Skip to article frontmatterSkip to article content
Site not loading correctly?

This may be due to an incorrect BASE_URL configuration. See the MyST Documentation for reference.

Cite CyteOnto

CyteOnto is part of CyteType. If you use CyteOnto in your work, please cite the CyteType preprint:

Ahuja G, Antill A, Su Y, Dall’Olio GM, Basnayake S, Karlsson G, Dhapola P. Multi-agent AI enables evidence-based cell annotation in single-cell transcriptomics. bioRxiv 2025. doi:Ahuja et al. (2025)

BibTeX:

@article{cytetype2025,
  title   = {Multi-agent {AI} enables evidence-based cell annotation in single-cell transcriptomics},
  author  = {Ahuja, Gautam and Antill, Alex and Su, Yi and Dall'Olio, Giovanni Marco and Basnayake, Sukhitha and Karlsson, G{\"o}ran and Dhapola, Parashar},
  journal = {bioRxiv},
  year    = {2025},
  doi     = {10.1101/2025.11.06.686964},
  url     = {https://www.biorxiv.org/content/10.1101/2025.11.06.686964v1}
}

Record what you ran

The scores depend on the models and the options of the comparison, and the LLM’s descriptions can differ between runs. Record these items for each comparison you report:

ItemWhere to find it
CyteOnto versioncyteonto.__version__, and the commit you installed
Model pairThe provider and model of LlmConfig and EmbdConfig, or of the request to the hosted API
Fallback usecyto.model_pair_usage.to_status_dict(), or the modelPairUsage of the job’s status. When a tier is not primary, it names the fallback model; in Python, the fallback LLM only if you passed fallback_llm
Optionsmetric, metric_params, min_match_similarity and compound_scoring, or the request body without its API keys
Run IDThe run_id column of the results
ResultsThe result DataFrame or file, with the label pairs, the matched terms and the scores

Keep the files behind the scores: the run caches in user_dir, which hold the descriptions and embeddings of your labels, and the ontology files of the model pair in data_dir, against which the labels were matched and scored. See Caching and runs.

License

The cyteonto package is released under the MIT license. The Cell Ontology is published by the OBO Foundry under its own license.

References
  1. Ahuja, G., Antill, A., Su, Y., Dall’Olio, G. M., Basnayake, S., Karlsson, G., & Dhapola, P. (2025). Multi-agent AI enables evidence-based cell annotation in single-cell transcriptomics. 10.1101/2025.11.06.686964
Support
Troubleshooting