用文本监督让细胞图像与扰动信息匹配，仅需消费级显卡训练。
MorphoCLIP: Text-Supervised Contrastive Learning for Perturbation Matching in Cell Painting Images
- 冻结视觉与语言模型，仅训练小型跨模态模块和投影层。
- 在独立数据集上，正确匹配率远超随机水平（前10名中出现）。
- 适合想用文本搜索化学/基因扰动图像的研究者，但基因-化合物匹配仍难。
Cell Painting 显微成像可捕捉细胞在化学或基因扰动后的变化。将这些图像与产生它们的扰动关联起来，能显著提升大规模成像筛选的可检索性和可解释性，但因生物效应微弱且技术差异大，该任务仍具挑战。我们提出 MorphoCLIP，一种对比学习模型，将 Cell Painting 图像与化合物、CRISPR 敲除、ORF 过表达等文本描述进行关联。模型保持视觉和语言主干网络冻结，仅训练一个紧凑的跨通道模块和投影层，可在单张消费级 GPU 上完成训练。在保留的 CPJUMP1 数据上，MorphoCLIP 可双向搜索：从图像找描述，或从描述找匹配图像。两种情况下，正确匹配均频繁出现在前十个结果中，显著优于随机预期。引入重复实验对齐损失后，重复实验的图像特征更一致，但尚未带来可靠的基因-化合物匹配性能提升。基因感知标签和板间校正也未表现出稳定的检索优势。结果表明，文本监督有助于组织化学与遗传的 Cell Painting 数据；然而，化合物与基因扰动的匹配仍是开放问题。
原文摘要 · Abstract (English)
Cell Painting microscopy captures how cells change after a chemical or genetic perturbation. Connecting these images to the perturbations that produced them could make large imaging screens easier to search and interpret, but the task remains difficult because biological effects are subtle and technical variation is substantial. We introduce MorphoCLIP, a contrastive model that links Cell Painting profiles with text descriptions of compounds, CRISPR knockouts, and ORF overexpressions. The model keeps its vision and language backbones frozen and trains only a compact cross-channel module and projection layers, so it can be trained on a single consumer GPU. On held-out CPJUMP1 data, MorphoCLIP searches in both directions: from a cell image to its perturbation description and from a description to matching cell images. In both cases, a correct match appears among the top ten results much more often than expected by chance. Adding a replicate-alignment loss makes profiles from repeated experiments more consistent, although this improvement does not yet translate into reliable gene-compound matching. Gene-aware labels and plate correction also show no consistent retrieval benefit. These findings suggest that text supervision can help organize chemical and genetic Cell Painting data. Matching compounds with genetic perturbations, however, remains an open problem.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。