Scalable analysis of cell-type composition from single-cell transcriptomics using deep recurrent learning.
Ontology highlight
ABSTRACT:
SUBMITTER: Deng Y
PROVIDER: S-EPMC6774994 | biostudies-literature | 2019 Apr
REPOSITORIES: biostudies-literature
Publications
Scalable analysis of cell-type composition from single-cell transcriptomics using deep recurrent learning.
Deng Yue Y Bao Feng F Dai Qionghai Q Wu Lani F LF Altschuler Steven J SJ
Nature methods 20190318 4
Recent advances in large-scale single-cell RNA-seq enable fine-grained characterization of phenotypically distinct cellular states in heterogeneous tissues. We present scScope, a scalable deep-learning-based approach that can accurately and rapidly identify cell-type composition from millions of noisy single-cell gene-expression profiles. ...[more]
Similar Datasets
Project description:Many applications in speech, robotics, finance, and biology deal with sequential data, where ordering matters and recurrent structures are common. However, this structure cannot be easily captured by standard kernel functions. To model such structure, we propose expressive closed-form kernel functions for Gaussian processes. The resulting model, GP-LSTM, fully encapsulates the inductive biases of long short-term memory (LSTM) recurrent networks, while retaining the non-parametric probabilistic advantages of Gaussian processes. We learn the properties of the proposed kernels by optimizing the Gaussian process marginal likelihood using a new provably convergent semi-stochastic gradient procedure, and exploit the structure of these kernels for scalable training and prediction. This approach provides a practical representation for Bayesian LSTMs. We demonstrate state-of-the-art performance on several benchmarks, and thoroughly investigate a consequential autonomous driving application, where the predictive uncertainties provided by GP-LSTM are uniquely valuable.
| S-EPMC6334642 | biostudies-other
Project description:Single-cell transcriptomics have revolutionized our understanding of the cell composition of tumors and allowed us to identify new subtypes of cells. Despite rapid technological advancements, single-cell analysis remains resource-intense hampering the scalability that is required to profile a sufficient number of samples for clinical associations. Therefore, more scalable approaches are needed to understand the contribution of individual cell types to the development and treatment response of solid tumors such as esophageal adenocarcinoma where comprehensive genomic studies have only led to a small number of targeted therapies. Due to the limited treatment options and late diagnosis, esophageal adenocarcinoma has a poor prognosis. Understanding the interaction between and dysfunction of individual cell populations provides an opportunity for the development of new interventions. In an attempt to address the technological and clinical needs, we developed a protocol for the separation of esophageal carcinoma tissue into leukocytes (CD45+), epithelial cells (EpCAM+), and fibroblasts (two out of PDGFR?, CD90, anti-fibroblast) by fluorescence-activated cell sorting and subsequent RNA sequencing. We confirm successful separation of the three cell populations by mapping their transcriptomic profiles to reference cell lineage expression data. Gene-level analysis further supports the isolation of individual cell populations with high expression of CD3, CD4, CD8, CD19, and CD20 for leukocytes, CDH1 and MUC1 for epithelial cells, and FAP, SMA, COL1A1, and COL3A1 for fibroblasts. As a proof of concept, we profiled tumor samples of nine patients and explored expression differences in the three cell populations between tumor and normal tissue. Interestingly, we found that angiogenesis-related genes were upregulated in fibroblasts isolated from tumors compared with normal tissue. Overall, we suggest our protocol as a complementary and more scalable approach compared with single-cell RNA sequencing to investigate associations between clinical parameters and transcriptomic alterations of specific cell populations in esophageal adenocarcinoma.
| S-EPMC7266280 | biostudies-literature
Project description:Advances in single-cell RNA sequencing (scRNA-seq) have furthered the simultaneous classification of thousands of cells in a single assay based on transcriptome profiling. In most analysis protocols, single-cell type annotation relies on marker genes or RNA-seq profiles, resulting in poor extrapolation. Still, the accurate cell-type annotation for single-cell transcriptomic data remains a great challenge. Here, we introduce scDeepSort (https://github.com/ZJUFanLab/scDeepSort), a pre-trained cell-type annotation tool for single-cell transcriptomics that uses a deep learning model with a weighted graph neural network (GNN). Using human and mouse scRNA-seq data resources, we demonstrate the high performance and robustness of scDeepSort in labeling 764 741 cells involving 56 human and 32 mouse tissues. Significantly, scDeepSort outperformed other known methods in annotating 76 external test datasets, reaching an 83.79% accuracy across 265 489 cells in humans and mice. Moreover, we demonstrate the universality of scDeepSort using more challenging datasets and using references from different scRNA-seq technology. Above all, scDeepSort is the first attempt to annotate cell types of scRNA-seq data with a pre-trained GNN model, which can realize the accurate cell-type annotation without additional references, i.e. markers or RNA-seq profiles.
| S-EPMC8643674 | biostudies-literature
Project description:Bilaterian animals display a wide variety of cell types, organized into defined anatomical structures and organ systems, which are mostly absent in prebilaterian animals. Xenacoelomorpha are an early-branching bilaterian phylum displaying an apparently relatively simple anatomical organization that have greatly diverged from other bilaterian clades. In this study, we use whole-body single-cell transcriptomics on the acoel Isodiametra pulchra to identify and characterize different cell types. Our analysis identifies the existence of ten major cell type categories in acoels all contributing to main biological functions of the organism: metabolism, locomotion and movements, behavior, defense, and development. Interestingly, although most cell clusters express core fate markers shared with other animal clades, we also describe a surprisingly large number of clade-specific marker genes, suggesting the emergence of clade-specific common molecular machineries functioning in distinct cell types. Together, these results provide novel insight into the evolution of bilaterian cell types and open the door to a better understanding of the origins of the bilaterian body plan and their constitutive cell types.
| S-EPMC8097308 | biostudies-literature
Project description:BackgroundWith the development of modern sequencing technology, hundreds of thousands of single-cell RNA-sequencing (scRNA-seq) profiles allow to explore the heterogeneity in the cell level, but it faces the challenges of high dimensions and high sparsity. Dimensionality reduction is essential for downstream analysis, such as clustering to identify cell subpopulations. Usually, dimensionality reduction follows unsupervised approach.ResultsIn this paper, we introduce a semi-supervised dimensionality reduction method named scSemiAE, which is based on an autoencoder model. It transfers the information contained in available datasets with cell subpopulation labels to guide the search of better low-dimensional representations, which can ease further analysis.ConclusionsExperiments on five public datasets show that, scSemiAE outperforms both unsupervised and semi-supervised baselines whether the transferred information embodied in the number of labeled cells and labeled cell subpopulations is much or less.
| S-EPMC9069784 | biostudies-literature
Project description:Single-cell RNA sequencing (scRNA-seq) data provides unprecedented information on cell fate decisions; however, the spatial arrangement of cells is often lost. Several recent computational methods have been developed to impute spatial information onto a scRNA-seq dataset through analyzing known spatial expression patterns of a small subset of genes known as a reference atlas. However, there is a lack of comprehensive analysis of the accuracy, precision, and robustness of the mappings, along with the generalizability of these methods, which are often designed for specific systems. We present a system-adaptive deep learning-based method (DEEPsc) to impute spatial information onto a scRNA-seq dataset from a given spatial reference atlas. By introducing a comprehensive set of metrics that evaluate the spatial mapping methods, we compare DEEPsc with four existing methods on four biological systems. We find that while DEEPsc has comparable accuracy to other methods, an improved balance between precision and robustness is achieved. DEEPsc provides a data-adaptive tool to connect scRNA-seq datasets and spatial imaging datasets to analyze cell fate decisions. Our implementation with a uniform API can serve as a portal with access to all the methods investigated in this work for spatial exploration of cell fate decisions in scRNA-seq data. All methods evaluated in this work are implemented as an open-source software with a uniform interface.
| S-EPMC8021700 | biostudies-literature
Project description:Single-cell transcriptome measurements can reveal unexplored biological diversity, but they suffer from technical noise and bias that must be modeled to account for the resulting uncertainty in downstream analyses. Here we introduce single-cell variational inference (scVI), a ready-to-use scalable framework for the probabilistic representation and analysis of gene expression in single cells ( https://github.com/YosefLab/scVI ). scVI uses stochastic optimization and deep neural networks to aggregate information across similar cells and genes and to approximate the distributions that underlie observed expression values, while accounting for batch effects and limited sensitivity. We used scVI for a range of fundamental analysis tasks including batch correction, visualization, clustering, and differential expression, and achieved high accuracy for each task.
| S-EPMC6289068 | biostudies-literature
Project description:Alternative polyadenylation (APA) is emerging as an important layer of gene regulation because the majority of mammalian protein-coding genes contain multiple polyadenylation (pA) sites in their 3' UTR. By alteration of 3' UTR length, APA can considerably affect post-transcriptional gene regulation. Yet, our understanding of APA remains rudimentary. Novel single-cell RNA sequencing (scRNA-seq) techniques allow molecular characterization of different cell types to an unprecedented degree. Notably, the most popular scRNA-seq protocols specifically sequence the 3' end of transcripts. Building on this property, we implemented a method for analysing patterns of APA regulation from such data. Analyzing multiple datasets from diverse tissues, we identified widespread modulation of APA in different cell types resulting in global 3' UTR shortening/lengthening and enhanced cleavage at intronic pA sites. Our results provide a proof-of-concept demonstration that the huge volume of scRNA-seq data that accumulates in the public domain offers a unique resource for the exploration of APA based on a very broad collection of cell types and biological conditions.
| S-EPMC6821429 | biostudies-literature
Project description:Dropouts distort gene expression and misclassify cell types in single-cell transcriptome. Although imputation may improve gene expression and downstream analysis to some degree, it also inevitably introduces false signals. We develop DISC, a novel deep learning network with semi-supervised learning to infer gene structure and expression obscured by dropouts. Compared with seven state-of-the-art imputation approaches on ten real-world datasets, we show that DISC consistently outperforms the other approaches. Its applicability, scalability, and reliability make DISC a promising approach to recover gene expression, enhance gene and cell structures, and improve cell type identification for sparse scRNA-seq data.
| S-EPMC7353747 | biostudies-literature
Project description:The rapid emergence of spatial transcriptomics (ST) technologies is revolutionizing our understanding of tissue spatial architecture and biology. Although current ST methods, whether based on next-generation sequencing (seq-based approaches) or fluorescence in situ hybridization (image-based approaches), offer valuable insights, they face limitations either in cellular resolution or transcriptome-wide profiling. To address these limitations, we present SpatialScope, a unified approach integrating scRNA-seq reference data and ST data using deep generative models. With innovation in model and algorithm designs, SpatialScope not only enhances seq-based ST data to achieve single-cell resolution, but also accurately infers transcriptome-wide expression levels for image-based ST data. We demonstrate SpatialScope's utility through simulation studies and real data analysis from both seq-based and image-based ST approaches. SpatialScope provides spatial characterization of tissue structures at transcriptome-wide single-cell resolution, facilitating downstream analysis, including detecting cellular communication through ligand-receptor interactions, localizing cellular subtypes, and identifying spatially differentially expressed genes.
| S-EPMC10687049 | biostudies-literature