Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Multi-agent AI enables evidence-based cell annotation in single-cell transcriptomics

Ahuja, Gautam ; Antill, Alex LU orcid ; Su, Yi ; Dall'Olio, Giovanni Marco ; Basnayake, Sukhitha ; Karlsson, Göran LU and Dhapola, Parashar LU (2025)
Abstract
Cell type annotation remains a critical bottleneck, with current methods often inaccurate and requiring extensive manual validation, particularly in disease contexts. While large language models (LLMs) show promise, they can be unreliable due to hallucinations. We developed CyteType, a multi-agent framework that generates competing hypotheses grounded in full expression data and study context, validates against external databases, and iteratively self-evaluates. Comprehensive benchmarking demonstrates that CyteType substantially outperforms reference-based and LLM-based methods, with self-generated confidence scores reliably identifying trustworthy annotations. CyteType transforms cell type annotation from label assignment into... (More)
Cell type annotation remains a critical bottleneck, with current methods often inaccurate and requiring extensive manual validation, particularly in disease contexts. While large language models (LLMs) show promise, they can be unreliable due to hallucinations. We developed CyteType, a multi-agent framework that generates competing hypotheses grounded in full expression data and study context, validates against external databases, and iteratively self-evaluates. Comprehensive benchmarking demonstrates that CyteType substantially outperforms reference-based and LLM-based methods, with self-generated confidence scores reliably identifying trustworthy annotations. CyteType transforms cell type annotation from label assignment into evidence-grounded biological discovery. (Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; and
organization
publishing date
type
Working paper/Preprint
publication status
published
subject
publisher
bioRxiv
DOI
10.1101/2025.11.06.686964
language
English
LU publication?
yes
id
4963b8c7-9cf4-4197-a113-a4bf76806e1b
date added to LUP
2025-11-10 09:14:39
date last changed
2025-11-10 13:39:08
@misc{4963b8c7-9cf4-4197-a113-a4bf76806e1b,
  abstract     = {{Cell type annotation remains a critical bottleneck, with current methods often inaccurate and requiring extensive manual validation, particularly in disease contexts. While large language models (LLMs) show promise, they can be unreliable due to hallucinations. We developed CyteType, a multi-agent framework that generates competing hypotheses grounded in full expression data and study context, validates against external databases, and iteratively self-evaluates. Comprehensive benchmarking demonstrates that CyteType substantially outperforms reference-based and LLM-based methods, with self-generated confidence scores reliably identifying trustworthy annotations. CyteType transforms cell type annotation from label assignment into evidence-grounded biological discovery.}},
  author       = {{Ahuja, Gautam and Antill, Alex and Su, Yi and Dall'Olio, Giovanni Marco and Basnayake, Sukhitha and Karlsson, Göran and Dhapola, Parashar}},
  language     = {{eng}},
  month        = {{11}},
  note         = {{Preprint}},
  publisher    = {{bioRxiv}},
  title        = {{Multi-agent AI enables evidence-based cell annotation in single-cell transcriptomics}},
  url          = {{http://dx.doi.org/10.1101/2025.11.06.686964}},
  doi          = {{10.1101/2025.11.06.686964}},
  year         = {{2025}},
}