用稀疏性偏向的无分类器引导改进scDiffusion
Improving scDiffusion with Sparsity-Biased Classifier-Free Guidance
浏览论文内容
中文总结 AI 辅助
本研究针对scRNA-seq生成中现有CFG引导效果受限的问题，提出SB-CFG策略，通过引入刻意信息不足的稀疏参考优化引导，在五个公开数据集上实现了标记基因表达等指标的一致提升。
中文摘要 AI 辅助
单细胞RNA测序（scRNA-seq）是现代细胞生物学的重要工具，生成准确的合成scRNA-seq数据愈发重要。尽管扩散模型在条件scRNA-seq生成中已取得良好效果，但现有引导策略（包括分类器引导和无分类器引导（CFG））依赖训练以近似真实边际分布的无条件分支，可能保留大量基因特异性结构并限制引导效果。受近期研究表明扩散模型可通过刻意退化的参考有效引导的启发，我们提出用于scRNA-seq生成的稀疏性偏向无分类器引导（SB-CFG）策略。SB-CFG不近似假设的“中性”边际分布，而是为无条件分支引入刻意信息不足的稀疏参考，该参考去除基因身份仅保留粗略稀疏性统计，这种“不良”参考放大了条件与无条件预测间的对比，在采样期间带来更强更有效的引导。我们在五个公开scRNA-seq数据集上评估SB-CFG作为无需训练的采样修改，实验结果显示其在标记基因表达保真度、细胞类型一致性和稀疏性保留方面均优于基于标准CFG的采样，表明SB-CFG能更好捕捉生物学上有意义的基因表达模式。
英文摘要
Single-cell RNA sequencing (scRNA-seq) has become an essential tool in modern cellular biology, and generating accurate synthetic scRNA-seq data is becoming increasingly important. Although diffusion models have achieved promising results in conditional scRNA-seq generation, existing guidance strategies, including classifier guidance and classifier-free guidance (CFG), rely on an unconditional branch trained to approximate the true marginal distribution, which may retain substantial gene-specific structure and limit guidance effectiveness. Inspired by recent work showing that diffusion models can be effectively guided using intentionally degraded references, we propose a sparsity-biased classifier-free guidance (SB-CFG) strategy for scRNA-seq generation. Rather than approximating the assumed "neutral" marginal distribution, SB-CFG introduces a deliberately under-informative sparse reference for the unconditional branch, removing gene identity while preserving only coarse sparsity statistics. This "bad" reference amplifies the contrast between conditional and unconditional predictions, leading to stronger and more effective guidance during sampling. We evaluated SB-CFG as a training-free sampling modification on five publicly available scRNA-seq datasets. Experimental results demonstrate consistent improvements over standard CFG-based sampling in terms of marker gene expression fidelity, cell-type consistency, and sparsity preservation, indicating that SB-CFG better captures biologically meaningful gene expression patterns.
发表机构
- College of Information Science and Engineering, Ritsumeikan University（立命馆大学信息科学与工程学院）
机构由 AI 辅助整理，请以论文原文为准。
