#-supreme-cellcarta-differentiators-8-707{items-data:[{"text":"Fast & Scalable"},{"text":"Regulation-Compliant"},{"text":"Safe & Secure"},{"text":"AI-Ready"},{"text":"Deeper Insights"}]}#-supreme-cellcarta-faq-12-707{oxy-supreme-cellcarta-faq-question-tag:h3;items-data:[{"faq_question":"Who uses CellEngine? Has it been referenced?","faq_answer":"

CellEngine is used by academics,small- and mid-sized biotech companies,and large biopharmas around the world. CellEngine also powers the analysis for all of CellCarta's expert flow cytometry services,including exploratory studies and phase 1 through phase 3 clinical trials.

\n

A listing of some of the publications that have used CellEngine,including numerous phase 1 and phase 2 trial reports,is available on our publications page.

"},{"faq_question":"What differentiates CellEngine’s autogating?","faq_answer":"

CellEngine’s automatic gate tailoring was designed in close collaboration with our cytometrists to address numerous shortcomings of existing solutions:

\n
    \n
  1. There’s no model training step or pipeline setup service,which can take hours to weeks with other software and providers. Simply,just gate a representative set of files,then run the tool and receive results in seconds. This means the tool can even be used in smaller studies where slow or costly setup isn’t economical.
    2. \n
  2. It’s completely deterministic. No random seeds,just reproducible output every time.
    3. \n
  3. The resulting gates are just that—gates. Whereas many other tools operate as black boxes and provide no options if you disagree with the result,CellEngine’s auto-tailored gates can be viewed and adjusted as needed. If you do make adjustments,you can re-run the tool to incorporate that fine-tuning in the gating of other files.
    4. \n
  4. It works even for rare populations. Many other tools rely on density- or clustering-based methods,which can break down for rare cell types.
    5. \n
  5. It can tailor by metadata. For example,if you want the same gate positions for every timepoint and condition for each donor,just pick “tailor by:donor.”
    6. \n
\n

See a case study here.

"},{"faq_question":"Can I import my existing data into CellEngine?","faq_answer":"

If you have existing analyses done in other flow cytometry software,CellEngine can import data from:

\n\n

Contact us to learn more about options for switching from other software.

"},{"faq_question":"What AI analysis algorithms does CellEngine have?","faq_answer":"

CellEngine has dimensionality-reduction algorithms,including PCA,t-SNE and UMAP,and clustering algorithms,including FlowSOM,Phenograph and ensemble clustering of graphs (ECG).

\n

CellEngine’s implementations of these algorithms often have improved functionality and ease of use over the original publications. For example,CellEngine’s t-SNE uses PCA initialization instead of random initialization,providing more statistically rigorous and consistent results between runs;and CellEngine’s Phenograph supports the Leiden method,which improves upon the original Louvain method.

\n

We’ve also heavily optimized the algorithms for performance,cutting the runtime down to a fraction of that in most other flow cytometry software:CellEngine’s UMAP can analyze 10 million cells in about 20 minutes,CellEngine’s Leiden can analyze 10 million cells in about 15 minutes,and CellEngine’s FlowSOM can analyze 400 million cells in only a few minutes.

\n

More information on CellEngine’s algorithms is available in this documentation.

"}]}#-supreme-cellcarta-service-blocks-9-707{blocks-data:[{"image":"https://cellcarta.com/wp-content/uploads/2026/07/ce-apps-1.png","image_alt":"","title":"Immune Monitoring","description":"Get a birds-eye view of your entire trial,spanning every timepoint for every donor.","button_text":"Discover","button_url":"https://docs.cellengine.com/illustrations/pivottables/#basic-pivot-table-organized-with-metadata","button_target":"_blank"},{"image":"https://cellcarta.com/wp-content/uploads/2026/07/ce-apps-2.png","image_alt":"","title":"Compound Screens","description":"Generate dose-response curves for high-throughput,plate-based assays.","button_text":"Discover","button_url":"https://docs.cellengine.com/illustrations/doseresponse/","button_target":"_blank"},{"image":"https://cellcarta.com/wp-content/uploads/2026/07/ce-apps-3.png","image_alt":"","title":"Cytometer & Assay QC","description":"Interactive Levey-Jennings plots track performance down to underlying single-cell data.","button_text":"Discover","button_url":"https://docs.cellengine.com/illustrations/barlineboxheat/#create-control-charts-with-threshold-lines-levey-jennings-charts","button_target":"_self"}]}#-supreme-cellcarta-tab-content-4-707{oxy-supreme-cellcarta-tab-content-content-heading-tag:h3;oxy-supreme-cellcarta-tab-content-content-heading-size:default;oxy-supreme-cellcarta-tab-content-content-body-size:default;tabs-data:[{"tab_title":"Fast Algorithms","content_title":"","content_body":"

CellEngine includes a suite of dimensionality reduction and clustering algorithms,including UMAP,FlowSOM,and Phenograph. CellEngine’s optimized versions can analyze tens to hundreds of millions of cells in minutes,not hours. The results can be subsequently visualized and interrogated without leaving CellEngine.

","tab_image":"https://cellcarta.com/wp-content/uploads/2026/07/ce-tabs-2.png","image_alt":"CellEngine advanced gating workflow and percentile gating"},{"tab_title":"Easy Autogating","content_title":"","content_body":"

CellEngine's autogating tool uses machine learning (ML) to automatically tailor gate positions according to your hierarchy. CellEngine learns your placement decisions from a small set of manually gated files and seamlessly applies them to your remaining files in seconds.

\n

Unlike other flow cytometry software,CellEngine requires no training step or pipeline development,and,if needed,you can manually adjust the gates afterward.

","tab_image":"https://cellcarta.com/wp-content/uploads/2026/07/74-IMG_2514-2-scaled.jpg","image_alt":"CellEngine autogating tool interface showing gate hierarchy"},{"tab_title":"Metadata-Driven","content_title":"","content_body":"

Start by adding sample metadata,such as timepoint,donor,dosage,and treatment,using a familiar spreadsheet interface. That metadata can then be used to systematically gate your data,automatically lay out your visualizations,or filter your dataset down to a subset of interest.

\n

This automated approach reduces human error and saves time compared to manually organizing and reporting data.

","tab_image":"https://cellcarta.com/wp-content/uploads/2026/07/ce-tabs-3.png","image_alt":"CellEngine metadata-driven analysis spreadsheet interface"},{"tab_title":"AI-Ready API","content_title":"","content_body":"

Integrate CellEngine seamlessly with your LIMS,ELN,and automation pipelines to streamline data management.

\n

Our fully featured API empowers you to take analysis to the limits of your imagination. Feed your research into custom AI models or use it from within Jupyter notebooks to conduct reproducible bioinformatics analysis.

\n

Standard import/export formats,including Gating-ML,make CellEngine interoperable with the scientific ecosystem.

","tab_image":"https://cellcarta.com/wp-content/uploads/2026/07/ce-tabs-4.png","image_alt":"CellCarta bioinformatics team integrating CellEngine API with LIMS"},{"tab_title":"Hardened Security","content_title":"","content_body":"

Safety and security are integral to CellEngine. We protect your data with enterprise-grade,defense-in-depth security measures,validated by CellCarta’s company-wide ISO 27001 certification. Backed by our availability SLA,your research remains safe,private,and always available when you need it.

","tab_image":"https://cellcarta.com/wp-content/uploads/2026/07/ce-tabs-5.jpg","image_alt":"CellEngine visualization and charting capabilities dashboard"}]}