Abstract
In vitro pharmacology studies using cultures of biological models, such as cancer cell lines or lately organoids in the oncology field, are commonly used to assess drug efficacy. The baseline genetic or epigenetic features, including those reflective of the original patient tissue, can be characterized by genomic profiling of the respective models, and correlated to the efficacy observed during pharmacology studies to discover potential predictive biomarkers. On the other hand, the changes of these features following specific treatment (pharmacodynamic changes) can be used to explore the drug mechanism of action (MOA) or potential drug targets. Discovery and/or validation of relevant biomarkers using these in vitro preclinical pharmacology studies are obviously critical in drug discovery/development. Although important, the biomarker discovery and validation process can be complex and labor intensive, and currently there are few robust tools that can be used readily to take on the task of automated computation discovery. To this end, we have established an automated biomarker discovery platform for in vitro preclinical pharmacology studies by implementing a variety of machine learning algorithms and statistical methods, combining them with Shiny package in R, an integrated suite of software facilities for data manipulation, calculation and graphical display. This platform is user-friendly and efficiently manages raw data uploads, data conversions, drug efficacy overview, biomarker discovery analysis as well as data report generation. In conclusion, our platform provides a new solution for precision biomarker discovery in preclinical, especially immune-oncology studies.
Citation Format: Jia Xue, Henry QX Li, Sheng Guo. An automated biomarker discovery platform based on in vitro pharmacology raw data [abstract]. In: Proceedings of the AACR-NCI-EORTC International Conference on Molecular Targets and Cancer Therapeutics; 2019 Oct 26-30; Boston, MA. Philadelphia (PA): AACR; Mol Cancer Ther 2019;18(12 Suppl):Abstract nr A026. doi:10.1158/1535-7163.TARG-19-A026
