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

TL;DR

This paper introduces LICT, a novel LLM-based software that improves cell type annotation reliability in single-cell RNA-sequencing by using multi-model fusion and an objective 'talk-to-machine' evaluation strategy.

Contribution

The paper presents LICT, a new multi-model fusion approach with a 'talk-to-machine' strategy for objective reliability assessment in cell type annotation.

Findings

Significantly improved annotation reliability across datasets.

Established objective criteria for reliability assessment.

Enhanced annotation credibility without reference data.

Abstract

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.