Scholarlink

<p>Single-cell RNA sequencing has revolutionized cellular heterogeneity research, but analyzing the abundance of unannotated public datasets remains challenging. We present scExtract, a framework leveraging large language models to automate scRNA-seq data analysis from preprocessing to annotation and integration. scExtract extracts information from research articles to guide data processing, outperforming existing reference transfer methods in benchmarks. We introduce scanorama-prior and cellhint-prior, which incorporate prior annotation information for improved batch correction while preserving biological diversities. We demonstrate scExtract’s utility by integrating 14 datasets to create a comprehensive human skin atlas of 440,000 cells. </p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

scExtract: leveraging large language models for fully automated single-cell RNA-seq data annotation and prior-informed multi-dataset integration

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年6月19日

查看全文
  • Yuxuan Wu,
  • Fuchou Tang

摘要

Single-cell RNA sequencing has revolutionized cellular heterogeneity research, but analyzing the abundance of unannotated public datasets remains challenging. We present scExtract, a framework leveraging large language models to automate scRNA-seq data analysis from preprocessing to annotation and integration. scExtract extracts information from research articles to guide data processing, outperforming existing reference transfer methods in benchmarks. We introduce scanorama-prior and cellhint-prior, which incorporate prior annotation information for improved batch correction while preserving biological diversities. We demonstrate scExtract’s utility by integrating 14 datasets to create a comprehensive human skin atlas of 440,000 cells.