Joint representation and visualization of derailed cell states with Decipher

Biological insights often depend on comparing conditions such as disease and health. Yet, we lack effective computational tools for integrating single-cell genomics data across conditions or characterizing transitions from normal to deviant cell states. Here, we present Decipher, a deep generative model that characterizes derailed cell-state trajectories. Decipher jointly models and visualizes gene expression and cell state from normal and perturbed single-cell RNA-seq data, revealing shared and disrupted dynamics. We demonstrate its superior performance across diverse contexts, including in pancreatitis with oncogene mutation, acute myeloid leukemia, and gastric cancer. scRNAseq on bone marrow samples for AML and healthy patients with mutations in TET2 and DNMT3a

生物学研究的关键认知往往源于对疾病与健康等不同生理状态的比较分析。然而，目前尚缺乏能够整合跨状态单细胞基因组学数据，或精准刻画正常细胞状态向异常细胞状态转变过程的有效计算工具。本研究提出了解析器（Decipher）——一款能够刻画失调细胞状态轨迹的深度生成模型。该模型可联合建模并可视化正常与受扰单细胞RNA测序（single-cell RNA-seq）数据中的基因表达与细胞状态，进而揭示细胞动态过程的保守性与失调特征。我们在多种实验场景中验证了该模型的优异性能，涵盖携带致癌基因突变的胰腺炎、急性髓系白血病（acute myeloid leukemia, AML）以及胃癌。此外，本研究还包含针对AML患者与携带TET2、DNMT3a基因突变的健康个体的骨髓样本的单细胞RNA测序（scRNAseq）数据。