Objectively Evaluating the Reliability of Cell Type Annotation Using LLM-Based Strategies

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ye, Wenjin, Ma, Yuanchen, Xiang, Junkai, Liang, Hongjie, Wang, Tao, Xiang, Qiuling, Xiang, Andy Peng, Song, Wu, Li, Weiqiang, Huang, Weijun
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912042467721216
author Ye, Wenjin
Ma, Yuanchen
Xiang, Junkai
Liang, Hongjie
Wang, Tao
Xiang, Qiuling
Xiang, Andy Peng
Song, Wu
Li, Weiqiang
Huang, Weijun
author_facet Ye, Wenjin
Ma, Yuanchen
Xiang, Junkai
Liang, Hongjie
Wang, Tao
Xiang, Qiuling
Xiang, Andy Peng
Song, Wu
Li, Weiqiang
Huang, Weijun
contents Reliability in cell type annotation is challenging in single-cell RNA-sequencing data analysis because both expert-driven and automated methods can be biased or constrained by their training data, especially for novel or rare cell types. Although large language models (LLMs) are useful, our evaluation found that only a few matched expert annotations due to biased data sources and inflexible training inputs. To overcome these limitations, we developed the LICT (Large language model-based Identifier for Cell Types) software package using a multi-model fusion and "talk-to-machine" strategy. Tested across various single-cell RNA sequencing datasets, our approach significantly improved annotation reliability, especially in datasets with low cellular heterogeneity. Notably, we established objective criteria to assess annotation reliability using the "talk-to-machine" approach, which addresses discrepancies between our annotations and expert ones, enabling reliable evaluation even without reference data. This strategy enhances annotation credibility and sets the stage for advancing future LLM-based cell type annotation methods.
format Preprint
id arxiv_https___arxiv_org_abs_2409_15678
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Objectively Evaluating the Reliability of Cell Type Annotation Using LLM-Based Strategies
Ye, Wenjin
Ma, Yuanchen
Xiang, Junkai
Liang, Hongjie
Wang, Tao
Xiang, Qiuling
Xiang, Andy Peng
Song, Wu
Li, Weiqiang
Huang, Weijun
Quantitative Methods
Genomics
Reliability in cell type annotation is challenging in single-cell RNA-sequencing data analysis because both expert-driven and automated methods can be biased or constrained by their training data, especially for novel or rare cell types. Although large language models (LLMs) are useful, our evaluation found that only a few matched expert annotations due to biased data sources and inflexible training inputs. To overcome these limitations, we developed the LICT (Large language model-based Identifier for Cell Types) software package using a multi-model fusion and "talk-to-machine" strategy. Tested across various single-cell RNA sequencing datasets, our approach significantly improved annotation reliability, especially in datasets with low cellular heterogeneity. Notably, we established objective criteria to assess annotation reliability using the "talk-to-machine" approach, which addresses discrepancies between our annotations and expert ones, enabling reliable evaluation even without reference data. This strategy enhances annotation credibility and sets the stage for advancing future LLM-based cell type annotation methods.
title Objectively Evaluating the Reliability of Cell Type Annotation Using LLM-Based Strategies
topic Quantitative Methods
Genomics
url https://arxiv.org/abs/2409.15678