Mapping single-cell developmental potential in health and disease with interpretable deep learning
Authors:
- Minji KangMKMinji Kang
- Jose Juan Almagro ArmenterosJAJose Juan Almagro Armenteros
- Gunsagar S. GulatiGGGunsagar S. Gulati
- Rachel GleyzerRGRachel Gleyzer
- Susanna AvagyanSASusanna Avagyan
- Erin L. BrownEBErin L. Brown
- Wubing ZhangWZWubing Zhang
- Abul UsmaniAUAbul Usmani
- Noah EarlandNENoah Earland
- Zhenqin WuZWZhenqin Wu
- James ZouJZJames Zou
- Ryan C. FieldsRFRyan C. Fields
Top Cited Papers
Preprint
Abstract
Single-cell RNA sequencing (scRNA-seq) has transformed our understanding of cell fate in developmental systems. However, identifying the molecular hallmarks of potency – the capacity of a cell to differentiate into other cell types – has remained challenging. Here, we introduce CytoTRACE 2, an interpretable deep learning framework for characterizing potency and differentiation states on an absolute scale from scRNA-seq data. Across 31 human and mouse scRNA-seq datasets encompassing 28 tissue types, CytoTRACE 2 outperformed existing methods for recovering experimentally determined potency levels and differentiation states covering the entire range of cellular ontogeny. Moreover, it reconstructed the temporal hierarchy of mouse embryogenesis across 62 timepoints; identified pan-tissue expression programs that discriminate major potency levels; and facilitated discovery of cellular phenotypes in cancer linked to survival and immunotherapy resistance. Our results illuminate a fundamental feature of cell biology and provide a broadly applicable platform for delineating single-cell differentiation landscapes in health and disease.Keywords
All Related Versions
- Published version: Nature Methods, 22 (11), 2258.
This publication has 63 references indexed in Scilit:
- Lineage tracing reveals the phylodynamics, plasticity, and paths of tumor evolutionCell, 2022
- Single-Cell RNA-Seq Reveals Cellular Heterogeneity of Pluripotency Transition and X Chromosome Dynamics during Early Mouse DevelopmentCell Reports, 2019
- Machine Learning Identifies Stemness Features Associated with Oncogenic DedifferentiationCell, 2018
- Single-Cell Landscape of Transcriptional Heterogeneity and Cell Fate Decisions during Mouse Early GastrulationCell Reports, 2017
- The Molecular Signatures Database Hallmark Gene Set CollectionCell Systems, 2015
- Lineage TracingCell, 2012
- PML-RARα/RXR Alters the Epigenetic Landscape in Acute Promyelocytic LeukemiaCancer Cell, 2010
- Module Map of Stem Cell Genes Guides Creation of Epithelial Cancer Stem CellsCell Stem Cell, 2008
- Genomic Analysis of Gastrulation and Organogenesis in the MouseDevelopmental Cell, 2007
- The embryonic cell lineage of the nematode Caenorhabditis elegansDevelopmental Biology, 1983