D-SPIN constructs regulatory network models from scRNA-seq that reveal organizing principles of perturbation response

Gene regulatory networks modulate the expression of the genome in response to signals and environmental conditions. Reconstructions of such networks can reveal the control principles cells use to maintain homeostasis and execute cell-state transitions. Here, we introduce a computational framework, D-SPIN, that infers mechanistically interpretable and generative models of gene regulatory networks from single-cell mRNA-seq datasets collected across thousands of perturbation conditions. The models explain how perturbations modulate cell state proportions by reconfiguring underlying regulatory interactions. Using large Perturb-seq and drug-response datasets, D-SPIN models reveal key regulators of cell-fate decisions and the coordination of distant cellular pathways in response to gene knockdowns and drug treatments, elucidate how combinations of immunomodulatory drugs induce combinatorial cell states through additive recruitment of gene expression programs, and simulate shifts in immune cell population structures across unobserved drug dosage combinations. D-SPIN provides a computational framework for revealing principles of cellular information processing and physiological control.

基因调控网络（Gene Regulatory Networks, GRNs）可响应各类信号与环境条件，对基因组的表达进行调控。对这类网络进行重构，能够揭示细胞维持稳态（homeostasis）、完成细胞状态转换所依托的调控原理。本研究提出一款名为D-SPIN的计算框架，该框架可基于数千种扰动条件下采集的单细胞mRNA测序（single-cell mRNA-seq）数据集，推断出具备机制可解释性的基因调控网络生成式模型。此类模型可阐释扰动如何通过重构底层调控互作关系，改变细胞状态的占比。依托大规模扰动测序（Perturb-seq）与药物响应数据集，D-SPIN模型可揭示细胞命运决策的关键调控因子，以及细胞响应基因敲低与药物治疗时远端细胞通路的协调机制；同时阐明免疫调节药物组合如何通过叠加招募基因表达程序，诱导出组合型细胞状态，并可模拟未被观测的药物剂量组合下免疫细胞群体结构的变化。D-SPIN为揭示细胞信息处理与生理调控的核心原理，提供了一套通用计算框架。