发表机构
Carnegie Mellon University; GenBio AI; Mohamed bin Zayed University of AI（卡内基梅隆大学; GenBio AI; 穆罕默德·本·扎耶德人工智能大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出FACET框架，通过因子化非对称条件化分离序列与形态学背景的贡献，实现高效高保真荧光显微图像合成，显著提升空间重叠与FID指标。
AI 中文摘要
荧光显微镜能够揭示蛋白质的定位信息，但在同一细胞中仅能对有限数量的蛋白质进行成像；从氨基酸序列和细胞的形态学背景生成这些图像，能够实现对未成像蛋白质的计算机模拟定位。然而，这两个条件扮演着非对称的角色：形态学背景与目标图像在空间上对齐，而序列是非空间性的，必须在其内部指定依赖于蛋白质的定位，其中存在跨蛋白质共享的重复粗粒度模式以及更细粒度的蛋白质特异性变异。现有的生成器将两者联合作为条件，而未分离各自所解释的内容。我们提出了FACET（因子化非对称条件化高效传输），这是一个概率生成框架，将该结构编码为显式的归纳偏置：序列语义从背景未能解释的部分中学习，粗粒度定位规律通过语义记忆在蛋白质间共享，而蛋白质特异性变异则是围绕它们的有限残差。进一步地，一种方差保持的状态投影使FACET能够通过预训练的扩散预测器以最小的参数开销执行连续的随机传输。在保留的蛋白质上，FACET在Human Protein Atlas数据集上将空间重叠度提高了34.3%，在OpenCell数据集上提高了14.0%，相对于骨干匹配的基线，FID分别降低了27.2%和46.5%，且网络评估次数减少了75%。它还显著改善了蛋白质关联结构的恢复，并产生了校准更好的预测，而详细的消融实验显示其设计选择具有互补的贡献。这些结果表明，因子化非对称条件化，而非仅生成器容量，是实现高保真、高效且具有生物学意义的细胞图像合成的关键杠杆。
英文摘要
Fluorescence microscopy reveals where proteins localize, but only a limited number of proteins can be imaged in the same cell; generating these images from amino-acid sequence and the cell's morphological context enables in silico localization of unimaged proteins. The two conditions, however, play asymmetric roles: morphological context is spatially aligned with the target, whereas sequence is non-spatial and must specify protein-dependent localization within it, with recurring coarse patterns shared across proteins and finer protein-specific variation. Existing generators condition on both jointly, without separating what each explains. We introduce FACET (Factorized Asymmetric Conditioning for Efficient Transport), a probabilistic generative framework that encodes this structure as an explicit inductive bias: sequence semantics are learned from what context leaves unexplained, coarse localization regularities are shared across proteins through a semantic memory, and protein-specific variation is a bounded residual around them. A variance-preserving state projection further lets FACET perform continuous stochastic transport through a pretrained diffusion predictor with minimal parameter overhead. On held-out proteins, FACET improves spatial overlap by 34.3% on the Human Protein Atlas and 14.0% on OpenCell over a backbone-matched baseline, and reduces FID by 27.2% and 46.5%, respectively, with 75% fewer network evaluations. It also substantially improves protein-association structure recovery and yields better-calibrated predictions, while detailed ablations show complementary contributions from its design choices. These results identify factorized asymmetric conditioning, rather than generator capacity alone, as a key lever for high-fidelity, efficient, and biologically meaningful cellular image synthesis.
