The paper introduces FiCS Perturb-seq, an innovative, industrialized platform designed to overcome challenges in scalability and consistency when generating large-scale perturbation data for biological research. This new method integrates chemical fixation, cryopreservation, and automation to produce high-quality, reproducible Perturb-seq datasets, which are essential for training next-generation biological foundation models that aim to predict causal genetic effects. The authors release a significant public resource, X-Atlas/Orion, the largest publicly available Perturb-seq atlas, which contains data targeting nearly all human protein-coding genes across eight million cells. Crucially, the research demonstrates that sgRNA abundance serves as a reliable proxy for gene knockdown efficiency, allowing for the quantification of dose-dependent genetic effects to improve the predictive power of computational models. Ultimately, the FiCS Perturb-seq platform is presented as a crucial technological advancement for accelerating the construction of robust, causal predictive biology models.

References:

• Huang A C, Hsieh T H S, Zhu J, et al. X-Atlas/Orion: Genome-wide Perturb-seq Datasets via a Scalable Fix-Cryopreserve Platform for Training Dose-Dependent Biological Foundation Models[J]. bioRxiv, 2025: 2025.06. 11.659105.