Search

Motivation Clustering spatial-resolved gene expression is an essential analysis to reveal gene activities in the underlying morphological context by their functional roles. However, conventional clustering analysis does not consider gene expression co-localizations in tissue for detecting spatial expression patterns or functional relationships among the genes for biological interpretation in the spatial context. In this article, we present a convolutional neural network (CNN) regularized by the graph of protein–protein interaction (PPI) network to cluster spatially resolved gene expression. This method improves the coherence of spatial patterns and provides biological interpretation of the gene clusters in the spatial context by exploiting the spatial localization by convolution and gene functional relationships by graph-Laplacian regularization. Results In this study, we tested clustering the spatially variable genes or all expressed genes in the transcriptome in 22 Visium spatial transcriptomics datasets of different tissue sections publicly available from 10× Genomics and spatialLIBD. The results demonstrate that the PPI-regularized CNN constantly detects gene clusters with coherent spatial patterns and significantly enriched by gene functions with the state-of-the-art performance. Additional case studies on mouse kidney tissue and human breast cancer tissue suggest that the PPI-regularized CNN also detects spatially co-expressed genes to define the corresponding morphological context in the tissue with valuable insights. Availability and implementation Source code is available at https://github.com/kuanglab/CNN-PReg. Supplementary information Supplementary data are available at Bioinformatics online.

Single-cell RNAsequencing (scRNA-seq) technologies have enabled the large-scale whole-transcriptome profiling of each individual single cell in a cell population. A core analysis of the scRNA-seq transcriptome profiles is to cluster the single cells to reveal cell subtypes and infer cell lineages based on the relations among the cells. This article reviews the machine learning and statistical methods for clustering scRNA-seq transcriptomes developed in the past few years. The review focuses on how conventional clustering techniques such as hierarchical clustering, graph-based clustering, mixture models, $k$-means, ensemble learning, neural networks and density-based clustering are modified or customized to tackle the unique challenges in scRNA-seq data analysis, such as the dropout of low-expression genes, low and uneven read coverage of transcripts, highly variable total mRNAs from single cells and ambiguous cell markers in the presence of technical biases and irrelevant confounding biological variations. We review how cell-specific normalization, the imputation of dropouts and dimension reduction methods can be applied with new statistical or optimization strategies to improve the clustering of single cells. We will also introduce those more advanced approaches to cluster scRNA-seq transcriptomes in time series data and multiple cell populations and to detect rare cell types. Several software packages developed to support the cluster analysis of scRNA-seq data are also reviewed and experimentally compared to evaluate their performance and efficiency. Finally, we conclude with useful observations and possible future directions in scRNA-seq data analytics. Availability All the source code and data are available at https://github.com/kuanglab/single-cell-review.

The global connectivities in very large protein similarity networks contain traces of evolution among the proteins for detecting protein remote evolutionary relations or structural similarities. To investigate how well a protein network captures the evolutionary information, a key limitation is the intensive computation of pairwise sequence similarities needed to construct very large protein networks. In this article, we introduce label propagation on low-rank kernel approximation (LP-LOKA) for searching massively large protein networks. LP-LOKA propagates initial protein similarities in a low-rank graph by Nyström approximation without computing all pairwise similarities. With scalable parallel implementations based on distributed-memory using message-passing interface and Apache-Hadoop/Spark on cloud, LP-LOKA can search protein networks with one million proteins or more. In the experiments on Swiss-Prot/ADDA/CASP data, LP-LOKA significantly improved protein ranking over the widely used HMM-HMM or profile-sequence alignment methods utilizing large protein networks. It was observed that the larger the protein similarity network, the better the performance, especially on relatively small protein superfamilies and folds. The results suggest that computing massively large protein network is necessary to meet the growing need of annotating proteins from newly sequenced species and LP-LOKA is both scalable and accurate for searching massively large protein networks.

BackgroundPrediction of which traumatic and hypoxic brain injuries will progress to brain death is currently based predominantly on history, physical examination and radiographic findings. We investigated how accurately purely objective measures including three neurologic serum markers and algorithmic CT (computed tomograph) scan analysis can predict brain death and differentiate its etiology.MethodsThis prospective observational study enrolled 51 isolated trauma subjects and 19 clinically brain dead subjects that were further divided by mechanism of injury into high-velocity trauma with presumed diffuse axonal injury, cardiopulmonary/respiratory arrest, and found down groups. Levels of glial fibrillary acidic protein (GFAP), ubiquitin carboxy-terminal hydrolase L1 (UCH-L1), and S100 Calcium-Binding Protein B (S100B) were compared, and algorithmic analysis of CT scan imaging was performed using an open-source deep learning software (BLAST-CT).FindingsThe prognostic value of various biomarker combinations in identifying subjects progressing to brain death was assessed using machine learning. Prediction accuracy for GFAP, UCH-L1, and S100B and algorithmic CT analysis in combination to predict brain death from among all other cohorts yielded an area under the receiver operator curve of 0.98 versus all other brain injury subjects. This model was also able to distinguish brain death attributed to cardiopulmonary/respiratory arrest from combined non-trauma controls and diffuse axonal injury with an area under the curve of 0.99.InterpretationSerum concentrations of GFAP, UCH-L1, and S100B measured within 32 hours of traumatic and hypoxic brain injury (cardiopulmonary/respiratory arrest) and algorithmic CT analysis have utility in prognosticating brain death and predicting its mechanism of injury as either hypoxic or traumatic/unknown (diffuse axonal injury/found down).FundingAbbott Labs and the Minnesota State Office of Higher Education.

BackgroundBrain injury is pathophysiologically diverse, with many cases presenting with mixed pathologies. Utilizing objective measures to investigate the pathophysiology of injury would aid in understanding prognosis and targeting therapeutics.ObjectiveThe goal of this study is to develop a traumatic brain injury classification scheme based on open source deep learning computer tomography (CT) analysis and the two serum biomarkers, glial fibrillary acidic protein (GFAP) and ubiquitin carboxy-terminal L1 (UCH-L1).MethodsMachine learning was utilized to develop a novel algorithm capable of classifying the type of brain injury based on a CT scan analysis algorithm and GFAP and UCH-L1 concentrations. Injury was stratified into one of four groups: spontaneous hemorrhage, oxygen deprivation, trauma resulting in vascular injury or high-velocity trauma with negative CT scan.Outcomes100 research subjects were enrolled. Using a combination of CT analysis and serum markers, the subjects with CT positive trauma were distinguishable from those with spontaneous hemorrhage, ischemic injury, CT negative trauma and controls with AUCs of 0.96, 0.99., 0.98 and 1.00 respectively. Ischemic injury was distinguishable from CT positive trauma with an AUC of 0.98. All forms of brain injury could be distinguished from controls with AUC = 1.00.DiscussionAn open source algorithmic CT scan analysis algorithm and serum biomarkers accurately classified the nature of brain injury across major etiologies. Further implementation of such algorithms and addition of other objective measures will enable better prognostication of injury and improved development of therapeutics.

High-throughput spatial-transcriptomics RNA sequencing (sptRNA-seq) based on in-situ capturing technologies has recently been developed to spatially resolve transcriptome-wide mRNA expressions mapped to the captured locations in a tissue sample. Due to the low RNA capture efficiency by in-situ capturing and the complication of tissue section preparation, sptRNA-seq data often only provides an incomplete profiling of the gene expressions over the spatial regions of the tissue. In this paper, we introduce a graph-regularized tensor completion model for imputing the missing mRNA expressions in sptRNA-seq data, namely FIST, Fast Imputation of Spatially-resolved transcriptomes by graph-regularized Tensor completion. We first model sptRNA-seq data as a 3-way sparse tensor in genes (p-mode) and the (x, y) spatial coordinates (x-mode and y-mode) of the observed gene expressions, and then consider the imputation of the unobserved entries or fibers as a tensor completion problem in Canonical Polyadic Decomposition (CPD) form. To improve the imputation of highly sparse sptRNA-seq data, we also introduce a protein-protein interaction network to add prior knowledge of gene functions, and a spatial graph to capture the the spatial relations among the capture spots. The tensor completion model is then regularized by a Cartesian product graph of protein-protein interaction network and the spatial graph to capture the high-order relations in the tensor. In the experiments, FIST was tested on ten 10x Genomics Visium spatial transcriptomic datasets of different tissue sections with cross-validation among the known entries in the imputation. FIST significantly outperformed the state-of-the-art methods for single-cell RNAseq data imputation. We also demonstrate that both the spatial graph and PPI network play an important role in improving the imputation. In a case study, we further analyzed the gene clusters obtained from the imputed gene expressions to show that the imputations by FIST indeed capture the spatial characteristics in the gene expressions and reveal functions that are highly relevant to three different kinds of tissues in mouse kidney., Author summary Biological tissues are composed of different types of structurally organized cell units playing distinct functional roles. The exciting new spatial gene expression profiling methods have enabled the analysis of spatially resolved transcriptomes to understand the spatial and functional characteristics of these cells in the context of eco-environment of tissue. Due to the technical limitations, spatial transcriptomics data suffers from only sparsely measured mRNAs by in-situ capture and possibly missing spots in tissue regions that entirely failed fixing and permeabilizing RNAs. Our method, FIST (Fast Imputation of Spatially-resolved transcriptomes by graph-regularized Tensor completion), focuses on the spatial and high-sparsity nature of spatial transcriptomics data by modeling the data as a 3-way gene-by-(x, y)-location tensor and a product graph of a spatial graph and a protein-protein interaction network. Our comprehensive evaluation of FIST on ten 10x Genomics Visium spatial genomics datasets and comparison with the methods for single-cell RNA sequencing data imputation demonstrate that FIST is a better method more suitable for spatial gene expression imputation. Overall, we found FIST a useful new method for analyzing spatially resolved gene expressions based on novel modeling of spatial and functional information.

Learning pharmacogenomic multi-relations among diseases, genes and chemicals from content-rich biomedical and biological networks can provide important guidance for drug discovery, drug repositioning and disease treatment. Most of the existing methods focus on imputing missing values in the disease-gene, disease chemical and gene-chemical pairwise relations from the observed relations instead of being designed for learning high-order disease-gene-chemical multi-relations. To achieve the goal, we propose a general tensor-based optimization framework and a scalable Graph-Regularized Tensor Completion from Observed Pairwise Relations (GT-COPR) algorithm to infer the multi-relations among the entities across multiple networks in a low-rank tensor, based on manifold regularization with the graph Laplacian of a Cartesian, tensor or strong product of the networks, and consistencies between the collapsed tensors and the observed bipartite relations. Our theoretical analyses also prove the convergence and efficiency of GT-COPR. In the experiments, the tensor fiber-wise and slice-wise evaluations demonstrate the accuracy of GT-COPR for predicting the diseasegene-chemical associations across the large-scale protein-protein interactions network, chemical structural similarity network and phenotype-based human disease network; and the validation on Genomics of Drug Sensitivity in Cancer cell line dataset shows a potential clinical application of GT-COPR for learning diseasespecific chemical-gene interactions. Statistical enrichment analysis demonstrates that GT-COPR is also capable of producing both topologically and biologically relevant disease, gene and chemical components with high significance.

Single-cell RNA sequencing (scRNA-seq) has been widely applied to discover new cell types by detecting sub-populations in a heterogeneous group of cells. Since scRNA-seq experiments have lower read coverage/tag counts and introduce more technical biases compared to bulk RNA-seq experiments, the limited number of sampled cells combined with the experimental biases and other dataset specific variations presents a challenge to cross-dataset analysis and discovery of relevant biological variations across multiple cell populations. In this paper, we introduce a method of variance-driven multitask clustering of single-cell RNA-seq data (scVDMC) that utilizes multiple single-cell populations from biological replicates or different samples. scVDMC clusters single cells in multiple scRNA-seq experiments of similar cell types and markers but varying expression patterns such that the scRNA-seq data are better integrated than typical pooled analyses which only increase the sample size. By controlling the variance among the cell clusters within each dataset and across all the datasets, scVDMC detects cell sub-populations in each individual experiment with shared cell-type markers but varying cluster centers among all the experiments. Applied to two real scRNA-seq datasets with several replicates and one large-scale droplet-based dataset on three patient samples, scVDMC more accurately detected cell populations and known cell markers than pooled clustering and other recently proposed scRNA-seq clustering methods. In the case study applied to in-house Recessive Dystrophic Epidermolysis Bullosa (RDEB) scRNA-seq data, scVDMC revealed several new cell types and unknown markers validated by flow cytometry. MATLAB/Octave code available at https://github.com/kuanglab/scVDMC., Author summary scRNA-seq enables detailed profiling of heterogeneous cell populations and can be used to reveal lineage relationships or discover new cell types. In the literature, there has been little effort directed towards developing computational methods for cross-population transcriptome analysis of multiple single-cell populations. The cross-cell-population clustering problem is different from the traditional clustering problem because single-cell populations can be collected from different patients, different samples of a tissue, or different experimental replicates. The accompanying biological and technical variation tends to dominate the signals for clustering the pooled single cells from the multiple populations. In this work, we have developed a multitask clustering method to address the cross-population clustering problem. The method simultaneously clusters each individual cell population and controls variance among the cell-type cluster centers within each cell population and across the cell populations. We demonstrate that our multitask clustering method significantly improves clustering accuracy and marker discovery in three public scRNA-seq datasets and also apply the method to an in-house Recessive Dystrophic Epidermolysis Bullosa (RDEB) dataset. Our results make it evident that multitask clustering is a promising new approach for cross-population analysis of scRNA-seq data.

Multi-relational learning on knowledge graphs infers high-order relations among the entities across the graphs. This learning task can be solved by label propagation on the tensor product of the knowledge graphs to learn the high-order relations as a tensor. In this paper, we generalize a widely used label propagation model to the normalized tensor product graph, and propose an optimization formulation and a scalable Low-rank Tensor-based Label Propagation algorithm (LowrankTLP) to infer multi-relations for two learning tasks, hyperlink prediction and multiple graph alignment. The optimization formulation minimizes the upper bound of the noisy tensor estimation error for multiple graph alignment, by learning with a subset of the eigen-pairs in the spectrum of the normalized tensor product graph. We also provide a data-dependent transductive Rademacher bound for binary hyperlink prediction. We accelerate LowrankTLP with parallel tensor computation which enables label propagation on a tensor product of 100 graphs each of size 1000 in less than half hour in the simulation. LowrankTLP was also applied to predicting the author-paper-venue hyperlinks in publication records, alignment of segmented regions across up to 26 CT-scan images and alignment of protein-protein interaction networks across multiple species. The experiments demonstrate that LowrankTLP indeed well approximates the original label propagation with better scalability and accuracy., Comment: 9 pages, 6 figures

Full-duplex MIMO relays can provide cost-effective coverage and higher spectral efficiency, but simultaneous reception and transmission in the same frequency band could make relays prone to oscillate. Because the loop back channel response matrix is frequently full rank, conventional spatial loop interference suppression techniques using receive and transmit filters are not feasible. This paper presents an algorithm which uses the null space projection and subspace projection to enhance the loop interference mitigation. Meanwhile, the multipath propagation of loop interference channel is also taken into account. Analysis and simulation proved that the proposed algorithm outperforms conventional algorithms. Especially, even though the loop back channel matrix is full rank, the proposed algorithm can still completely suppress the loop interference.