Learning common and specific patterns from data of multiple interrelated biological scenarios with matrix factorization

A new Bayesian factor analysis method improves detection of genes and biological processes affected by perturbations in single-cell CRISPR screening

Clustered regularly interspaced short palindromic repeats (CRISPR) screening coupled with single-cell RNA sequencing has emerged as a powerful tool to characterize the effects of genetic perturbations on the whole transcriptome at a single-cell level. However, due to its sparsity and complex structure, analysis of single-cell CRISPR screening data is challenging. In particular, standard differential expression analysis methods are often underpowered to detect genes affected by CRISPR perturbations. We developed a statistical method for such data, called guided sparse factor analysis (GSFA). GSFA infers latent factors that represent coregulated genes or gene modules; by borrowing information from these factors, it infers the effects of genetic perturbations on individual genes. We demonstrated through extensive simulation studies that GSFA detects perturbation effects with much higher power than state-of-the-art methods. Using single-cell CRISPR data from human CD8+ T cells and neural progenitor cells, we showed that GSFA identified biologically relevant gene modules and specific genes affected by CRISPR perturbations, many of which were missed by existing methods, providing new insights into the functions of genes involved in T cell activation and neurodevelopment.

Computational Methods for Single-cell DNA Methylome Analysis

Dissecting intercellular epigenetic differences is key to understanding tissue heterogeneity. Recent advances in single-cell DNA methylome profiling have presented opportunities to resolve this heterogeneity at the maximum resolution. While these advances enable us to explore frontiers of chromatin biology and better understand cell lineage relationships, they pose new challenges in data processing and interpretation. This review surveys the current state of computational tools developed for single-cell DNA methylome data analysis. We discuss critical components of single-cell DNA methylome data analysis, including data preprocessing, quality control, imputation, dimensionality reduction, cell clustering, supervised cell annotation, cell lineage reconstruction, gene activity scoring, and integration with transcriptome data. We also highlight unique aspects of single-cell DNA methylome data analysis and discuss how techniques common to other single-cell omics data analyses can be adapted to analyze DNA methylomes. Finally, we discuss existing challenges and opportunities for future development.

Cross-species cell-type assignment from single-cell RNA-seq data by a heterogeneous graph neural network

Cross-species comparative analyses of single-cell RNA sequencing (scRNA-seq) data allow us to explore, at single-cell resolution, the origins of the cellular diversity and evolutionary mechanisms that shape cellular form and function. Cell-type assignment is a crucial step to achieve that. However, the poorly annotated genome and limited known biomarkers hinder us from assigning cell identities for nonmodel species. Here, we design a heterogeneous graph neural network model, CAME, to learn aligned and interpretable cell and gene embeddings for cross-species cell-type assignment and gene module extraction from scRNA-seq data. CAME achieves significant improvements in cell-type characterization across distant species owing to the utilization of non-one-to-one homologous gene mapping ignored by early methods. Our large-scale benchmarking study shows that CAME significantly outperforms five classical methods in terms of cell-type assignment and model robustness to insufficiency and inconsistency of sequencing depths. CAME can transfer the major cell types and interneuron subtypes of human brains to mouse and discover shared cell-type-specific functions in homologous gene modules. CAME can align the trajectories of human and macaque spermatogenesis and reveal their conservative expression dynamics. In short, CAME can make accurate cross-species cell-type assignments even for nonmodel species and uncover shared and divergent characteristics between two species from scRNA-seq data.

The scINSIGHT Package for Integrating Single-Cell RNA-Seq Data from Different Biological Conditions

Data integration is a critical step in the analysis of multiple single-cell RNA sequencing samples to account for heterogeneity due to both biological and technical variability. scINSIGHT is a new integration method for single-cell gene expression data, and can effectively use the information of biological condition to improve the integration of multiple single-cell samples. scINSIGHT is based on a novel non-negative matrix factorization model that learns common and condition-specific gene modules in samples from different biological or experimental conditions. Using these gene modules, scINSIGHT can further identify cellular identities and active biological processes in different cell types or conditions. Here we introduce the installation and main functionality of the scINSIGHT R package, including how to preprocess the data, apply the scINSIGHT algorithm, and analyze the output.

Monitoring Wound Healing with Topically Applied Optical NanoFlare mRNA Nanosensors

An effective wound management strategy needs accurate assessment of wound status throughout the whole healing process. This can be achieved by examining molecular biomarkers including proteins, DNAs, and RNAs. However, existing methods for quantifying these biomarkers such as immunohistochemistry and quantitative polymerase chain reaction are usually laborious, resource-intensive, and disruptive. This article reports the development and utilization of mRNA nanosensors (i.e., NanoFlare) that are topically applied on cutaneous wounds to reveal the healing status through targeted and semi-quantitative examination of the mRNA biomarkers in skin cells. In 2D and 3D in vitro models, the efficacy and efficiency of these nanosensors are demonstrated in revealing the dynamic changes of mRNA biomarkers for different stages of wound development. In mouse models, this platform permits the tracking and identification of wound healing stages and a normal and diabetic wound healing process by wound healing index in real time.

Shared and Cell-Type-Specific Gene Expression Patterns Associated With Autism Revealed by Integrative Regularized Non-Negative Matrix Factorization

Human brain-related disorders, such as autism spectrum disorder (ASD), are often characterized by cell heterogeneity, as the cell atlas of brains consists of diverse cell types. There are commonality and specificity in gene expression among different cell types of brains; hence, there may also be commonality and specificity in dysregulated gene expression affected by ASD among brain cells. Moreover, as genes interact together, it is important to identify shared and cell-type-specific ASD-related gene modules for studying the cell heterogeneity of ASD. To this end, we propose integrative regularized non-negative matrix factorization (iRNMF) by imposing a new regularization based on integrative non-negative matrix factorization. Using iRNMF, we analyze gene expression data of multiple cell types of the human brain to obtain shared and cell-type-specific gene modules. Based on ASD risk genes, we identify shared and cell-type-specific ASD-associated gene modules. By analyzing these gene modules, we study the commonality and specificity among different cell types in dysregulated gene expression affected by ASD. The shared ASD-associated gene modules are mostly relevant to the functioning of synapses, while in different cell types, different kinds of gene functions may be specifically dysregulated in ASD, such as inhibitory extracellular ligand-gated ion channel activity in GABAergic interneurons and excitatory postsynaptic potential and ionotropic glutamate receptor signaling pathway in glutamatergic neurons. Our results provide new insights into the molecular mechanism and pathogenesis of ASD. The identification of shared and cell-type-specific ASD-related gene modules can facilitate the development of more targeted biomarkers and treatments for ASD.

MOMA: a multi-task attention learning algorithm for multi-omics data interpretation and classification

MOTIVATION

Accurate diagnostic classification and biological interpretation are important in biology and medicine, which are data-rich sciences. Thus, integration of different data types is necessary for the high predictive accuracy of clinical phenotypes, and more comprehensive analyses for predicting the prognosis of complex diseases are required.

RESULTS

Here, we propose a novel multi-task attention learning algorithm for multi-omics data, termed MOMA, which captures important biological processes for high diagnostic performance and interpretability. MOMA vectorizes features and modules using a geometric approach and focuses on important modules in multi-omics data via an attention mechanism. Experiments using public data on Alzheimer's disease and cancer with various classification tasks demonstrated the superior performance of this approach. The utility of MOMA was also verified using a comparison experiment with an attention mechanism that was turned on or off and biological analysis.

AVAILABILITY AND IMPLEMENTATION

The source codes are available at https://github.com/dmcb-gist/MOMA.

SUPPLEMENTARY INFORMATION

Supplementary materials are available at Bioinformatics online.

scINSIGHT for interpreting single-cell gene expression from biologically heterogeneous data

The increasing number of scRNA-seq data emphasizes the need for integrative analysis to interpret similarities and differences between single-cell samples. Although different batch effect removal methods have been developed, none are suitable for heterogeneous single-cell samples coming from multiple biological conditions. We propose a method, scINSIGHT, to learn coordinated gene expression patterns that are common among, or specific to, different biological conditions, and identify cellular identities and processes across single-cell samples. We compare scINSIGHT with state-of-the-art methods using simulated and real data, which demonstrate its improved performance. Our results show the applicability of scINSIGHT in diverse biomedical and clinical problems.

Matrix factorization for biomedical link prediction and scRNA-seq data imputation: an empirical survey

Advances in high-throughput experimental technologies promote the accumulation of vast number of biomedical data. Biomedical link prediction and single-cell RNA-sequencing (scRNA-seq) data imputation are two essential tasks in biomedical data analyses, which can facilitate various downstream studies and gain insights into the mechanisms of complex diseases. Both tasks can be transformed into matrix completion problems. For a variety of matrix completion tasks, matrix factorization has shown promising performance. However, the sparseness and high dimensionality of biomedical networks and scRNA-seq data have raised new challenges. To resolve these issues, various matrix factorization methods have emerged recently. In this paper, we present a comprehensive review on such matrix factorization methods and their usage in biomedical link prediction and scRNA-seq data imputation. Moreover, we select representative matrix factorization methods and conduct a systematic empirical comparison on 15 real data sets to evaluate their performance under different scenarios. By summarizing the experimental results, we provide general guidelines for selecting matrix factorization methods for different biomedical matrix completion tasks and point out some future directions to further improve the performance for biomedical link prediction and scRNA-seq data imputation.

Approximate distance correlation for selecting highly interrelated genes across datasets

With the rapid accumulation of biological omics datasets, decoding the underlying relationships of cross-dataset genes becomes an important issue. Previous studies have attempted to identify differentially expressed genes across datasets. However, it is hard for them to detect interrelated ones. Moreover, existing correlation-based algorithms can only measure the relationship between genes within a single dataset or two multi-modal datasets from the same samples. It is still unclear how to quantify the strength of association of the same gene across two biological datasets with different samples. To this end, we propose Approximate Distance Correlation (ADC) to select interrelated genes with statistical significance across two different biological datasets. ADC first obtains the k most correlated genes for each target gene as its approximate observations, and then calculates the distance correlation (DC) for the target gene across two datasets. ADC repeats this process for all genes and then performs the Benjamini-Hochberg adjustment to control the false discovery rate. We demonstrate the effectiveness of ADC with simulation data and four real applications to select highly interrelated genes across two datasets. These four applications including 21 cancer RNA-seq datasets of different tissues; six single-cell RNA-seq (scRNA-seq) datasets of mouse hematopoietic cells across six different cell types along the hematopoietic cell lineage; five scRNA-seq datasets of pancreatic islet cells across five different technologies; coupled single-cell ATAC-seq (scATAC-seq) and scRNA-seq data of peripheral blood mononuclear cells (PBMC). Extensive results demonstrate that ADC is a powerful tool to uncover interrelated genes with strong biological implications and is scalable to large-scale datasets. Moreover, the number of such genes can serve as a metric to measure the similarity between two datasets, which could characterize the relative difference of diverse cell types and technologies.

Interpretable, Scalable, and Transferrable Functional Projection of Large-Scale Transcriptome Data Using Constrained Matrix Decomposition

Large-scale transcriptome data, such as single-cell RNA-sequencing data, have provided unprecedented resources for studying biological processes at the systems level. Numerous dimensionality reduction methods have been developed to visualize and analyze these transcriptome data. In addition, several existing methods allow inference of functional variations among samples using gene sets with known biological functions. However, it remains challenging to analyze transcriptomes with reduced dimensions that are interpretable in terms of dimensions’ directionalities, transferrable to new data, and directly expose the contribution or association of individual genes. In this study, we used gene set non-negative principal component analysis (gsPCA) and non-negative matrix factorization (gsNMF) to analyze large-scale transcriptome datasets. We found that these methods provide low-dimensional information about the progression of biological processes in a quantitative manner, and their performances are comparable to existing functional variation analysis methods in terms of distinguishing multiple cell states and samples from multiple conditions. Remarkably, upon training with a subset of data, these methods allow predictions of locations in the functional space using data from experimental conditions that are not exposed to the models. Specifically, our models predicted the extent of progression and reversion for cells in the epithelial-mesenchymal transition (EMT) continuum. These methods revealed conserved EMT program among multiple types of single cells and tumor samples. Finally, we demonstrate this approach is broadly applicable to data and gene sets beyond EMT and provide several recommendations on the choice between the two linear methods and the optimal algorithmic parameters. Our methods show that simple constrained matrix decomposition can produce to low-dimensional information in functionally interpretable and transferrable space, and can be widely useful for analyzing large-scale transcriptome data.

Single cell RNA sequencing for breast cancer: present and future

Breast cancer is one of the most common malignant tumors in women. It is a heterogeneous disease related to genetic and environmental factors. Presently, the treatment of breast cancer still faces challenges due to recurrence and metastasis. The emergence of single-cell RNA sequencing (scRNA-seq) technology has brought new strategies to deeply understand the biological behaviors of breast cancer. By analyzing cell phenotypes and transcriptome differences at the single-cell level, scRNA-seq reveals the heterogeneity, dynamic growth and differentiation process of cells. This review summarizes the application of scRNA-seq technology in breast cancer research, such as in studies on cell heterogeneity, cancer cell metastasis, drug resistance, and prognosis. scRNA-seq technology is of great significance to deeply analyze the mechanism of breast cancer occurrence and development, identify new therapeutic targets and develop new therapeutic approaches for breast cancer.

DeFusion: a denoised network regularization framework for multi-omics integration

With diverse types of omics data widely available, many computational methods have been recently developed to integrate these heterogeneous data, providing a comprehensive understanding of diseases and biological mechanisms. But most of them hardly take noise effects into account. Data-specific patterns unique to data types also make it challenging to uncover the consistent patterns and learn a compact representation of multi-omics data. Here we present a multi-omics integration method considering these issues. We explicitly model the error term in data reconstruction and simultaneously consider noise effects and data-specific patterns. We utilize a denoised network regularization in which we build a fused network using a denoising procedure to suppress noise effects and data-specific patterns. The error term collaborates with the denoised network regularization to capture data-specific patterns. We solve the optimization problem via an inexact alternating minimization algorithm. A comparative simulation study shows the method's superiority at discovering common patterns among data types at three noise levels. Transcriptomics-and-epigenomics integration, in seven cancer cohorts from The Cancer Genome Atlas, demonstrates that the learned integrative representation extracted in an unsupervised manner can depict survival information. Specially in liver hepatocellular carcinoma, the learned integrative representation attains average Harrell's C-index of 0.78 in 10 times 3-fold cross-validation for survival prediction, which far exceeds competing methods, and we discover an aggressive subtype in liver hepatocellular carcinoma with this latent representation, which is validated by an external dataset GSE14520. We also show that DeFusion is applicable to the integration of other omics types.

Inference and analysis of cell-cell communication using CellChat

Understanding global communications among cells requires accurate representation of cell-cell signaling links and effective systems-level analyses of those links. We construct a database of interactions among ligands, receptors and their cofactors that accurately represent known heteromeric molecular complexes. We then develop CellChat, a tool that is able to quantitatively infer and analyze intercellular communication networks from single-cell RNA-sequencing (scRNA-seq) data. CellChat predicts major signaling inputs and outputs for cells and how those cells and signals coordinate for functions using network analysis and pattern recognition approaches. Through manifold learning and quantitative contrasts, CellChat classifies signaling pathways and delineates conserved and context-specific pathways across different datasets. Applying CellChat to mouse and human skin datasets shows its ability to extract complex signaling patterns. Our versatile and easy-to-use toolkit CellChat and a web-based Explorer ( http://www.cellchat.org/ ) will help discover novel intercellular communications and build cell-cell communication atlases in diverse tissues.

scMC learns biological variation through the alignment of multiple single-cell genomics datasets

Distinguishing biological from technical variation is crucial when integrating and comparing single-cell genomics datasets across different experiments. Existing methods lack the capability in explicitly distinguishing these two variations, often leading to the removal of both variations. Here, we present an integration method scMC to remove the technical variation while preserving the intrinsic biological variation. scMC learns biological variation via variance analysis to subtract technical variation inferred in an unsupervised manner. Application of scMC to both simulated and real datasets from single-cell RNA-seq and ATAC-seq experiments demonstrates its capability of detecting context-shared and context-specific biological signals via accurate alignment.

MHSNMF: multi-view hessian regularization based symmetric nonnegative matrix factorization for microbiome data analysis

BACKGROUND

With the rapid development of high-throughput technique, multiple heterogeneous omics data have been accumulated vastly (e.g., genomics, proteomics and metabolomics data). Integrating information from multiple sources or views is challenging to obtain a profound insight into the complicated relations among micro-organisms, nutrients and host environment. In this paper we propose a multi-view Hessian regularization based symmetric nonnegative matrix factorization algorithm (MHSNMF) for clustering heterogeneous microbiome data. Compared with many existing approaches, the advantages of MHSNMF lie in: (1) MHSNMF combines multiple Hessian regularization to leverage the high-order information from the same cohort of instances with multiple representations; (2) MHSNMF utilities the advantages of SNMF and naturally handles the complex relationship among microbiome samples; (3) uses the consensus matrix obtained by MHSNMF, we also design a novel approach to predict the classification of new microbiome samples.

RESULTS

We conduct extensive experiments on two real-word datasets (Three-source dataset and Human Microbiome Plan dataset), the experimental results show that the proposed MHSNMF algorithm outperforms other baseline and state-of-the-art methods. Compared with other methods, MHSNMF achieves the best performance (accuracy: 95.28%, normalized mutual information: 91.79%) on microbiome data. It suggests the potential application of MHSNMF in microbiome data analysis.

CONCLUSIONS

Results show that the proposed MHSNMF algorithm can effectively combine the phylogenetic, transporter, and metabolic profiles into a unified paradigm to analyze the relationships among different microbiome samples. Furthermore, the proposed prediction method based on MHSNMF has been shown to be effective in judging the types of new microbiome samples.

MOFA+: a statistical framework for comprehensive integration of multi-modal single-cell data

Technological advances have enabled the profiling of multiple molecular layers at single-cell resolution, assaying cells from multiple samples or conditions. Consequently, there is a growing need for computational strategies to analyze data from complex experimental designs that include multiple data modalities and multiple groups of samples. We present Multi-Omics Factor Analysis v2 (MOFA+), a statistical framework for the comprehensive and scalable integration of single-cell multi-modal data. MOFA+ reconstructs a low-dimensional representation of the data using computationally efficient variational inference and supports flexible sparsity constraints, allowing to jointly model variation across multiple sample groups and data modalities.

Horizontal and vertical integrative analysis methods for mental disorders omics data

In recent biomedical studies, omics profiling has been extensively conducted on various types of mental disorders. In most of the existing analyses, a single type of mental disorder and a single type of omics measurement are analyzed. In the study of other complex diseases, integrative analysis, both vertical and horizontal integration, has been conducted and shown to bring significantly new insights into disease etiology, progression, biomarkers, and treatment. In this article, we showcase the applicability of integrative analysis to mental disorders. In particular, the horizontal integration of bipolar disorder and schizophrenia and the vertical integration of gene expression and copy number variation data are conducted. The analysis is based on the sparse principal component analysis, penalization, and other advanced statistical techniques. In data analysis, integration leads to biologically sensible findings, including the disease-related gene expressions, copy number variations, and their associations, which differ from the “benchmark” analysis. Overall, this study suggests the potential of integrative analysis in mental disorder research.