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

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.