Gene Regulatory Relationships Research Articles

Refining computational inference of gene regulatory networks: integrating knockout data within a multi-task framework.

Constructing accurate gene regulatory network s (GRNs), which reflect the dynamic governing process between genes, is critical to understanding the diverse cellular process and unveiling the complexities in biological systems. With the development of computer sciences, computational-based approaches have been applied to the GRNs inference task. However, current methodologies face challenges in effectively utilizing existing topological information and prior knowledge of gene regulatory relationships, hindering the comprehensive understanding and accurate reconstruction of GRNs. In response, we propose a novel graph neural network (GNN)-based Multi-Task Learning framework for GRN reconstruction, namely MTLGRN. Specifically, we first encode the gene promoter sequences and the gene biological features and concatenate the corresponding feature representations. Then, we construct a multi-task learning framework including GRN reconstruction, Gene knockout predict, and Gene expression matrix reconstruction. With joint training, MTLGRN can optimize the gene latent representations by integrating gene knockout information, promoter characteristics, and other biological attributes. Extensive experimental results demonstrate superior performance compared with state-of-the-art baselines on the GRN reconstruction task, efficiently leveraging biological knowledge and comprehensively understanding the gene regulatory relationships. MTLGRN also pioneered attempts to simulate gene knockouts on bulk data by incorporating gene knockout information.

Reconstruction of gene regulatory networks for Caenorhabditis elegans using tree-shaped gene expression data.

Constructing gene regulatory networks is a widely adopted approach for investigating gene regulation, offering diverse applications in biology and medicine. A great deal of research focuses on using time series data or single-cell RNA-sequencing data to infer gene regulatory networks. However, such gene expression data lack either cellular or temporal information. Fortunately, the advent of time-lapse confocal laser microscopy enables biologists to obtain tree-shaped gene expression data of Caenorhabditis elegans, achieving both cellular and temporal resolution. Although such tree-shaped data provide abundant knowledge, they pose challenges like non-pairwise time series, laying the inaccuracy of downstream analysis. To address this issue, a comprehensive framework for data integration and a novel Bayesian approach based on Boolean network with time delay are proposed. The pre-screening process and Markov Chain Monte Carlo algorithm are applied to obtain the parameter estimates. Simulation studies show that our method outperforms existing Boolean network inference algorithms. Leveraging the proposed approach, gene regulatory networks for five subtrees are reconstructed based on the real tree-shaped datatsets of Caenorhabditis elegans, where some gene regulatory relationships confirmed in previous genetic studies are recovered. Also, heterogeneity of regulatory relationships in different cell lineage subtrees is detected. Furthermore, the exploration of potential gene regulatory relationships that bear importance in human diseases is undertaken. All source code is available at the GitHub repository https://github.com/edawu11/BBTD.git.

A gene regulatory network-aware graph learning method for cell identity annotation in single-cell RNA-seq data.

Cell identity annotation for single-cell transcriptome data is a crucial process for constructing cell atlases, unraveling pathogenesis, and inspiring therapeutic approaches. Currently, the efficacy of existing methodologies is contingent upon specific data sets. Nevertheless, such data are often sourced from various batches, sequencing technologies, tissues, and even species. Notably, the gene regulatory relationship remains unaffected by the aforementioned factors, highlighting the extensive gene interactions within organisms. Therefore, we propose scHGR, an automated annotation tool designed to leverage gene regulatory relationships in constructing gene-mediated cell communication graphs for single-cell transcriptome data. This strategy helps reduce noise from diverse data sources while establishing distant cellular connections, yielding valuable biological insights. Experiments involving 22 scenarios demonstrate that scHGR precisely and consistently annotates cell identities, benchmarked against state-of-the-art methods. Crucially, scHGR uncovers novel subtypes within peripheral blood mononuclear cells, specifically from CD4+ T cells and cytotoxic T cells. Furthermore, by characterizing a cell atlas comprising 56 cell types for COVID-19 patients, scHGR identifies vital factors like IL1 and calcium ions, offering insights for targeted therapeutic interventions.

A comprehensive evaluation of large language models in mining gene relations and pathway knowledge.

Understanding complex biological pathways, including gene-gene interactions and gene regulatory networks, is critical for exploring disease mechanisms and drug development. Manual literature curation of biological pathways cannot keep up with the exponential growth of new discoveries in the literature. Large-scale language models (LLMs) trained on extensive text corpora contain rich biological information, and they can be mined as a biological knowledge graph. This study assesses 21 LLMs, including both application programming interface (API)-based models and open-source models in their capacities of retrieving biological knowledge. The evaluation focuses on predicting gene regulatory relations (activation, inhibition, and phosphorylation) and the Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway components. Results indicated a significant disparity in model performance. API-based models GPT-4 and Claude-Pro showed superior performance, with an F1 score of 0.4448 and 0.4386 for the gene regulatory relation prediction, and a Jaccard similarity index of 0.2778 and 0.2657 for the KEGG pathway prediction, respectively. Open-source models lagged behind their API-based counterparts, whereas Falcon-180b and llama2-7b had the highest F1 scores of 0.2787 and 0.1923 in gene regulatory relations, respectively. The KEGG pathway recognition had a Jaccard similarity index of 0.2237 for Falcon-180b and 0.2207 for llama2-7b. Our study suggests that LLMs are informative in gene network analysis and pathway mapping, but their effectiveness varies, necessitating careful model selection. This work also provides a case study and insight into using LLMs das knowledge graphs. Our code is publicly available at the website of GitHub (Muh-aza).

Abstract 4944: Divergent proteogenomic gene expression is driven by microenvironment across tumor types

Abstract Solid tumors develop through a complex series of genome and downstream expression alterations that interact with the local tissue microenvironment, leading to a transformed cell and malignant phenotype. With massive multi-omic data, recent proteogenomics studies have jointly analyzed RNA and protein expression to uncover new gene regulatory relationships; however, many of these studies focused on single tumor types and lack a generalizable view of joint RNA and protein expression. Here, we present the first pan-cancer analysis of sample-wise RNA to protein correlation (SRPC). We re-analyzed over 1,000 tumors across 10 tumor types from published proteogenomic data from the Clinical Proteomic Tumor Analysis Consortium (CPTAC) and the Applied Proteogenomics OrganizationaL Learning and Outcomes (APOLLO) Research Network. We identified a wide range of SRPC across all tumors (ρ range: -0.08 to 0.70, median: 0.45). We then analyzed tumor pathologic and molecular characteristics versus the range of SRPC. High SRPC tumors had high tumor purity by pathology review, by somatic DNA whole exome sequencing, and by RNA and protein purity scores. In contrast, low SRPC tumors had high immune cell and stromal cell expression scores as inferred by either protein or RNA based signatures. We observed marked differences in cell type populations estimated by expression in different SRPC tumor tranches (low SRPC: macrophages, endothelial cells, cancer-associated fibroblasts; high SRPC: CD4+ Th2 cells). Tumors expressed signaling pathways depending on their SRPC (low SRPC: hypoxia, inflammatory response, and KRAS signaling; high SRPC: DNA repair and E2F targets). SRPC also stratifies tumors with distinct somatic DNA alterations (low SRPC: HRAS and NF2; high SRPC: TP53, MEN1, high Tumor Mutational Burden and high DNA chromosomal instability). Finally, we found that cancer driver genes displayed divergent gene-wise RNA to protein correlations (GRPC) among tumor types with a median absolute deviation interquartile range of 0.1 - 0.2, suggesting tumor-type-specific regulation. In summary, divergent RNA and protein expression is driven, in part, by tumor microenvironment composition across tumor types. Tumors with a diverse cellular microenvironment display a summation of RNA and protein expression resulting from this cell type diversity leading to a low SRPC, while tumors predominated by tumor cells display coordinated RNA and protein expression levels resulting from a pure clonal or cell type leading to a high SRPC. This first deep analysis into sample-wise RNA to protein correlation represents a large proteogenomic community resource for informing biomarker analysis by modality and by tranches of tumor microenvironment. The views expressed in this abstract are solely of the authors and do not reflect the official policy of the Departments of Army/Navy/Air Force, Department of Defense, USUHS, HJF, or U.S. Government. Citation Format: Joseph LaMorte, Nicholas Bateman, Thomas Conrads, Robert F. Browning, Craig D. Shriver, Robert L. Kortum, Matthew D. Wilkerson. Divergent proteogenomic gene expression is driven by microenvironment across tumor types [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 4944.

Abstract 4943: Benchmarking unpaired single-cell RNA and single-cell ATAC integration

Abstract The integration of single-cell RNA-sequencing (scRNA-seq) and single-cell ATAC-sequencing (scATAC-seq) data offers a unique opportunity to gain a comprehensive view of cellular identity with defining features and to infer gene-regulatory relationships. Despite the emergence of technologies that simultaneously capture both the gene expression and chromatin accessibility of individual cells (paired data), the practical challenges of these approaches (e.g., the unavailability in previous samples and prohibitive cost) have led researchers to turn to the existing trove of single-modality data generated from independent biological samples (unpaired data). Various computational tools have been developed to integrate these unpaired single modality datasets. However, the comparative performance of these tools has not been comprehensively evaluated, and a standard benchmark pipeline is still lacking. To address these challenges, we used pseudo-unpaired scRNA-seq and scATAC-seq data derived from publicly available paired single-cell multi-omics datasets to benchmark 14 publicly available integration methods. The primary goal of unpaired single-cell multi-omics integration is to narrow the omics gap while preserving cell type diversity. We therefore focused on pair-wise cell distance and cluster performance in the joint latent space constructed by various integration tools in our benchmarking pipeline. To ensure the robustness of these computational approaches, we examined their stability across a variety of scenarios, including variations in cell number, cell types, and biological and technical batch effects. A number of the integration methods tested produced promising results. While the widely used Seurat package was recently reported to have the best performance (Lee et al., Genome Biology 2023), other computational tools such as scVI, Cobolt, scJoint, scglue and scBridge performed equally well or better in reducing omics differences and facilitating the identification of cell clusters. Notably, scglue and Cobolt demonstrated strong performance in aligning the same cell from different modalities, and discrete clusters emerged in the joint latent space using scJoint and scBridge. These findings suggest that it may not be strictly necessary to use paired multi-omics data to guide integration to achieve favorable results. Our freely available benchmarking pipeline will empower researchers to identify the optimal data integration methods for their specific data, facilitate the benchmarking of new methods, and contribute to future method development in the field. Citation Format: Jiani Chen, Wanzi Xiao, Eric Zhang, Xiang Chen. Benchmarking unpaired single-cell RNA and single-cell ATAC integration [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 4943.

Integrated Bioinformatics and Multi-Omics Analyses Reveal Possible Molecular Mechanisms for Seed Starch Content Differences between Glycine max and Cicer arietinum

Although soybean and chickpea belong to the legume family, their seed starch content is very different. Currently, many studies focus on the molecular mechanisms of starch synthesis within a single species. However, the key genes and regulatory relationships responsible for the difference in seed starch content between the two species remain unknown. To elucidate the molecular mechanisms responsible for the above difference, multi-omics and bioinformatics analyses were used here to analyze gene expression patterns, protein–protein interaction networks, gene-transcription factor co-expression networks, and miRNA–gene regulatory relationships based on reported sucrose and starch metabolic genes in Arabidopsis. The results were as follows. First, seven differential expression genes of the two species in starch synthesis metabolism, including GBSS1, APL3, APS1, SS2, PTST, SBE2, and ISA, and the starch degradation gene BMY in soybean and chickpea, may contribute to their seed starch content differences. Then, the protein–protein interaction between DPEs and PHS may facilitate seed starch synthesis in chickpea. Finally, the positive regulation of two starch degradation genes (GmBMY and GmPHS) and four sucrose metabolism genes (GmHXK, GmPFK, GmTPS, and GmFRK) by transcription factors may lead to lower seed starch content in soybean. This study elucidates the possible molecular mechanisms underlying the difference in seed starch content between the two species and addresses the scientific problem of why soybean seeds have lower starch content than chickpea seeds.

XL-DNase-Seq: Footprinting Analysis of Dynamic Transcription Factors.

We have developed a novel method for genomic footprinting of transcription factors (TFs) that detects potential gene regulatory relationships from DNase-seq data at the nucleotide level. We introduce an assay termed cross-link (XL)-DNase-seq, designed to capture chromatin interactions of dynamic TFs. A mild cross-linking step in XL-DNase-seq improves the detection of DNase-based footprints of dynamic TFs. The footprint strengths and detectability depend on an optimal cross-linking procedure. This method may help extract novel gene regulatory circuits involving previously undetectable TFs. The XL-DNase-seq method is illustrated here for activated mouse macrophage-like cells, which share several features with inflammatory macrophages.

Deciphering driver regulators of cell fate decisions from single-cell transcriptomics data with CEFCON

Single-cell technologies enable the dynamic analyses of cell fate mapping. However, capturing the gene regulatory relationships and identifying the driver factors that control cell fate decisions are still challenging. We present CEFCON, a network-based framework that first uses a graph neural network with attention mechanism to infer a cell-lineage-specific gene regulatory network (GRN) from single-cell RNA-sequencing data, and then models cell fate dynamics through network control theory to identify driver regulators and the associated gene modules, revealing their critical biological processes related to cell states. Extensive benchmarking tests consistently demonstrated the superiority of CEFCON in GRN construction, driver regulator identification, and gene module identification over baseline methods. When applied to the mouse hematopoietic stem cell differentiation data, CEFCON successfully identified driver regulators for three developmental lineages, which offered useful insights into their differentiation from a network control perspective. Overall, CEFCON provides a valuable tool for studying the underlying mechanisms of cell fate decisions from single-cell RNA-seq data.

Data integration and inference of gene regulation using single-cell temporal multimodal data with scTIE.

Single-cell technologies offer unprecedented opportunities to dissect gene regulatory mechanisms in context-specific ways. Although there are computational methods for extracting gene regulatory relationships from scRNA-seq and scATAC-seq data, the data integration problem, essential for accurate cell type identification, has been mostly treated as a standalone challenge. Here we present scTIE, a unified method that integrates temporal multimodal data and infers regulatory relationships predictive of cellular state changes. scTIE uses an autoencoder to embed cells from all time points into a common space by using iterative optimal transport, followed by extracting interpretable information to predict cell trajectories. Using a variety of synthetic and real temporal multimodal data sets, we show scTIE achieves effective data integration while preserving more biological signals than existing methods, particularly in the presence of batch effects and noise. Furthermore, on the exemplar multiome data set we generated from differentiating mouse embryonic stem cells over time, we show scTIE captures regulatory elements highly predictive of cell transition probabilities, providing new potentials to understand the regulatory landscape driving developmental processes.

BBOX1-AS1 Activates Hedgehog Signaling Pathway to Facilitate the Proliferation and Stemness of Esophageal Squamous Cell Carcinoma Cells via miR-506-5p/EIF5A/PTCH1 Axis.

This study aimed to unveil the specific function of lncRNA BBOX1 antisense RNA 1 (BBOX1-AS1) in ESCC cells and the underlying regulatory mechanism. Esophageal squamous cell carcinoma (ESCC) is a deadly disease. Molecular mechanisms essential to ESCC development and progression require in-depth investigation. Long noncoding RNAs (lncRNAs) have been suggested as crucial effectors in modulating tumor growth. RT-qPCR and western blot examined the expression of genes and proteins of concern, respectively. Colony formation and EdU assays assessed the changes in cell proliferation. Sphere formation assay also detected the stemness of ESCC cells. Bioinformatics prediction, along with mechanistic assays (FISH, Subcellular fractionation, RNA pull-down, RIP, and luciferase reporter), was conducted to explore the gene interactions and regulatory relationship. BBOX1-AS1 was observed to be aberrantly up-regulated in ESCC tissues and cell lines. BBOX1-AS1 depletion exerted suppressive impacts on ESCC cell proliferation and stemness, while BBOX1-AS1 overexpression led to the opposite consequences. Moreover, BBOX1-AS1 was verified to activate Hedgehog signaling pathway via up-regulating PTCH1, and BBOX1-AS1 could sponge miR-506-5p to up-regulate EIF5A, thus stabilizing PTCH1 mRNA. Rescue experiments indicated that BBOX1-AS1 could affect ESCC cell proliferation and stemness via modulation on PTCH1. To conclude, BBOX1-AS1 activates Hedgehog signaling pathway to facilitate the proliferation and stemness of ESCC cells via miR-506-5p/EIF5A/PTCH1 axis.

Single-cell sequencing reveals SATB2/NOTCH1 signaling promotes the progression of malignancy of epithelial cells from papillary thyroid cancer.

Although most papillary thyroid cancers (PTCs) are deemed to have a favorable clinical course and outcome, some develop an aggressive biological behavior at diagnosis or during treatment. Single-cell RNA sequencing (scRNA-seq), which is based on quantifying the features of individual cells to resolve tumor tissue heterogeneity, was used to uncover gene regulatory relationships and trace the transcriptional trajectories underlying the malignant transformation. In this study, we performed single-cell sequencing on samples from four PTC patients and one benign thyroid tumor patient. These included two papillary thyroid microcarcinoma cancers (PTMC) patients, two age-matched advanced PTC patients with invading surrounding tissues, and one patient undergoing surgical treatment due to a benign thyroid tumor. We constructed a new PTC RNA spectrum using single-cell sequencing. Single-cell sequencing analysis indicated that there was a highly invasive subgroup in the PTC epithelial cells, the expression of SATB2 (special AT-rich binding protein-2) was related to the prognosis and clinical progress of PTC, and SATB2 could promote the proliferation, migration, and invasion of PTC cells. We found that NOTCH1 was the key target gene of SATB2, and the activation of the SATB2/NOTCH1 pathway was one of the reasons for the high carcinogenicity of this subgroup.

LncRNA-Top: Controlled deep learning approaches for lncRNA gene regulatory relationship annotations across different platforms

By soaking microRNAs (miRNAs), long non-coding RNAs (lncRNAs) have the potential to regulate gene expression. Few methods have been created based on this mechanism to anticipate the lncRNA-gene relationship prediction. Hence, we present lncRNA-Top to forecast potential lncRNA-gene regulation relationships. Specifically, we constructed controlled deep-learning methods using 12417 lncRNAs and 16127 genes. We have provided retrospective and innovative views among negative sampling, random seeds, cross-validation, metrics, and independent datasets. The AUC, AUPR, and our defined precision@k were leveraged to evaluate performance. In-depth case studies demonstrate that 47 out of 100 projected top unknown pairings were recorded in publications, supporting the predictive power. Our additional software can annotate the scores with target candidates. The lncRNA-Top will be a helpful tool to uncover prospective lncRNA targets and better comprehend the regulatory processes of lncRNAs.

Inferring circadian gene regulatory relationships from gene expression data with a hybrid framework

BackgroundThe central biological clock governs numerous facets of mammalian physiology, including sleep, metabolism, and immune system regulation. Understanding gene regulatory relationships is crucial for unravelling the mechanisms that underlie various cellular biological processes. While it is possible to infer circadian gene regulatory relationships from time-series gene expression data, relying solely on correlation-based inference may not provide sufficient information about causation. Moreover, gene expression data often have high dimensions but a limited number of observations, posing challenges in their analysis.MethodsIn this paper, we introduce a new hybrid framework, referred to as Circadian Gene Regulatory Framework (CGRF), to infer circadian gene regulatory relationships from gene expression data of rats. The framework addresses the challenges of high-dimensional data by combining the fuzzy C-means clustering algorithm with dynamic time warping distance. Through this approach, we efficiently identify the clusters of genes related to the target gene. To determine the significance of genes within a specific cluster, we employ the Wilcoxon signed-rank test. Subsequently, we use a dynamic vector autoregressive method to analyze the selected significant gene expression profiles and reveal directed causal regulatory relationships based on partial correlation.ConclusionThe proposed CGRF framework offers a comprehensive and efficient solution for understanding circadian gene regulation. Circadian gene regulatory relationships are inferred from the gene expression data of rats based on the Aanat target gene. The results show that genes Pde10a, Atp7b, Prok2, Per1, Rhobtb3 and Dclk1 stand out, which have been known to be essential for the regulation of circadian activity. The potential relationships between genes Tspan15, Eprs, Eml5 and Fsbp with a circadian rhythm need further experimental research.

CircEXOC5 Aggravates Sepsis-Induced Acute Lung Injury by Promoting Ferroptosis Through the IGF2BP2/ATF3 Axis.

Patients with sepsis resulting in acute lung injury (ALI) usually have increased mortality. Ferroptosis is a vital regulator in sepsis-induced ALI. Exploring the association of ferroptosis and sepsis-induced ALI is crucial for the management of sepsis-induced ALI. Whole blood was collected from sepsis patients. Mice were treated with cecal ligation and puncture (CLP) to model sepsis. Primary murine pulmonary microvascular endothelial cells were treated with lipopolysaccharide as a cell model. Ferroptosis was evaluated by analyzing levels of iron, malonaldehyde, glutathione, nonheme iron, ferroportin, ferritin, and GPX4. Hematoxylin and eosin and Masson's trichrome staining were applied to examine lung injury and collagen deposition. Cell apoptosis was analyzed by caspase-3 activity and TUNEL assays. Gene regulatory relationship was verified using RNA pull-down and immunoprecipitation assays. CircEXOC5 was highly expressed in sepsis patients and CLP-treated mice, in which knockdown alleviated CLP-induced pulmonary inflammation and injury, and ferroptosis. CircEXOC5 recruited IGF2BP2 to degrade ATF3 mRNA. The demethylase ALKBH5 was responsible for circEXOC5 upregulation through demethylation. CircEXOC5 silencing significantly improved sepsis-induced ALI and survival rate of mice by downregulating ATF3. ALKBH5-mediated upregulation of circEXOC5 exacerbates sepsis-induced ALI by facilitating ferroptosis through IGF2BP2 recruitment to degrade ATF3 mRNA.

Orchestrating information across tissues via a novel multitask GAT framework to improve quantitative gene regulation relation modeling for survival analysis.

Survival analysis is critical to cancer prognosis estimation. High-throughput technologies facilitate the increase in the dimension of genic features, but the number of clinical samples in cohorts is relatively small due to various reasons, including difficulties in participant recruitment and high data-generation costs. Transcriptome is one of the most abundantly available OMIC (referring to the high-throughput data, including genomic, transcriptomic, proteomic and epigenomic) data types. This study introduced a multitask graph attention network (GAT) framework DQSurv for the survival analysis task. We first used a large dataset of healthy tissue samples to pretrain the GAT-based HealthModel for the quantitative measurement of the gene regulatory relations. The multitask survival analysis framework DQSurv used the idea of transfer learning to initiate the GAT model with the pretrained HealthModel and further fine-tuned this model using two tasks i.e. the main task of survival analysis and the auxiliary task of gene expression prediction. This refined GAT was denoted as DiseaseModel. We fused the original transcriptomic features with the difference vector between the latent features encoded by the HealthModel and DiseaseModel for the final task of survival analysis. The proposed DQSurv model stably outperformed the existing models for the survival analysis of 10 benchmark cancer types and an independent dataset. The ablation study also supported the necessity of the main modules. We released the codes and the pretrained HealthModel to facilitate the feature encodings and survival analysis of transcriptome-based future studies, especially on small datasets. The model and the code are available at http://www.healthinformaticslab.org/supp/.

Understanding cell fate acquisition in stem-cell-derived pancreatic islets using single-cell multiome-inferred regulomes.

Pancreatic islet cells derived from human pluripotent stem cells hold great promise for modeling and treating diabetes. Differences between stem-cell-derived and primary islets remain, but molecular insights to inform improvements are limited. Here, we acquire single-cell transcriptomes and accessible chromatin profiles during invitro islet differentiation and pancreas from childhood and adult donors for comparison. We delineate major cell types, define their regulomes, and describe spatiotemporal gene regulatory relationships between transcription factors. CDX2 emerged as a regulator of enterochromaffin-like cells, which we show resemble a transient, previously unrecognized, serotonin-producing pre-β cell population in fetal pancreas, arguing against a proposed non-pancreatic origin. Furthermore, we observe insufficient activation of signal-dependent transcriptional programs during invitro β cell maturation and identify sex hormones as drivers of β cell proliferation in childhood. Altogether, our analysis provides a comprehensive understanding of cell fate acquisition in stem-cell-derived islets and a framework for manipulating cell identities and maturity.

A gene regulatory network inference model based on pseudo-siamese network

MotivationGene regulatory networks (GRNs) arise from the intricate interactions between transcription factors (TFs) and their target genes during the growth and development of organisms. The inference of GRNs can unveil the underlying gene interactions in living systems and facilitate the investigation of the relationship between gene expression patterns and phenotypic traits. Although several machine-learning models have been proposed for inferring GRNs from single-cell RNA sequencing (scRNA-seq) data, some of these models, such as Boolean and tree-based networks, suffer from sensitivity to noise and may encounter difficulties in handling the high noise and dimensionality of actual scRNA-seq data, as well as the sparse nature of gene regulation relationships. Thus, inferring large-scale information from GRNs remains a formidable challenge.ResultsThis study proposes a multilevel, multi-structure framework called a pseudo-Siamese GRN (PSGRN) for inferring large-scale GRNs from time-series expression datasets. Based on the pseudo-Siamese network, we applied a gated recurrent unit to capture the time features of each TF and target matrix and learn the spatial features of the matrices after merging by applying the DenseNet framework. Finally, we applied a sigmoid function to evaluate interactions. We constructed two maize sub-datasets, including gene expression levels and GRNs, using existing open-source maize multi-omics data and compared them to other GRN inference methods, including GENIE3, GRNBoost2, nonlinear ordinary differential equations, CNNC, and DGRNS. Our results show that PSGRN outperforms state-of-the-art methods. This study proposed a new framework: a PSGRN that allows GRNs to be inferred from scRNA-seq data, elucidating the temporal and spatial features of TFs and their target genes. The results show the model’s robustness and generalization, laying a theoretical foundation for maize genotype-phenotype associations with implications for breeding work.

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.

Mapping Multi-factor-mediated Chromatin Interactions to Assess Dysregulation of Lung Cancer-related Genes

Studies on the lung cancer genome are indispensable for developing a cure for lung cancer. Whole-genome resequencing, genome-wide association studies, and transcriptome sequencing have greatly improved our understanding of the cancer genome. However, dysregulation of long-range chromatin interactions in lung cancer remains poorly described. To better understand the three-dimensional (3D) genomic interaction features of the lung cancer genome, we used the A549 cell line as a model system and generated high-resolution chromatin interactions associated with RNA polymerase II (RNAPII), CCCTC-binding factor (CTCF), enhancer of zeste homolog 2 (EZH2), and histone 3 lysine 27 trimethylation (H3K27me3) using long-read chromatin interaction analysis by paired-end tag sequencing (ChIA-PET). Analysis showed that EZH2/H3K27me3-mediated interactions further repressed target genes, either through loops or domains, and their distributions along the genome were distinct from and complementary to those associated with RNAPII. Cancer-related genes were highly enriched with chromatin interactions, and chromatin interactions specific to the A549 cell line were associated with oncogenes and tumor suppressor genes, such as additional repressive interactions on FOXO4 and promoter–promoter interactions between NF1 and RNF135. Knockout of an anchor associated with chromatin interactions reversed the dysregulation of cancer-related genes, suggesting that chromatin interactions are essential for proper expression of lung cancer-related genes. These findings demonstrate the 3D landscape and gene regulatory relationships of the lung cancer genome.