近日，美国加州大学教授Zev J. Gartner团队的研究认为通过CONCORD揭示单细胞数据集的连贯细胞状态景观。相关论文于2026年1月5日发表于国际顶尖学术期刊《自然—生物技术》杂志上。

在这里，课题组人员提出了CONCORD，一个统一的框架，同时在一个单一的自我监督模型中解决这些挑战。在其核心，CONCORD实现了一种概率采样策略，通过数据集感知采样纠正批处理效应，并通过硬负采样提高生物分辨率。仅使用具有单个隐藏层和对比学习的极简神经网络，CONCORD在不依赖深度架构、辅助损失或外部监督的情况下超越了最先进的性能。它无缝地集成了批次、技术甚至物种之间的数据，以生成高分辨率的细胞图谱。由此产生的潜在表征被去噪并具有生物学意义，捕获基因共表达程序，揭示详细的谱系轨迹，并保留局部几何关系和全局拓扑结构。该课题组展示了CONCORD在不同数据集上的广泛适用性，将其建立为一个通用框架，用于学习统一的、高保真的细胞身份和动态表示。

据悉，从单细胞数据中揭示潜在的细胞状态景观需要克服批量集成，去噪和降维的关键障碍。

附：英文原文

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

Author: Zhu, Qin, Jiang, Zuzhi, Zuckerman, Binyamin, Weinberger, Leor, Thomson, Matt, Gartner, Zev J.

Issue&Volume: 2026-01-05

Abstract: 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.

DOI: 10.1038/s41587-025-02950-z

Source: https://www.nature.com/articles/s41587-025-02950-z