Abstract 5115: Enhancing data quality for clinical studies of investigational cancer immunotherapy drug candidates by a new data analytics tool

Cancer immunotherapy is rapidly becoming a treatment of choice in fighting deadly cancers, especially late stage or metastatic cancers. Humanized antibodies such as alemtuzumab and nivolumab alter the dynamics of regulatory T cells, cytotoxic T cells, B cells, NK cells and dendritic cells. All of these cells can be analyzed for a wide array of intracellular and surface biomarkers with flow cytometric technology. The biggest challenges with the use of flow cytometry in the clinical trial setting are the assessment of the amount of data produced and the lack of replicable standards for each set of biomarkers as it relates to the particular characteristics and functions of leukocytes. Previously, we reported a new method to improve data quality in clinical research using big data analytics and data visualization (AACR 2018 Bioinformatics and System Biology, Abstract #2605). By statistical analysis and pattern recognition, we can simultaneously monitor unlimited data points related to numerous biomarkers. Here we describe widening the application of the new analytic method for use in the field of flow cytometry and cancer immunotherapy. A flow cytometer measures multiple fluorescence signals at once, and antibodies directed against different cellular proteins can be conjugated with a variety of fluorochromes. When an antibody, such as anti-PD-L1 Alexa Fluor 647, has a quality issue, caused either by the manufacturing process or a technical error within the clinical laboratory, an error signal can be detected by running data analytic. Through consistently monitoring each reagent used, we are working toward improving the reliability of the process itself and the quality of data. Human-machine interaction and automation are some of the most profound changes in the clinical research setting. The entire process relies heavily on the high volume of sample processing and data generated by advanced machine systems, and intermittent human intervention between each cycle of data collection, analysis, reporting and finalization. Every step in flow cytometric analyses, such as antibody quality and data validation, as well as improvement in staff training and administration of proficiency testing may be improved by this new data analytic tool. In the near future clinical research combining with artificial intelligence and machine learning will be more efficient. This will substantially reduce the time, cost and failure rate of research and development in creating new drugs. Citation Format: Chengsen Xue, Joanne Cuomo, Melissa L. Baptiste, Kai Chen, Danielle L. Kurkowski, Thomas W. Mc Closkey. Enhancing data quality for clinical studies of investigational cancer immunotherapy drug candidates by a new data analytics tool [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2019; 2019 Mar 29-Apr 3; Atlanta, GA. Philadelphia (PA): AACR; Cancer Res 2019;79(13 Suppl):Abstract nr 5115.