Scholarlink

<p>Biological studies rely on embeddings of single-cell profiles but assessing the quality of these embeddings is challenging. Here we show that current evaluation metrics are incomplete by training a three-layer perceptron, Islander. Islander outperforms all leading embedding methods on a diverse set of cell atlases but it distorts biological structures, limiting its use for biological discovery. We then present a new metric, scGraph, to help flag such distortions.</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

Limitations of cell embedding metrics assessed using drifting islands

  • 期刊论文

  • 发表日期：

    2025年6月11日

查看全文
  • Hanchen Wang,
  • Jure Leskovec,
  • Aviv Regev

摘要

Biological studies rely on embeddings of single-cell profiles but assessing the quality of these embeddings is challenging. Here we show that current evaluation metrics are incomplete by training a three-layer perceptron, Islander. Islander outperforms all leading embedding methods on a diverse set of cell atlases but it distorts biological structures, limiting its use for biological discovery. We then present a new metric, scGraph, to help flag such distortions.