Use this page when you need to interpret confidence, ambiguity, and edge cases in a CyteType report. For data handling and access controls, see Security and privacy. For setup, pricing, and troubleshooting questions, see the FAQ.
Where CyteType is strong
CyteType is built for cluster-level annotation with ontology mapping, marker-level evidence, and a reviewable report. It tends to help most when:
- You already have solid clustering and marker gene priors
- You provide a specific
study_context(tissue, disease, organism, experiment) - You use confidence, heterogeneity, and reviewer alternatives to decide what needs human review
Confidence and review habits
Scores above 0.8 generally indicate high reliability for cell type, subtype, or state calls. Lower scores mark ambiguous or poorly supported populations that warrant manual review.
When a call looks surprising:
- Check marker-level evidence for unexpected or missing genes
- Read decision traceability for close runner-up candidates
- Use multi-expert synthesis alternatives as hypotheses, not errors
- Ask the Cluster Copilot before escalating
💡 Tip: High heterogeneity often means the cluster should be split or cleaned before you trust a subtype call. See Confidence and heterogeneity QC.
Known limits
- Annotations are assigned at the cluster level and propagated to cells
- Repeated runs can differ in wording, reasoning, confidence, or the final label
- UMAP display sampling does not change annotation inputs
- CyteType currently expects transcriptomic input; multimodal, CITE-seq, and spatial support are limited or in development
- CyteType does not detect or remove direct identifiers or protected health information
- The standard hosted workflow requires the documented expression and observation artifacts
❗️ Important: Complete the required institutional review before uploading confidential human data. Customers using CyteType under a commercial license can request a Data Processing Agreement. Contact contact@nygen.io to discuss customer-specific provider, access, or deployment requirements before use.
Reproducibility
The annotation pipeline runs on the CyteType server. A compatible client submits the scientific inputs, while the server controls the workflow stages, evidence sequence, and active model routing. This means a client installed before a server update can use the updated server workflow when it submits a later job.
The structured workflow reduces uncontrolled variation, but it does not guarantee identical output across repeated runs. Record the job ID, client version, run date, and query.json, and validate important annotations against marker evidence and study context. query.json captures the submitted request, but it does not identify the complete server release, effective provider routing, or uploaded artifact state.
How to cite
Please cite the bioRxiv preprint: Ahuja G et al., Multi-agent AI enables evidence-based cell annotation in single-cell transcriptomics, bioRxiv 2025. doi:10.1101/2025.11.06.686964
Learn more
