scDFM:用于鲁棒单细胞扰动预测的分布流匹配模型
scDFM: Distributional Flow Matching Model for Robust Single-Cell Perturbation Prediction
AI总结:
scDFM通过分布级生成建模提升单细胞扰动预测的鲁棒性,结合流匹配与PAD-Transformer架构,在多个基准测试中实现更优性能。
摘要:
系统生物学和药物发现的核心目标之一是预测细胞对扰动的转录响应。这项任务具有挑战性,因为单细胞测量具有噪声性和稀疏性,且扰动通常引起群体水平的变化,而非单个细胞的变化。现有深度学习方法通常假设细胞层面的对应关系,限制了其捕捉此类全局效应的能力。我们提出了scDFM,一种基于条件流匹配的生成框架,该框架基于控制状态建模扰动细胞的完整分布。通过引入最大均值差(MMD)目标,我们的方法在细胞层面之外对扰动和控制群体进行对齐。为进一步提高对稀疏性和噪声的鲁棒性,我们引入了Perturbation-Aware Differential Transformer(PAD-Transformer)作为骨干架构,该架构利用基因相互作用图和差异注意力来捕捉特定上下文的表达变化。在多个遗传和药物扰动基准测试中,scDFM在多个遗传和药物扰动基准测试中持续优于先前方法,展示了在未见过和组合设置中的强大泛化能力。在组合设置中,它相对于最强基线减少了19.6%的均方误差。这些结果突显了分布级生成建模在鲁棒的计算机模拟扰动预测中的重要性。代码可在https://github.com/AI4Science-WestlakeU/scDFM上获得。
英文摘要:
A central goal in systems biology and drug discovery is to predict the transcriptional response of cells to perturbations. This task is challenging due to the noisy and sparse nature of single-cell measurements, as well as the fact that perturbations often induce population-level shifts rather than changes in individual cells. Existing deep learning methods typically assume cell-level correspondences, limiting their ability to capture such global effects. We present scDFM, a generative framework based on conditional flow matching that models the full distribution of perturbed cells conditioned on control states. By incorporating a maximum mean discrepancy (MMD) objective, our method aligns perturbed and control populations beyond cell-level correspondences. To further improve robustness to sparsity and noise, we introduce the Perturbation-Aware Differential Transformer (PAD-Transformer), a backbone architecture that leverages gene interaction graphs and differential attention to capture context-specific expression changes. Across multiple genetic and drug perturbation benchmarks, scDFM consistently outperforms prior methods, demonstrating strong generalization in both unseen and combinatorial settings. In the combinatorial setting, it reduces mean squared error by 19.6% relative to the strongest baseline. These results highlight the importance of distribution-level generative modeling for robust in silico perturbation prediction. The code is available at https://github.com/AI4Science-WestlakeU/scDFM
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。