Temporal modelling using single-cell transcriptomics

Joint trajectory inference for single-cell genomics using deep learning with a mixture prior

Trajectory inference methods are essential for analyzing the developmental paths of cells in single-cell sequencing datasets. It provides insights into cellular differentiation, transitions, and lineage hierarchies, helping unravel the dynamic processes underlying development and disease progression. However, many existing tools lack a coherent statistical model and reliable uncertainty quantification, limiting their utility and robustness. In this paper, we introduce VITAE (Variational Inference for Trajectory by AutoEncoder), a statistical approach that integrates a latent hierarchical mixture model with variational autoencoders to infer trajectories. The statistical hierarchical model enhances the interpretability of our framework, while the posterior approximations generated by our variational autoencoder ensure computational efficiency and provide uncertainty quantification of cell projections along trajectories. Specifically, VITAE enables simultaneous trajectory inference and data integration, improving the accuracy of learning a joint trajectory structure in the presence of biological and technical heterogeneity across datasets. We show that VITAE outperforms other state-of-the-art trajectory inference methods on both real and synthetic data under various trajectory topologies. Furthermore, we apply VITAE to jointly analyze three distinct single-cell RNA sequencing datasets of the mouse neocortex, unveiling comprehensive developmental lineages of projection neurons. VITAE effectively reduces batch effects within and across datasets and uncovers finer structures that might be overlooked in individual datasets. Additionally, we showcase VITAE's efficacy in integrative analyses of multiomic datasets with continuous cell population structures.

FateNet: an integration of dynamical systems and deep learning for cell fate prediction

MOTIVATION

Understanding cellular decision-making, particularly its timing and impact on the biological system such as tissue health and function, is a fundamental challenge in biology and medicine. Existing methods for inferring fate decisions and cellular state dynamics from single-cell RNA sequencing data lack precision regarding decision points and broader tissue implications. Addressing this gap, we present FateNet, a computational approach integrating dynamical systems theory and deep learning to probe the cell decision-making process using scRNA-seq data.

RESULTS

By leveraging information about normal forms and scaling behavior near bifurcations common to many dynamical systems, FateNet predicts cell decision occurrence with higher accuracy than conventional methods and offers qualitative insights into the new state of the biological system. Also, through in-silico perturbation experiments, FateNet identifies key genes and pathways governing the differentiation process in hematopoiesis. Validated using different scRNA-seq data, FateNet emerges as a user-friendly and valuable tool for predicting critical points in biological processes, providing insights into complex trajectories.

AVAILABILITY AND IMPLEMENTATION

github.com/ThomasMBury/fatenet.

scNODE : generative model for temporal single cell transcriptomic data prediction

SUMMARY

Measurement of single-cell gene expression at different timepoints enables the study of cell development. However, due to the resource constraints and technical challenges associated with the single-cell experiments, researchers can only profile gene expression at discrete and sparsely sampled timepoints. This missing timepoint information impedes downstream cell developmental analyses. We propose scNODE, an end-to-end deep learning model that can predict in silico single-cell gene expression at unobserved timepoints. scNODE integrates a variational autoencoder with neural ordinary differential equations to predict gene expression using a continuous and nonlinear latent space. Importantly, we incorporate a dynamic regularization term to learn a latent space that is robust against distribution shifts when predicting single-cell gene expression at unobserved timepoints. Our evaluations on three real-world scRNA-seq datasets show that scNODE achieves higher predictive performance than state-of-the-art methods. We further demonstrate that scNODE's predictions help cell trajectory inference under the missing timepoint paradigm and the learned latent space is useful for in silico perturbation analysis of relevant genes along a developmental cell path.

AVAILABILITY AND IMPLEMENTATION

The data and code are publicly available at https://github.com/rsinghlab/scNODE.

Single-Cell RNA-Sequencing: Opening New Horizons for Breast Cancer Research

Breast cancer is the most prevalent malignant tumor among women with high heterogeneity. Traditional techniques frequently struggle to comprehensively capture the intricacy and variety of cellular states and interactions within breast cancer. As global precision medicine rapidly advances, single-cell RNA sequencing (scRNA-seq) has become a highly effective technique, revolutionizing breast cancer research by offering unprecedented insights into the cellular heterogeneity and complexity of breast cancer. This cutting-edge technology facilitates the analysis of gene expression profiles at the single-cell level, uncovering diverse cell types and states within the tumor microenvironment. By dissecting the cellular composition and transcriptional signatures of breast cancer cells, scRNA-seq provides new perspectives for understanding the mechanisms behind tumor therapy, drug resistance and metastasis in breast cancer. In this review, we summarized the working principle and workflow of scRNA-seq and emphasized the major applications and discoveries of scRNA-seq in breast cancer research, highlighting its impact on our comprehension of breast cancer biology and its potential for guiding personalized treatment strategies.

scGPT: toward building a foundation model for single-cell multi-omics using generative AI

Generative pretrained models have achieved remarkable success in various domains such as language and computer vision. Specifically, the combination of large-scale diverse datasets and pretrained transformers has emerged as a promising approach for developing foundation models. Drawing parallels between language and cellular biology (in which texts comprise words; similarly, cells are defined by genes), our study probes the applicability of foundation models to advance cellular biology and genetic research. Using burgeoning single-cell sequencing data, we have constructed a foundation model for single-cell biology, scGPT, based on a generative pretrained transformer across a repository of over 33 million cells. Our findings illustrate that scGPT effectively distills critical biological insights concerning genes and cells. Through further adaptation of transfer learning, scGPT can be optimized to achieve superior performance across diverse downstream applications. This includes tasks such as cell type annotation, multi-batch integration, multi-omic integration, perturbation response prediction and gene network inference.

Single-cell omics: experimental workflow, data analyses and applications

Cells are the fundamental units of biological systems and exhibit unique development trajectories and molecular features. Our exploration of how the genomes orchestrate the formation and maintenance of each cell, and control the cellular phenotypes of various organismsis, is both captivating and intricate. Since the inception of the first single-cell RNA technology, technologies related to single-cell sequencing have experienced rapid advancements in recent years. These technologies have expanded horizontally to include single-cell genome, epigenome, proteome, and metabolome, while vertically, they have progressed to integrate multiple omics data and incorporate additional information such as spatial scRNA-seq and CRISPR screening. Single-cell omics represent a groundbreaking advancement in the biomedical field, offering profound insights into the understanding of complex diseases, including cancers. Here, we comprehensively summarize recent advances in single-cell omics technologies, with a specific focus on the methodology section. This overview aims to guide researchers in selecting appropriate methods for single-cell sequencing and related data analysis.

An increment of diversity method for cell state trajectory inference of time-series scRNA-seq data

The increasing emergence of the time-series single-cell RNA sequencing (scRNA-seq) data, inferring developmental trajectory by connecting transcriptome similar cell states (i.e., cell types or clusters) has become a major challenge. Most existing computational methods are designed for individual cells and do not take into account the available time series information. We present IDTI based on the Increment of Diversity for Trajectory Inference, which combines time series information and the minimum increment of diversity method to infer cell state trajectory of time-series scRNA-seq data. We apply IDTI to simulated and three real diverse tissue development datasets, and compare it with six other commonly used trajectory inference methods in terms of topology similarity and branching accuracy. The results have shown that the IDTI method accurately constructs the cell state trajectory without the requirement of starting cells. In the performance test, we further demonstrate that IDTI has the advantages of high accuracy and strong robustness.

Integrating patients in time series clinical transcriptomics data

MOTIVATION

Analysis of time series transcriptomics data from clinical trials is challenging. Such studies usually profile very few time points from several individuals with varying response patterns and dynamics. Current methods for these datasets are mainly based on linear, global orderings using visit times which do not account for the varying response rates and subgroups within a patient cohort.

RESULTS

We developed a new method that utilizes multi-commodity flow algorithms for trajectory inference in large scale clinical studies. Recovered trajectories satisfy individual-based timing restrictions while integrating data from multiple patients. Testing the method on multiple drug datasets demonstrated an improved performance compared to prior approaches suggested for this task, while identifying novel disease subtypes that correspond to heterogeneous patient response patterns.

AVAILABILITY AND IMPLEMENTATION

The source code and instructions to download the data have been deposited on GitHub at https://github.com/euxhenh/Truffle.

Optimal sequencing budget allocation for trajectory reconstruction of single cells

BACKGROUND

Charting cellular trajectories over gene expression is key to understanding dynamic cellular processes and their underlying mechanisms. While advances in single-cell RNA-sequencing technologies and computational methods have pushed forward the recovery of such trajectories, trajectory inference remains a challenge due to the noisy, sparse, and high-dimensional nature of single-cell data. This challenge can be alleviated by increasing either the number of cells sampled along the trajectory (breadth) or the sequencing depth, i.e. the number of reads captured per cell (depth). Generally, these two factors are coupled due to an inherent breadth-depth tradeoff that arises when the sequencing budget is constrained due to financial or technical limitations.

RESULTS

Here we study the optimal allocation of a fixed sequencing budget to optimize the recovery of trajectory attributes. Empirical results reveal that reconstruction accuracy of internal cell structure in expression space scales with the logarithm of either the breadth or depth of sequencing. We additionally observe a power law relationship between the optimal number of sampled cells and the corresponding sequencing budget. For linear trajectories, non-monotonicity in trajectory reconstruction across the breadth-depth tradeoff can impact downstream inference, such as expression pattern analysis along the trajectory. We demonstrate these results for five single-cell RNA-sequencing datasets encompassing differentiation of embryonic stem cells, pancreatic beta cells, hepatoblast and multipotent hematopoietic cells, as well as induced reprogramming of embryonic fibroblasts into neurons. By addressing the challenges of single-cell data, our study offers insights into maximizing the efficiency of cellular trajectory analysis through strategic allocation of sequencing resources.

From transcriptomics to digital twins of organ function

Cell level functions underlie tissue and organ physiology. Gene expression patterns offer extensive views of the pathways and processes within and between cells. Single cell transcriptomics provides detailed information on gene expression within cells, cell types, subtypes and their relative proportions in organs. Functional pathways can be scalably connected to physiological functions at the cell and organ levels. Integrating experimentally obtained gene expression patterns with prior knowledge of pathway interactions enables identification of networks underlying whole cell functions such as growth, contractility, and secretion. These pathways can be computationally modeled using differential equations to simulate cell and organ physiological dynamics regulated by gene expression changes. Such computational systems can be thought of as parts of digital twins of organs. Digital twins, at the core, need computational models that represent in detail and simulate how dynamics of pathways and networks give rise to whole cell level physiological functions. Integration of transcriptomic responses and numerical simulations could simulate and predict whole cell functional outputs from transcriptomic data. We developed a computational pipeline that integrates gene expression timelines and systems of coupled differential equations to generate cell-type selective dynamical models. We tested our integrative algorithm on the eicosanoid biosynthesis network in macrophages. Converting transcriptomic changes to a dynamical model allowed us to predict dynamics of prostaglandin and thromboxane synthesis and secretion by macrophages that matched published lipidomics data obtained in the same experiments. Integration of cell-level system biology simulations with genomic and clinical data using a knowledge graph framework will allow us to create explicit predictive models that mechanistically link genomic determinants to organ function. Such integration requires a multi-domain ontological framework to connect genomic determinants to gene expression and cell pathways and functions to organ level phenotypes in healthy and diseased states. These integrated scalable models of tissues and organs as accurate digital twins predict health and disease states for precision medicine.

Longitudinal single-cell data informs deterministic modelling of inflammatory bowel disease

Single-cell-based methods such as flow cytometry or single-cell mRNA sequencing (scRNA-seq) allow deep molecular and cellular profiling of immunological processes. Despite their high throughput, however, these measurements represent only a snapshot in time. Here, we explore how longitudinal single-cell-based datasets can be used for deterministic ordinary differential equation (ODE)-based modelling to mechanistically describe immune dynamics. We derived longitudinal changes in cell numbers of colonic cell types during inflammatory bowel disease (IBD) from flow cytometry and scRNA-seq data of murine colitis using ODE-based models. Our mathematical model generalised well across different protocols and experimental techniques, and we hypothesised that the estimated model parameters reflect biological processes. We validated this prediction of cellular turnover rates with KI-67 staining and with gene expression information from the scRNA-seq data not used for model fitting. Finally, we tested the translational relevance of the mathematical model by deconvolution of longitudinal bulk mRNA-sequencing data from a cohort of human IBD patients treated with olamkicept. We found that neutrophil depletion may contribute to IBD patients entering remission. The predictive power of IBD deterministic modelling highlights its potential to advance our understanding of immune dynamics in health and disease.

SCTC: inference of developmental potential from single-cell transcriptional complexity

Inferring the developmental potential of single cells from scRNA-Seq data and reconstructing the pseudo-temporal path of cell development are fundamental but challenging tasks in single-cell analysis. Although single-cell transcriptional diversity (SCTD) measured by the number of expressed genes per cell has been widely used as a hallmark of developmental potential, it may lead to incorrect estimation of differentiation states in some cases where gene expression does not decrease monotonously during the development process. In this study, we propose a novel metric called single-cell transcriptional complexity (SCTC), which draws on insights from the economic complexity theory and takes into account the sophisticated structure information of scRNA-Seq count matrix. We show that SCTC characterizes developmental potential more accurately than SCTD, especially in the early stages of development where cells typically have lower diversity but higher complexity than those in the later stages. Based on the SCTC, we provide an unsupervised method for accurate, robust, and transferable inference of single-cell pseudotime. Our findings suggest that the complexity emerging from the interplay between cells and genes determines the developmental potential, providing new insights into the understanding of biological development from the perspective of complexity theory.

Decoding changes in tumor-infiltrating leukocytes through dynamic experimental models and single-cell technologies

The ability to characterize immune cells and explore the molecular interactions that govern their functions has never been greater, fueled in recent years by the revolutionary advance of single-cell analysis platforms. However, precisely how immune cells respond to different stimuli and where differentiation processes and effector functions operate remain incompletely understood. Inferring cellular fate within single-cell transcriptomic analyses is now omnipresent, despite the assumptions typically required in such analyses. Recently developed experimental models support dynamic analyses of the immune response, providing insights into the temporal changes that occur within cells and the tissues in which such transitions occur. Here we will review these approaches and discuss how these can be combined with single-cell technologies to develop a deeper understanding of the immune responses that should support the development of better therapeutic options for patients.

Gene regulatory network topology governs resistance and treatment escape in glioma stem-like cells

Poor prognosis and drug resistance in glioblastoma (GBM) can result from cellular heterogeneity and treatment-induced shifts in phenotypic states of tumor cells, including dedifferentiation into glioma stem-like cells (GSCs). This rare tumorigenic cell subpopulation resists temozolomide, undergoes proneural-to-mesenchymal transition (PMT) to evade therapy, and drives recurrence. Through inference of transcriptional regulatory networks (TRNs) of patient-derived GSCs (PD-GSCs) at single-cell resolution, we demonstrate how the topology of transcription factor interaction networks drives distinct trajectories of cell-state transitions in PD-GSCs resistant or susceptible to cytotoxic drug treatment. By experimentally testing predictions based on TRN simulations, we show that drug treatment drives surviving PD-GSCs along a trajectory of intermediate states, exposing vulnerability to potentiated killing by siRNA or a second drug targeting treatment-induced transcriptional programs governing nongenetic cell plasticity. Our findings demonstrate an approach to uncover TRN topology and use it to rationally predict combinatorial treatments that disrupt acquired resistance in GBM.

Nanoscale Methods for Longitudinal Extraction of Intracellular Contents

Longitudinal analysis of intracellular contents including gene and protein expression is crucial for deciphering the fundamentally dynamic nature of cells. This offers invaluable insights into complex tissue composition and behavior, and drives progress in disease diagnosis, biomarker discovery, and drug development. Traditional longitudinal analysis workflows, involving the destruction of cells at various timepoints, limit insights to singular moments and fail to account for cellular heterogeneity. Current non-destructive approaches, like temporal modeling with single-cell ribonucleic acid sequencing (RNA-seq) and live-cell fluorescence imaging, either rely on biological assumptions or possess the risk of cellular perturbation. Recent advances in nanoscale technologies for non-destructive intracellular content extraction offer a promising solution to these challenges. These novel methods work at the nanoscale to non-destructively access cellular membranes and can be broadly classified into three mechanisms: tip-facilitated aspiration, membrane-based, and probe-based methods. This perspective focuses on these emerging nanotechnologies for repeated intracellular content extraction. Their potential in longitudinal analysis is discussed, the critical requirements for effective repeated sampling are addressed, and the suitability of each technique for various applications is explored. Furthermore, unresolved challenges in repeated sampling are highlighted to encourage further research in this growing field.

Unveiling gene regulatory networks during cellular state transitions without linkage across time points

Time-stamped cross-sectional data, which lack linkage across time points, are commonly generated in single-cell transcriptional profiling. Many previous methods for inferring gene regulatory networks (GRNs) driving cell-state transitions relied on constructing single-cell temporal ordering. Introducing COSLIR (COvariance restricted Sparse LInear Regression), we presented a direct approach to reconstructing GRNs that govern cell-state transitions, utilizing only the first and second moments of samples between two consecutive time points. Simulations validated COSLIR's perfect accuracy in the oracle case and demonstrated its robust performance in real-world scenarios. When applied to single-cell RT-PCR and RNAseq datasets in developmental biology, COSLIR competed favorably with existing methods. Notably, its running time remained nearly independent of the number of cells. Therefore, COSLIR emerges as a promising addition to GRN reconstruction methods under cell-state transitions, bypassing the single-cell temporal ordering to enhance accuracy and efficiency in single-cell transcriptional profiling.

LogicGep: Boolean networks inference using symbolic regression from time-series transcriptomic profiling data

Reconstructing the topology of gene regulatory network from gene expression data has been extensively studied. With the abundance functional transcriptomic data available, it is now feasible to systematically decipher regulatory interaction dynamics in a logic form such as a Boolean network (BN) framework, which qualitatively indicates how multiple regulators aggregated to affect a common target gene. However, inferring both the network topology and gene interaction dynamics simultaneously is still a challenging problem since gene expression data are typically noisy and data discretization is prone to information loss. We propose a new method for BN inference from time-series transcriptional profiles, called LogicGep. LogicGep formulates the identification of Boolean functions as a symbolic regression problem that learns the Boolean function expression and solve it efficiently through multi-objective optimization using an improved gene expression programming algorithm. To avoid overly emphasizing dynamic characteristics at the expense of topology structure ones, as traditional methods often do, a set of promising Boolean formulas for each target gene is evolved firstly, and a feed-forward neural network trained with continuous expression data is subsequently employed to pick out the final solution. We validated the efficacy of LogicGep using multiple datasets including both synthetic and real-world experimental data. The results elucidate that LogicGep adeptly infers accurate BN models, outperforming other representative BN inference algorithms in both network topology reconstruction and the identification of Boolean functions. Moreover, the execution of LogicGep is hundreds of times faster than other methods, especially in the case of large network inference.

Causal gene regulatory analysis with RNA velocity reveals an interplay between slow and fast transcription factors

Single-cell expression dynamics, from differentiation trajectories or RNA velocity, have the potential to reveal causal links between transcription factors (TFs) and their target genes in gene regulatory networks (GRNs). However, existing methods either overlook these expression dynamics or necessitate that cells be ordered along a linear pseudotemporal axis, which is incompatible with branching trajectories. We introduce Velorama, an approach to causal GRN inference that represents single-cell differentiation dynamics as a directed acyclic graph of cells, constructed from pseudotime or RNA velocity measurements. Additionally, Velorama enables the estimation of the speed at which TFs influence target genes. Applying Velorama, we uncover evidence that the speed of a TF's interactions is tied to its regulatory function. For human corticogenesis, we find that slow TFs are linked to gliomas, while fast TFs are associated with neuropsychiatric diseases. We expect Velorama to become a critical part of the RNA velocity toolkit for investigating the causal drivers of differentiation and disease.

Powerful and accurate detection of temporal gene expression patterns from multi-sample multi-stage single-cell transcriptomics data with TDEseq

We present a non-parametric statistical method called TDEseq that takes full advantage of smoothing splines basis functions to account for the dependence of multiple time points in scRNA-seq studies, and uses hierarchical structure linear additive mixed models to model the correlated cells within an individual. As a result, TDEseq demonstrates powerful performance in identifying four potential temporal expression patterns within a specific cell type. Extensive simulation studies and the analysis of four published scRNA-seq datasets show that TDEseq can produce well-calibrated p-values and up to 20% power gain over the existing methods for detecting temporal gene expression patterns.

Microfluidic platform for omics analysis on single cells with diverse morphology and size: A review

BACKGROUND

Microfluidic techniques have emerged as powerful tools in single-cell research, facilitating the exploration of omics information from individual cells. Cell morphology is crucial for gene expression and physiological processes. However, there is currently a lack of integrated analysis of morphology and single-cell omics information. A critical challenge remains: what platform technologies are the best option to decode omics data of cells that are complex in morphology and size?

RESULTS

This review highlights achievements in microfluidic-based single-cell omics and isolation of cells based on morphology, along with other cell sorting methods based on physical characteristics. Various microfluidic platforms for single-cell isolation are systematically presented, showcasing their diversity and adaptability. The discussion focuses on microfluidic devices tailored to the distinct single-cell isolation requirements in plants and animals, emphasizing the significance of considering cell morphology and cell size in optimizing single-cell omics strategies. Simultaneously, it explores the application of microfluidic single-cell sorting technologies to single-cell sequencing, aiming to effectively integrate information about cell shape and size.

SIGNIFICANCE AND NOVELTY

The novelty lies in presenting a comprehensive overview of recent accomplishments in microfluidic-based single-cell omics, emphasizing the integration of different microfluidic platforms and their implications for cell morphology-based isolation. By underscoring the pivotal role of the specialized morphology of different cells in single-cell research, this review provides robust support for delving deeper into the exploration of single-cell omics data.

Single-cell nanobiopsy enables multigenerational longitudinal transcriptomics of cancer cells

Single-cell RNA sequencing has revolutionized our understanding of cellular heterogeneity, but routine methods require cell lysis and fail to probe the dynamic trajectories responsible for cellular state transitions, which can only be inferred. Here, we present a nanobiopsy platform that enables the injection of exogenous molecules and multigenerational longitudinal cytoplasmic sampling from a single cell and its progeny. The technique is based on scanning ion conductance microscopy (SICM) and, as a proof of concept, was applied to longitudinally profile the transcriptome of single glioblastoma (GBM) brain tumor cells in vitro over 72 hours. The GBM cells were biopsied before and after exposure to chemotherapy and radiotherapy, and our results suggest that treatment either induces or selects for more transcriptionally stable cells. We envision the nanobiopsy will contribute to transforming standard single-cell transcriptomics from a static analysis into a dynamic assay.

CDSKNNXMBD: a novel clustering framework for large-scale single-cell data based on a stable graph structure

BACKGROUND

Accurate and efficient cell grouping is essential for analyzing single-cell transcriptome sequencing (scRNA-seq) data. However, the existing clustering techniques often struggle to provide timely and accurate cell type groupings when dealing with datasets with large-scale or imbalanced cell types. Therefore, there is a need for improved methods that can handle the increasing size of scRNA-seq datasets while maintaining high accuracy and efficiency.

METHODS

We propose CDSKNNXMBD (Community Detection based on a Stable K-Nearest Neighbor Graph Structure), a novel single-cell clustering framework integrating partition clustering algorithm and community detection algorithm, which achieves accurate and fast cell type grouping by finding a stable graph structure.

RESULTS

We evaluated the effectiveness of our approach by analyzing 15 tissues from the human fetal atlas. Compared to existing methods, CDSKNN effectively counteracts the high imbalance in single-cell data, enabling effective clustering. Furthermore, we conducted comparisons across multiple single-cell datasets from different studies and sequencing techniques. CDSKNN is of high applicability and robustness, and capable of balancing the complexities of across diverse types of data. Most importantly, CDSKNN exhibits higher operational efficiency on datasets at the million-cell scale, requiring an average of only 6.33 min for clustering 1.46 million single cells, saving 33.3% to 99% of running time compared to those of existing methods.

CONCLUSIONS

The CDSKNN is a flexible, resilient, and promising clustering tool that is particularly suitable for clustering imbalanced data and demonstrates high efficiency on large-scale scRNA-seq datasets.

Opticool: Cutting-edge transgenic optical tools

Only a few short decades have passed since the sequencing of GFP, yet the modern repertoire of transgenically encoded optical tools implies an exponential proliferation of ever improving constructions to interrogate the subcellular environment. A myriad of tags for labeling proteins, RNA, or DNA have arisen in the last few decades, facilitating unprecedented visualization of subcellular components and processes. Development of a broad array of modern genetically encoded sensors allows real-time, in vivo detection of molecule levels, pH, forces, enzyme activity, and other subcellular and extracellular phenomena in ever expanding contexts. Optogenetic, genetically encoded optically controlled manipulation systems have gained traction in the biological research community and facilitate single-cell, real-time modulation of protein function in vivo in ever broadening, novel applications. While this field continues to explosively expand, references are needed to assist scientists seeking to use and improve these transgenic devices in new and exciting ways to interrogate development and disease. In this review, we endeavor to highlight the state and trajectory of the field of in vivo transgenic optical tools.

Gene regulatory network topology governs resistance and treatment escape in glioma stem-like cells

Poor prognosis and drug resistance in glioblastoma (GBM) can result from cellular heterogeneity and treatment-induced shifts in phenotypic states of tumor cells, including dedifferentiation into glioma stem-like cells (GSCs). This rare tumorigenic cell subpopulation resists temozolomide, undergoes proneural-to-mesenchymal transition (PMT) to evade therapy, and drives recurrence. Through inference of transcriptional regulatory networks (TRNs) of patient-derived GSCs (PD-GSCs) at single-cell resolution, we demonstrate how the topology of transcription factor interaction networks drives distinct trajectories of cell state transitions in PD-GSCs resistant or susceptible to cytotoxic drug treatment. By experimentally testing predictions based on TRN simulations, we show that drug treatment drives surviving PD-GSCs along a trajectory of intermediate states, exposing vulnerability to potentiated killing by siRNA or a second drug targeting treatment-induced transcriptional programs governing non-genetic cell plasticity. Our findings demonstrate an approach to uncover TRN topology and use it to rationally predict combinatorial treatments that disrupts acquired resistance in GBM.

Resolving cellular dynamics using single-cell temporal transcriptomics

Cellular dynamics, the transition of a cell from one state to another, is central to understanding developmental processes and disease progression. Single-cell transcriptomics has been pushing the frontiers of cellular dynamics studies into a genome-wide and single-cell level. While most single-cell RNA sequencing approaches are disruptive and only provide a snapshot of cell states, the dynamics of a cell could be reconstructed by either exploiting temporal information hiding in the transcriptomics data or integrating additional information. In this review, we describe these approaches, highlighting their underlying principles, key assumptions, and the rationality to interpret the results as models. We also discuss the recently emerging nondisruptive live-cell transcriptomics methods, which are highly complementary to the computational models for their assumption-free nature.

Time-resolved single-cell transcriptomics defines immune trajectories in glioblastoma

Deciphering the cell-state transitions underlying immune adaptation across time is fundamental for advancing biology. Empirical in vivo genomic technologies that capture cellular dynamics are currently lacking. We present Zman-seq, a single-cell technology recording transcriptomic dynamics across time by introducing time stamps into circulating immune cells, tracking them in tissues for days. Applying Zman-seq resolved cell-state and molecular trajectories of the dysfunctional immune microenvironment in glioblastoma. Within 24 hours of tumor infiltration, cytotoxic natural killer cells transitioned to a dysfunctional program regulated by TGFB1 signaling. Infiltrating monocytes differentiated into immunosuppressive macrophages, characterized by the upregulation of suppressive myeloid checkpoints Trem2, Il18bp, and Arg1, over 36 to 48 hours. Treatment with an antagonistic anti-TREM2 antibody reshaped the tumor microenvironment by redirecting the monocyte trajectory toward pro-inflammatory macrophages. Zman-seq is a broadly applicable technology, enabling empirical measurements of differentiation trajectories, which can enhance the development of more efficacious immunotherapies.

Inferring Tree-Shaped Single-Cell Trajectories with Totem

Single-cell transcriptomics allows unbiased characterization of cell heterogeneity in a sample by profiling gene expression at single-cell level. These profiles capture snapshots of transient or steady states in dynamic processes, such as cell cycle, activation, or differentiation, which can be computationally ordered into a "flip-book" of cell development using trajectory inference methods. However, prediction of more complex topology structures, such as multifurcations or trees, remains challenging. In this chapter, we present two user-friendly protocols for inferring tree-shaped single-cell trajectories and pseudotime from single-cell transcriptomics data with Totem. Totem is a trajectory inference method that offers flexibility in inferring both nonlinear and linear trajectories and usability by avoiding the cumbersome fine-tuning of parameters. The QuickStart protocol provides a simple and practical example, whereas the GuidedStart protocol details the analysis step-by-step. Both protocols are demonstrated using a case study of human bone marrow CD34+ cells, allowing the study of the branching of three lineages: erythroid, lymphoid, and myeloid. All the analyses can be fully reproduced in Linux, macOS, and Windows operating systems (amd64 architecture) with >8 Gb of RAM using the provided docker image distributed with notebooks, scripts, and data in Docker Hub (elolab/repro-totem-ti). These materials are shared online under open-source license at https://elolab.github.io/Totem-protocol .

Therapeutic uses of oxytocin in stress-related neuropsychiatric disorders

Oxytocin (OXT), produced and secreted in the paraventricular nucleus and supraoptic nucleus of magnocellular and parvocellular neurons. The diverse presence and activity of oxytocin suggests a potential for this neuropeptide in the pathogenesis and treatment of stress-related neuropsychiatric disorders (anxiety, depression and post-traumatic stress disorder (PTSD)). For a more comprehensive understanding of the mechanism of OXT's anti-stress action, the signaling cascade of OXT binding to targeting stress were summarized. Then the advance of OXT treatment in depression, anxiety, PTSD and the major projection region of OXT neuron were discussed. Further, the efficacy of endogenous and exogenous OXT in stress responses were highlighted in this review. To augment the level of OXT in stress-related neuropsychiatric disorders, current biological strategies were summarized to shed a light on the treatment of stress-induced psychiatric disorders. We also conclude some of the major puzzles in the therapeutic uses of OXT in stress-related neuropsychiatric disorders. Although some questions remain to be resolved, OXT has an enormous potential therapeutic use as a hormone that regulates stress responses.

Deciphering tumor-infiltrating dendritic cells in the single-cell era

Dendritic cells (DCs) serve as a pivotal link connecting innate and adaptive immunity by processing tumor-derived antigens and activating T cells. The advent of single-cell sequencing has revolutionized the categorization of DCs, enabling a high-resolution characterization of the previously unrecognized diversity of DC populations infiltrating the intricate tumor microenvironment (TME). The application of single-cell sequencing technologies has effectively elucidated the heterogeneity of DCs present in the tumor milieu, yielding invaluable insights into their subpopulation structures and functional diversity. This review provides a comprehensive summary of the current state of knowledge regarding DC subtypes in the TME, drawing from single-cell studies conducted across various human tumors. We focused on the categorization, functions, and interactions of distinct DC subsets, emphasizing their crucial roles in orchestrating tumor-related immune responses. Additionally, we delve into the potential implications of these findings for the identification of predictive biomarkers and therapeutic targets. Enhanced insight into the intricate interplay between DCs and the TME promises to advance our comprehension of tumor immunity and, in turn, pave the way for the development of more efficacious cancer immunotherapies.

Adversarial training improves model interpretability in single-cell RNA-seq analysis

Motivation

Predictive computational models must be accurate, robust, and interpretable to be considered reliable in important areas such as biology and medicine. A sufficiently robust model should not have its output affected significantly by a slight change in the input. Also, these models should be able to explain how a decision is made to support user trust in the results. Efforts have been made to improve the robustness and interpretability of predictive computational models independently; however, the interaction of robustness and interpretability is poorly understood.

Results

As an example task, we explore the computational prediction of cell type based on single-cell RNA-seq data and show that it can be made more robust by adversarially training a deep learning model. Surprisingly, we find this also leads to improved model interpretability, as measured by identifying genes important for classification using a range of standard interpretability methods. Our results suggest that adversarial training may be generally useful to improve deep learning robustness and interpretability and that it should be evaluated on a range of tasks.

Availability and implementation

Our Python implementation of all analysis in this publication can be found at: https://github.com/MehrshadSD/robustness-interpretability. The analysis was conducted using numPy 0.2.5, pandas 2.0.3, scanpy 1.9.3, tensorflow 2.10.0, matplotlib 3.7.1, seaborn 0.12.2, sklearn 1.1.1, shap 0.42.0, lime 0.2.0.1, matplotlib_venn 0.11.9.

Digitize your Biology! Modeling multicellular systems through interpretable cell behavior

Cells are fundamental units of life, constantly interacting and evolving as dynamical systems. While recent spatial multi-omics can quantitate individual cells' characteristics and regulatory programs, forecasting their evolution ultimately requires mathematical modeling. We develop a conceptual framework-a cell behavior hypothesis grammar-that uses natural language statements (cell rules) to create mathematical models. This allows us to systematically integrate biological knowledge and multi-omics data to make them computable. We can then perform virtual "thought experiments" that challenge and extend our understanding of multicellular systems, and ultimately generate new testable hypotheses. In this paper, we motivate and describe the grammar, provide a reference implementation, and demonstrate its potential through a series of examples in tumor biology and immunotherapy. Altogether, this approach provides a bridge between biological, clinical, and systems biology researchers for mathematical modeling of biological systems at scale, allowing the community to extrapolate from single-cell characterization to emergent multicellular behavior.

Macrophage heterogeneity in the single-cell era: facts and artifacts

In this spotlight, we review technical issues that compromise single-cell analysis of tissue macrophages, including limited and unrepresentative yields, fragmentation and generation of remnants, and activation during tissue disaggregation. These issues may lead to a misleading definition of subpopulations of macrophages and the expression of macrophage-specific transcripts by unrelated cells. Recognition of the technical limitations of single-cell approaches is required in order to map the full spectrum of tissue-resident macrophage heterogeneity and assess its biological significance.

Principles and challenges of modeling temporal and spatial omics data

Studies with temporal or spatial resolution are crucial to understand the molecular dynamics and spatial dependencies underlying a biological process or system. With advances in high-throughput omic technologies, time- and space-resolved molecular measurements at scale are increasingly accessible, providing new opportunities to study the role of timing or structure in a wide range of biological questions. At the same time, analyses of the data being generated in the context of spatiotemporal studies entail new challenges that need to be considered, including the need to account for temporal and spatial dependencies and compare them across different scales, biological samples or conditions. In this Review, we provide an overview of common principles and challenges in the analysis of temporal and spatial omics data. We discuss statistical concepts to model temporal and spatial dependencies and highlight opportunities for adapting existing analysis methods to data with temporal and spatial dimensions.

Inferring single-cell transcriptomic dynamics with structured latent gene expression dynamics

Gene expression dynamics provide directional information for trajectory inference from single-cell RNA sequencing data. Traditional approaches compute RNA velocity using strict modeling assumptions about transcription and splicing of RNA. This can fail in scenarios where multiple lineages have distinct gene dynamics or where rates of transcription and splicing are time dependent. We present "LatentVelo," an approach to compute a low-dimensional representation of gene dynamics with deep learning. LatentVelo embeds cells into a latent space with a variational autoencoder and models differentiation dynamics on this "dynamics-based" latent space with neural ordinary differential equations. LatentVelo infers a latent regulatory state that controls the dynamics of an individual cell to model multiple lineages. LatentVelo can predict latent trajectories, describing the inferred developmental path for individual cells rather than just local RNA velocity vectors. The dynamics-based embedding batch corrects cell states and velocities, outperforming comparable autoencoder batch correction methods that do not consider gene expression dynamics.

Microfluidic design in single-cell sequencing and application to cancer precision medicine

Single-cell sequencing (SCS) is a crucial tool to reveal the genetic and functional heterogeneity of tumors, providing unique insights into the clonal evolution, microenvironment, drug resistance, and metastatic progression of cancers. Microfluidics is a critical component of many SCS technologies and workflows, conferring advantages in throughput, economy, and automation. Here, we review the current landscape of microfluidic architectures and sequencing techniques for single-cell omics analysis and highlight how these have enabled recent applications in oncology research. We also discuss the challenges and the promise of microfluidics-based single-cell analysis in the future of precision oncology.

Inferring chromatin accessibility during murine hematopoiesis through phylogenetic analysis

OBJECTIVE

Diversification of cell types and changes in epigenetic states during cell differentiation processes are important for understanding development. Recently, phylogenetic analysis using DNA methylation and histone modification information has been shown useful for inferring these processes. The purpose of this study was to examine whether chromatin accessibility data can help infer these processes in murine hematopoiesis.

RESULTS

Chromatin accessibility data could partially infer the hematopoietic differentiation hierarchy. Furthermore, based on the ancestral state estimation of internal nodes, the open/closed chromatin states of differentiating progenitor cells could be predicted with a specificity of 0.86-0.99 and sensitivity of 0.29-0.72. These results suggest that the phylogenetic analysis of chromatin accessibility could offer important information on cell differentiation, particularly for organisms from which progenitor cells are difficult to obtain.

Single cell multiomic analysis reveals diabetes-associated β-cell heterogeneity driven by HNF1A

Broad heterogeneity in pancreatic β-cell function and morphology has been widely reported. However, determining which components of this cellular heterogeneity serve a diabetes-relevant function remains challenging. Here, we integrate single-cell transcriptome, single-nuclei chromatin accessibility, and cell-type specific 3D genome profiles from human islets and identify Type II Diabetes (T2D)-associated β-cell heterogeneity at both transcriptomic and epigenomic levels. We develop a computational method to explicitly dissect the intra-donor and inter-donor heterogeneity between single β-cells, which reflect distinct mechanisms of T2D pathogenesis. Integrative transcriptomic and epigenomic analysis identifies HNF1A as a principal driver of intra-donor heterogeneity between β-cells from the same donors; HNF1A expression is also reduced in β-cells from T2D donors. Interestingly, HNF1A activity in single β-cells is significantly associated with lower Na+ currents and we nominate a HNF1A target, FXYD2, as the primary mitigator. Our study demonstrates the value of investigating disease-associated single-cell heterogeneity and provides new insights into the pathogenesis of T2D.

Single-cell lipidomics enabled by dual-polarity ionization and ion mobility-mass spectrometry imaging

Single-cell (SC) analysis provides unique insight into individual cell dynamics and cell-to-cell heterogeneity. Here, we utilize trapped ion mobility separation coupled with dual-polarity ionization mass spectrometry imaging (MSI) to enable high-throughput in situ profiling of the SC lipidome. Multimodal SC imaging, in which dual-polarity-mode MSI is used to perform serial data acquisition runs on individual cells, significantly enhanced SC lipidome coverage. High-spatial resolution SC-MSI identifies both inter- and intracellular lipid heterogeneity; this heterogeneity is further explicated by Uniform Manifold Approximation and Projection and machine learning-driven classifications. We characterize SC lipidome alteration in response to stearoyl-CoA desaturase 1 inhibition and, additionally, identify cell-layer specific lipid distribution patterns in mouse cerebellar cortex. This integrated multimodal SC-MSI technology enables high-resolution spatial mapping of intercellular and cell-to-cell lipidome heterogeneity, SC lipidome remodeling induced by pharmacological intervention, and region-specific lipid diversity within tissue.

Advances in single-cell RNA sequencing and its applications in cancer research

Cancers are a group of heterogeneous diseases characterized by the acquisition of functional capabilities during the transition from a normal to a neoplastic state. Powerful experimental and computational tools can be applied to elucidate the mechanisms of occurrence, progression, metastasis, and drug resistance; however, challenges remain. Bulk RNA sequencing techniques only reflect the average gene expression in a sample, making it difficult to understand tumor heterogeneity and the tumor microenvironment. The emergence and development of single-cell RNA sequencing (scRNA-seq) technologies have provided opportunities to understand subtle changes in tumor biology by identifying distinct cell subpopulations, dissecting the tumor microenvironment, and characterizing cellular genomic mutations. Recently, scRNA-seq technology has been increasingly used in cancer studies to explore tumor heterogeneity and the tumor microenvironment, which has increased the understanding of tumorigenesis and evolution. This review summarizes the basic processes and development of scRNA-seq technologies and their increasing applications in cancer research and clinical practice.

Spatial transcriptomics: recent developments and insights in respiratory research

The respiratory system's complex cellular heterogeneity presents unique challenges to researchers in this field. Although bulk RNA sequencing and single-cell RNA sequencing (scRNA-seq) have provided insights into cell types and heterogeneity in the respiratory system, the relevant specific spatial localization and cellular interactions have not been clearly elucidated. Spatial transcriptomics (ST) has filled this gap and has been widely used in respiratory studies. This review focuses on the latest iterative technology of ST in recent years, summarizing how ST can be applied to the physiological and pathological processes of the respiratory system, with emphasis on the lungs. Finally, the current challenges and potential development directions are proposed, including high-throughput full-length transcriptome, integration of multi-omics, temporal and spatial omics, bioinformatics analysis, etc. These viewpoints are expected to advance the study of systematic mechanisms, including respiratory studies.

Spatial mapping of cellular senescence: emerging challenges and opportunities

Cellular senescence is a well-established driver of aging and age-related diseases. There are many challenges to mapping senescent cells in tissues such as the absence of specific markers and their relatively low abundance and vast heterogeneity. Single-cell technologies have allowed unprecedented characterization of senescence; however, many methodologies fail to provide spatial insights. The spatial component is essential, as senescent cells communicate with neighboring cells, impacting their function and the composition of extracellular space. The Cellular Senescence Network (SenNet), a National Institutes of Health (NIH) Common Fund initiative, aims to map senescent cells across the lifespan of humans and mice. Here, we provide a comprehensive review of the existing and emerging methodologies for spatial imaging and their application toward mapping senescent cells. Moreover, we discuss the limitations and challenges inherent to each technology. We argue that the development of spatially resolved methods is essential toward the goal of attaining an atlas of senescent cells.

Understanding tumour endothelial cell heterogeneity and function from single-cell omics

Anti-angiogenic therapies (AATs) are used to treat different types of cancers. However, their success is limited owing to insufficient efficacy and resistance. Recently, single-cell omics studies of tumour endothelial cells (TECs) have provided new mechanistic insight. Here, we overview the heterogeneity of human TECs of all tumour types studied to date, at the single-cell level. Notably, most human tumour types contain varying numbers but only a small population of angiogenic TECs, the presumed targets of AATs, possibly contributing to the limited efficacy of and resistance to AATs. In general, TECs are heterogeneous within and across all tumour types, but comparing TEC phenotypes across tumours is currently challenging, owing to the lack of a uniform nomenclature for endothelial cells and consistent single-cell analysis protocols, urgently raising the need for a more consistent approach. Nonetheless, across most tumour types, universal TEC markers (ACKR1, PLVAP and IGFBP3) can be identified. Besides angiogenesis, biological processes such as immunomodulation and extracellular matrix organization are among the most commonly predicted enriched signatures of TECs across different tumour types. Although angiogenesis and extracellular matrix targets have been considered for AAT (without the hoped success), the immunomodulatory properties of TECs have not been fully considered as a novel anticancer therapeutic approach. Therefore, we also discuss progress, limitations, solutions and novel targets for AAT development.

E3 ubiquitin ligases in cancer stem cells: key regulators of cancer hallmarks and novel therapeutic opportunities

BACKGROUND

Human malignancies are composed of heterogeneous subpopulations of cancer cells with phenotypic and functional diversity. Among them, a unique subset of cancer stem cells (CSCs) has both the capacity for self-renewal and the potential to differentiate and contribute to multiple tumor properties. As such, CSCs are promising cellular targets for effective cancer therapy. At the molecular level, hyper-activation of multiple stemness regulatory signaling pathways and downstream transcription factors play critical roles in controlling CSCs establishment and maintenance. To regulate CSC properties, these stemness pathways are controlled by post-translational modifications including, but not limited to phosphorylation, acetylation, methylation, and ubiquitination.

CONCLUSION

In this review, we focus on E3 ubiquitin ligases and their roles and mechanisms in regulating essential hallmarks of CSCs, such as self-renewal, invasion and metastasis, metabolic reprogramming, immune evasion, and therapeutic resistance. Moreover, we discuss emerging therapeutic approaches to eliminate CSCs through targeting E3 ubiquitin ligases by chemical inhibitors and proteolysis-targeting chimera (PROTACs) which are currently under development at the discovery, preclinical, and clinical stages. Several outstanding issues such as roles for E3 ubiquitin ligases in heterogeneity and phenotypical/functional evolution of CSCs remain to be studied under pathologically and clinically relevant conditions. With the rapid application of functional genomic and proteomic approaches at single cell, spatiotemporal, and even single molecule levels, we anticipate that more specific and precise functions of E3 ubiquitin ligases will be delineated in dictating CSC properties. Rational design and proper translation of these mechanistic understandings may lead to novel therapeutic modalities for cancer procession medicine.

Applications of single-cell RNA sequencing in drug discovery and development

Single-cell technologies, particularly single-cell RNA sequencing (scRNA-seq) methods, together with associated computational tools and the growing availability of public data resources, are transforming drug discovery and development. New opportunities are emerging in target identification owing to improved disease understanding through cell subtyping, and highly multiplexed functional genomics screens incorporating scRNA-seq are enhancing target credentialling and prioritization. ScRNA-seq is also aiding the selection of relevant preclinical disease models and providing new insights into drug mechanisms of action. In clinical development, scRNA-seq can inform decision-making via improved biomarker identification for patient stratification and more precise monitoring of drug response and disease progression. Here, we illustrate how scRNA-seq methods are being applied in key steps in drug discovery and development, and discuss ongoing challenges for their implementation in the pharmaceutical industry.

Neural cell diversity in the light of single-cell transcriptomics

The development of highly parallel and affordable high-throughput single-cell transcriptomics technologies has revolutionized our understanding of brain complexity. These methods have been used to build cellular maps of the brain, its different regions, and catalog the diversity of cells in each of them during development, aging and even in disease. Now we know that cellular diversity is way beyond what was previously thought. Single-cell transcriptomics analyses have revealed that cell types previously considered homogeneous based on imaging techniques differ depending on several factors including sex, age and location within the brain. The expression profiles of these cells have also been exploited to understand which are the regulatory programs behind cellular diversity and decipher the transcriptional pathways driving them. In this review, we summarize how single-cell transcriptomics have changed our view on the cellular diversity in the human brain, and how it could impact the way we study neurodegenerative diseases. Moreover, we describe the new computational approaches that can be used to study cellular differentiation and gain insight into the functions of individual cell populations under different conditions and their alterations in disease.

Single-cell RNA sequencing in skeletal muscle developmental biology

Skeletal muscle is the most extensive tissue in mammals, and they perform several functions; it is derived from paraxial mesodermal somites and undergoes hyperplasia and hypertrophy to form multinucleated, contractile, and functional muscle fibers. Skeletal muscle is a complex heterogeneous tissue composed of various cell types that establish communication strategies to exchange biological information; therefore, characterizing the cellular heterogeneity and transcriptional signatures of skeletal muscle is central to understanding its ontogeny's details. Studies of skeletal myogenesis have focused primarily on myogenic cells' proliferation, differentiation, migration, and fusion and ignored the intricate network of cells with specific biological functions. The rapid development of single-cell sequencing technology has recently enabled the exploration of skeletal muscle cell types and molecular events during development. This review summarizes the progress in single-cell RNA sequencing and its applications in skeletal myogenesis, which will provide insights into skeletal muscle pathophysiology.

Emergence of division of labor in tissues through cell interactions and spatial cues

Most cell types in multicellular organisms can perform multiple functions. However, not all functions can be optimally performed simultaneously by the same cells. Functions incompatible at the level of individual cells can be performed at the cell population level, where cells divide labor and specialize in different functions. Division of labor can arise due to instruction by tissue environment or through self-organization. Here, we develop a computational framework to investigate the contribution of these mechanisms to division of labor within a cell-type population. By optimizing collective cellular task performance under trade-offs, we find that distinguishable expression patterns can emerge from cell-cell interactions versus instructive signals. We propose a method to construct ligand-receptor networks between specialist cells and use it to infer division-of-labor mechanisms from single-cell RNA sequencing (RNA-seq) and spatial transcriptomics data of stromal, epithelial, and immune cells. Our framework can be used to characterize the complexity of cell interactions within tissues.

Matters arising: Insufficient evidence that pancreatic β cells are derived from adult ductal Neurog3-expressing progenitors

Understanding the origin of pancreatic β cells has profound implications for regenerative therapies in diabetes. For over a century, it was widely held that adult pancreatic duct cells act as endocrine progenitors, but lineage-tracing experiments challenged this dogma. Gribben et al. recently used two existing lineage-tracing models and single-cell RNA sequencing to conclude that adult pancreatic ducts contain endocrine progenitors that differentiate to insulin-expressing β cells at a physiologically important rate. We now offer an alternative interpretation of these experiments. Our data indicate that the two Cre lines that were used directly label adult islet somatostatin-producing ∂ cells, which precludes their use to assess whether β cells originate from duct cells. Furthermore, many labeled ∂ cells, which have an elongated neuron-like shape, were likely misclassified as β cells because insulin-somatostatin coimmunolocalizations were not used. We conclude that most evidence so far indicates that endocrine and exocrine lineage borders are rarely crossed in the adult pancreas.

Depicting pseudotime-lagged causality across single-cell trajectories for accurate gene-regulatory inference

Identifying the causal interactions in gene-regulatory networks requires an accurate understanding of the time-lagged relationships between transcription factors and their target genes. Here we describe DELAY (short for Depicting Lagged Causality), a convolutional neural network for the inference of gene-regulatory relationships across pseudotime-ordered single-cell trajectories. We show that combining supervised deep learning with joint probability matrices of pseudotime-lagged trajectories allows the network to overcome important limitations of ordinary Granger causality-based methods, for example, the inability to infer cyclic relationships such as feedback loops. Our network outperforms several common methods for inferring gene regulation and, when given partial ground-truth labels, predicts novel regulatory networks from single-cell RNA sequencing (scRNA-seq) and single-cell ATAC sequencing (scATAC-seq) data sets. To validate this approach, we used DELAY to identify important genes and modules in the regulatory network of auditory hair cells, as well as likely DNA-binding partners for two hair cell cofactors (Hist1h1c and Ccnd1) and a novel binding sequence for the hair cell-specific transcription factor Fiz1. We provide an easy-to-use implementation of DELAY under an open-source license at https://github.com/calebclayreagor/DELAY.