SCODE: an efficient regulatory network inference algorithm from single-cell RNA-Seq during differentiation

One model fits all: Combining inference and simulation of gene regulatory networks

The rise of single-cell data highlights the need for a nondeterministic view of gene expression, while offering new opportunities regarding gene regulatory network inference. We recently introduced two strategies that specifically exploit time-course data, where single-cell profiling is performed after a stimulus: HARISSA, a mechanistic network model with a highly efficient simulation procedure, and CARDAMOM, a scalable inference method seen as model calibration. Here, we combine the two approaches and show that the same model driven by transcriptional bursting can be used simultaneously as an inference tool, to reconstruct biologically relevant networks, and as a simulation tool, to generate realistic transcriptional profiles emerging from gene interactions. We verify that CARDAMOM quantitatively reconstructs causal links when the data is simulated from HARISSA, and demonstrate its performance on experimental data collected on in vitro differentiating mouse embryonic stem cells. Overall, this integrated strategy largely overcomes the limitations of disconnected inference and simulation.

De-novo reconstruction and identification of transcriptional gene regulatory network modules differentiating single-cell clusters

Single-cell RNA sequencing (scRNA-seq) technology provides an unprecedented opportunity to understand gene functions and interactions at single-cell resolution. While computational tools for scRNA-seq data analysis to decipher differential gene expression profiles and differential pathway expression exist, we still lack methods to learn differential regulatory disease mechanisms directly from the single-cell data. Here, we provide a new methodology, named DiNiro, to unravel such mechanisms de novo and report them as small, easily interpretable transcriptional regulatory network modules. We demonstrate that DiNiro is able to uncover novel, relevant, and deep mechanistic models that not just predict but explain differential cellular gene expression programs. DiNiro is available at https://exbio.wzw.tum.de/diniro/.

Computational approaches to understand transcription regulation in development

Gene regulatory networks (GRNs) serve as useful abstractions to understand transcriptional dynamics in developmental systems. Computational prediction of GRNs has been successfully applied to genome-wide gene expression measurements with the advent of microarrays and RNA-sequencing. However, these inferred networks are inaccurate and mostly based on correlative rather than causative interactions. In this review, we highlight three approaches that significantly impact GRN inference: (1) moving from one genome-wide functional modality, gene expression, to multi-omics, (2) single cell sequencing, to measure cell type-specific signals and predict context-specific GRNs, and (3) neural networks as flexible models. Together, these experimental and computational developments have the potential to significantly impact the quality of inferred GRNs. Ultimately, accurately modeling the regulatory interactions between transcription factors and their target genes will be essential to understand the role of transcription factors in driving developmental gene expression programs and to derive testable hypotheses for validation.

Using single cell atlas data to reconstruct regulatory networks

Inference of global gene regulatory networks from omics data is a long-term goal of systems biology. Most methods developed for inferring transcription factor (TF)-gene interactions either relied on a small dataset or used snapshot data which is not suitable for inferring a process that is inherently temporal. Here, we developed a new computational method that combines neural networks and multi-task learning to predict RNA velocity rather than gene expression values. This allows our method to overcome many of the problems faced by prior methods leading to more accurate and more comprehensive set of identified regulatory interactions. Application of our method to atlas scale single cell data from 6 HuBMAP tissues led to several validated and novel predictions and greatly improved on prior methods proposed for this task.

Complex Analysis of Single-Cell RNA Sequencing Data

Single-cell RNA sequencing (scRNA-seq) is a revolutionary tool for studying the physiology of normal and pathologically altered tissues. This approach provides information about molecular features (gene expression, mutations, chromatin accessibility, etc.) of cells, opens up the possibility to analyze the trajectories/phylogeny of cell differentiation and cell-cell interactions, and helps in discovery of new cell types and previously unexplored processes. From a clinical point of view, scRNA-seq facilitates deeper and more detailed analysis of molecular mechanisms of diseases and serves as a basis for the development of new preventive, diagnostic, and therapeutic strategies. The review describes different approaches to the analysis of scRNA-seq data, discusses the advantages and disadvantages of bioinformatics tools, provides recommendations and examples of their successful use, and suggests potential directions for improvement. We also emphasize the need for creating new protocols, including multiomics ones, for the preparation of DNA/RNA libraries of single cells with the purpose of more complete understanding of individual cells.

MetaSEM: Gene Regulatory Network Inference from Single-Cell RNA Data by Meta-Learning

Regulators in gene regulatory networks (GRNs) are crucial for identifying cell states. However, GRN inference based on scRNA-seq data has several problems, including high dimensionality and sparsity, and requires more label data. Therefore, we propose a meta-learning GRN inference framework to identify regulatory factors. Specifically, meta-learning solves the parameter optimization problem caused by high-dimensional sparse data features. In addition, a few-shot solution was used to solve the problem of lack of label data. A structural equation model (SEM) was embedded in the model to identify important regulators. We integrated the parameter optimization strategy into the bi-level optimization to extract the feature consistent with GRN reasoning. This unique design makes our model robust to small-scale data. By studying the GRN inference task, we confirmed that the selected regulators were closely related to gene expression specificity. We further analyzed the GRN inferred to find the important regulators in cell type identification. Extensive experimental results showed that our model effectively captured the regulator in single-cell GRN inference. Finally, the visualization results verified the importance of the selected regulators for cell type recognition.

Inferring gene regulatory networks from single-cell gene expression data via deep multi-view contrastive learning

The inference of gene regulatory networks (GRNs) is of great importance for understanding the complex regulatory mechanisms within cells. The emergence of single-cell RNA-sequencing (scRNA-seq) technologies enables the measure of gene expression levels for individual cells, which promotes the reconstruction of GRNs at single-cell resolution. However, existing network inference methods are mainly designed for data collected from a single data source, which ignores the information provided by multiple related data sources. In this paper, we propose a multi-view contrastive learning (DeepMCL) model to infer GRNs from scRNA-seq data collected from multiple data sources or time points. We first represent each gene pair as a set of histogram images, and then introduce a deep Siamese convolutional neural network with contrastive loss to learn the low-dimensional embedding for each gene pair. Moreover, an attention mechanism is introduced to integrate the embeddings extracted from different data sources and different neighbor gene pairs. Experimental results on synthetic and real-world datasets validate the effectiveness of our contrastive learning and attention mechanisms, demonstrating the effectiveness of our model in integrating multiple data sources for GRN inference.

A data-driven optimization method for coarse-graining gene regulatory networks

One major challenge in systems biology is to understand how various genes in a gene regulatory network (GRN) collectively perform their functions and control network dynamics. This task becomes extremely hard to tackle in the case of large networks with hundreds of genes and edges, many of which have redundant regulatory roles and functions. The existing methods for model reduction usually require the detailed mathematical description of dynamical systems and their corresponding kinetic parameters, which are often not available. Here, we present a data-driven method for coarse-graining large GRNs, named SacoGraci, using ensemble-based mathematical modeling, dimensionality reduction, and gene circuit optimization by Markov Chain Monte Carlo methods. SacoGraci requires network topology as the only input and is robust against errors in GRNs. We benchmark and demonstrate its usage with synthetic, literature-based, and bioinformatics-derived GRNs. We hope SacoGraci will enhance our ability to model the gene regulation of complex biological systems.

A Consensus Gene Regulatory Network for Neurodegenerative Diseases Using Single-Cell RNA-Seq Data

Gene regulatory network (GRN) inference from gene expression data is a highly complex and challenging task in systems biology. Despite the challenges, GRNs have emerged, and for complex diseases such as neurodegenerative diseases, they have the potential to provide vital information and identify key regulators. However, every GRN method produced predicts results based on its assumptions, providing limited biological insights. For that reason, the current work focused on the development of an ensemble method from individual GRN methods to address this issue. Four state-of-the-art GRN algorithms were selected to form a consensus GRN from their common gene interactions. Each algorithm uses a different construction method, and for a more robust behavior, both static and dynamic methods were selected as well. The algorithms were applied to a scRNA-seq dataset from the CK-p25 mus musculus model during neurodegeneration. The top subnetworks were constructed from the consensus network, and potential key regulators were identified. The results also demonstrated the overlap between the algorithms for the current dataset and the necessity for an ensemble approach. This work aims to demonstrate the creation of an ensemble network and provide insights into whether a combination of different GRN methods can produce valuable results.

What Makes a Functional Gene Regulatory Network? A Circuit Motif Analysis

One of the key questions in systems biology is to understand the roles of gene regulatory circuits in determining cellular states and their functions. In previous studies, some researchers have inferred large gene networks from genome wide genomics/transcriptomics data using the top-down approach, while others have modeled core gene circuits of small sizes using the bottom-up approach. Despite many existing systems biology studies, there is still no general rule on what sizes of gene networks and what types of circuit motifs a system would need to achieve robust biological functions. Here, we adopt a gene circuit motif analysis to discover four-node circuits responsible for multiplicity (rich in dynamical behavior), flexibility (versatile to alter gene expression), or both. We identify the most reoccurring two-node circuit motifs and the co-occurring motif pairs. Furthermore, we investigate the contributing factors of multiplicity and flexibility for large gene networks of different types and sizes. We find that gene networks of intermediate sizes tend to have combined high levels of multiplicity and flexibility. Our study will contribute to a better understanding of the dynamical mechanisms of gene regulatory circuits and provide insights into rational designs of robust gene circuits in synthetic and systems biology.

Systematic comparison of modeling fidelity levels and parameter inference settings applied to negative feedback gene regulation

Quantitative stochastic models of gene regulatory networks are important tools for studying cellular regulation. Such models can be formulated at many different levels of fidelity. A practical challenge is to determine what model fidelity to use in order to get accurate and representative results. The choice is important, because models of successively higher fidelity come at a rapidly increasing computational cost. In some situations, the level of detail is clearly motivated by the question under study. In many situations however, many model options could qualitatively agree with available data, depending on the amount of data and the nature of the observations. Here, an important distinction is whether we are interested in inferring the true (but unknown) physical parameters of the model or if it is sufficient to be able to capture and explain available data. The situation becomes complicated from a computational perspective because inference needs to be approximate. Most often it is based on likelihood-free Approximate Bayesian Computation (ABC) and here determining which summary statistics to use, as well as how much data is needed to reach the desired level of accuracy, are difficult tasks. Ultimately, all of these aspects-the model fidelity, the available data, and the numerical choices for inference-interplay in a complex manner. In this paper we develop a computational pipeline designed to systematically evaluate inference accuracy for a wide range of true known parameters. We then use it to explore inference settings for negative feedback gene regulation. In particular, we compare a detailed spatial stochastic model, a coarse-grained compartment-based multiscale model, and the standard well-mixed model, across several data-scenarios and for multiple numerical options for parameter inference. Practically speaking, this pipeline can be used as a preliminary step to guide modelers prior to gathering experimental data. By training Gaussian processes to approximate the distance function values, we are able to substantially reduce the computational cost of running the pipeline.

scAnalyzeR: A Comprehensive Software Package With Graphical User Interface for Single-Cell RNA Sequencing Analysis and its Application on Liver Cancer

Introduction: The application of single-cell RNA sequencing to delineate tissue heterogeneity and complexity has become increasingly popular. Given its tremendous resolution and high-dimensional capacity for in-depth investigation, single-cell RNA sequencing offers an unprecedented research power. Although some popular software packages are available for single-cell RNA sequencing data analysis and visualization, it is still a big challenge for their usage, as they provide only a command-line interface and require significant level of bioinformatics skills. Methods: We have developed scAnalyzeR, which is a single-cell RNA sequencing analysis pipeline with an interactive and user-friendly graphical interface for analyzing and visualizing single-cell RNA sequencing data. It accepts single-cell RNA sequencing data from various technology platforms and different model organisms (human and mouse) and allows flexibility in input file format. It provides functionalities for data preprocessing, quality control, basic summary statistics, dimension reduction, unsupervised clustering, differential gene expression, gene set enrichment analysis, correlation analysis, pseudotime cell trajectory inference, and various visualization plots. It also provides default parameters for easy usage and allows a wide range of flexibility and optimization by accepting user-defined options. It has been developed as a docker image that can be run in any docker-supported environment including Linux, Mac, and Windows, without installing any dependencies. Results: We compared the performance of scAnalyzeR with 2 other graphical tools that are popular for analyzing single-cell RNA sequencing data. The comparison was based on the comprehensiveness of functionalities, ease of usage and flexibility, and execution time. In general, scAnalyzeR outperformed the other tested counterparts in various aspects, demonstrating its superior overall performance. To illustrate the usefulness of scAnalyzeR in cancer research, we have analyzed the in-house liver cancer single-cell RNA sequencing dataset. Liver cancer tumor cells were revealed to have multiple subpopulations with distinctive gene expression signatures. Conclusion: scAnalyzeR has comprehensive functionalities and demonstrated usability. We anticipate more functionalities to be adopted in the future development.

Data analysis guidelines for single-cell RNA-seq in biomedical studies and clinical applications

The application of single-cell RNA sequencing (scRNA-seq) in biomedical research has advanced our understanding of the pathogenesis of disease and provided valuable insights into new diagnostic and therapeutic strategies. With the expansion of capacity for high-throughput scRNA-seq, including clinical samples, the analysis of these huge volumes of data has become a daunting prospect for researchers entering this field. Here, we review the workflow for typical scRNA-seq data analysis, covering raw data processing and quality control, basic data analysis applicable for almost all scRNA-seq data sets, and advanced data analysis that should be tailored to specific scientific questions. While summarizing the current methods for each analysis step, we also provide an online repository of software and wrapped-up scripts to support the implementation. Recommendations and caveats are pointed out for some specific analysis tasks and approaches. We hope this resource will be helpful to researchers engaging with scRNA-seq, in particular for emerging clinical applications.

DeepVelo: Single-cell transcriptomic deep velocity field learning with neural ordinary differential equations

Recent advances in single-cell sequencing technologies have provided unprecedented opportunities to measure the gene expression profile and RNA velocity of individual cells. However, modeling transcriptional dynamics is computationally challenging because of the high-dimensional, sparse nature of the single-cell gene expression measurements and the nonlinear regulatory relationships. Here, we present DeepVelo, a neural network-based ordinary differential equation that can model complex transcriptome dynamics by describing continuous-time gene expression changes within individual cells. We apply DeepVelo to public datasets from different sequencing platforms to (i) formulate transcriptome dynamics on different time scales, (ii) measure the instability of cell states, and (iii) identify developmental driver genes via perturbation analysis. Benchmarking against the state-of-the-art methods shows that DeepVelo can learn a more accurate representation of the velocity field. Furthermore, our perturbation studies reveal that single-cell dynamical systems could exhibit chaotic properties. In summary, DeepVelo allows data-driven discoveries of differential equations that delineate single-cell transcriptome dynamics.

SRGS: sparse partial least squares-based recursive gene selection for gene regulatory network inference

BACKGROUND

The identification of gene regulatory networks (GRNs) facilitates the understanding of the underlying molecular mechanism of various biological processes and complex diseases. With the availability of single-cell RNA sequencing data, it is essential to infer GRNs from single-cell expression. Although some GRN methods originally developed for bulk expression data can be applicable to single-cell data and several single-cell specific GRN algorithms were developed, recent benchmarking studies have emphasized the need of developing more accurate and robust GRN modeling methods that are compatible for single-cell expression data.

RESULTS

We present SRGS, SPLS (sparse partial least squares)-based recursive gene selection, to infer GRNs from bulk or single-cell expression data. SRGS recursively selects and scores the genes which may have regulations on the considered target gene based on SPLS. When dealing with gene expression data with dropouts, we randomly scramble samples, set some values in the expression matrix to zeroes, and generate multiple copies of data through multiple iterations to make SRGS more robust. We test SRGS on different kinds of expression data, including simulated bulk data, simulated single-cell data without and with dropouts, and experimental single-cell data, and also compared with the existing GRN methods, including the ones originally developed for bulk data, the ones developed specifically for single-cell data, and even the ones recommended by recent benchmarking studies.

CONCLUSIONS

It has been shown that SRGS is competitive with the existing GRN methods and effective in the gene regulatory network inference from bulk or single-cell gene expression data. SRGS is available at: https://github.com/JGuan-lab/SRGS .

Reconstructing gene regulatory networks of biological function using differential equations of multilayer perceptrons

BACKGROUND

Building biological networks with a certain function is a challenge in systems biology. For the functionality of small (less than ten nodes) biological networks, most methods are implemented by exhausting all possible network topological spaces. This exhaustive approach is difficult to scale to large-scale biological networks. And regulatory relationships are complex and often nonlinear or non-monotonic, which makes inference using linear models challenging.

RESULTS

In this paper, we propose a multi-layer perceptron-based differential equation method, which operates by training a fully connected neural network (NN) to simulate the transcription rate of genes in traditional differential equations. We verify whether the regulatory network constructed by the NN method can continue to achieve the expected biological function by verifying the degree of overlap between the regulatory network discovered by NN and the regulatory network constructed by the Hill function. And we validate our approach by adapting to noise signals, regulator knockout, and constructing large-scale gene regulatory networks using link-knockout techniques. We apply a real dataset (the mesoderm inducer Xenopus Brachyury expression) to construct the core topology of the gene regulatory network and find that Xbra is only strongly expressed at moderate levels of activin signaling.

CONCLUSION

We have demonstrated from the results that this method has the ability to identify the underlying network topology and functional mechanisms, and can also be applied to larger and more complex gene network topologies.

dynDeepDRIM: a dynamic deep learning model to infer direct regulatory interactions using time-course single-cell gene expression data

Time-course single-cell RNA sequencing (scRNA-seq) data have been widely used to explore dynamic changes in gene expression of transcription factors (TFs) and their target genes. This information is useful to reconstruct cell-type-specific gene regulatory networks (GRNs). However, the existing tools are commonly designed to analyze either time-course bulk gene expression data or static scRNA-seq data via pseudo-time cell ordering. A few methods successfully utilize the information from multiple time points while also considering the characteristics of scRNA-seq data. We proposed dynDeepDRIM, a novel deep learning model to reconstruct GRNs using time-course scRNA-seq data. It represents the joint expression of a gene pair as an image and utilizes the image of the target TF-gene pair and the ones of the potential neighbors to reconstruct GRNs from time-course scRNA-seq data. dynDeepDRIM can effectively remove the transitive TF-gene interactions by considering neighborhood context and model the gene expression dynamics using high-dimensional tensors. We compared dynDeepDRIM with six GRN reconstruction methods on both simulation and four real time-course scRNA-seq data. dynDeepDRIM achieved substantially better performance than the other methods in inferring TF-gene interactions and eliminated the false positives effectively. We also applied dynDeepDRIM to annotate gene functions and found it achieved evidently better performance than the other tools due to considering the neighbor genes.

MINI-EX: Integrative inference of single-cell gene regulatory networks in plants

Multicellular organisms, such as plants, are characterized by highly specialized and tightly regulated cell populations, establishing specific morphological structures and executing distinct functions. Gene regulatory networks (GRNs) describe condition-specific interactions of transcription factors (TFs) regulating the expression of target genes, underpinning these specific functions. As efficient and validated methods to identify cell-type-specific GRNs from single-cell data in plants are lacking, limiting our understanding of the organization of specific cell types in both model species and crops, we developed MINI-EX (Motif-Informed Network Inference based on single-cell EXpression data), an integrative approach to infer cell-type-specific networks in plants. MINI-EX uses single-cell transcriptomic data to define expression-based networks and integrates TF motif information to filter the inferred regulons, resulting in networks with increased accuracy. Next, regulons are assigned to different cell types, leveraging cell-specific expression, and candidate regulators are prioritized using network centrality measures, functional annotations, and expression specificity. This embedded prioritization strategy offers a unique and efficient means to unravel signaling cascades in specific cell types controlling a biological process of interest. We demonstrate the stability of MINI-EX toward input data sets with low number of cells and its robustness toward missing data, and show that it infers state-of-the-art networks with a better performance compared with other related single-cell network tools. MINI-EX successfully identifies key regulators controlling root development in Arabidopsis and rice, leaf development in Arabidopsis, and ear development in maize, enhancing our understanding of cell-type-specific regulation and unraveling the roles of different regulators controlling the development of specific cell types in plants.

Fuzzy and Rough Set Theory Based Computational Framework for Mining Genetic Interaction Triplets From Gene Expression Profiles for Lung Adenocarcinoma

Genetic interactions are very helpful in understanding different disease and discovering drugs for it. Compared to the gene pairs that represent the genetic interactions between two genes, the gene triplets are more informative and useful. However, existing works on genetic interactions among gene triplets have primarily focused on detecting gene triplets from time series gene expression profiles. Generating the time series gene expression profiles for humans is quite impracticable but the labeled gene expression profiles are available for different diseases in case of humans. In this paper, a computational framework has been proposed to detect gene triplets from labeled gene expression profiles. First, it employs Rough Set Theory for extracting the key genes and then designs a fuzzy inference system for generating possible gene triplets. Further, Root Mean Squared Error measure has been used to prune out the irrelevant gene triplets. In the present work, the proposed computational framework has been applied to labeled lung adenocarcinoma dataset and can be applied to any other labeled gene expression dataset. The extracted gene triplets and their functionalities have been verified with existing biological literature and benchmark databases and the results of verification signify that the proposed framework is promising in terms of finding useful genetic triplets. Further, the proposed framework has been found more efficient as compared to an existing mutual information-based technique in terms of detecting known genetic interactions.

IReNA: Integrated regulatory network analysis of single-cell transcriptomes and chromatin accessibility profiles

Recently, single-cell RNA sequencing (scRNA-seq) and single-cell assay for transposase-accessible chromatin using sequencing (scATAC-seq) have been developed to separately measure transcriptomes and chromatin accessibility profiles at the single-cell resolution. However, few methods can reliably integrate these data to perform regulatory network analysis. Here, we developed integrated regulatory network analysis (IReNA) for network inference through the integrated analysis of scRNA-seq and scATAC-seq data, network modularization, transcription factor enrichment, and construction of simplified intermodular regulatory networks. Using public datasets, we showed that integrated network analysis of scRNA-seq data with scATAC-seq data is more precise to identify known regulators than scRNA-seq data analysis alone. Moreover, IReNA outperformed currently available methods in identifying known regulators. IReNA facilitates the systems-level understanding of biological regulatory mechanisms and is available at https://github.com/jiang-junyao/IReNA.

spliceJAC: transition genes and state-specific gene regulation from single-cell transcriptome data

Extracting dynamical information from single-cell transcriptomics is a novel task with the promise to advance our understanding of cell state transition and interactions between genes. Yet, theory-oriented, bottom-up approaches that consider differences among cell states are largely lacking. Here, we present spliceJAC, a method to quantify the multivariate mRNA splicing from single-cell RNA sequencing (scRNA-seq). spliceJAC utilizes the unspliced and spliced mRNA count matrices to constructs cell state-specific gene-gene regulatory interactions and applies stability analysis to predict putative driver genes critical to the transitions between cell states. By applying spliceJAC to biological systems including pancreas endothelium development and epithelial-mesenchymal transition (EMT) in A549 lung cancer cells, we predict genes that serve specific signaling roles in different cell states, recover important differentially expressed genes in agreement with pre-existing analysis, and predict new transition genes that are either exclusive or shared between different cell state transitions.

Graph attention network for link prediction of gene regulations from single-cell RNA-sequencing data

MOTIVATION

Single-cell RNA sequencing (scRNA-seq) data provides unprecedented opportunities to reconstruct gene regulatory networks (GRNs) at fine-grained resolution. Numerous unsupervised or self-supervised models have been proposed to infer GRN from bulk RNA-seq data, but few of them are appropriate for scRNA-seq data under the circumstance of low signal-to-noise ratio and dropout. Fortunately, the surging of TF-DNA binding data (e.g. ChIP-seq) makes supervised GRN inference possible. We regard supervised GRN inference as a graph-based link prediction problem that expects to learn gene low-dimensional vectorized representations to predict potential regulatory interactions.

RESULTS

In this paper, we present GENELink to infer latent interactions between transcription factors (TFs) and target genes in GRN using graph attention network. GENELink projects the single-cell gene expression with observed TF-gene pairs to a low-dimensional space. Then, the specific gene representations are learned to serve for downstream similarity measurement or causal inference of pairwise genes by optimizing the embedding space. Compared to eight existing GRN reconstruction methods, GENELink achieves comparable or better performance on seven scRNA-seq datasets with four types of ground-truth networks. We further apply GENELink on scRNA-seq of human breast cancer metastasis and reveal regulatory heterogeneity of Notch and Wnt signalling pathways between primary tumour and lung metastasis. Moreover, the ontology enrichment results of unique lung metastasis GRN indicate that mitochondrial oxidative phosphorylation (OXPHOS) is functionally important during the seeding step of the cancer metastatic cascade, which is validated by pharmacological assays.

AVAILABILITY AND IMPLEMENTATION

The code and data are available at https://github.com/zpliulab/GENELink.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Angiogenesis goes computational - The future way forward to discover new angiogenic targets?

Multi-omics technologies are being increasingly utilized in angiogenesis research. Yet, computational methods have not been widely used for angiogenic target discovery and prioritization in this field, partly because (wet-lab) vascular biologists are insufficiently familiar with computational biology tools and the opportunities they may offer. With this review, written for vascular biologists who lack expertise in computational methods, we aspire to break boundaries between both fields and to illustrate the potential of these tools for future angiogenic target discovery. We provide a comprehensive survey of currently available computational approaches that may be useful in prioritizing candidate genes, predicting associated mechanisms, and identifying their specificity to endothelial cell subtypes. We specifically highlight tools that use flexible, machine learning frameworks for large-scale data integration and gene prioritization. For each purpose-oriented category of tools, we describe underlying conceptual principles, highlight interesting applications and discuss limitations. Finally, we will discuss challenges and recommend some guidelines which can help to optimize the process of accurate target discovery.

Boosting single-cell gene regulatory network reconstruction via bulk-cell transcriptomic data

Computational recovery of gene regulatory network (GRN) has recently undergone a great shift from bulk-cell towards designing algorithms targeting single-cell data. In this work, we investigate whether the widely available bulk-cell data could be leveraged to assist the GRN predictions for single cells. We infer cell-type-specific GRNs from both the single-cell RNA sequencing data and the generic GRN derived from the bulk cells by constructing a weakly supervised learning framework based on the axial transformer. We verify our assumption that the bulk-cell transcriptomic data are a valuable resource, which could improve the prediction of single-cell GRN by conducting extensive experiments. Our GRN-transformer achieves the state-of-the-art prediction accuracy in comparison to existing supervised and unsupervised approaches. In addition, we show that our method can identify important transcription factors and potential regulations for Alzheimer's disease risk genes by using the predicted GRN. Availability: The implementation of GRN-transformer is available at https://github.com/HantaoShu/GRN-Transformer.

INSISTC: Incorporating network structure information for single-cell type classification

Uncovering gene regulatory mechanisms in individual cells can provide insight into cell heterogeneity and function. Recent accumulated Single-Cell RNA-Seq data have made it possible to analyze gene regulation at single-cell resolution. Understanding cell-type-specific gene regulation can assist in more accurate cell type and state identification. Computational approaches utilizing such relationships are under development. Methods pioneering in integrating gene regulatory mechanism discovery with cell-type classification encounter challenges such as determine gene regulatory relationships and incorporate gene regulatory network structure. To fill this gap, we developed INSISTC, a computational method to incorporate gene regulatory network structure information for single-cell type classification. INSISTC is capable of identifying cell-type-specific gene regulatory mechanisms while performing single-cell type classification. INSISTC demonstrated its accuracy in cell type classification and its potential for providing insight into molecular mechanisms specific to individual cells. In comparison with the alternative methods, INSISTC demonstrated its complementary performance for gene regulation interpretation.

Understanding of the various aspects of gene regulatory networks related to crop improvement

The hierarchical relationship between transcription factors, associated proteins, and their target genes is defined by a gene regulatory network (GRN). GRNs allow us to understand how the genotype and environment of a plant are incorporated to control the downstream physiological responses. During plant growth or environmental acclimatization, GRNs are diverse and can be differently regulated across tissue types and organs. An overview of recent advances in the development of GRN that speed up basic and applied plant research is given here. Furthermore, the overview of genome and transcriptome involving GRN research along with the exciting advancement and application are discussed. In addition, different approaches to GRN predictions were elucidated. In this review, we also describe the role of GRN in crop improvement, crop plant manipulation, stress responses, speed breeding and identifying genetic variations/locus. Finally, the challenges and prospects of GRN in plant biology are discussed.

A probabilistic Boolean model on hair follicle cell fate regulation by TGF-β

Hair follicles (HFs) are mini skin organs that undergo cyclic growth. Various signals regulate HF cell fate decisions jointly. Recent experimental results suggest that transforming growth factor beta (TGF-β) exhibits a dual role in HF cell fate regulation that can be either anti- or pro-apoptosis. To understand the underlying mechanisms of HF cell fate control, we develop a novel probabilistic Boolean network (pBN) model on the HF epithelial cell gene regulation dynamics. First, the model is derived from literature, then refined using single-cell RNA sequencing data. Using the model, we both explore the mechanisms underlying HF cell fate decisions and make predictions that could potentially guide future experiments: 1) we propose that a threshold-like switch in the TGF-β strength may necessitate the dual roles of TGF-β in either activating apoptosis or cell proliferation, in cooperation with bone morphogenetic protein (BMP) and tumor necrosis factor (TNF) and at different stages of a follicle growth cycle; 2) our model shows concordance with the high-activator-low-inhibitor theory of anagen initiation; 3) we predict that TNF may be more effective in catagen initiation than TGF-β, and they may cooperate in a two-step fashion; 4) finally, predictions of gene knockout and overexpression reveal the roles in HF cell fate regulations of each gene. Attractor and motif analysis from the associated Boolean networks reveal the relations between the topological structure of the gene regulation network and the cell fate regulation mechanism. A discrete spatial model equipped with the pBN illustrates how TGF-β and TNF cooperate in initiating and driving the apoptosis wave during catagen.

SAREV: A review on statistical analytics of single-cell RNA sequencing data

Due to the development of next-generation RNA sequencing (NGS) technologies, there has been tremendous progress in research involving determining the role of genomics, transcriptomics and epigenomics in complex biological systems. However, scientists have realized that information obtained using earlier technology, frequently called 'bulk RNA-seq' data, provides information averaged across all the cells present in a tissue. Relatively newly developed single cell (scRNA-seq) technology allows us to provide transcriptomic information at a single-cell resolution. Nevertheless, these high-resolution data have their own complex natures and demand novel statistical data analysis methods to provide effective and highly accurate results on complex biological systems. In this review, we cover many such recently developed statistical methods for researchers wanting to pursue scRNA-seq statistical and computational research as well as scientific research about these existing methods and free software tools available for their generated data. This review is certainly not exhaustive due to page limitations. We have tried to cover the popular methods starting from quality control to the downstream analysis of finding differentially expressed genes and concluding with a brief description of network analysis.

Single_cell_GRN: gene regulatory network identification based on supervised learning method and Single-cell RNA-seq data

Single-cell RNA-seq overcomes the shortcomings of conventional transcriptome sequencing technology and could provide a powerful tool for distinguishing the transcriptome characteristics of various cell types in biological tissues, and comprehensively revealing the heterogeneity of gene expression between cells. Many Intelligent Computing methods have been presented to infer gene regulatory network (GRN) with single-cell RNA-seq data. In this paper, we investigate the performances of seven classifiers including support vector machine (SVM), random forest (RF), Naive Bayesian (NB), GBDT, logical regression (LR), decision tree (DT) and K-Nearest Neighbor (KNN) for solving the binary classification problems of GRN inference with single-cell RNA-seq data (Single_cell_GRN). In SVM, three different kernel functions (linear, polynomial and radial basis function) are utilized, respectively. Three real single-cell RNA-seq datasets from mouse and human are utilized. The experiment results prove that in most cases supervised learning methods (SVM, RF, NB, GBDT, LR, DT and KNN) perform better than unsupervised learning method (GENIE3) in terms of AUC. SVM, RF and KNN have the better performances than other four classifiers. In SVM, linear and polynomial kernels are more fit to model single-cell RNA-seq data.

Inferring Gene Regulatory Networks From Single-Cell Transcriptomic Data Using Bidirectional RNN

Accurate inference of gene regulatory rules is critical to understanding cellular processes. Existing computational methods usually decompose the inference of gene regulatory networks (GRNs) into multiple subproblems, rather than detecting potential causal relationships simultaneously, which limits the application to data with a small number of genes. Here, we propose BiRGRN, a novel computational algorithm for inferring GRNs from time-series single-cell RNA-seq (scRNA-seq) data. BiRGRN utilizes a bidirectional recurrent neural network to infer GRNs. The recurrent neural network is a complex deep neural network that can capture complex, non-linear, and dynamic relationships among variables. It maps neurons to genes, and maps the connections between neural network layers to the regulatory relationship between genes, providing an intuitive solution to model GRNs with biological closeness and mathematical flexibility. Based on the deep network, we transform the inference of GRNs into a regression problem, using the gene expression data at previous time points to predict the gene expression data at the later time point. Furthermore, we adopt two strategies to improve the accuracy and stability of the algorithm. Specifically, we utilize a bidirectional structure to integrate the forward and reverse inference results and exploit an incomplete set of prior knowledge to filter out some candidate inferences of low confidence. BiRGRN is applied to four simulated datasets and three real scRNA-seq datasets to verify the proposed method. We perform comprehensive comparisons between our proposed method with other state-of-the-art techniques. These experimental results indicate that BiRGRN is capable of inferring GRN simultaneously from time-series scRNA-seq data. Our method BiRGRN is implemented in Python using the TensorFlow machine-learning library, and it is freely available at https://gitee.com/DHUDBLab/bi-rgrn.

Connections for Matters of the Heart: Network Medicine in Cardiovascular Diseases

Cardiovascular diseases (CVD) are diverse disorders affecting the heart and vasculature in millions of people worldwide. Like other fields, CVD research has benefitted from the deluge of multiomics biomedical data. Current CVD research focuses on disease etiologies and mechanisms, identifying disease biomarkers, developing appropriate therapies and drugs, and stratifying patients into correct disease endotypes. Systems biology offers an alternative to traditional reductionist approaches and provides impetus for a comprehensive outlook toward diseases. As a focus area, network medicine specifically aids the translational aspect of in silico research. This review discusses the approach of network medicine and its application to CVD research.

Breaking the Immune Complexity of the Tumor Microenvironment Using Single-Cell Technologies

Tumors are not a simple aggregate of transformed cells but rather a complicated ecosystem containing various components, including infiltrating immune cells, tumor-related stromal cells, endothelial cells, soluble factors, and extracellular matrix proteins. Profiling the immune contexture of this intricate framework is now mandatory to develop more effective cancer therapies and precise immunotherapeutic approaches by identifying exact targets or predictive biomarkers, respectively. Conventional technologies are limited in reaching this goal because they lack high resolution. Recent developments in single-cell technologies, such as single-cell RNA transcriptomics, mass cytometry, and multiparameter immunofluorescence, have revolutionized the cancer immunology field, capturing the heterogeneity of tumor-infiltrating immune cells and the dynamic complexity of tenets that regulate cell networks in the tumor microenvironment. In this review, we describe some of the current single-cell technologies and computational techniques applied for immune-profiling the cancer landscape and discuss future directions of how integrating multi-omics data can guide a new "precision oncology" advancement.

Inference of Molecular Regulatory Systems Using Statistical Path-Consistency Algorithm

One of the key challenges in systems biology and molecular sciences is how to infer regulatory relationships between genes and proteins using high-throughout omics datasets. Although a wide range of methods have been designed to reverse engineer the regulatory networks, recent studies show that the inferred network may depend on the variable order in the dataset. In this work, we develop a new algorithm, called the statistical path-consistency algorithm (SPCA), to solve the problem of the dependence of variable order. This method generates a number of different variable orders using random samples, and then infers a network by using the path-consistent algorithm based on each variable order. We propose measures to determine the edge weights using the corresponding edge weights in the inferred networks, and choose the edges with the largest weights as the putative regulations between genes or proteins. The developed method is rigorously assessed by the six benchmark networks in DREAM challenges, the mitogen-activated protein (MAP) kinase pathway, and a cancer-specific gene regulatory network. The inferred networks are compared with those obtained by using two up-to-date inference methods. The accuracy of the inferred networks shows that the developed method is effective for discovering molecular regulatory systems.

Identification of condition-specific regulatory mechanisms in normal and cancerous human lung tissue

Background

Lung cancer is the leading cause of cancer death in both men and women. The most common lung cancer subtype is non-small cell lung carcinoma (NSCLC) comprising about 85% of all cases. NSCLC can be further divided into three subtypes: adenocarcinoma (LUAD), squamous cell carcinoma (LUSC), and large cell lung carcinoma. Specific genetic mutations and epigenetic aberrations play an important role in the developmental transition to a specific tumor subtype. The elucidation of normal lung versus lung tumor gene expression patterns and regulatory targets yields biomarker systems that discriminate lung phenotypes (i.e., biomarkers) and provide a foundation for the discovery of normal and aberrant gene regulatory mechanisms.

Results

We built condition-specific gene co-expression networks (csGCNs) for normal lung, LUAD, and LUSC conditions. Then, we integrated normal lung tissue-specific gene regulatory networks (tsGRNs) to elucidate control-target biomarker systems for normal and cancerous lung tissue. We characterized co-expressed gene edges, possibly under common regulatory control, for relevance in lung cancer.

Conclusions

Our approach demonstrates the ability to elucidate csGCN:tsGRN merged biomarker systems based on gene expression correlation and regulation. The biomarker systems we describe can be used to classify and further describe lung specimens. Our approach is generalizable and can be used to discover and interpret complex gene expression patterns for any condition or species.

Supplementary Information

The online version contains available at 10.1186/s12864-022-08591-9.

Dynamical Systems Model of RNA Velocity Improves Inference of Single-cell Trajectory, Pseudo-time and Gene Regulation

Recent development in inferring RNA velocity from single-cell RNA-seq opens up exciting new vista into developmental lineage and cellular dynamics. However, the estimated velocity only gives a snapshot of how the transcriptome instantaneously changes in individual cells, and it does not provide quantitative predictions and insights about the whole system. In this work, we develop RNA-ODE, a principled computational framework that extends RNA velocity to quantify systems level dynamics and improve single-cell data analysis. We model the gene expression dynamics by an ordinary differential equation (ODE) based formalism. Given a snapshot of gene expression at one time, RNA-ODE is able to predict and extrapolate the expression trajectory of each cell by solving the dynamic equations. Systematic experiments on simulations and on new data from developing brain demonstrate that RNA-ODE substantially improves many aspects of standard single-cell analysis. By leveraging temporal dynamics, RNA-ODE more accurately estimates cell state lineage and pseudo-time compared to previous state-of-the-art methods. It also infers gene regulatory networks and identifies influential genes whose expression changes can decide cell fate. We expect RNA-ODE to be a Swiss army knife that aids many facets of single-cell RNA-seq analysis.

SimiC enables the inference of complex gene regulatory dynamics across cell phenotypes

Single-cell RNA-Sequencing has the potential to provide deep biological insights by revealing complex regulatory interactions across diverse cell phenotypes at single-cell resolution. However, current single-cell gene regulatory network inference methods produce a single regulatory network per input dataset, limiting their capability to uncover complex regulatory relationships across related cell phenotypes. We present SimiC, a single-cell gene regulatory inference framework that overcomes this limitation by jointly inferring distinct, but related, gene regulatory dynamics per phenotype. We show that SimiC uncovers key regulatory dynamics missed by previously proposed methods across a range of systems, both model and non-model alike. In particular, SimiC was able to uncover CAR T cell dynamics after tumor recognition and key regulatory patterns on a regenerating liver, and was able to implicate glial cells in the generation of distinct behavioral states in honeybees. SimiC hence establishes a new approach to quantitating regulatory architectures between distinct cellular phenotypes, with far-reaching implications for systems biology.

Fusion prior gene network for high reliable single-cell gene regulatory network inference

Single-Cell RNA sequencing technology provides an opportunity to discover gene regulatory networks(GRN) that control cell differentiation and drive cell type transformation. However, it is faced with the challenge of high loss and high noise of sequencing data and contains many pseudo-connections. To solve these problems, we propose a framework called Fusion prior gene network for Gene Regulatory Network inference Accuracy Enhancement(FGRNAE) to infer a high reliable gene regulatory network. Specifically, based on the Single-Cell RNA-sequencing Network Propagation and network Fusion(scNPF) preprocessing framework, we employ the Random Walk with Restart on the prior gene network to interpolate the missing data. Furthermore, we infer the network using the Random Forest algorithm with the results achieved above. In addition, we apply data from the Co-Function Network to build a meta-gene network and select the regulatory connection with the Markov Random Field. Extensive experiments based on datasets from BEELINE validate the effectiveness of our framework for improving the accuracy of inference.

Guidelines for bioinformatics of single-cell sequencing data analysis in Alzheimer's disease: review, recommendation, implementation and application

Alzheimer's disease (AD) is the most common form of dementia, characterized by progressive cognitive impairment and neurodegeneration. Extensive clinical and genomic studies have revealed biomarkers, risk factors, pathways, and targets of AD in the past decade. However, the exact molecular basis of AD development and progression remains elusive. The emerging single-cell sequencing technology can potentially provide cell-level insights into the disease. Here we systematically review the state-of-the-art bioinformatics approaches to analyze single-cell sequencing data and their applications to AD in 14 major directions, including 1) quality control and normalization, 2) dimension reduction and feature extraction, 3) cell clustering analysis, 4) cell type inference and annotation, 5) differential expression, 6) trajectory inference, 7) copy number variation analysis, 8) integration of single-cell multi-omics, 9) epigenomic analysis, 10) gene network inference, 11) prioritization of cell subpopulations, 12) integrative analysis of human and mouse sc-RNA-seq data, 13) spatial transcriptomics, and 14) comparison of single cell AD mouse model studies and single cell human AD studies. We also address challenges in using human postmortem and mouse tissues and outline future developments in single cell sequencing data analysis. Importantly, we have implemented our recommended workflow for each major analytic direction and applied them to a large single nucleus RNA-sequencing (snRNA-seq) dataset in AD. Key analytic results are reported while the scripts and the data are shared with the research community through  GitHub. In summary, this comprehensive review provides insights into various approaches to analyze single cell sequencing data and offers specific guidelines for study design and a variety of analytic directions. The review and the accompanied software tools will serve as a valuable resource for studying cellular and molecular mechanisms of AD, other diseases, or biological systems at the single cell level.

Single-Cell Transcriptome and Network Analyses Unveil Key Transcription Factors Regulating Mesophyll Cell Development in Maize

Background: Maize mesophyll (M) cells play important roles in various biological processes such as photosynthesis II and secondary metabolism. Functional differentiation occurs during M-cell development, but the underlying mechanisms for regulating M-cell development are largely unknown. Results: We conducted single-cell RNA sequencing (scRNA-seq) to profile transcripts in maize leaves. We then identified coregulated modules by analyzing the resulting pseudo-time-series data through gene regulatory network analyses. WRKY, ERF, NAC, MYB and Heat stress transcription factor (HSF) families were highly expressed in the early stage, whereas CONSTANS (CO)-like (COL) and ERF families were highly expressed in the late stage of M-cell development. Construction of regulatory networks revealed that these transcript factor (TF) families, especially HSF and COL, were the major players in the early and later stages of M-cell development, respectively. Integration of scRNA expression matrix with TF ChIP-seq and Hi-C further revealed regulatory interactions between these TFs and their targets. HSF1 and COL8 were primarily expressed in the leaf bases and tips, respectively, and their targets were validated with protoplast-based ChIP-qPCR, with the binding sites of HSF1 being experimentally confirmed. Conclusions: Our study provides evidence that several TF families, with the involvement of epigenetic regulation, play vital roles in the regulation of M-cell development in maize.

Reconstruction of dynamic regulatory networks reveals signaling-induced topology changes associated with germ layer specification

Elucidating regulatory relationships between transcription factors (TFs) and target genes is fundamental to understanding how cells control their identity and behavior. Unfortunately, existing computational gene regulatory network (GRN) reconstruction methods are imprecise, computationally burdensome, and fail to reveal dynamic regulatory topologies. Here, we present Epoch, a reconstruction tool that uses single-cell transcriptomics to accurately infer dynamic networks. We apply Epoch to identify the dynamic networks underpinning directed differentiation of mouse embryonic stem cells (ESCs) guided by multiple signaling pathways, and we demonstrate that modulating these pathways drives topological changes that bias cell fate potential. We also find that Peg3 rewires the pluripotency network to favor mesoderm specification. By integrating signaling pathways with GRNs, we trace how Wnt activation and PI3K suppression govern mesoderm and endoderm specification, respectively. Finally, we identify regulatory circuits of patterning and axis formation that distinguish in vitro and in vivo mesoderm specification.

Network inference with Granger causality ensembles on single-cell transcriptomics

Cellular gene expression changes throughout a dynamic biological process, such as differentiation. Pseudotimes estimate cells' progress along a dynamic process based on their individual gene expression states. Ordering the expression data by pseudotime provides information about the underlying regulator-gene interactions. Because the pseudotime distribution is not uniform, many standard mathematical methods are inapplicable for analyzing the ordered gene expression states. Here we present single-cell inference of networks using Granger ensembles (SINGE), an algorithm for gene regulatory network inference from ordered single-cell gene expression data. SINGE uses kernel-based Granger causality regression to smooth irregular pseudotimes and missing expression values. It aggregates predictions from an ensemble of regression analyses to compile a ranked list of candidate interactions between transcriptional regulators and target genes. In two mouse embryonic stem cell differentiation datasets, SINGE outperforms other contemporary algorithms. However, a more detailed examination reveals caveats about poor performance for individual regulators and uninformative pseudotimes.

Single-Cell Differential Network Analysis with Sparse Bayesian Factor Models

Differential network analysis plays an important role in learning how gene interactions change under different biological conditions, and the high resolution of single-cell RNA (scRNA-seq) sequencing provides new opportunities to explore these changing gene-gene interactions. Here, we present a sparse hierarchical Bayesian factor model to identify differences across network structures from different biological conditions in scRNA-seq data. Our methodology utilizes latent factors to impact gene expression values for each cell to help account for zero-inflation, increased cell-to-cell variability, and overdispersion that are unique characteristics of scRNA-seq data. Condition-dependent parameters determine which latent factors are activated in a gene, which allows for not only the calculation of gene-gene co-expression within each group but also the calculation of the co-expression differences between groups. We highlight our methodology’s performance in detecting differential gene-gene associations across groups by analyzing simulated datasets and a SARS-CoV-2 case study dataset.

To the proteome and beyond: advances in single-cell omics profiling for plant systems

Recent advances in single-cell proteomics for animal systems could be adapted for plants to increase our understanding of plant development, response to stimuli, and cell-to-cell signaling.

The biology of time: dynamic responses of cell types to developmental, circadian and environmental cues

As sessile organisms, plants are finely tuned to respond dynamically to developmental, circadian and environmental cues. Genome-wide studies investigating these types of cues have uncovered the intrinsically different ways they can impact gene expression over time. Recent advances in single-cell sequencing and time-based bioinformatic algorithms are now beginning to reveal the dynamics of these time-based responses within individual cells and plant tissues. Here, we review what these techniques have revealed about the spatiotemporal nature of gene regulation, paying particular attention to the three distinct ways in which plant tissues are time sensitive. (i) First, we discuss how studying plant cell identity can reveal developmental trajectories hidden in pseudotime. (ii) Next, we present evidence that indicates that plant cell types keep their own local time through tissue-specific regulation of the circadian clock. (iii) Finally, we review what determines the speed of environmental signaling responses, and how they can be contingent on developmental and circadian time. By these means, this review sheds light on how these different scales of time-based responses can act with tissue and cell-type specificity to elicit changes in whole plant systems.

A hybrid deep learning framework for gene regulatory network inference from single-cell transcriptomic data

Inferring gene regulatory networks (GRNs) based on gene expression profiles is able to provide an insight into a number of cellular phenotypes from the genomic level and reveal the essential laws underlying various life phenomena. Different from the bulk expression data, single-cell transcriptomic data embody cell-to-cell variance and diverse biological information, such as tissue characteristics, transformation of cell types, etc. Inferring GRNs based on such data offers unprecedented advantages for making a profound study of cell phenotypes, revealing gene functions and exploring potential interactions. However, the high sparsity, noise and dropout events of single-cell transcriptomic data pose new challenges for regulation identification. We develop a hybrid deep learning framework for GRN inference from single-cell transcriptomic data, DGRNS, which encodes the raw data and fuses recurrent neural network and convolutional neural network (CNN) to train a model capable of distinguishing related gene pairs from unrelated gene pairs. To overcome the limitations of such datasets, it applies sliding windows to extract valuable features while preserving the direction of regulation. DGRNS is constructed as a deep learning model containing gated recurrent unit network for exploring time-dependent information and CNN for learning spatially related information. Our comprehensive and detailed comparative analysis on the dataset of mouse hematopoietic stem cells illustrates that DGRNS outperforms state-of-the-art methods. The networks inferred by DGRNS are about 16% higher than the area under the receiver operating characteristic curve of other unsupervised methods and 10% higher than the area under the precision recall curve of other supervised methods. Experiments on human datasets show the strong robustness and excellent generalization of DGRNS. By comparing the predictions with standard network, we discover a series of novel interactions which are proved to be true in some specific cell types. Importantly, DGRNS identifies a series of regulatory relationships with high confidence and functional consistency, which have not yet been experimentally confirmed and merit further research.

GRNUlar: A Deep Learning Framework for Recovering Single-Cell Gene Regulatory Networks

We propose GRNUlar, a novel deep learning framework for supervised learning of gene regulatory networks (GRNs) from single-cell RNA-Sequencing (scRNA-Seq) data. Our framework incorporates two intertwined models. First, we leverage the expressive ability of neural networks to capture complex dependencies between transcription factors and the corresponding genes they regulate, by developing a multitask learning framework. Second, to capture sparsity of GRNs observed in the real world, we design an unrolled algorithm technique for our framework. Our deep architecture requires supervision for training, for which we repurpose existing synthetic data simulators that generate scRNA-Seq data guided by an underlying GRN. Experimental results demonstrate that GRNUlar outperforms state-of-the-art methods on both synthetic and real data sets. Our study also demonstrates the novel and successful use of expression data simulators for supervised learning of GRN inference.

The use of machine learning to discover regulatory networks controlling biological systems

Biological systems are composed of a vast web of multiscale molecular interactors and interactions. High-throughput technologies, both bulk and single cell, now allow for investigation of the properties and quantities of these interactors. Computational algorithms and machine learning methods then provide the tools to derive meaningful insights from the resulting data sets. One such approach is graphical network modeling, which provides a computational framework to explicitly model the molecular interactions within and between the cells comprising biological systems. These graphical networks aim to describe a putative chain of cause and effect between interacting molecules. This feature allows for determination of key molecules in a biological process, accelerated generation of mechanistic hypotheses, and simulation of experimental outcomes. We review the computational concepts and applications of graphical network models across molecular scales for both intracellular and intercellular regulatory biology, examples of successful applications, and the future directions needed to overcome current limitations.