Generative modeling of single-cell time series with PRESCIENT enables prediction of cell trajectories with interventions.
Generative modeling of single-cell time series with PRESCIENT enables prediction of cell trajectories with interventions.
复制标题
DOI：
10.1038/s41467-021-23518-w
复制
发表时间：
2021-05-28
影响因子：
16.6
通讯作者：
Gifford DK
中科院分区：
文献类型：
--
作者：
Yeo GHT;Saksena SD;Gifford DK
现有的使用单细胞RNA测序(scRNA-seq)预测细胞命运的计算方法没有对细胞如何随机和在物理时间内进化进行建模，也不能预测拟议的干预措施如何改变分化轨迹。我们介绍了Precicient(潜在单细胞梯度的势能)，一个生成性建模框架，从时间序列scRNA-seq数据中学习潜在的分化图景。我们在一个实验性的谱系追踪数据集上验证了Precient，其中我们表明Precient能够在考虑细胞增殖时预测造血祖细胞的命运偏差，改进了现有的最好的方法。我们演示了先见之明如何模拟受扰细胞的轨迹，恢复已知的细胞命运调节器在造血和胰腺β细胞分化中的预期效果。Precient能够适应不同时间点和不同起始细胞群的多个基因的复杂扰动，并可在https://github.com/gifford-lab/prescient.上获得单细胞RNA-Seq使我们能够以细胞分辨率观察生物系统如何随时间变化的快照。在这里，作者开发了一个生成性框架，使用时间分辨的单细胞数据来模拟细胞如何在物理时间内变化，包括对扰动的响应。
Existing computational methods that use single-cell RNA-sequencing (scRNA-seq) for cell fate prediction do not model how cells evolve stochastically and in physical time, nor can they predict how differentiation trajectories are altered by proposed interventions. We introduce PRESCIENT (Potential eneRgy undErlying Single Cell gradIENTs), a generative modeling framework that learns an underlying differentiation landscape from time-series scRNA-seq data. We validate PRESCIENT on an experimental lineage tracing dataset, where we show that PRESCIENT is able to predict the fate biases of progenitor cells in hematopoiesis when accounting for cell proliferation, improving upon the best-performing existing method. We demonstrate how PRESCIENT can simulate trajectories for perturbed cells, recovering the expected effects of known modulators of cell fate in hematopoiesis and pancreatic β cell differentiation. PRESCIENT is able to accommodate complex perturbations of multiple genes, at different time points and from different starting cell populations, and is available at https://github.com/gifford-lab/prescient. Single-cell RNA-Seq allows us to observe snapshots of how biological systems change over time at cellular resolution. Here, the authors develop a generative framework that uses time-resolved single-cell data to model how cells change in physical time, including in response to perturbations.