Aigenpulse’s Data Analysis Suite Automates Flow Cytometry

Published on: 

The company’s new CytoML Experiment Suite fully automates each stage of the flow cytometry data lifecycle, allowing for clearer data visualization and analysis.

A new data analysis suite by Aigenpulse, a life science and data technology innovator company, offers an automated, end-to-end, machine learning solution aimed specifically at streamlining and automating cytometry analysis at scale and replacing manual gating processes. The new technology, CytoML Experiment Suite, allows users to benefit from a single point-of-truth about all cytometry data across any organization.

CytoML enables the automation of every stage of the flow cytometry data lifecycle—from data acquisition to insight generation— and it can help increase throughput of data processing and analytics by as much as 600%. At the same time, the data analysis suite increases the accuracy, reproducibility, and quality of flow cytometry data.

CytoML also makes it possible to leverage machine learning to scale-up and automate gating, using both unsupervised and guided population identification. This allows it to clearly visualize populations and have full control over gating parameters in the Decision Space, according to Aigenpulse in a Sept. 9, 2020 press release. Further, the suite retains all algorithm parameters, which offers fully transparent and reproducible cytometry gating.

The data analysis suite was developed from the ground-up to be a validated computerized system to comply with good automatic manufacturing practices issue 5. For instance, every analysis, dataset, parameter, and report generated in CytoML is retrievable and reproducible with timestamps, user information, parameters used, and data input and output.

The technology, moreover, makes it possible for users to parse, integrate, and standardize all popular flow cytometry data formats into the system using one seamless process as well as importing data with an easy-to-use web interface, or via command line or application programing interface. Quality assurance reporting is instantly generated during integration, which provides full visibility of data quality.


CytoML also provides fully federated and audited logging for processing and integration parameters, which enables re-use and enhances efficiency. Built in plotting tools allows for users to easily derive insights by exploring data in different planes, and, because of the reliable gating, events can be sorted and annotated into populations that are presented to the user in a hierarchy tree. The latter empowers the user to select sub-populations for analysis and save/reload collections that can be shared with colleagues. Users can thus calculate and visualize selected sub-populations-to-parent ratios, enabling them to quickly focus on identifying significant findings from their experiments.

“The clear advantages of the high throughput, multiparameter functionality of flow cytometry are hampered by the immense output of highly complex data. Significant expertise is required to interpret this data correctly, and there is a lack of standardization in assay and instrument set up. Aigenpulse’s CytoML Experiment Suite offers an automated end-to-end process for large numbers of raw files by leveraging machine learning to empower cytometry data processing and enables users to integrate population counts identified by manual gating to increase the value of data and allow for cross-project analysis,” said Steve Yemm, chief commercial officer, Aigenpulse, in the press release. “This provides significant savings in terms of both time and money and will tackle the all-too-common bottlenecks in the research process, making it possible to maximize the true value of flow cytometry data in pharma R&D.”

Source: Aigenpulse