Synapse - Joint representation and visualization of derailed cell states with Decipher

Joint representation and visualization of derailed cell states with Decipher Journal Article

Authors:	Nazaret, A.; Fan, J. L.; Lavallée, V. P.; Burdziak, C.; Cornish, A. E.; Kiseliovas, V.; Bowman, R. L.; Masilionis, I.; Chun, J.; Eisman, S. E.; Wang, J.; Hong, J.; Shi, L.; Levine, R. L.; Mazutis, L.; Blei, D.; Pe'er, D.; Azizi, E.
Article Title:	Joint representation and visualization of derailed cell states with Decipher
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.
Keywords:	inflammation; evolution; progression; identification; plasticity; tumor heterogeneity; acute myeloid leukemia; dimensionality reduction; hematopoietic stem; deep generative model; cell-state trajectories
Journal Title:	Genome Biology
Volume:	26
ISSN:	1465-6906
Publisher:	Biomed Central Ltd
Date Published:	2025-07-23
Start Page:	219
Language:	English
ACCESSION:	WOS:001536213100001
DOI:	10.1186/s13059-025-03682-8
PROVIDER:	wos
PMCID:	PMC12285193
PUBMED:	40702544
Notes:	Article -- MSK Cancer Center Support Grant (P30 CA008748) acknowledged in PubMed and PDF -- MSK corresponding author is Dana Pe’er -- Source: WOS