Cell identity is governed by the complex regulation of gene expression, represented as gene-regulatory networks¹. Here we use gene-regulatory networks inferred from single-cell multi-omics data to perform in silico transcription factor perturbations, simulating the consequent changes in cell identity using only unperturbed wild-type data. We apply this machine-learning-based approach, CellOracle, to well-established paradigms—mouse and human haematopoiesis, and zebrafish embryogenesis—and we correctly model reported changes in phenotype that occur as a result of transcription factor perturbation. Through systematic in silico transcription factor perturbation in the developing zebrafish, we simulate and experimentally validate a previously unreported phenotype that results from the loss of noto, an established notochord regulator. Furthermore, we identify an axial mesoderm regulator, lhx1a. Together, these results show that CellOracle can be used to analyse the regulation of cell identity by transcription factors, and can provide mechanistic insights into development and differentiation.

细胞身份受基因表达的复杂调控所控制，表现为基因调控网络¹ 。在这里，我们使用从单细胞多组学数据推断的基因调控网络来执行计算机转录因子扰动，仅使用未扰动的野生型数据模拟细胞身份的后续变化。我们将这种基于机器学习的方法 CellOracle 应用于成熟的范例——小鼠和人类造血以及斑马鱼胚胎发生——并且我们正确地模拟了由于转录因子扰动而发生的表型变化。通过对发育中的斑马鱼进行系统的计算机转录因子扰动，我们模拟并通过实验验证了一种先前未报道的表型，该表型是由于noto （一种已建立的脊索调节因子）丧失而导致的。此外，我们还确定了一个轴向中胚层调节因子lhx1a 。总之，这些结果表明 CellOracle 可用于分析转录因子对细胞身份的调节，并可以提供发育和分化的机制见解。