ABSTRACT
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.
Competing Interest Statement
D.P. is on the scientific advisory board of Insitro. R.L.L. is on the supervisory board of Qiagen and on the board of directors of Ajax Therapeutics, for which he receives compensation and equity support. He is or has recently been a scientific advisor to Imago, Mission Bio, Syndax. Zentalis, Ajax, Bakx, Auron, Prelude, C4 Therapeutics and Isoplexis for which he receives equity support. He has research support from Ajax and AbbVie, consulted for Janssen, and received honoraria from Astra Zeneca and Kura for invited lectures.
Footnotes
We highlight Decipher's ability to jointly model and visualize 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 new and diverse contexts, including in pancreatitis with oncogene mutation, acute myeloid leukemia, and gastric cancer.
↵1 Because the Gaussian Process is used here only to define the distribution of the observations, and not to sample an unobserved latent variable, there is no computational difficulty in using it.
