干预感知的多尺度表征学习：从成像表型组学到扰动转录组学
Intervention-Aware Multiscale Representation Learning from Imaging Phenomics and Perturbation Transcriptomics
提出一种干预感知的蒸馏框架，利用转录组学教师模型指导仅图像的student模型，在测试时无需转录组数据即可预测干预语义；其基于化学感知码本和剂量解耦的设计，可迁移到其他需要从图像预测干预效果或处理弱配对多模态数据的视觉任务中。
原文依据 we introduce an intervention-aware distillation framework that leverages perturbational transcriptomics to guide image representation learning.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于显微镜的表型分析在药物发现中具有可扩展性，但缺乏转录组学的机制深度，而转录组学仍然昂贵且稀缺。现有多模态方法要么使用图像来支持其他模态，要么简单地按样本身份对齐表征，忽略了弱配对数据中的细胞类型和剂量变化，限制了对未见干预的泛化。本文引入一个干预感知的蒸馏框架，利用扰动转录组学来指导图像表征学习。一个以转录组为条件的教师模型整合基因表达和干预元数据，在按药物相似性组织的化学感知码本上产生软分布。该教师模型采用微调的单细胞基础模型来编码细胞类型上下文并解耦剂量效应。一个仅图像的student模型学习仅从显微镜图像预测这些分布，在测试时独立运行的同时蒸馏机制知识。这种设计强调干预语义而非身份对齐，并显式处理剂量和细胞类型不匹配。我们提供理论保证，表明转录组指导收紧了基于图像预测的风险界。在Cell Painting和RxRx数据集与L1000配对的情况下，与自监督和对齐基线相比，我们的方法显著改善了对未见干预的单样本迁移和药物靶点基因发现。
英文原文摘要 1480 字符
Microscopy-based phenotypic profiling is scalable for drug discovery but lacks the mechanistic depth of transcriptomics, which remains costly and scarce. Existing multimodal approaches either use images to support other modalities or naively align representations by sample identity, ignoring cell-type and dose variations in weakly paired data-limiting generalization to unseen interventions. In this paper, we introduce an intervention-aware distillation framework that leverages perturbational transcriptomics to guide image representation learning. A transcriptome-conditioned teacher integrates gene expression and intervention metadata to produce soft distributions over a chemistry-aware codebook organized by drug similarity. The teacher employs a fine-tuned single-cell foundation model to encode cell-type context and disentangle dose effects. An image-only student learns to predict these distributions from microscopy alone, distilling mechanistic knowledge while operating independently at test time. This design emphasizes intervention semantics rather than identity alignment and explicitly handles dose and cell-type mismatches. We provide theoretical guarantees showing that transcriptomic guidance tightens the risk bound for image-based prediction. On Cell Painting and RxRx datasets paired with L1000, our method significantly improves one-shot transfer to unseen interventions and drug-target gene discovery compared to self-supervised and alignment baselines