3.6.4 FlowDx Abstract

Back to Phase II Grant Documents

Project Summary:
Flow cytometry is used to rapidly gather large quantities of data on cell type and function. The manual process of classifying hundreds of thousands of cells forms a bottleneck in diagnostics, high-throughput screening, clinical trials, and large-scale research experiments. The process currently requires a trained expert to identify populations on a digital graph of the data by manually drawing regions. As the complexity of the data increases, this gating task becomes more lengthy and laborious. Minimizing or eliminating human processing is essential to increasing both throughput and consistency. In clinical tests and diagnostic environments, automated gating would eliminate a complex set of human instructions and decisions in the Standard Operating Procedure (SOP), reducing error and speeding results to the doctor. In many cases, the software will be able to recognize the need for additional tests before the doctor has an opportunity to look at the first report. Currently no software is available to perform complex multi-parameter analyses in an automated and rigorously validated manner. FlowDx will fill an important gap in the evolution of the technology and facilitate ever larger phenotypic studies and for the translation of this research process to a clinical environment.

Specific Aims

1) Fully define the experimental protocol, whereby a researcher can compare two or more classifications of identical data sets to study the differences, biases and effectiveness of human and algorithmic classifiers.
Milestone: An abstracted workflow document beginning with a client's assay and finishing with automated analysis.

2) Describe and evaluate metrics that compare classification algorithms.
Milestone: Database utilities that apply five comparison metrics gating files in the FlowDx database and records the results.

3) Conduct analytical experiments on our identified use cases, illustrating the potential of this technique to affect clinical analysis.
Milestone: Completed matrix of results showing which algorithms and metrics perform best for each use case.

4) Iteratively implement the tools to automate these experiments, improve the experimental capabilities, and collaborate in new use cases.
Milestone: Operational implementations of the database, repository, and utilities. These aims will be satisfied while maintaining quantitative standards of software quality, establishing measurements in system uptime, throughput and robustness to set the baseline for subsequent iterations.