A copula based topology preserving graph convolution network for clustering of single-cell RNA-seq data

Annotation of cells in single-cell clustering requires a homogeneous grouping of cell populations. There are various issues in single cell sequencing that effect homogeneous grouping (clustering) of cells, such as small amount of starting RNA, limited per-cell sequenced reads, cell-to-cell variability due to cell-cycle, cellular morphology, and variable reagent concentrations. Moreover, single cell data is susceptible to technical noise, which affects the quality of genes (or features) selected/extracted prior to clustering. Here we introduce sc-CGconv (copula based graph convolution network for single cell clustering), a stepwise robust unsupervised feature extraction and clustering approach that formulates and aggregates cell–cell relationships using copula correlation (Ccor), followed by a graph convolution network based clustering approach. sc-CGconv formulates a cell-cell graph using Ccor that is learned by a graph-based artificial intelligence model, graph convolution network. The learned representation (low dimensional embedding) is utilized for cell clustering. sc-CGconv features the following advantages. a. sc-CGconv works with substantially smaller sample sizes to identify homogeneous clusters. b. sc-CGconv can model the expression co-variability of a large number of genes, thereby outperforming state-of-the-art gene selection/extraction methods for clustering. c. sc-CGconv preserves the cell-to-cell variability within the selected gene set by constructing a cell-cell graph through copula correlation measure. d. sc-CGconv provides a topology-preserving embedding of cells in low dimensional space. The source code and usage information are available at https://github.com/Snehalikalall/CopulaGCN .

A topology-preserving dimensionality reduction method for single-cell RNA-seq data using graph autoencoder

Dimensionality reduction is crucial for the visualization and interpretation of the high-dimensional single-cell RNA sequencing (scRNA-seq) data. However, preserving topological structure among cells to low dimensional space remains a challenge. Here, we present the single-cell graph autoencoder (scGAE), a dimensionality reduction method that preserves topological structure in scRNA-seq data. scGAE builds a cell graph and uses a multitask-oriented graph autoencoder to preserve topological structure information and feature information in scRNA-seq data simultaneously. We further extended scGAE for scRNA-seq data visualization, clustering, and trajectory inference. Analyses of simulated data showed that scGAE accurately reconstructs developmental trajectory and separates discrete cell clusters under different scenarios, outperforming recently developed deep learning methods. Furthermore, implementation of scGAE on empirical data showed scGAE provided novel insights into cell developmental lineages and preserved inter-cluster distances.

CGAT: Cell Graph ATtention Network for Grading of Pancreatic Disease Histology Images

Early detection of Pancreatic Ductal Adenocarcinoma (PDAC), one of the most aggressive malignancies of the pancreas, is crucial to avoid metastatic spread to other body regions. Detection of pancreatic cancer is typically carried out by assessing the distribution and arrangement of tumor and immune cells in histology images. This is further complicated due to morphological similarities with chronic pancreatitis (CP), and the co-occurrence of precursor lesions in the same tissue. Most of the current automated methods for grading pancreatic cancers rely on extensive feature engineering involving accurate identification of cell features or utilising single number spatially informed indices for grading purposes. Moreover, sophisticated methods involving black-box approaches, such as neural networks, do not offer insights into the model’s ability to accurately identify the correct disease grade. In this paper, we develop a novel cell-graph based Cell-Graph Attention (CGAT) network for the precise classification of pancreatic cancer and its precursors from multiplexed immunofluorescence histology images into the six different types of pancreatic diseases. The issue of class imbalance is addressed through bootstrapping multiple CGAT-nets, while the self-attention mechanism facilitates visualization of cell-cell features that are likely responsible for the predictive capabilities of the model. It is also shown that the model significantly outperforms the decision tree classifiers built using spatially informed metric, such as the Morisita-Horn (MH) indices.

Cell graph neural networks enable the digital staging of tumor microenvironment and precise prediction of patient survival in gastric cancer

ABSTRACTGastric cancer is one of the deadliest cancers worldwide. Accurate prognosis is essential for effective clinical assessment and treatment. Spatial patterns in the tumor microenvironment (TME) are conceptually indicative of the staging and progression of gastric cancer patients. Using spatial patterns of the TME by integrating and transforming the multiplexed immunohistochemistry (mIHC) images as Cell-Graphs, we propose a novel graph neural network-based approach, termed Cell-Graph Signature or CGSignature, powered by artificial intelligence, for digital staging of TME and precise prediction of patient survival in gastric cancer. In this study, patient survival prediction is formulated as either a binary (short-term and long-term) or ternary (short-term, medium-term, and long-term) classification task. Extensive benchmarking experiments demonstrate that the CGSignature achieves outstanding model performance, with Area Under the Receiver-Operating Characteristic curve (AUROC) of 0.960±0.01, and 0.771±0.024 to 0.904±0.012 for the binary- and ternary-classification, respectively. Moreover, Kaplan-Meier survival analysis indicates that the ‘digital-grade’ cancer staging produced by CGSignature provides a remarkable capability in discriminating both binary and ternary classes with statistical significance (p-value < 0.0001), significantly outperforming the AJCC 8th edition Tumor-Node-Metastasis staging system. Using Cell-Graphs extracted from mIHC images, CGSignature improves the assessment of the link between the TME spatial patterns and patient prognosis. Our study suggests the feasibility and benefits of such artificial intelligence-powered digital staging system in diagnostic pathology and precision oncology.

scGAE: topology-preserving dimensionality reduction for single-cell RNA-seq data using graph autoencoder

ABSTRACTDimensionality reduction is crucial for the visualization and interpretation of the high-dimensional single-cell RNA sequencing (scRNA-seq) data. However, preserving topological structure among cells to low dimensional space remains a challenge. Here, we present the single-cell graph autoencoder (scGAE), a dimensionality reduction method that preserves topological structure in scRNA-seq data. scGAE builds a cell graph and uses a multitask-oriented graph autoencoder to preserve topological structure information and feature information in scRNA-seq data simultaneously. We further extended scGAE for scRNA-seq data visualization, clustering, and trajectory inference. Analyses of simulated data showed that scGAE accurately reconstructs developmental trajectory and separates discrete cell clusters under different scenarios, outperforming recently developed deep learning methods. Furthermore, implementation of scGAE on empirical data showed scGAE provided novel insights into cell developmental lineages and preserved inter-cluster distances.

Predicting cell fate commitment of embryonic differentiation by single-cell graph entropy

Cell fate commitment occurs during early embryonic development, that is, the embryonic differentiation sometimes undergoes a critical phase transition or “tipping point” of cell fate commitment, at which there is a drastic or qualitative shift of the cell populations. In this study, we presented a novel computational approach, the single-cell graph entropy (SGE), to explore the gene-gene associations among cell populations based on single-cell RNA sequencing (scRNA-seq) data. Specifically, by transforming the sparse and fluctuating gene expression data to the stable local network entropy, the SGE score quantitatively characterizes the criticality of gene regulatory networks among cell populations, and thus can be employed to predict the tipping point of cell fate or lineage commitment at the single cell level. The proposed SGE method was applied to five scRNA-seq datasets. For all these datasets of embryonic differentiation, SGE effectively captures the signal of the impending cell fate transitions, which cannot be detected by gene expressions. Some “dark” genes that are non-differential but sensitive to SGE values were revealed. The successful identification of critical transition for all five datasets demonstrates the effectiveness of our method in analyzing scRNA-seq data from a network perspective, and the potential of SGE to track the dynamics of cell differentiation.