Genotoxic mode of action predictions from a multiplexed flow cytometric assay and a machine learning approach

Abstract

Several endpoints associated with cellular responses to DNA damage as well as overt cytotoxicity were multiplexed into a miniaturized, “add and read” type flow cytometric assay. Reagents included a detergent to liberate nuclei, propidium iodide and RNase to serve as a pan-DNA dye, fluorescent antibodies against γH2AX, phospho-histone H3, and p53, and fluorescent microspheres for absolute nuclei counts. The assay was applied to TK6 cells and 67 diverse reference chemicals that served as a training set. Exposure was for 24 hrs in 96 well plates, and unless precipitation or foreknowledge about cytotoxicity suggested otherwise, the highest concentration was 1 mM. At 4 and 24 hrs aliquots were removed and added to microtiter plates containing the reagent mix. Following a brief incubation period robotic sampling facilitated walk-away data acquisition. Univariate analyses identified biomarkers and time points that were valuable for classifying agents into one of three groups: clastogenic, aneugenic, or non-genotoxic. These mode of action predictions were optimized with a forward-stepping process that considered Wald test p-values, receiver operator characteristic curves, and pseudo R2 values, among others. A particularly high performing multinomial logistic regression model was comprised of four factors: 4hr γH2AX and phospho-histone H3 values, and 24 hr p53 and polyploidy values. For the training set chemicals, the four-factor model resulted in 94% concordance with our a priori classifications. Cross validation occurred via a leave-one-out approach, and in this case 91% concordance was observed. A test set of 17 chemicals that were not used to construct the model were evaluated, some of which utilized a short-term treatment in the presence of a metabolic activation system, and in 16 cases mode of action was correctly predicted. These initial results are encouraging as they suggest a machine learning strategy can be used to rapidly and reliably predict new chemicals’ genotoxic mode of action based on data from an efficient and highly scalable multiplexed assay.

Interlaboratory evaluation of a multiplexed high information content in vitro genotoxicity assay

“…In terms of positive controls, we recommend beginning with reference chemicals from Table , agents with relatively well known MoA that have been studied at multiple laboratories. Biomarker response profiles described here and elsewhere [Bryce et al, ] should be observed before initiating more extensive testing or beginning work with uncharacterized compounds, especially if they represent new chemical space.…”

“…At each site stock photomultiplier tube detectors and associated optical filter sets were used to detect fluorescence emissions associated with the fluorochromes: FITC (i.e., FL1 in BD instrument parlance), PE (FL2), propidium iodide (FL3), and Alexa Fluor® 647 (FL4). Recommended mixing and fluidics parameters for the autosampler devices were described in Bryce et al []. Generally speaking, across the sites, 4 hr samples provided 1000 or more 2 n and greater nuclei for analysis, and 24 hr samples provided 4000 or more 2 n and greater nuclei.…”

“…Meeting or exceeding these interlaboratory‐derived values identified a significant biomarker response at a particular time point. Note that as previously described [Bryce et al, ], assay data were restricted to those concentrations that exhibited ≥ 20% relative nuclei counts at 24 hr. In general, the greatest differentiation of genotoxic MoA was evident with increasing chemical exposure.…”

“…In addition to GEFs, we also evaluated a second strategy for assessing whether a genotoxic response occurred. A 4‐factor multinomial logistic regression model that predicts predominant genotoxic MoA based on MultiFlow response data has been previously described [Bryce et al, ]. The approach used herein is a variant, an ensemble of two 4‐factor multinomial logistic regression models that we believe has certain advantages for detecting genotoxicants that exhibit atypical response profiles.…”

“…One line of investigation that has been pursued by our laboratories is the development of a multiplexed flow cytometric assay that combines several biomarkers relevant to DNA damage response pathways [Bernacki et al, ; Bryce et al, ]. This method involves a one‐step, add‐and‐read process that efficiently prepares samples in microtiter plate‐format for high throughput analysis via flow cytometry.…”