This on-demand recording is part of the Pistoia Alliance Conference: Collaborative R&D in Action, April 20-23, 2021.  For more information about related events, please visit our online calendar.

Summary

Manual analysis of flow cytometry is currently not only highly subjective and time consuming, but the complexity of datasets has made it impossible to access the full amount of information embedded within them.

To address these challenges and aid scientists using flow cytometry technology to study COVID-19, in June 2020 we launched a crowdsourced science effort called Project Discovery in collaboration with CCP, developers of Eve Online (a space-based, persistent world massive multiplayer online role-playing game). Citizen scientists have already generated an unprecedented amount of training data that will benefit the entire community interested in developing ML algorithms for FCM.

Over 263K participants have generated over 88M bivariate plots. 46M of these plots come from data associated with peer-reviewed publications focused on COVID-19.

Featured Topics

• Limitations of manual analysis and automated approaches for flow cytometry data analysis for clinical trials, patient diagnosis and biomarker discovery
• Project Discovery, a citizen science approach to generating training data for cell population identification for machine learning and to aid scientists in their analysis of COVID-19 data

Learning Objectives

At the conclusion of this session, participants should be able to:

• Recognize the challenges in the application of current analysis approaches for quick, accurate, and thorough analysis flow cytometry data for cell population reporting and discovery
• Describe the advantages of a machine learning approach for data analysis, and the challenges developing robust approaches to do so

Speaker

Conference Sponsors

Access Conference Recordings