Investigating the Generalizability of the MultiFlow ® DNA Damage Assay and Several Companion Machine Learning Models With a Set of 103 Diverse Test Chemicals

Abstract

The in vitro MultiFlow DNA Damage assay multiplexes p53, γH2AX, phospho-histone H3, and polyploidization biomarkers into 1 flow cytometric analysis (Bryce, S. M., Bernacki, D. T., Bemis, J. C., and Dertinger, S. D. (2016). Genotoxic mode of action predictions from a multiplexed flow cytometric assay and a machine learning approach. Environ. Mol. Mutagen. 57, 171-189). The work reported herein evaluated the generalizability of the method, as well as several data analytics strategies, to a range of chemical classes not studied previously. TK6 cells were exposed to each of 103 diverse chemicals, 86 of which were supplied by the National Toxicology Program (NTP) and selected based upon responses in genetic damage assays conducted under the Tox21 program. Exposures occurred for 24 h over a range of concentrations, and cell aliquots were removed at 4 and 24 h for analysis. Multiplexed response data were evaluated using 3 machine learning models designed to predict genotoxic mode of action based on data from a training set of 85 previously studied chemicals. Of 54 chemicals with sufficient information to make an a priori call on genotoxic potential, the prediction models' accuracies were 79.6% (random forest), 88.9% (logistic regression), and 90.7% (artificial neural network). A majority vote ensemble of the 3 models provided 92.6% accuracy. Forty-nine NTP chemicals were not adequately tested (maximum concentration did not approach assay's cytotoxicity limit) and/or had insufficient conventional genotoxicity data to allow their genotoxic potential to be defined. For these chemicals MultiFlow data will be useful in future research and hypothesis testing. Collectively, the results suggest the MultiFlow assay and associated data analysis strategies are broadly generalizable, demonstrating high predictability when applied to new chemicals and classes of compounds.

Predictions of genotoxic potential, mode of action, molecular targets, and potency via a tiered multiflow® assay data analysis strategy

“…The identities of 85 previously reported training set chemicals (Bryce et al 2018) and a new set of pharmaceutical-centric test set chemicals (n = 40), the source, and other information, are provided in Table I. Merck Sharp & Dohme Corp., a subsidiary of Merck & Co., Inc., Kenilworth, NJ (MSD), supplied 20 of the 40 test chemicals (coded) to Litron, and these were stored at −20 C until they were solubilized in dimethyl sulfoxide (DMSO), at which point they were refrozen at −20 C. Additional test set chemicals (n = 20) were selected by Litron scientists largely from the list recommended by Kirkland and colleagues for evaluating new genotoxicity tests (Kirkland Fig.…”

“…Our laboratories have pursued the development and validation of a multiplexed flow cytometric assay that combines information from several biomarkers relevant to DNA damage response pathways and aneuploidy induction (Bryce et al , , , ; Bernacki et al ). This so‐called MultiFlow® DNA Damage Assay is formatted as an add‐and‐read test that efficiently prepares cells in microtiter plates for flow cytometric analysis.…”

Benchmark Dose Analysis of DNA Damage Biomarker Responses Provides Compound Potency and Adverse Outcome Pathway Information for the Topoisomerase II Inhibitor Class of Compounds

“…Until now, the MultiFlow assay has been shown to discriminate between broad modes of action, that is, clastogens, aneugens, and non‐genotoxic compounds (Bryce et al, , , , ; Bernacki et al, ). However, given the reproducible, quantitative nature of the assay, we believe that BMD analysis of the response data can be used to provide robust potency ranks within a specific MoA.…”

“…Hence, following exposure to Topo II poison compounds, one would expect the response for double‐strand breaks to increase by exhibiting elevated γH2AX responses, as well as increases in the genome “guardian” p53 endpoint. Discrimination between clastogenic and aneugenic events by MultiFlow's p‐H3 response to cell cycle perturbations was previously described (Bryce et al, , , , ). By understanding the process by which Topo II induces clastogenicity complemented with cell cycle arrest, a decrease in p‐H3 response would be expected to coincide with Topo II poison‐mediated cell cycle delay.…”

Evidence for an Aneugenic Mechanism of Action for Micronucleus Induction by Black Cohosh Extract

“…The biomarker responses include phosphorylation of H2AX (γH2AX), translocation of p53 to the nucleus, phosphorylation of histone H3 at serine 10 (p‐H3), and induction of polyploidy. Together with information on cytotoxicity at 24 h, the machine‐learning algorithms translate the collection of MultiFlow responses into predictions about predominant MoA—clastogenic, aneugenic, or non‐genotoxic (Bryce et al ; Bryce et al ; Bryce et al ; Dertinger et al ). The NTP BCE and BC XRM samples were characterized by the MultiFlow assay as having aneugenic activity (Smith‐Roe et al ).…”