Genetic screens using pooled CRISPR-based approaches are scalable and inexpensive, but restricted to standard readouts, including survival, proliferation and sortable markers. However, many biologically relevant cell states involve cellular and subcellular changes that are only accessible by microscopic visualization, and are currently impossible to screen with pooled methods. Here we combine pooled CRISPR-Cas9 screening with microraft array technology and high-content imaging to screen image-based phenotypes (CRaft-ID; CRISPR-based microRaft followed by guide RNA identification). By isolating microrafts that contain genetic clones harboring individual guide RNAs (gRNA), we identify RNA-binding proteins (RBPs) that influence the formation of stress granules, the punctate protein-RNA assemblies that form during stress. To automate hit identification, we developed a machine-learning model trained on nuclear morphology to remove unhealthy cells or imaging artifacts. In doing so, we identified and validated previously uncharacterized RBPs that modulate stress granule abundance, highlighting the applicability of our approach to facilitate image-based pooled CRISPR screens.

中文翻译：

---

结合微筏阵列成像的 CRISPR 筛选揭示了应激颗粒调节因素。


使用基于 CRISPR 的混合方法进行遗传筛选可扩展且成本低廉，但仅限于标准读数，包括生存、增殖和可分类标记。然而，许多生物学相关的细胞状态涉及细胞和亚细胞变化，这些变化只能通过显微可视化来观察，并且目前无法使用汇总方法进行筛选。在这里，我们将混合 CRISPR-Cas9 筛选与微筏阵列技术和高内涵成像相结合，以筛选基于图像的表型（CRaft-ID；基于 CRISPR 的 microRaft，然后进行引导 RNA 识别）。通过分离含有含有个体向导RNA（gRNA）的基因克隆的微筏，我们鉴定了影响应激颗粒形成的RNA结合蛋白（RBP），应激颗粒是在应激过程中形成的点状蛋白质-RNA组装体。为了自动识别命中，我们开发了一种机器学习模型，该模型经过核形态训练，以去除不健康的细胞或成像伪影。在此过程中，我们识别并验证了先前未表征的调节应激颗粒丰度的 RBP，突出了我们的方法在促进基于图像的汇集 CRISPR 筛选方面的适用性。