Universal prediction of cell cycle position using transfer learning
Authors:
- Shijie C. ZhengSZShijie C. Zheng
- Genevieve Stein-O’brienGSGenevieve Stein-O’brien
- Jonathan J. AugustinJAJonathan J. Augustin
- Jared SlosbergJSJared Slosberg
- Giovanni A. CarossoGCGiovanni A. Carosso
- Briana WinerBWBriana Winer
- Hans T. BjornssonHBHans T. Bjornsson
- Loyal A. GoffLGLoyal A. Goff
- Kasper D. HansenKHKasper D. Hansen
Preprint
Abstract
Background: The cell cycle is a highly conserved, continuous process which controls faithful replication and division of cells. Single-cell technologies have enabled increasingly precise measurements of the cell cycle both as a biological process of interest and as a possible confounding factor. Despite its importance and conservation, there is no universally applicable approach to infer position in the cell cycle with high-resolution from single-cell RNA-seq data. Results: Here, we present tricycle, an R/Bioconductor package, to address this challenge by leveraging key features of the biology of the cell cycle, the mathematical properties of principal component analysis of periodic functions, and the use of transfer learning. We estimate a cell cycle embedding using a fixed reference dataset and project new data into this reference embedding; an approach that overcomes key limitations of learning a dataset dependent embedding. Tricycle then predicts a cell-specific position in the cell cycle based on the data projection. The accuracy of tricycle compares favorably to gold-standard experimental assays, which generally require specialized measurements in specifically constructed in vitro systems. Using internal controls which are available for any dataset, we show that tricycle predictions generalize to datasets with multiple cell types, across tissues, species and even sequencing assays. Conclusions: Tricycle generalizes across datasets, is highly scalable and applicable to atlas-level single-cell RNA-seq data.Keywords
All Related Versions
- Published version: Genome Biology, 23 (1), 1.
This publication has 41 references indexed in Scilit:
- Computational analysis of cell-to-cell heterogeneity in single-cell RNA-sequencing data reveals hidden subpopulations of cellsNature Biotechnology, 2015
- Concurrent inhibition of enzymatic activity and NF-Y-mediated transcription of Topoisomerase-IIα by bis-DemethoxyCurcumin in cancer cellsCell Death & Disease, 2013
- Coordinating genome expression with cell sizeTrends in Genetics, 2012
- Interpreting principal component analyses of spatial population genetic variationNature Genetics, 2008
- Visualizing Spatiotemporal Dynamics of Multicellular Cell-Cycle ProgressionCell, 2008
- Cyclebase.org a comprehensive multi-organism online database of cell-cycle experimentsNucleic Acids Research, 2007
- Ontogeny of the Hematopoietic SystemAnnual Review of Immunology, 2007
- Toeplitz and Circulant Matrices: A ReviewFoundations and Trends® in Communications and Information Theory, 2006
- Comprehensive Identification of Cell Cycle–regulated Genes of the YeastSaccharomyces cerevisiaeby Microarray HybridizationMolecular Biology of the Cell, 1998
- Differential expression of DNA topoisomerases I and II during the eukaryotic cell cycle.Proceedings of the National Academy of Sciences, 1988