发表机构
School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences; Institute of Computing Technology, CAS; University of Chinese Academy of Sciences; Hong Kong University of Science and Technology（中国科学院大学先进交叉科学学院; 中国科学院计算技术研究所; 中国科学院大学; 香港科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
PerturbMap 结合受体局部低秩基与源到受体岭专家提案，实现单细胞扰动响应跨上下文迁移，在 Perturb-CITE-seq 黑色素瘤队列上优于多种对照方法，提升了扰动效应预测精度。
AI 中文摘要
单细胞扰动图谱很少在每个细胞上下文测量所有干预措施：查询扰动通常在一个或多个源上下文中被观测到，但在需要其效应的受体上下文中缺失。忽略这些已测量的响应会丢弃查询特定的实验证据，而在上下文间复制或弱校准这些响应则存在传递错误信号的风险。我们提出 PerturbMap，该模型通过结合受体局部低秩基，以及接受的提案来预测缺失的受体上下文效应，这些提案通过源到受体岭专家（基于配对训练扰动拟合）迁移同一扰动的已测量源响应，提案权重由验证锚点估计的路径可靠性决定。在 Perturb-CITE-seq 黑色素瘤队列上，PerturbMap 相比受体局部低秩基将全效应 MSE 提升了 4.1%，且达到比 FedAvg、零响应、原始复制、校准复制和身份混洗仿射对照更低的 MSE。其 MSE 与使用更强训练接口的集中式 token 匹配合并参考的差距保持在 2.82×10⁻⁶ 以内。条件均值特异性诊断显示出相同趋势：余弦相似度的同受体前 10 个对应项检索率从低秩基的 74.5%提升至 PerturbMap 的 80.5%。
英文摘要
Single-cell perturbation atlases rarely measure every intervention in every cellular context: a query perturbation is often observed in one or more source contexts but missing in the recipient context where its effect is needed. Ignoring those measured responses discards query-specific experimental evidence, whereas copying or weakly calibrating them across contexts risks transferring the wrong signal. We propose PerturbMap, which predicts a missing recipient-context effect by combining a recipient-local low-rank base with accepted proposals that transport the same perturbation's measured source responses through source-to-recipient ridge experts fit on paired training perturbations, with proposal weights determined by route reliability estimated on validation anchors. On the Perturb-CITE-seq melanoma cohort, PerturbMap improves full-effect MSE by 4.1\% over a recipient-local low-rank base and achieves lower MSE than FedAvg, zero-response, raw-copy, calibrated-copy, and identity-shuffled affine controls. It remains within $2.82\times10^{-6}$ MSE of our centralized token-matched pooled reference, which uses a stronger training interface. A condition-mean specificity diagnostic shows the same direction: same-recipient top-10 counterpart retrieval by cosine increases from 74.5\% for the low-rank base to 80.5\% for PerturbMap.
Comments14 pages, 5 figs
