Statistical single cell multi-omics integration

MOCAT: multi-omics integration with auxiliary classifiers enhanced autoencoder

BACKGROUND

Integrating multi-omics data is emerging as a critical approach in enhancing our understanding of complex diseases. Innovative computational methods capable of managing high-dimensional and heterogeneous datasets are required to unlock the full potential of such rich and diverse data.

METHODS

We propose a Multi-Omics integration framework with auxiliary Classifiers-enhanced AuToencoders (MOCAT) to utilize intra- and inter-omics information comprehensively. Additionally, attention mechanisms with confidence learning are incorporated for enhanced feature representation and trustworthy prediction.

RESULTS

Extensive experiments were conducted on four benchmark datasets to evaluate the effectiveness of our proposed model, including BRCA, ROSMAP, LGG, and KIPAN. Our model significantly improved most evaluation measurements and consistently surpassed the state-of-the-art methods. Ablation studies showed that the auxiliary classifiers significantly boosted classification accuracy in the ROSMAP and LGG datasets. Moreover, the attention mechanisms and confidence evaluation block contributed to improvements in the predictive accuracy and generalizability of our model.

CONCLUSIONS

The proposed framework exhibits superior performance in disease classification and biomarker discovery, establishing itself as a robust and versatile tool for analyzing multi-layer biological data. This study highlights the significance of elaborated designed deep learning methodologies in dissecting complex disease phenotypes and improving the accuracy of disease predictions.

SHARE-Topic: Bayesian interpretable modeling of single-cell multi-omic data

Multi-omic single-cell technologies, which simultaneously measure the transcriptional and epigenomic state of the same cell, enable understanding epigenetic mechanisms of gene regulation. However, noisy and sparse data pose fundamental statistical challenges to extract biological knowledge from complex datasets. SHARE-Topic, a Bayesian generative model of multi-omic single cell data using topic models, aims to address these challenges. SHARE-Topic identifies common patterns of co-variation between different omic layers, providing interpretable explanations for the data complexity. Tested on data from different technological platforms, SHARE-Topic provides low dimensional representations recapitulating known biology and defines associations between genes and distal regulators in individual cells.

scMGCN: A Multi-View Graph Convolutional Network for Cell Type Identification in scRNA-seq Data

Single-cell RNA sequencing (scRNA-seq) data reveal the complexity and diversity of cellular ecosystems and molecular interactions in various biomedical research. Hence, identifying cell types from large-scale scRNA-seq data using existing annotations is challenging and requires stable and interpretable methods. However, the current cell type identification methods have limited performance, mainly due to the intrinsic heterogeneity among cell populations and extrinsic differences between datasets. Here, we present a robust graph artificial intelligence model, a multi-view graph convolutional network model (scMGCN) that integrates multiple graph structures from raw scRNA-seq data and applies graph convolutional networks with attention mechanisms to learn cell embeddings and predict cell labels. We evaluate our model on single-dataset, cross-species, and cross-platform experiments and compare it with other state-of-the-art methods. Our results show that scMGCN outperforms the other methods regarding stability, accuracy, and robustness to batch effects. Our main contributions are as follows: Firstly, we introduce multi-view learning and multiple graph construction methods to capture comprehensive cellular information from scRNA-seq data. Secondly, we construct a scMGCN that combines graph convolutional networks with attention mechanisms to extract shared, high-order information from cells. Finally, we demonstrate the effectiveness and superiority of the scMGCN on various datasets.

Multi-omics Integration and Epilepsy: Towards a Better Understanding of Biological Mechanisms

The epilepsies are a group of complex neurological disorders characterised by recurrent seizures. Approximately 30% of patients fail to respond to anti-seizure medications, despite the recent introduction of many new drugs. The molecular processes underlying epilepsy development are not well understood and this knowledge gap impedes efforts to identify effective targets and develop novel therapies against epilepsy. Omics studies allow a comprehensive characterisation of a class of molecules. Omics-based biomarkers have led to clinically validated diagnostic and prognostic tests for personalised oncology, and more recently for non-cancer diseases. We believe that, in epilepsy, the full potential of multi-omics research is yet to be realised and we envisage that this review will serve as a guide to researchers planning to undertake omics-based mechanistic studies.

Single-cell profiling to explore pancreatic cancer heterogeneity, plasticity and response to therapy

Pancreatic ductal adenocarcinoma (PDAC) is a highly lethal cancer entity characterized by a heterogeneous genetic landscape and an immunosuppressive tumor microenvironment. Recent advances in high-resolution single-cell sequencing and spatial transcriptomics technologies have enabled an in-depth characterization of both malignant and host cell types and increased our understanding of the heterogeneity and plasticity of PDAC in the steady state and under therapeutic perturbation. In this Review we outline single-cell analyses in PDAC, discuss their implications on our understanding of the disease and present future perspectives of multimodal approaches to elucidate its biology and response to therapy at the single-cell level.

iPoLNG-An unsupervised model for the integrative analysis of single-cell multiomics data

Single-cell multiomics technologies, where the transcriptomic and epigenomic profiles are simultaneously measured in the same set of single cells, pose significant challenges for effective integrative analysis. Here, we propose an unsupervised generative model, iPoLNG, for the effective and scalable integration of single-cell multiomics data. iPoLNG reconstructs low-dimensional representations of the cells and features using computationally efficient stochastic variational inference by modelling the discrete counts in single-cell multiomics data with latent factors. The low-dimensional representation of cells enables the identification of distinct cell types, and the feature by factor loading matrices help characterize cell-type specific markers and provide rich biological insights on the functional pathway enrichment analysis. iPoLNG is also able to handle the setting of partial information where certain modality of the cells is missing. Taking advantage of GPU and probabilistic programming, iPoLNG is scalable to large datasets and it takes less than 15 min to implement on datasets with 20,000 cells.

scAWMV: an adaptively weighted multi-view learning framework for the integrative analysis of parallel scRNA-seq and scATAC-seq data

MOTIVATION

Technological advances have enabled us to profile single-cell multi-omics data from the same cells, providing us with an unprecedented opportunity to understand the cellular phenotype and links to its genotype. The available protocols and multi-omics datasets [including parallel single-cell RNA sequencing (scRNA-seq) and single-cell ATAC sequencing (scATAC-seq) data profiled from the same cell] are growing increasingly. However, such data are highly sparse and tend to have high level of noise, making data analysis challenging. The methods that integrate the multi-omics data can potentially improve the capacity of revealing the cellular heterogeneity.

RESULTS

We propose an adaptively weighted multi-view learning (scAWMV) method for the integrative analysis of parallel scRNA-seq and scATAC-seq data profiled from the same cell. scAWMV considers both the difference in importance across different modalities in multi-omics data and the biological connection of the features in the scRNA-seq and scATAC-seq data. It generates biologically meaningful low-dimensional representations for the transcriptomic and epigenomic profiles via unsupervised learning. Application to four real datasets demonstrates that our framework scAWMV is an efficient method to dissect cellular heterogeneity for single-cell multi-omics data.

AVAILABILITY AND IMPLEMENTATION

The software and datasets are available at https://github.com/pengchengzeng/scAWMV.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Single-cell profiling to transform immunotherapy usage and target discovery in immune-mediated inflammatory diseases

Immunotherapy drugs are transforming the clinical care landscape of major human diseases from cancer, to inflammatory diseases, cardiovascular diseases, neurodegenerative diseases and even aging. In polygenic immune-mediated inflammatory diseases (IMIDs), the clinical benefits of immunotherapy have nevertheless remained limited to a subset of patients. Yet the identification of new actionable molecular candidates has remained challenging, and the use of standard of care imaging and/or histological diagnostic assays has failed to stratify potential responders from non-responders to biotherapies already available. We argue that these limitations partly stem from a poor understanding of disease pathophysiology and insufficient characterization of the roles assumed by candidate targets during disease initiation, progression and treatment. By transforming the resolution and scale of tissue cell mapping, high-resolution profiling strategies offer unprecedented opportunities to the understanding of immunopathogenic events in human IMID lesions. Here we discuss the potential for single-cell technologies to reveal relevant pathogenic cellular programs in IMIDs and to enhance patient stratification to guide biotherapy eligibility and clinical trial design.

The performance of deep generative models for learning joint embeddings of single-cell multi-omics data

Recent extensions of single-cell studies to multiple data modalities raise new questions regarding experimental design. For example, the challenge of sparsity in single-omics data might be partly resolved by compensating for missing information across modalities. In particular, deep learning approaches, such as deep generative models (DGMs), can potentially uncover complex patterns via a joint embedding. Yet, this also raises the question of sample size requirements for identifying such patterns from single-cell multi-omics data. Here, we empirically examine the quality of DGM-based integrations for varying sample sizes. We first review the existing literature and give a short overview of deep learning methods for multi-omics integration. Next, we consider eight popular tools in more detail and examine their robustness to different cell numbers, covering two of the most common multi-omics types currently favored. Specifically, we use data featuring simultaneous gene expression measurements at the RNA level and protein abundance measurements for cell surface proteins (CITE-seq), as well as data where chromatin accessibility and RNA expression are measured in thousands of cells (10x Multiome). We examine the ability of the methods to learn joint embeddings based on biological and technical metrics. Finally, we provide recommendations for the design of multi-omics experiments and discuss potential future developments.

Computational Methods for Single-cell Multi-omics Integration and Alignment

Recently developed technologies to generate single-cell genomic data have made a revolutionary impact in the field of biology. Multi-omics assays offer even greater opportunities to understand cellular states and biological processes. The problem of integrating different omics data with very different dimensionality and statistical properties remains, however, quite challenging. A growing body of computational tools is being developed for this task, leveraging ideas ranging from machine translation to the theory of networks, and represents another frontier on the interface of biology and data science. Our goal in this review is to provide a comprehensive, up-to-date survey of computational techniques for the integration of single-cell multi-omics data, while making the concepts behind each algorithm approachable to a non-expert audience.

Single-cell multi-omics sequencing and its applications in studying the nervous system

Single-cell sequencing has become one of the most powerful and popular techniques in dissecting molecular heterogeneity and modeling the cellular architecture of a biological system. During the past twenty years, the throughput of single-cell sequencing has increased from hundreds of cells to over tens of thousands of cells in parallel. Moreover, this technology has been developed from sequencing transcriptome to measure different omics such as DNA methylome, chromatin accessibility, and so on. Currently, multi-omics which can analyze different omics in the same cell is rapidly advancing. This work advances the study of many biosystems, including the nervous system. Here, we review current single-cell multi-omics sequencing techniques and describe how they improve our understanding of the nervous system. Finally, we discuss the open scientific questions in neural research that may be answered through further improvement of single-cell multi-omics sequencing technology.

How a cell decides its own fate: a single-cell view of molecular mechanisms and dynamics of cell-type specification

On its path from a fertilized egg to one of the many cell types in a multicellular organism, a cell turns the blank canvas of its early embryonic state into a molecular profile fine-tuned to achieve a vital organismal function. This remarkable transformation emerges from the interplay between dynamically changing external signals, the cell's internal, variable state, and tremendously complex molecular machinery; we are only beginning to understand. Recently developed single-cell omics techniques have started to provide an unprecedented, comprehensive view of the molecular changes during cell-type specification and promise to reveal the underlying gene regulatory mechanism. The exponentially increasing amount of quantitative molecular data being created at the moment is slated to inform predictive, mathematical models. Such models can suggest novel ways to manipulate cell types experimentally, which has important biomedical applications. This review is meant to give the reader a starting point to participate in this exciting phase of molecular developmental biology. We first introduce some of the principal molecular players involved in cell-type specification and discuss the important organizing ability of biomolecular condensates, which has been discovered recently. We then review some of the most important single-cell omics methods and relevant findings they produced. We devote special attention to the dynamics of the molecular changes and discuss methods to measure them, most importantly lineage tracing. Finally, we introduce a conceptual framework that connects all molecular agents in a mathematical model and helps us make sense of the experimental data.

Intricacies of single-cell multi-omics data integration

A wealth of single-cell protocols makes it possible to characterize different molecular layers at unprecedented resolution. Integrating the resulting multimodal single-cell data to find cell-to-cell correspondences remains a challenge. We argue that data integration needs to happen at a meaningful biological level of abstraction and that it is necessary to consider the inherent discrepancies between modalities to strike a balance between biological discovery and noise removal. A survey of current methods reveals that a distinction between technical and biological origins of presumed unwanted variation between datasets is not yet commonly considered. The increasing availability of paired multimodal data will aid the development of improved methods by providing a ground truth on cell-to-cell matches.

LISA2: Learning Complex Single-Cell Trajectory and Expression Trends

Single-cell transcriptional and epigenomics profiles have been applied in a variety of tissues and diseases for discovering new cell types, differentiation trajectories, and gene regulatory networks. Many methods such as Monocle 2/3, URD, and STREAM have been developed for tree-based trajectory building. Here, we propose a fast and flexible trajectory learning method, LISA2, for single-cell data analysis. This new method has two distinctive features: (1) LISA2 utilizes specified leaves and root to reduce the complexity for building the developmental trajectory, especially for some special cases such as rare cell populations and adjacent terminal cell states; and (2) LISA2 is applicable for both transcriptomics and epigenomics data. LISA2 visualizes complex trajectories using 3D Landmark ISOmetric feature MAPping (L-ISOMAP). We apply LISA2 to simulation and real datasets in cerebellum, diencephalon, and hematopoietic stem cells including both single-cell transcriptomics data and single-cell assay for transposase-accessible chromatin data. LISA2 is efficient in estimating single-cell trajectory and expression trends for different kinds of molecular state of cells.

Antigen-Specific Treg Therapy in Type 1 Diabetes - Challenges and Opportunities

Regulatory T cells (Tregs) are key mediators of peripheral self-tolerance and alterations in their frequencies, stability, and function have been linked to autoimmunity. The antigen-specific induction of Tregs is a long-envisioned goal for the treatment of autoimmune diseases given reduced side effects compared to general immunosuppressive therapies. However, the translation of antigen-specific Treg inducing therapies for the treatment or prevention of autoimmune diseases into the clinic remains challenging. In this mini review, we will discuss promising results for antigen-specific Treg therapies in allergy and specific challenges for such therapies in autoimmune diseases, with a focus on type 1 diabetes (T1D). We will furthermore discuss opportunities for antigen-specific Treg therapies in T1D, including combinatorial strategies and tissue-specific Treg targeting. Specifically, we will highlight recent advances in miRNA-targeting as a means to foster Tregs in autoimmunity. Additionally, we will discuss advances and perspectives of computational strategies for the detailed analysis of tissue-specific Tregs on the single-cell level.

scGCN is a graph convolutional networks algorithm for knowledge transfer in single cell omics

Single-cell omics is the fastest-growing type of genomics data in the literature and public genomics repositories. Leveraging the growing repository of labeled datasets and transferring labels from existing datasets to newly generated datasets will empower the exploration of single-cell omics data. However, the current label transfer methods have limited performance, largely due to the intrinsic heterogeneity among cell populations and extrinsic differences between datasets. Here, we present a robust graph artificial intelligence model, single-cell Graph Convolutional Network (scGCN), to achieve effective knowledge transfer across disparate datasets. Through benchmarking with other label transfer methods on a total of 30 single cell omics datasets, scGCN consistently demonstrates superior accuracy on leveraging cells from different tissues, platforms, and species, as well as cells profiled at different molecular layers. scGCN is implemented as an integrated workflow as a python software, which is available at https://github.com/QSong-github/scGCN .

Computational principles and challenges in single-cell data integration

The development of single-cell multimodal assays provides a powerful tool for investigating multiple dimensions of cellular heterogeneity, enabling new insights into development, tissue homeostasis and disease. A key challenge in the analysis of single-cell multimodal data is to devise appropriate strategies for tying together data across different modalities. The term 'data integration' has been used to describe this task, encompassing a broad collection of approaches ranging from batch correction of individual omics datasets to association of chromatin accessibility and genetic variation with transcription. Although existing integration strategies exploit similar mathematical ideas, they typically have distinct goals and rely on different principles and assumptions. Consequently, new definitions and concepts are needed to contextualize existing methods and to enable development of new methods.

Advances in bulk and single-cell multi-omics approaches for systems biology and precision medicine

Multi-omics allows the systematic understanding of the information flow across different omics layers, while single omics can mainly reflect one aspect of the biological system. The advancement of bulk and single-cell sequencing technologies and related computational methods for multi-omics largely facilitated the development of system biology and precision medicine. Single-cell approaches have the advantage of dissecting cellular dynamics and heterogeneity, whereas traditional bulk technologies are limited to individual/population-level investigation. In this review, we first summarize the technologies for producing bulk and single-cell multi-omics data. Then, we survey the computational approaches for integrative analysis of bulk and single-cell multimodal data, respectively. Moreover, the databases and data storage for multi-omics, as well as the tools for visualizing multimodal data are summarized. We also outline the integration between bulk and single-cell data, and discuss the applications of multi-omics in precision medicine. Finally, we present the challenges and perspectives for multi-omics development.

STATegra: Multi-Omics Data Integration - A Conceptual Scheme With a Bioinformatics Pipeline

Technologies for profiling samples using different omics platforms have been at the forefront since the human genome project. Large-scale multi-omics data hold the promise of deciphering different regulatory layers. Yet, while there is a myriad of bioinformatics tools, each multi-omics analysis appears to start from scratch with an arbitrary decision over which tools to use and how to combine them. Therefore, it is an unmet need to conceptualize how to integrate such data and implement and validate pipelines in different cases. We have designed a conceptual framework (STATegra), aiming it to be as generic as possible for multi-omics analysis, combining available multi-omic anlaysis tools (machine learning component analysis, non-parametric data combination, and a multi-omics exploratory analysis) in a step-wise manner. While in several studies, we have previously combined those integrative tools, here, we provide a systematic description of the STATegra framework and its validation using two The Cancer Genome Atlas (TCGA) case studies. For both, the Glioblastoma and the Skin Cutaneous Melanoma (SKCM) cases, we demonstrate an enhanced capacity of the framework (and beyond the individual tools) to identify features and pathways compared to single-omics analysis. Such an integrative multi-omics analysis framework for identifying features and components facilitates the discovery of new biology. Finally, we provide several options for applying the STATegra framework when parametric assumptions are fulfilled and for the case when not all the samples are profiled for all omics. The STATegra framework is built using several tools, which are being integrated step-by-step as OpenSource in the STATegRa Bioconductor package.

Measuring evolutionary cancer dynamics from genome sequencing, one patient at a time

Cancers progress through the accumulation of somatic mutations which accrue during tumour evolution, allowing some cells to proliferate in an uncontrolled fashion. This growth process is intimately related to latent evolutionary forces moulding the genetic and epigenetic composition of tumour subpopulations. Understanding cancer requires therefore the understanding of these selective pressures. The adoption of widespread next-generation sequencing technologies opens up for the possibility of measuring molecular profiles of cancers at multiple resolutions, across one or multiple patients. In this review we discuss how cancer genome sequencing data from a single tumour can be used to understand these evolutionary forces, overviewing mathematical models and inferential methods adopted in field of Cancer Evolution.

Measuring and Modeling Single-Cell Heterogeneity and Fate Decision in Mouse Embryos

Cellular heterogeneity is a property of any living system; however, its relationship with cellular fate decision remains an open question. Recent technological advances have enabled valuable insights, especially in complex systems such as the mouse embryo. In this review, we discuss recent studies that characterize cellular heterogeneity at different levels during mouse development, from the two-cell stage up to gastrulation. In addition to key experimental findings, we review mathematical modeling approaches that help researchers interpret these findings. Disentangling the role of heterogeneity in cell fate decision will likely rely on the refined integration of experiments, large-scale omics data, and mathematical modeling, complemented by the use of synthetic embryos and gastruloids as promising in vitro models.

Deep-joint-learning analysis model of single cell transcriptome and open chromatin accessibility data

Simultaneous profiling transcriptomic and chromatin accessibility information in the same individual cells offers an unprecedented resolution to understand cell states. However, computationally effective methods for the integration of these inherent sparse and heterogeneous data are lacking. Here, we present a single-cell multimodal variational autoencoder model, which combines three types of joint-learning strategies with a probabilistic Gaussian Mixture Model to learn the joint latent features that accurately represent these multilayer profiles. Studies on both simulated datasets and real datasets demonstrate that it has more preferable capability (i) dissecting cellular heterogeneity in the joint-learning space, (ii) denoising and imputing data and (iii) constructing the association between multilayer omics data, which can be used for understanding transcriptional regulatory mechanisms.

Probing infectious disease by single-cell RNA sequencing: Progresses and perspectives

The increasing application of single-cell RNA sequencing (scRNA-seq) technology in life science and biomedical research has significantly increased our understanding of the cellular heterogeneities in immunology, oncology and developmental biology. This review will summarize the development of various scRNA-seq technologies; primarily discussing the application of scRNA-seq on infectious diseases, and exploring the current development, challenges, and potential applications of scRNA-seq technology in the future.

A Review of Integrative Imputation for Multi-Omics Datasets

Multi-omics studies, which explore the interactions between multiple types of biological factors, have significant advantages over single-omics analysis for their ability to provide a more holistic view of biological processes, uncover the causal and functional mechanisms for complex diseases, and facilitate new discoveries in precision medicine. However, omics datasets often contain missing values, and in multi-omics study designs it is common for individuals to be represented for some omics layers but not all. Since most statistical analyses cannot be applied directly to the incomplete datasets, imputation is typically performed to infer the missing values. Integrative imputation techniques which make use of the correlations and shared information among multi-omics datasets are expected to outperform approaches that rely on single-omics information alone, resulting in more accurate results for the subsequent downstream analyses. In this review, we provide an overview of the currently available imputation methods for handling missing values in bioinformatics data with an emphasis on multi-omics imputation. In addition, we also provide a perspective on how deep learning methods might be developed for the integrative imputation of multi-omics datasets.

Integrative Methods and Practical Challenges for Single-Cell Multi-omics

Fast-developing single-cell multimodal omics (scMulti-omics) technologies enable the measurement of multiple modalities, such as DNA methylation, chromatin accessibility, RNA expression, protein abundance, gene perturbation, and spatial information, from the same cell. scMulti-omics can comprehensively explore and identify cell characteristics, while also presenting challenges to the development of computational methods and tools for integrative analyses. Here, we review these integrative methods and summarize the existing tools for studying a variety of scMulti-omics data. The various functionalities and practical challenges in using the available tools in the public domain are explored through several case studies. Finally, we identify remaining challenges and future trends in scMulti-omics modeling and analyses.

Advances and challenges in epigenomic single-cell sequencing applications

Understanding multicellular physiology and pathobiology requires analysis of the relationship between genotype, chromatin organisation and phenotype. In the multi-omics era, many methods exist to investigate biological processes across the genome, transcriptome, epigenome, proteome and metabolome. Until recently, this was only possible for populations of cells or complex tissues, creating an averaging effect that may obscure direct correlations between multiple layers of data. Single-cell sequencing methods have removed this averaging effect, but computational integration after profiling distinct modalities separately may still not completely reflect underlying biology. Multiplexed assays resolving multiple modalities in the same cell are required to overcome these shortcomings and have the potential to deliver unprecedented understanding of biology and disease.

Multiview learning for understanding functional multiomics

The molecular mechanisms and functions in complex biological systems currently remain elusive. Recent high-throughput techniques, such as next-generation sequencing, have generated a wide variety of multiomics datasets that enable the identification of biological functions and mechanisms via multiple facets. However, integrating these large-scale multiomics data and discovering functional insights are, nevertheless, challenging tasks. To address these challenges, machine learning has been broadly applied to analyze multiomics. This review introduces multiview learning-an emerging machine learning field-and envisions its potentially powerful applications to multiomics. In particular, multiview learning is more effective than previous integrative methods for learning data's heterogeneity and revealing cross-talk patterns. Although it has been applied to various contexts, such as computer vision and speech recognition, multiview learning has not yet been widely applied to biological data-specifically, multiomics data. Therefore, this paper firstly reviews recent multiview learning methods and unifies them in a framework called multiview empirical risk minimization (MV-ERM). We further discuss the potential applications of each method to multiomics, including genomics, transcriptomics, and epigenomics, in an aim to discover the functional and mechanistic interpretations across omics. Secondly, we explore possible applications to different biological systems, including human diseases (e.g., brain disorders and cancers), plants, and single-cell analysis, and discuss both the benefits and caveats of using multiview learning to discover the molecular mechanisms and functions of these systems.

scAI: an unsupervised approach for the integrative analysis of parallel single-cell transcriptomic and epigenomic profiles

Simultaneous measurements of transcriptomic and epigenomic profiles in the same individual cells provide an unprecedented opportunity to understand cell fates. However, effective approaches for the integrative analysis of such data are lacking. Here, we present a single-cell aggregation and integration (scAI) method to deconvolute cellular heterogeneity from parallel transcriptomic and epigenomic profiles. Through iterative learning, scAI aggregates sparse epigenomic signals in similar cells learned in an unsupervised manner, allowing coherent fusion with transcriptomic measurements. Simulation studies and applications to three real datasets demonstrate its capability of dissecting cellular heterogeneity within both transcriptomic and epigenomic layers and understanding transcriptional regulatory mechanisms.

ManiNetCluster: a novel manifold learning approach to reveal the functional links between gene networks

BACKGROUND

The coordination of genomic functions is a critical and complex process across biological systems such as phenotypes or states (e.g., time, disease, organism, environmental perturbation). Understanding how the complexity of genomic function relates to these states remains a challenge. To address this, we have developed a novel computational method, ManiNetCluster, which simultaneously aligns and clusters gene networks (e.g., co-expression) to systematically reveal the links of genomic function between different conditions. Specifically, ManiNetCluster employs manifold learning to uncover and match local and non-linear structures among networks, and identifies cross-network functional links.

RESULTS

We demonstrated that ManiNetCluster better aligns the orthologous genes from their developmental expression profiles across model organisms than state-of-the-art methods (p-value <2.2×10^-16). This indicates the potential non-linear interactions of evolutionarily conserved genes across species in development. Furthermore, we applied ManiNetCluster to time series transcriptome data measured in the green alga Chlamydomonas reinhardtii to discover the genomic functions linking various metabolic processes between the light and dark periods of a diurnally cycling culture. We identified a number of genes putatively regulating processes across each lighting regime.

CONCLUSIONS

ManiNetCluster provides a novel computational tool to uncover the genes linking various functions from different networks, providing new insight on how gene functions coordinate across different conditions. ManiNetCluster is publicly available as an R package at https://github.com/daifengwanglab/ManiNetCluster.

Integrative single-cell analysis

The recent maturation of single-cell RNA sequencing (scRNA-seq) technologies has coincided with transformative new methods to profile genetic, epigenetic, spatial, proteomic and lineage information in individual cells. This provides unique opportunities, alongside computational challenges, for integrative methods that can jointly learn across multiple types of data. Integrated analysis can discover relationships across cellular modalities, learn a holistic representation of the cell state, and enable the pooling of data sets produced across individuals and technologies. In this Review, we discuss the recent advances in the collection and integration of different data types at single-cell resolution with a focus on the integration of gene expression data with other types of single-cell measurement.

Machine and deep learning meet genome-scale metabolic modeling

Omic data analysis is steadily growing as a driver of basic and applied molecular biology research. Core to the interpretation of complex and heterogeneous biological phenotypes are computational approaches in the fields of statistics and machine learning. In parallel, constraint-based metabolic modeling has established itself as the main tool to investigate large-scale relationships between genotype, phenotype, and environment. The development and application of these methodological frameworks have occurred independently for the most part, whereas the potential of their integration for biological, biomedical, and biotechnological research is less known. Here, we describe how machine learning and constraint-based modeling can be combined, reviewing recent works at the intersection of both domains and discussing the mathematical and practical aspects involved. We overlap systematic classifications from both frameworks, making them accessible to nonexperts. Finally, we delineate potential future scenarios, propose new joint theoretical frameworks, and suggest concrete points of investigation for this joint subfield. A multiview approach merging experimental and knowledge-driven omic data through machine learning methods can incorporate key mechanistic information in an otherwise biologically-agnostic learning process.

The Human Lung Cell Atlas: A High-Resolution Reference Map of the Human Lung in Health and Disease

Lung disease accounts for every sixth death globally. Profiling the molecular state of all lung cell types in health and disease is currently revolutionizing the identification of disease mechanisms and will aid the design of novel diagnostic and personalized therapeutic regimens. Recent progress in high-throughput techniques for single-cell genomic and transcriptomic analyses has opened up new possibilities to study individual cells within a tissue, classify these into cell types, and characterize variations in their molecular profiles as a function of genetics, environment, cell-cell interactions, developmental processes, aging, or disease. Integration of these cell state definitions with spatial information allows the in-depth molecular description of cellular neighborhoods and tissue microenvironments, including the tissue resident structural and immune cells, the tissue matrix, and the microbiome. The Human Cell Atlas consortium aims to characterize all cells in the healthy human body and has prioritized lung tissue as one of the flagship projects. Here, we present the rationale, the approach, and the expected impact of a Human Lung Cell Atlas.

Current best practices in single-cell RNA-seq analysis: a tutorial

Single-cell RNA-seq has enabled gene expression to be studied at an unprecedented resolution. The promise of this technology is attracting a growing user base for single-cell analysis methods. As more analysis tools are becoming available, it is becoming increasingly difficult to navigate this landscape and produce an up-to-date workflow to analyse one's data. Here, we detail the steps of a typical single-cell RNA-seq analysis, including pre-processing (quality control, normalization, data correction, feature selection, and dimensionality reduction) and cell- and gene-level downstream analysis. We formulate current best-practice recommendations for these steps based on independent comparison studies. We have integrated these best-practice recommendations into a workflow, which we apply to a public dataset to further illustrate how these steps work in practice. Our documented case study can be found at https://www.github.com/theislab/single-cell-tutorial This review will serve as a workflow tutorial for new entrants into the field, and help established users update their analysis pipelines.

Concepts and limitations for learning developmental trajectories from single cell genomics

Single cell genomics has become a popular approach to uncover the cellular heterogeneity of progenitor and terminally differentiated cell types with great precision. This approach can also delineate lineage hierarchies and identify molecular programmes of cell-fate acquisition and segregation. Nowadays, tens of thousands of cells are routinely sequenced in single cell-based methods and even more are expected to be analysed in the future. However, interpretation of the resulting data is challenging and requires computational models at multiple levels of abstraction. In contrast to other applications of single cell sequencing, where clustering approaches dominate, developmental systems are generally modelled using continuous structures, trajectories and trees. These trajectory models carry the promise of elucidating mechanisms of development, disease and stimulation response at very high molecular resolution. However, their reliable analysis and biological interpretation requires an understanding of their underlying assumptions and limitations. Here, we review the basic concepts of such computational approaches and discuss the characteristics of developmental processes that can be learnt from trajectory models.

Inferring Interaction Networks From Multi-Omics Data

A major goal in systems biology is a comprehensive description of the entirety of all complex interactions between different types of biomolecules-also referred to as the interactome-and how these interactions give rise to higher, cellular and organism level functions or diseases. Numerous efforts have been undertaken to define such interactomes experimentally, for example yeast-two-hybrid based protein-protein interaction networks or ChIP-seq based protein-DNA interactions for individual proteins. To complement these direct measurements, genome-scale quantitative multi-omics data (transcriptomics, proteomics, metabolomics, etc.) enable researchers to predict novel functional interactions between molecular species. Moreover, these data allow to distinguish relevant functional from non-functional interactions in specific biological contexts. However, integration of multi-omics data is not straight forward due to their heterogeneity. Numerous methods for the inference of interaction networks from homogeneous functional data exist, but with the advent of large-scale paired multi-omics data a new class of methods for inferring comprehensive networks across different molecular species began to emerge. Here we review state-of-the-art techniques for inferring the topology of interaction networks from functional multi-omics data, encompassing graphical models with multiple node types and quantitative-trait-loci (QTL) based approaches. In addition, we will discuss Bayesian aspects of network inference, which allow for leveraging already established biological information such as known protein-protein or protein-DNA interactions, to guide the inference process.

Multi-omics at single-cell resolution: comparison of experimental and data fusion approaches

Biological samples are inherently heterogeneous and complex. Tackling this complexity requires innovative technological and analytical solutions. Recent advances in high-throughput single-cell isolation and nucleic acid barcoding methods are rapidly changing the technological landscape of biological sciences and now make it possible to measure the (epi)genomic, transcriptomic, or proteomic state of individual cells. In addition, few experimental approaches enable multi-omics measurements of the same cell. However, merging-omics data collected from different experiments remains a considerable challenge. Although several strategies for merging transcriptomics datasets have recently been introduced, cell-to-cell variability and heterogeneity remains one of the confounding factors limiting data fusion and integration. Here, we focus our discussion on the latest single-cell technological and analytical solutions to achieve high data dimensionality and resolution. Obtaining datasets with a wealth of multi-omics information will undoubtedly provide new avenues for researchers to unravel the complexity of biological samples encountered in modern biological research and molecular diagnostics.

Multi-Omics Profiling of the Tumor Microenvironment: Paving the Way to Precision Immuno-Oncology

The tumor microenvironment (TME) is a multifaceted ecosystem characterized by profound cellular heterogeneity, dynamicity, and complex intercellular cross-talk. The striking responses obtained with immune checkpoint blockers, i.e., antibodies targeting immune-cell regulators to boost antitumor immunity, have demonstrated the enormous potential of anticancer treatments that target TME components other than tumor cells. However, as checkpoint blockade is currently beneficial only to a limited fraction of patients, there is an urgent need to understand the mechanisms orchestrating the immune response in the TME to guide the rational design of more effective anticancer therapies. In this Mini Review, we give an overview of the methodologies that allow studying the heterogeneity of the TME from multi-omics data generated from bulk samples, single cells, or images of tumor-tissue slides. These include approaches for the characterization of the different cell phenotypes and for the reconstruction of their spatial organization and inter-cellular cross-talk. We discuss how this broader vision of the cellular heterogeneity and plasticity of tumors, which is emerging thanks to these methodologies, offers the opportunity to rationally design precision immuno-oncology treatments. These developments are fundamental to overcome the current limitations of targeted agents and checkpoint blockers and to bring long-term clinical benefits to a larger fraction of cancer patients.

Multi-Omics Factor Analysis-a framework for unsupervised integration of multi-omics data sets

Multi-omics studies promise the improved characterization of biological processes across molecular layers. However, methods for the unsupervised integration of the resulting heterogeneous data sets are lacking. We present Multi-Omics Factor Analysis (MOFA), a computational method for discovering the principal sources of variation in multi-omics data sets. MOFA infers a set of (hidden) factors that capture biological and technical sources of variability. It disentangles axes of heterogeneity that are shared across multiple modalities and those specific to individual data modalities. The learnt factors enable a variety of downstream analyses, including identification of sample subgroups, data imputation and the detection of outlier samples. We applied MOFA to a cohort of 200 patient samples of chronic lymphocytic leukaemia, profiled for somatic mutations, RNA expression, DNA methylation and ex vivo drug responses. MOFA identified major dimensions of disease heterogeneity, including immunoglobulin heavy-chain variable region status, trisomy of chromosome 12 and previously underappreciated drivers, such as response to oxidative stress. In a second application, we used MOFA to analyse single-cell multi-omics data, identifying coordinated transcriptional and epigenetic changes along cell differentiation.