Dataset Information

Establishment of interpretable cytotoxicity prediction models using machine learning analysis of transcriptome features

ABSTRACT: Cytotoxicity, usually represented by cell viability, is a crucial parameter for evaluating drug safety in vitro. Accurate prediction of cell viability/cytotoxicity could accelerate drug development in the early stage. In this study, by using machine learning algorithms on cellular transcriptome and cell viability data, highly accurate prediction models of 50% and 80% cell viability were developed with AUROCs of 0.90 and 0.84, respectively, which also showed good performance on diverse cell lines. With respect to the characterization of Feature Genes employed, the models can be interpreted, and the mechanisms of bioactive compounds with narrow therapeutic indices can also be analyzed. In summary, the models established in this study have the capacity to predict cytotoxicity highly accurately across cell lines and can be used for high safety substances screening efficiently. Moreover, the Cytotoxicity Signature genes from interpretability analysis is valuable for studying the mechanisms of action, especially for substances with narrow therapeutic indices.

ORGANISM(S): Homo sapiens

PROVIDER: GSE252529 | GEO | 2025/05/28

REPOSITORIES: GEO

ACCESS DATA

Dataset's files

Source:

			Action	DRS
		Other

Items per page:

1 - 1 of 1

Similar Datasets

Project description:Introduction: The flavonoid myricetin has been shown to induce cell cycle arrest and mitochondrial-dependent apoptosis in preclinical cancer models. We hypothesised that myricetin-derived flavonoids with redox properties and improved physicochemical attributes that enhance cell uptake and mitochondrial targeting might have increased potential as antitumour agents, since mitochondria are the main site of production of reactive oxygen species (ROS) and redox status is known to regulate the development and advancement of certain cancers. In this study we assessed a small library of novel flavonoids, then focussed on the lead compound, second-generation analogue OncamexTM, its mechanism of action and structure-activity relationships as an anti-proliferative agent. Methods: With this aim, we studied the effect of OncamexTM in a panel of 7 breast cancer cell lines using proliferation, cytotoxicity and apoptosis assays. The redox properties and mitochondrial delivery of the drug were studied using cyclic voltammetry and fluorescence microscopy, respectively. The mechanism of action was further studied using western blotting, gene expression analysis and immunohistochemistry (IHC) of treated xenograft tissue from in vivo mice models. Results: Sulforhodamine B (SRB) proliferation assays demonstrated strong, anti-proliferative properties of OncamexTM, with IC50 values in the low micromolar range. Treatment for 8 h exerted concentration-dependent reduction in cell viability and induction of cytotoxicity and apoptosis, with increased caspase activation. Microarray analysis suggested that OncamexTM regulates changes in cell cycle and apoptosis at gene expression level. Fluorescence microscopy was used to investigate mitochondrial targeting and ROS regulation in treated cells. OncamexTM was found to induce production of superoxide at concentrations which exerted anti-proliferative effects. Initial in vivo studies in mice implanted with a MDA-MB-231 breast cancer xenograft showed that OncamexTM inhibited tumour growth, reducing tissue viability and Ki-67 proliferation, with no overall systemic toxicity. Conclusions: OncamexTM is a novel flavonoid capable of specific delivery to the mitochondria and induction of ROS production. We have shown its antitumor activity in preclinical models of breast cancer, both in vitro and in initial in vivo models, where tumour growth was arrested without inducing toxicity, support the potential of this novel drug for its continued development as an anticancer agent. Total RNA was obtained from 5 breast cancer cell lines subjected to 6 hours of 10µM OncamexTM and matched untreated controls (1% DMSO)

Dataset Information

Establishment of interpretable cytotoxicity prediction models using machine learning analysis of transcriptome features

Dataset's files

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets