LineageVAE: Reconstructing Historical Cell States and Transcriptomes toward Unobserved Progenitors
September 11, 2024
Abstract
Motivation
Single-cell RNA sequencing (scRNA-seq) enables comprehensive characterization of the cell state. However, its destructive nature prohibits measuring gene expression changes during dynamic processes such as embryogenesis. Although recent studies integrating scRNA-seq with lineage tracing have provided clonal insights between progenitor and mature cells, challenges remain. Because of their experimental nature, observations are sparse, and cells observed in the early state are not the exact progenitors of cells observed at later time points. To overcome these limitations, we developed LineageVAE, a novel computational methodology that utilizes deep learning based on the property that cells sharing barcodes have identical progenitors.
Results
LineageVAE is a deep generative model that transforms scRNA-seq observations with identical lineage barcodes into sequential trajectories toward a common progenitor in a latent cell state space. This method enables the reconstruction of unobservable cell state transitions, historical transcriptomes, and regulatory dynamics at a single-cell resolution. Applied to hematopoiesis and reprogrammed fibroblast datasets, LineageVAE demonstrated its ability to restore backward cell state transitions and infer progenitor heterogeneity and transcription factor activity along differentiation trajectories.
Availability and Implementation
The LineageVAE model was implemented in Python using the PyTorch deep learning library. The code is available on GitHub at https://github.com/LzrRacer/LineageVAE/.
Supplementary Information
Available at Bioinformatics online.
Key words: single-cell RNA sequencing (scRNA-seq), lineage tracing, machine learning, deep learning, neural network, deep generative model, variational autoencoder (VAE), dimensionality reduction, time series data, differentiation, hematopoiesis, reprogramming, tumor evolution, generalized linear model (GLM), transcription factor activity
Single-cell RNA sequencing (scRNA-seq) enables comprehensive characterization of the cell state. However, its destructive nature prohibits measuring gene expression changes during dynamic processes such as embryogenesis. Although recent studies integrating scRNA-seq with lineage tracing have provided clonal insights between progenitor and mature cells, challenges remain. Because of their experimental nature, observations are sparse, and cells observed in the early state are not the exact progenitors of cells observed at later time points. To overcome these limitations, we developed LineageVAE, a novel computational methodology that utilizes deep learning based on the property that cells sharing barcodes have identical progenitors.
Results
LineageVAE is a deep generative model that transforms scRNA-seq observations with identical lineage barcodes into sequential trajectories toward a common progenitor in a latent cell state space. This method enables the reconstruction of unobservable cell state transitions, historical transcriptomes, and regulatory dynamics at a single-cell resolution. Applied to hematopoiesis and reprogrammed fibroblast datasets, LineageVAE demonstrated its ability to restore backward cell state transitions and infer progenitor heterogeneity and transcription factor activity along differentiation trajectories.
Availability and Implementation
The LineageVAE model was implemented in Python using the PyTorch deep learning library. The code is available on GitHub at https://github.com/LzrRacer/LineageVAE/.
Supplementary Information
Available at Bioinformatics online.
Key words: single-cell RNA sequencing (scRNA-seq), lineage tracing, machine learning, deep learning, neural network, deep generative model, variational autoencoder (VAE), dimensionality reduction, time series data, differentiation, hematopoiesis, reprogramming, tumor evolution, generalized linear model (GLM), transcription factor activity
Journal Article
JOURNAL：Bioinformatics
TITLE：LineageVAE: Reconstructing Historical Cell States and Transcriptomes toward Unobserved Progenitors
DOI：https://doi.org/10.1093/bioinformatics/btae520
TITLE：LineageVAE: Reconstructing Historical Cell States and Transcriptomes toward Unobserved Progenitors
DOI：https://doi.org/10.1093/bioinformatics/btae520
Correspondence to
Teppei Shimamura, Professor
Department of Computational and Systems Biology,
Medical Research Institute,
Tokyo Medical and Dental University(TMDU)
E-mail:shimamura.csb（at）tmd.ac.jp
＊Please change (at) in e-mail addresses to @ on sending your e-mail to contact personnels.