Reversed graph embedding resolves complex single-cell trajectories.
Ontology highlight
ABSTRACT:
SUBMITTER: Qiu X
PROVIDER: S-EPMC5764547 | biostudies-literature | 2017 Oct
REPOSITORIES: biostudies-literature
Publications
Reversed graph embedding resolves complex single-cell trajectories.
Qiu Xiaojie X Mao Qi Q Tang Ying Y Wang Li L Chawla Raghav R Pliner Hannah A HA Trapnell Cole C
Nature methods 20170821 10
Single-cell trajectories can unveil how gene regulation governs cell fate decisions. However, learning the structure of complex trajectories with multiple branches remains a challenging computational problem. We present Monocle 2, an algorithm that uses reversed graph embedding to describe multiple fate decisions in a fully unsupervised manner. We applied Monocle 2 to two studies of blood development and found that mutations in the genes encoding key lineage transcription factors divert cells to ...[more]
Similar Datasets
Project description:Many scientific datasets are of high dimension, and the analysis usually requires retaining the most important structures of data. Principal curve is a widely used approach for this purpose. However, many existing methods work only for data with structures that are mathematically formulated by curves, which is quite restrictive for real applications. A few methods can overcome the above problem, but they either require complicated human-made rules for a specific task with lack of adaption flexibility to different tasks, or cannot obtain explicit structures of data. To address these issues, we develop a novel principal graph and structure learning framework that captures the local information of the underlying graph structure based on reversed graph embedding. As showcases, models that can learn a spanning tree or a weighted undirected `1 graph are proposed, and a new learning algorithm is developed that learns a set of principal points and a graph structure from data, simultaneously. The new algorithm is simple with guaranteed convergence. We then extend the proposed framework to deal with large-scale data. Experimental results on various synthetic and six real world datasets show that the proposed method compares favorably with baselines and can uncover the underlying structure correctly.
| S-EPMC5899072 | biostudies-literature
Project description:Recent advances in chromatin architecture profiling technologies, such as single-cell Hi-C (scHi-C), allow us to dissect the heterogeneity of chromosome higher-order structures across diverse cell states and different individuals. However, scHi-C experiments are still expensive and not immediately available for population-scale profiling. Here, we present scENCORE, a computational method, to reconstruct personalized and cell-type-specific higher-order chromatin structures, such as A/B compartments, directly from more cost-effective and widely available single-cell epigenetic data (e.g., scATAC-seq). We apply scENCORE on scATAC-seq data from post-mortem prefrontal cortex brains and demonstrate its utility to 1) project Mega-base scale chromatin regions into lower dimensional space by leveraging graph embedding technologies based on cell-type-specific co-variability patterns, 2) define A/B compartments via unsupervised clustering, 3) perform an alignment algorithm for multi-graph embedding to derive comparable chromatin representations and highlight dynamic chromatin compartments across cell states and individuals. Validated by Hi-C experiments using FACS-sorted cells, scENCORE can faithfully reconstruct cell-type-specific chromatin compartments. Furthermore, scENCORE uniformly constructs chromosome conformation across population-scale scATAC-seq data and discovers key 3D structural switching events associated with psychiatric disorders. In summary, scENCORE allows cost-effective cell-type-specific and personalized reconstruction that delineate higher-order chromatin structures.
2023-09-27 | GSE216270 | GEO
Project description:Scientists often embed cells into a lower-dimensional space when studying single-cell RNA-seq data for improved downstream analyses such as developmental trajectory analyses, but the statistical properties of such nonlinear embedding methods are often not well understood. In this article, we develop the exponential-family SVD (eSVD), a nonlinear embedding method for both cells and genes jointly with respect to a random dot product model using exponential-family distributions. Our estimator uses alternating minimization, which enables us to have a computationally efficient method, prove the identifiability conditions and consistency of our method, and provide statistically principled procedures to tune our method. All these qualities help advance the single-cell embedding literature, and we provide extensive simulations to demonstrate that the eSVD is competitive compared to other embedding methods. We apply the eSVD via Gaussian distributions where the standard deviations are proportional to the means to analyze a single-cell dataset of oligodendrocytes in mouse brains. Using the eSVD estimated embedding, we then investigate the cell developmental trajectories of the oligodendrocytes. While previous results are not able to distinguish the trajectories among the mature oligodendrocyte cell types, our diagnostics and results demonstrate there are two major developmental trajectories that diverge at mature oligodendrocytes. Supplementary materials for this article, including a standardized description of the materials available for reproducing the work, are available as an online supplementary materials.
| S-EPMC8336573 | biostudies-literature
Project description:Hematopoietic stem and progenitor cells (HSPCs) maintain the adult blood system, and their dysregulation causes a multitude of diseases. However, the differentiation journeys toward specific hematopoietic lineages remain ill defined, and system-wide disease interpretation remains challenging. Here, we have profiled 44?802 mouse bone marrow HSPCs using single-cell RNA sequencing to provide a comprehensive transcriptional landscape with entry points to 8 different blood lineages (lymphoid, megakaryocyte, erythroid, neutrophil, monocyte, eosinophil, mast cell, and basophil progenitors). We identified a common basophil/mast cell bone marrow progenitor and characterized its molecular profile at the single-cell level. Transcriptional profiling of 13 815 HSPCs from the c-Kit mutant (W41/W41) mouse model revealed the absence of a distinct mast cell lineage entry point, together with global shifts in cell type abundance. Proliferative defects were accompanied by reduced Myc expression. Potential compensatory processes included upregulation of the integrated stress response pathway and downregulation of proapoptotic gene expression in erythroid progenitors, thus providing a template of how large-scale single-cell transcriptomic studies can bridge between molecular phenotypes and quantitative population changes.
| S-EPMC5969381 | biostudies-literature
Project description:A better understanding of the cell-fate transitions that occur in complex cellular ecosystems in normal development and disease could inform cell engineering efforts and lead to improved therapies. However, a major challenge is to simultaneously identify new cell states, and their transitions, to elucidate the gene expression dynamics governing cell-type diversification. Here, we present CellRouter, a multifaceted single-cell analysis platform that identifies complex cell-state transition trajectories by using flow networks to explore the subpopulation structure of multi-dimensional, single-cell omics data. We demonstrate its versatility by applying CellRouter to single-cell RNA sequencing data sets to reconstruct cell-state transition trajectories during hematopoietic stem and progenitor cell (HSPC) differentiation to the erythroid, myeloid and lymphoid lineages, as well as during re-specification of cell identity by cellular reprogramming of monocytes and B-cells to HSPCs. CellRouter opens previously undescribed paths for in-depth characterization of complex cellular ecosystems and establishment of enhanced cell engineering approaches.
| S-EPMC5832860 | biostudies-literature
Project description:In this research, we improve upon the current state of the art in entity retrieval by re-ranking the result list using graph embeddings. The paper shows that graph embeddings are useful for entity-oriented search tasks. We demonstrate empirically that encoding information from the knowledge graph into (graph) embeddings contributes to a higher increase in effectiveness of entity retrieval results than using plain word embeddings. We analyze the impact of the accuracy of the entity linker on the overall retrieval effectiveness. Our analysis further deploys the cluster hypothesis to explain the observed advantages of graph embeddings over the more widely used word embeddings, for user tasks involving ranking entities.
| S-EPMC7148245 | biostudies-literature
Project description:Cell types can be characterized by expression profiles derived from single-cell RNA-seq. Subpopulations are identified via clustering, yielding intuitive outcomes that can be validated by marker genes. Clustering, however, implies a discretization that cannot capture the continuous nature of differentiation processes. One could give up the detection of subpopulations and directly estimate the differentiation process from cell profiles. A combination of both types of information, however, is preferable. Crucially, clusters can serve as anchor points of differentiation trajectories. Here we present GraphDDP, which integrates both viewpoints in an intuitive visualization. GraphDDP starts from a user-defined cluster assignment and then uses a force-based graph layout approach on two types of carefully constructed edges: one emphasizing cluster membership, the other, based on density gradients, emphasizing differentiation trajectories. We show on intestinal epithelial cells and myeloid progenitor data that GraphDDP allows the identification of differentiation pathways that cannot be easily detected by other approaches.
| S-EPMC6134144 | biostudies-literature
Project description:Graph embedding methods are useful for a wide range of graph analysis tasks including link prediction and node classification. Most graph embedding methods learn only the topological structure of graphs. Nevertheless, it has been shown that the incorporation of node attributes is beneficial in improving the expressive power of node embeddings. However, real-world graphs are often noisy in terms of structure and/or attributes (missing and/or erroneous edges/attributes). Most existing graph embedding methods are susceptible to this noise, as they do not consider uncertainty during the modelling process. In this paper, we introduce RASE, a Robust Attribute and Structure preserving graph Embedding model. RASE is a novel graph representation learning model which effectively preserves both graph structure and node attributes through a unified loss function. To be robust, RASE uses a denoising attribute auto-encoder to deal with node attribute noise, and models uncertainty in the embedding space as Gaussians to cope with graph structure noise. We evaluate the performance of RASE through an extensive experimental study on various real-world datasets. Results demonstrate that RASE outperforms state-of-the-art embedding methods on multiple graph analysis tasks and is robust to both structure and attribute noise.
| S-EPMC7206273 | biostudies-literature
Project description:BackgroundRecent advances in simultaneous measurement of RNA and protein abundances at single-cell level provide a unique opportunity to predict protein abundance from scRNA-seq data using machine learning models. However, existing machine learning methods have not considered relationship among the proteins sufficiently.ResultsWe formulate this task in a multi-label prediction framework where multiple proteins are linked to each other at the single-cell level. Then, we propose a novel method for single-cell RNA to protein prediction named PIKE-R2P, which incorporates protein-protein interactions (PPI) and prior knowledge embedding into a graph neural network. Compared with existing methods, PIKE-R2P could significantly improve prediction performance in terms of smaller errors and higher correlations with the gold standard measurements.ConclusionThe superior performance of PIKE-R2P indicates that adding the prior knowledge of PPI to graph neural networks can be a powerful strategy for cross-modality prediction of protein abundances at the single-cell level.
| S-EPMC8170782 | biostudies-literature
Project description:BackgroundProtein-protein interactions (PPIs) are central to many biological processes. Considering that the experimental methods for identifying PPIs are time-consuming and expensive, it is important to develop automated computational methods to better predict PPIs. Various machine learning methods have been proposed, including a deep learning technique which is sequence-based that has achieved promising results. However, it only focuses on sequence information while ignoring the structural information of PPI networks. Structural information of PPI networks such as their degree, position, and neighboring nodes in a graph has been proved to be informative in PPI prediction.ResultsFacing the challenge of representing graph information, we introduce an improved graph representation learning method. Our model can study PPI prediction based on both sequence information and graph structure. Moreover, our study takes advantage of a representation learning model and employs a graph-based deep learning method for PPI prediction, which shows superiority over existing sequence-based methods. Statistically, Our method achieves state-of-the-art accuracy of 99.15% on Human protein reference database (HPRD) dataset and also obtains best results on Database of Interacting Protein (DIP) Human, Drosophila, Escherichia coli (E. coli), and Caenorhabditis elegans (C. elegan) datasets.ConclusionHere, we introduce signed variational graph auto-encoder (S-VGAE), an improved graph representation learning method, to automatically learn to encode graph structure into low-dimensional embeddings. Experimental results demonstrate that our method outperforms other existing sequence-based methods on several datasets. We also prove the robustness of our model for very sparse networks and the generalization for a new dataset that consists of four datasets: HPRD, E.coli, C.elegan, and Drosophila.
| S-EPMC7372763 | biostudies-literature