CRISPR/Cas9-edited ROS1 + non-small cell lung cancer cell lines highlight differential drug sensitivity in 2D vs 3D cultures while reflecting established resistance profiles

Introduction The study of resistance-causing mutations in oncogene-driven tumors is fundamental to guide clinical decisions. Several point mutations affecting the ROS1 kinase domain have been identified in the clinical setting, but their impact requires further exploration, particularly in improved pre-clinical models. Given the scarcity of solid pre-clinical models to approach rare cancer subtypes like ROS1 + NSCLC, CRISPR/Cas9 technology allows the introduction of mutations in patient-derived cell lines for which resistant variants are difficult to obtain due to the low prevalence of cases within the clinical setting. Methods In the SLC34A2-ROS1 rearranged NSCLC cell line HCC78, we knocked-in through CRISPR/Cas9 technology three ROS1 drug resistance-causing mutations: G2032R, L2026M and S1986Y. Such variants are located in different functional regions of the ROS1 kinase domain, thus conferring TKI resistance through distinct mechanisms. We then performed pharmacological assays in 2D and 3D to assess the cellular response of the mutant lines to crizotinib, entrectinib, lorlatinib, repotrectinib and ceritinib. In addition, immunoblotting assays were performed in 2D-treated cell lines to determine ROS1 phosphorylation and MAP kinase pathway activity. The area over the curve (AOC) defined by the normalized growth rate (NGR_fit) dose-response curves was the variable used to quantify the cellular response towards TKIs. Results Spheroids derived from ROS1G2032R cells were significantly more resistant to repotrectinib (AOC fold change = - 7.33), lorlatinib (AOC fold change = - 6.17), ceritinib (AOC fold change = - 2.8) and entrectinib (AOC fold change = - 2.02) than wild type cells. The same cells cultured as a monolayer reflected the inefficacy of crizotinib (AOC fold change = - 2.35), entrectinib (AOC fold change = - 2.44) and ceritinib (AOC fold change = - 2.12) in targeting the ROS1 G2032R mutation. ROS1L2026M cells showed also remarkable resistance both in monolayer and spheroid culture compared to wild type cells, particularly against repotrectinib (spheroid AOC fold change = - 2.19) and entrectinib (spheroid AOC fold change = - 1.98). ROS1S1986Y cells were resistant only towards crizotinib in 2D (AOC fold change = - 1.86). Overall, spheroids showed an increased TKI sensitivity compared to 2D cultures, where the impact of each mutation that confers TKI resistance could be clearly distinguished. Western blotting assays qualitatively reflected the patterns of response towards TKI observed in 2D culture through the levels of phosphorylated-ROS1. However, we observed a dose-response increase of phosphorylated-Erk1/2, suggesting the involvement of the MAPK pathway in the mediation of apoptosis in HCC78 cells. Conclusion In this study we knock-in for the first time in a ROS1 + patient-derived cell line, three different known resistance-causing mutations using CRISPR/Cas9 in the endogenous translocated ROS1 alleles. Pharmacological assays performed in 2D and 3D cell culture revealed that spheroids are more sensitive to TKIs than cells cultured as a monolayer. This direct comparison between two culture systems could be done thanks to the implementation of normalized growth rates (NGR) to uniformly quantify drug response between 2D and 3D cell culture. Overall, this study presents the added value of using spheroids and positions lorlatinib and repotrectinib as the most effective TKIs against the studied ROS1 resistance point mutations.