Scholarlink

<p>Revealing the underlying cell-state landscape from single-cell data requires overcoming the critical obstacles of batch integration, denoising and dimensionality reduction. Here we present CONCORD, a unified framework that simultaneously addresses these challenges within a single self-supervised model. At its core, CONCORD implements a probabilistic sampling strategy that corrects batch effects through dataset-aware sampling and enhances biological resolution through hard-negative sampling. Using only a minimalist neural network with a single hidden layer and contrastive learning, CONCORD surpasses state-of-the-art performance without relying on deep architectures, auxiliary losses or external supervision. It seamlessly integrates data across batches, technologies and even species to generate high-resolution cell atlases. The resulting latent representations are denoised and biologically meaningful, capturing gene coexpression programs, revealing detailed lineage trajectories and preserving both local geometric relationships and global topological structures. We demonstrate CONCORD’s broad applicability across diverse datasets, establishing it as a general-purpose framework for learning unified, high-fidelity representations of cellular identity and dynamics.</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

Revealing a coherent cell-state landscape across single-cell datasets with CONCORD

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月5日

查看全文
  • Qin Zhu,
  • Zuzhi Jiang,
  • Binyamin Zuckerman,
  • Leor Weinberger,
  • Matt Thomson,
  • Zev J. Gartner

摘要

Revealing the underlying cell-state landscape from single-cell data requires overcoming the critical obstacles of batch integration, denoising and dimensionality reduction. Here we present CONCORD, a unified framework that simultaneously addresses these challenges within a single self-supervised model. At its core, CONCORD implements a probabilistic sampling strategy that corrects batch effects through dataset-aware sampling and enhances biological resolution through hard-negative sampling. Using only a minimalist neural network with a single hidden layer and contrastive learning, CONCORD surpasses state-of-the-art performance without relying on deep architectures, auxiliary losses or external supervision. It seamlessly integrates data across batches, technologies and even species to generate high-resolution cell atlases. The resulting latent representations are denoised and biologically meaningful, capturing gene coexpression programs, revealing detailed lineage trajectories and preserving both local geometric relationships and global topological structures. We demonstrate CONCORD’s broad applicability across diverse datasets, establishing it as a general-purpose framework for learning unified, high-fidelity representations of cellular identity and dynamics.