RAGCell：检索增强生成作为通用单细胞分析的监督信号
RAGCell: Retrieval-Augmented Generation as Supervision for Versatile Single-cell Analysis
- Tsinghua University（清华大学）
- The Chinese University of Hong Kong（香港中文大学）
- The Ohio State University（俄亥俄州立大学）
- Nanyang Technological University（南洋理工大学）
- Peking University（北京大学）
- Tencent Jarvis Lab（腾讯 Jarvis 实验室）
- Westlake University（西湖大学）
- Yale University（耶鲁大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
RAGCell利用LLM构建细胞级和特征级知识库作为监督信号，训练细胞模型并对齐文本与细胞表征，以低成本实现高性能的通用单细胞分析。
AI中文摘要：
单细胞基础模型（scFMs）通过为通用单细胞分析提供可泛化、任务无关的表征，正在变革计算生物学。尽管它们在促进下游任务快速部署方面取得了进展，但现成的scFMs仍存在一些被忽视的问题：（I）（预训练成本。）基于预训练的scFMs需要对海量细胞进行预训练，导致在应用中资源消耗巨大。（II）（异质性差距。）基于大型语言模型（LLM）的scFMs忽略了LLM文本空间与原始细胞空间之间巨大的异质性差距，导致在面对下游任务时能力不足。为此，我们引入了RAGCell，一个通用的单细胞分析框架，在成本效益和高性能方面实现了双赢。RAGCell的成功在于两个关键方面：利用LLMs构建细胞级和特征级知识数据库，这些数据库作为训练细胞模型的监督信号，显著降低了训练成本（优于基于预训练的scFMs）。将细胞表征与来自双层知识数据库的文本嵌入对齐，实现从文本空间到细胞空间的知识迁移，有效缓解了异质性差距（优于基于LLM的scFMs）。通过在六个下游单细胞分析任务上的大量实验，我们证明RAGCell在实现卓越性能的同时，其运行成本不到基于预训练的scFMs的约1/10。
英文摘要：
Single-cell foundation models (scFMs) are transforming computational biology by enabling generalizable, task-agnostic representations for versatile single-cell analysis. Despite their progress in facilitating rapid deployment for downstream tasks, off-the-shelf scFMs still have some overlooked concerns: (I) (Pretraining Cost.) Pretrain-based scFMs necessitate pretraining on a vast volume of cells, rendering it draining resources in applications. (II) (Heterogeneous Gap.) Large Language Models (LLM)-based scFMs ignore the tremendous heterogeneous gap between LLM textual and raw cellular spaces, leading to insufficient capability when facing downstream tasks. To this end, we introduce RAGCell, a versatile single-cell analysis framework that achieves a double-win in both cost-effectiveness and high performance. The success of RAGCell lies in two key aspects: Leveraging LLMs to construct cell-level and feature-level knowledge databases, which serve as supervision signals for training the cell model and significantly reduce the training cost ($>$pretrain-based scFMs). Aligning cell representations with text embeddings from the bi-level knowledge databases, enabling knowledge transfer from textual spaces to cellular spaces and effectively mitigating the heterogeneous gap ($>$LLM-based scFMs). Through extensive experiments on six downstream single-cell analysis tasks, we demonstrate that RAGCell achieves outstanding performance compared to state-of-the-art scFMs while operating at less than $\sim$1/10 the cost of pretrain-based scFMs.
