skip to main content

This content will become publicly available on December 1, 2022

Title: Single-cell classification using graph convolutional networks
Abstract Background Analyzing single-cell RNA sequencing (scRNAseq) data plays an important role in understanding the intrinsic and extrinsic cellular processes in biological and biomedical research. One significant effort in this area is the identification of cell types. With the availability of a huge amount of single cell sequencing data and discovering more and more cell types, classifying cells into known cell types has become a priority nowadays. Several methods have been introduced to classify cells utilizing gene expression data. However, incorporating biological gene interaction networks has been proved valuable in cell classification procedures. Results In this study, we propose a multimodal end-to-end deep learning model, named sigGCN, for cell classification that combines a graph convolutional network (GCN) and a neural network to exploit gene interaction networks. We used standard classification metrics to evaluate the performance of the proposed method on the within-dataset classification and the cross-dataset classification. We compared the performance of the proposed method with those of the existing cell classification tools and traditional machine learning classification methods. Conclusions Results indicate that the proposed method outperforms other commonly used methods in terms of classification accuracy and F1 scores. This study shows that the integration of prior knowledge about gene more » interactions with gene expressions using GCN methodologies can extract effective features improving the performance of cell classification. « less
Authors:
; ;
Award ID(s):
1942303
Publication Date:
NSF-PAR ID:
10326473
Journal Name:
BMC Bioinformatics
Volume:
22
Issue:
1
ISSN:
1471-2105
Sponsoring Org:
National Science Foundation
More Like this
  1. Introduction: Vaso-occlusive crises (VOCs) are a leading cause of morbidity and early mortality in individuals with sickle cell disease (SCD). These crises are triggered by sickle red blood cell (sRBC) aggregation in blood vessels and are influenced by factors such as enhanced sRBC and white blood cell (WBC) adhesion to inflamed endothelium. Advances in microfluidic biomarker assays (i.e., SCD Biochip systems) have led to clinical studies of blood cell adhesion onto endothelial proteins, including, fibronectin, laminin, P-selectin, ICAM-1, functionalized in microchannels. These microfluidic assays allow mimicking the physiological aspects of human microvasculature and help characterize biomechanical properties of adhered sRBCsmore »under flow. However, analysis of the microfluidic biomarker assay data has so far relied on manual cell counting and exhaustive visual morphological characterization of cells by trained personnel. Integrating deep learning algorithms with microscopic imaging of adhesion protein functionalized microfluidic channels can accelerate and standardize accurate classification of blood cells in microfluidic biomarker assays. Here we present a deep learning approach into a general-purpose analytical tool covering a wide range of conditions: channels functionalized with different proteins (laminin or P-selectin), with varying degrees of adhesion by both sRBCs and WBCs, and in both normoxic and hypoxic environments. Methods: Our neural networks were trained on a repository of manually labeled SCD Biochip microfluidic biomarker assay whole channel images. Each channel contained adhered cells pertaining to clinical whole blood under constant shear stress of 0.1 Pa, mimicking physiological levels in post-capillary venules. The machine learning (ML) framework consists of two phases: Phase I segments pixels belonging to blood cells adhered to the microfluidic channel surface, while Phase II associates pixel clusters with specific cell types (sRBCs or WBCs). Phase I is implemented through an ensemble of seven generative fully convolutional neural networks, and Phase II is an ensemble of five neural networks based on a Resnet50 backbone. Each pixel cluster is given a probability of belonging to one of three classes: adhered sRBC, adhered WBC, or non-adhered / other. Results and Discussion: We applied our trained ML framework to 107 novel whole channel images not used during training and compared the results against counts from human experts. As seen in Fig. 1A, there was excellent agreement in counts across all protein and cell types investigated: sRBCs adhered to laminin, sRBCs adhered to P-selectin, and WBCs adhered to P-selectin. Not only was the approach able to handle surfaces functionalized with different proteins, but it also performed well for high cell density images (up to 5000 cells per image) in both normoxic and hypoxic conditions (Fig. 1B). The average uncertainty for the ML counts, obtained from accuracy metrics on the test dataset, was 3%. This uncertainty is a significant improvement on the 20% average uncertainty of the human counts, estimated from the variance in repeated manual analyses of the images. Moreover, manual classification of each image may take up to 2 hours, versus about 6 minutes per image for the ML analysis. Thus, ML provides greater consistency in the classification at a fraction of the processing time. To assess which features the network used to distinguish adhered cells, we generated class activation maps (Fig. 1C-E). These heat maps indicate the regions of focus for the algorithm in making each classification decision. Intriguingly, the highlighted features were similar to those used by human experts: the dimple in partially sickled RBCs, the sharp endpoints for highly sickled RBCs, and the uniform curvature of the WBCs. Overall the robust performance of the ML approach in our study sets the stage for generalizing it to other endothelial proteins and experimental conditions, a first step toward a universal microfluidic ML framework targeting blood disorders. Such a framework would not only be able to integrate advanced biophysical characterization into fast, point-of-care diagnostic devices, but also provide a standardized and reliable way of monitoring patients undergoing targeted therapies and curative interventions, including, stem cell and gene-based therapies for SCD. Disclosures Gurkan: Dx Now Inc.: Patents & Royalties; Xatek Inc.: Patents & Royalties; BioChip Labs: Patents & Royalties; Hemex Health, Inc.: Consultancy, Current Employment, Patents & Royalties, Research Funding.« less
  2. Organisms switch their genes on and off to adapt to changing environments. This takes place thanks to complex networks of regulators that control which genes are actively ‘read’ by the cell to create the RNA molecules that are needed at the time. Piecing together these networks is key to fully understand the inner workings of living organisms, and how to potentially modify or artificially create them. Single-cell RNA sequencing is a powerful new tool that can measure which genes are turned on (or ‘expressed’) in an individual cell. Datasets with millions of gene expression profiles for individual cells now existmore »for organisms such as mice or humans. Yet, it is difficult to use these data to reconstruct networks of regulators; this is partly because scientists are not sure if the computational methods normally used to build these networks also work for single-cell RNA sequencing data. One way to check if this is the case is to use the methods on single-cell datasets from organisms where the networks of regulators are already known, and check whether the computational tools help to reach the same conclusion. Unfortunately, the regulatory networks in the organisms for which scientists have a lot of single-cell RNA sequencing data are still poorly known. There are living beings in which the networks are well characterised – such as yeast – but it has been difficult to do single-cell sequencing in them at the scale seen in other organisms. Jackson, Castro et al. first adapted a system for single-cell sequencing so that it would work in yeast. This generated a gene expression dataset of over 40,000 yeast cells. They then used a computational method (called the Inferelator) on these data to construct networks of regulators, and the results showed that the method performed well. This allowed Jackson, Castro et al. to start mapping how different networks connect, for example those that control the response to the environment and cell division. This is one of the benefits of single-cell RNA methods: cell division for example is not a process that can be examined at the level of a population, since the cells may all be at different life stages. In the future, the dataset will also be useful to scientists to benchmark a variety of single cell computational tools.« less
  3. null (Ed.)
    Large, comprehensive collections of single-cell RNA sequencing (scRNA-seq) datasets have been generated that allow for the full transcriptional characterization of cell types across a wide variety of biological and clinical conditions. As new methods arise to measure distinct cellular modalities, a key analytical challenge is to integrate these datasets or transfer knowledge from one to the other to better understand cellular identity and functions. Here, we present a simple yet surprisingly effective method named common factor integration and transfer learning (cFIT) for capturing various batch effects across experiments, technologies, subjects, and even species. The proposed method models the shared informationmore »between various datasets by a common factor space while allowing for unique distortions and shifts in genewise expression in each batch. The model parameters are learned under an iterative nonnegative matrix factorization (NMF) framework and then used for synchronized integration from across-domain assays. In addition, the model enables transferring via low-rank matrix from more informative data to allow for precise identification in data of lower quality. Compared with existing approaches, our method imposes weaker assumptions on the cell composition of each individual dataset; however, it is shown to be more reliable in preserving biological variations. We apply cFIT to multiple scRNA-seq datasets of developing brain from human and mouse, varying by technologies and developmental stages. The successful integration and transfer uncover the transcriptional resemblance across systems. The study helps establish a comprehensive landscape of brain cell-type diversity and provides insights into brain development.« less
  4. Abstract Cell–cell interactions (CCIs) are essential for multicellular organisms to coordinate biological processes and functions. One classical type of CCI interaction is between secreted ligands and cell surface receptors, i.e. ligand-receptor (LR) interactions. With the recent development of single-cell technologies, a large amount of single-cell ribonucleic acid (RNA) sequencing (scRNA-Seq) data has become widely available. This data availability motivated the single-cell-resolution study of CCIs, particularly LR-based CCIs. Dozens of computational methods and tools have been developed to predict CCIs by identifying LR-based CCIs. Many of these tools have been theoretically reviewed. However, there is little study on current LR-based CCImore »prediction tools regarding their performance and running results on public scRNA-Seq datasets. In this work, to fill this gap, we tested and compared nine of the most recent computational tools for LR-based CCI prediction. We used 15 well-studied scRNA-Seq samples that correspond to approximately 100K single cells under different experimental conditions for testing and comparison. Besides briefing the methodology used in these nine tools, we summarized the similarities and differences of these tools in terms of both LR prediction and CCI inference between cell types. We provided insight into using these tools to make meaningful discoveries in understanding cell communications.« less
  5. Abstract

    Single-cell RNA-seq (scRNASeq) has become a powerful technique for measuring the transcriptome of individual cells. Unlike the bulk measurements that average the gene expressions over the individual cells, gene measurements at individual cells can be used to study several different tissues and organs at different stages. Identifying the cell types present in the sample from the single cell transcriptome data is a common goal in many single-cell experiments. Several methods have been developed to do this. However, correctly identifying the true cell types remains a challenge. We present a framework that addresses this problem. Our hypothesis is that themore »meaningful characteristics of the data will remain despite small perturbations of data. We validate the performance of the proposed method on eight publicly available scRNA-seq datasets with known cell types as well as five simulation datasets with different degrees of the cluster separability. We compare the proposed method with five other existing methods: RaceID, SNN-Cliq, SINCERA, SEURAT, and SC3. The results show that the proposed method performs better than the existing methods.

    « less