用基因块注意力建模多条件单细胞数据，提升生成质量与泛化能力
SAVE: A Generalizable Framework for Multi-Condition Single-Cell Generation with Gene Block Attention
- 将基因分组为功能块，捕捉基因模块间的高阶依赖关系
- 在低资源和未见组合条件下，生成质量和泛化能力均优于现有方法
- 适合需要虚拟细胞合成与生物机制解析的研究者使用
跨多种生物与技术条件的单细胞基因表达建模对于表征细胞状态和模拟未知情景至关重要。现有方法通常将基因视为独立标记，忽视其高级生物学关系，导致性能不佳。我们提出SAVE，一种基于条件Transformer的统一生成框架，用于多条件单细胞建模。SAVE通过将语义相关的基因分组为基因块，实现粗粒度表示，捕捉基因模块间的高阶依赖。结合流匹配机制与条件掩码策略，进一步增强灵活模拟能力，并支持对未见条件组合的泛化。我们在多个基准上评估SAVE，包括条件生成、批次效应校正和扰动预测。结果表明，SAVE在生成保真度和外推泛化方面持续优于当前最优方法，尤其在低资源或组合式留出设置下表现突出。总体而言，SAVE为复杂单细胞数据建模提供了一种可扩展且通用的解决方案，广泛适用于虚拟细胞合成与生物学解释。代码已公开于https://github.com/fdu-wangfeilab/sc-save。
原文摘要 · Abstract (English)
Modeling single-cell gene expression across diverse biological and technical conditions is crucial for characterizing cellular states and simulating unseen scenarios. Existing methods often treat genes as independent tokens, overlooking their high-level biological relationships and leading to poor performance. We introduce SAVE, a unified generative framework based on conditional Transformers for multi-condition single-cell modeling. SAVE leverages a coarse-grained representation by grouping semantically related genes into blocks, capturing higher-order dependencies among gene modules. A Flow Matching mechanism and condition-masking strategy further enhance flexible simulation and enable generalization to unseen condition combinations. We evaluate SAVE on a range of benchmarks, including conditional generation, batch effect correction, and perturbation prediction. SAVE consistently outperforms state-of-the-art methods in generation fidelity and extrapolative generalization, especially in low-resource or combinatorially held-out settings. Overall, SAVE offers a scalable and generalizable solution for modeling complex single-cell data, with broad utility in virtual cell synthesis and biological interpretation. Our code is publicly available at https://github.com/fdu-wangfeilab/sc-save
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。