Dataset Information

Using single cell atlas data to reconstruct regulatory networks.

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

SUBMITTER: Song Q

PROVIDER: S-EPMC10123116 | biostudies-literature | 2023 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Using single cell atlas data to reconstruct regulatory networks.

Song Qi Q Ruffalo Matthew M Bar-Joseph Ziv Z

Nucleic acids research 20230401 7

Inference of global gene regulatory networks from omics data is a long-term goal of systems biology. Most methods developed for inferring transcription factor (TF)-gene interactions either relied on a small dataset or used snapshot data which is not suitable for inferring a process that is inherently temporal. Here, we developed a new computational method that combines neural networks and multi-task learning to predict RNA velocity rather than gene expression values. This allows our method to ov ...[more]

PMID: 36762475

Similar Datasets

Project description:Single-cell RNA-sequencing (scRNA-seq) has emerged as a powerful technique for studying gene expression patterns at the single-cell level. Inferring gene regulatory networks (GRNs) from scRNA-seq data provides insight into cellular phenotypes from the genomic level. However, the high sparsity, noise and dropout events inherent in scRNA-seq data present challenges for GRN inference. In recent years, the dramatic increase in data on experimentally validated transcription factors binding to DNA has made it possible to infer GRNs by supervised methods. In this study, we address the problem of GRN inference by framing it as a graph link prediction task. In this paper, we propose a novel framework called GNNLink, which leverages known GRNs to deduce the potential regulatory interdependencies between genes. First, we preprocess the raw scRNA-seq data. Then, we introduce a graph convolutional network-based interaction graph encoder to effectively refine gene features by capturing interdependencies between nodes in the network. Finally, the inference of GRN is obtained by performing matrix completion operation on node features. The features obtained from model training can be applied to downstream tasks such as measuring similarity and inferring causality between gene pairs. To evaluate the performance of GNNLink, we compare it with six existing GRN reconstruction methods using seven scRNA-seq datasets. These datasets encompass diverse ground truth networks, including functional interaction networks, Loss of Function/Gain of Function data, non-specific ChIP-seq data and cell-type-specific ChIP-seq data. Our experimental results demonstrate that GNNLink achieves comparable or superior performance across these datasets, showcasing its robustness and accuracy. Furthermore, we observe consistent performance across datasets of varying scales. For reproducibility, we provide the data and source code of GNNLink on our GitHub repository: https://github.com/sdesignates/GNNLink.

Project description:MicroRNAs (miRNAs) simultaneously target many transcripts through partial complementarity binding, and have emerged as a key type of post-transcriptional regulator for gene expression. How miRNA accomplishes its pleiotropic effects largely depends on its expression and its target repertoire. Previous studies discovered thousands of miRNAs and numerous miRNA target genes mainly through computation and prediction methods which produced high rates of false positive prediction. The development of Argonaute cross-linked immunoprecipitation coupled with high-throughput sequencing (CLIP-Seq) provides a system to effectively determine miRNA target genes. Likewise, the accuracy of dissecting the transcriptional regulation of miRNA genes has been greatly improved by chromatin immunoprecipitation of the transcription factors coupled with sequencing (ChIP-Seq). Elucidation of the miRNA target repertoire will provide an in-depth understanding of the functional roles of microRNA pathways. To reliably reconstruct a miRNA-mediated regulatory network, we established a computational framework using publicly available, sequence-based transcription factor-miRNA databases, including ChIPBase and TransmiR for the TF-miRNA interactions, along with miRNA-target databases, including miRTarBase, TarBase and starBase, for the miRNA-target interactions. We applied the computational framework to elucidate the miRNA-mediated regulatory network in the Mir122a?/? mouse model, which has an altered transcriptome and progressive liver disease.We applied our computational framework to the expression profiles of miRNA/mRNA of Mir122a?/? mutant mice and wild-type mice. The miRNA-mediated network involves 40 curated TFs contributing to the aberrant expression of 65 miRNAs and 723 curated miRNA target genes, of which 56% was found in the differentially-expressed genes of Mir122a--mice. Hence, the regulatory network disclosed previously-known and also many previously-unidentified miRNA-mediated regulations in mutant mice. Moreover, we demonstrate that loss of imprinting at the chromosome 12qF1 region is associated with miRNA overexpression in human hepatocellular carcinoma and stem cells, suggesting initiation of precancerous changes in young mice deficient in miR-122. A group of 9 miRNAs was found to share miR-122 target genes, indicating synergy between miRNAs and target genes by way of multiplicity and cooperativity.The study provides significant insight into miRNA-mediated regulatory networks. Based on experimentally verified data, this network is highly reliable and effective in revealing previously-undetermined disease-associated molecular mechanisms. This computational framework can be applied to explore the significant TF-miRNA-miRNA target interactions in any complex biological systems with high degrees of confidence.

Dataset Information

Using single cell atlas data to reconstruct regulatory networks.

Publications

Using single cell atlas data to reconstruct regulatory networks.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets