arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2503.09427cs.LGcs.AI
收藏

面向单细胞转录组学的语言增强表示学习

Language-Enhanced Representation Learning for Single-Cell Transcriptomics

University of Science and Technology of China(中国科学技术大学);Harbin Institute of Technology(哈尔滨工业大学);National University of Singapore(新加坡国立大学)

Yaorui Shi, Jiaqi Yang, Changhao Nai, Sihang Li, Junfeng Fang, Xiang Wang, Zhiyuan Liu, Yang Zhang

AI总结:

针对单细胞大语言模型仅利用转录组数据而忽略文本知识的问题,提出多模态框架scMMGPT,通过稳健细胞表示提取和两阶段预训练策略,在细胞注释、聚类及分布外泛化任务上显著超越现有基线。

摘要:

单细胞RNA测序(scRNA-seq)为细胞异质性提供了精细的洞察。近期进展利用单细胞大语言模型(scLLMs)进行有效的表示学习。这些模型仅专注于转录组数据,忽略了来自文本描述的互补生物学知识。为克服这一局限,我们提出scMMGPT,一个面向单细胞转录组学中语言增强表示学习的新型多模态框架。与现有方法不同,scMMGPT采用稳健的细胞表示提取,保留定量基因表达数据,并引入一种创新的两阶段预训练策略,将判别精度与生成灵活性相结合。大量实验表明,scMMGPT在包括细胞注释和聚类在内的关键下游任务上显著优于单模态和多模态基线,并在分布外场景中展现出优越的泛化能力。

英文摘要:

Single-cell RNA sequencing (scRNA-seq) offers detailed insights into cellular heterogeneity. Recent advancements leverage single-cell large language models (scLLMs) for effective representation learning. These models focus exclusively on transcriptomic data, neglecting complementary biological knowledge from textual descriptions. To overcome this limitation, we propose scMMGPT, a novel multimodal framework designed for language-enhanced representation learning in single-cell transcriptomics. Unlike existing methods, scMMGPT employs robust cell representation extraction, preserving quantitative gene expression data, and introduces an innovative two-stage pre-training strategy combining discriminative precision with generative flexibility. Extensive experiments demonstrate that scMMGPT significantly outperforms unimodal and multimodal baselines across key downstream tasks, including cell annotation and clustering, and exhibits superior generalization in out-of-distribution scenarios.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑