发表机构
College of Intelligence and Computing; Tianjin University（智能与计算学院; 天津大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出P2P方法，以随机细胞集为监督单元对未配对单细胞扰动响应进行群体级去噪预测，在多个数据集上优于现有基线，显著提升效应相关性和差异表达基因检测精度。
AI 中文摘要
AIVC（AI虚拟细胞）是一种跨条件下细胞行为的学习模拟器。预测细胞群体如何对遗传扰动产生转录组响应是一项核心任务。Perturb-seq通过破坏性测序记录该响应，因此对照细胞和扰动细胞永远不会被观测为配对，且同一条件下的细胞仍具有异质性和噪声。对单个细胞进行回归会将采样变异吸收到估计效应中，而解释需要可复现的群体效应。P2P（扰动到扰动）采用随机细胞集视图作为监督单元。从同一条件抽取的两个视图共享可复现的群体效应，并因视图特定变异而不同。置换不变的集合编码器总结对照群体，结构化编码器表示扰动标记、细胞环境、剂量和组合相互作用，门控机制融合经验条件效应记忆与神经残差。异方差头部预测群体均值和基因级响应方差。在一种方案和五个随机种子下，相对于GenePert、LinearPert、SLIM、Scouter和scPILOT，P2P在Adamson、Norman、Replogle K562和Replogle RPE1上均达到最低的表达RMSE和最高的效应Pearson、DEG F1和DEG平均精度。在Replogle K562上，相对于在两个指标上均为最强基线的Scouter，效应Pearson从0.643提升至0.702，DEG F1从0.067提升至0.178。
英文摘要
AIVC (AI Virtual Cell) is a learned simulator of cellular behavior across conditions. Predicting how a cell population responds transcriptionally to a genetic perturbation is a core task. Perturb-seq records that response by destructive sequencing, so a control cell and a perturbed cell are never observed as a pair, and cells under one condition remain heterogeneous and noisy. Regression on individual cells absorbs sampling variation into the estimated effect, whereas interpretation requires the reproducible population effect. P2P (Perturbation-to-Perturbation) takes a stochastic cell-set view as its supervision unit. Two views drawn from the same condition share a reproducible population effect and differ by view-specific variation. A permutation-invariant set encoder summarizes the control population, a structured encoder represents perturbation tokens, cellular context, dose, and combination interactions, and a gate blends empirical condition-effect memory with a neural residual. A heteroscedastic head predicts the population mean and gene-wise response variance. Under one protocol and five seeds, P2P attains the lowest expression RMSE and the highest Effect Pearson, DEG F1, and DEG average precision on each of Adamson, Norman, Replogle K562, and Replogle RPE1 relative to GenePert, LinearPert, SLIM, Scouter, and scPILOT. On Replogle K562, Effect Pearson rises from 0.643 to 0.702 and DEG F1 rises from 0.067 to 0.178 relative to Scouter, the strongest baseline on both metrics.
