaneously assesses micronuclei and multiple additional cellular markers associated with genotoxicity. Acoustic dosing (≤ 2 mg) of compound is followed by a 24-h treatment and a 24-h recovery period. Confocal images are captured [Cell Voyager CV7000 (Yokogawa, Japan)] and analysed using Columbus software (PerkinElmer). As standard the assay detects micronuclei (MN), cytotoxicity and cell-cycle profiles from Hoechst phenotypes. Mode of action information is primarily determined by kinetochore labelling in MN (aneugencity) and γH2AX foci analysis (a marker of DNA damage). Applying computational approaches and implementing machine learning models alongside Bayesian classifiers allows the identification of, with 95% accuracy, the aneugenic, clastogenic and negative compounds within the data set (Matthews correlation coefficient: 0.9), reducing analysis time by 80% whilst concurrently minimising human bias. Combining high throughput screening, multiparametric image analysis and machine learning approaches has provided the opportunity to revolutionise early Genetic Toxicology assessment within AstraZeneca. By multiplexing assay endpoints and minimising data generation and analysis time this assay enables complex genotoxicity safety assessments to be made sooner aiding the development of safer drug candidates.

A MATLAB-based program for three-dimensional quantitative analysis of micronuclei reveals that neuroinflammation induces micronuclei formation in the brain

“…This approach is used to obtain data effectively and for general use. Quantification in conjunction with high-throughput screening and machine learning is powerful for analyzing the genomic condition in vitro 25 , 26 . It is technically difficult, however, to obtain precise data on the micronucleus in tissues due to stereoscopic challenges (see the Results sections).…”

Development of an In Vitro whole cell Micronucleus Multiplex expansion assay: Using DRAQ5™ and the DNA damage biomarkers ɣH2AX, P53, pH3 along with cell cycle relationships and the MN genotoxic endpoint to assess chemical Mode of Action on an imaging flow cytometry platform with template development

“…This therefore suggests that at the 24 hour time point chosen combined with the rapid continual repair nature of NHEJ along with the dose concentrations selected results in any initial ɣH2AX response based on immediate DSB's generated on initial introduction of Etoposide would be repaired resulting in the dissipation of the ɣH2AX signal as seen here. It is therefore reasonable to suggest that to truly assess the Etoposide MoA in this system a more finite dose range exceeding 0.5 µg/mL at the 24 hour time point to overwhelm the system tolerance for Etoposide exceeding the DNA damage threshold should be assessed alongside similar doses at a 3-4 hour exposure time point (Smart et al, 2008;Lynch et al, 2003;Kirkland et al, 2010;Wilson et al, 2021).…”

“…The principal advantage of this assay is the simultaneous detection of DNA damage Mode of Action whilst maintaining the morphological high content localisation information of microscopy, with the high throughput potential of flow cytometry. These qualities of the ISMN-me assay place the platform within industry safety assessment, specifically in genetic toxicology within the drug development pipeline filling a niche not covered by current MoA genetic toxicology assays (Wilson et al, 2021;Dertinger et al, 2018).…”

“…Use of tools such as Toxicological Prioritization Index (ToxPi) visualisation software for generation of a carcinogenicity scores could go a long way to making this barrage of information easier to digest and draw conclusions from in terms of determining MoA (Chapman et al, 2021;Wilde et al, 2018). Whilst promising, generation of clean cut 'Yes/No' decision making, that is often relied upon in genetic toxicology with regard to compound progression and regulatory submissions, specifically in relation to biomarker response and best approaches is a topic of debate (Chapman et al, 2021;Wheeldon et al, 2020;Bryce et al, 2018;Dertinger et al, 2019;Gollapudi et al, 2013;Wilson et al, 2021).…”

“…The anti-ɣH2AX-Ser139 antibody has been used in numerous studies and publications, Bryce et al, 2016, Khoury et al, 2016, Smart et al, 2011, Cheung et al, 2015and Wilson et al, 2021 to name a few, it is a truly well defined biomarker associated with DNA damage directly in the form of strand breakage and of the DNA damage response pathway (Podhorecka et al, 2010). Selection of the ɣH2AX antibody conjugated to the BV421 fluorophore was mainly chosen as it is excited by the 405nm laser which was available on the FlowSight® used at Swansea University for preliminary optimisation and work.…”