Integration of single-cell multi-omics for gene regulatory network inference

Hu, Xinlin; Hu, Yaohua; Wu, Fanjie; Leung, Ricky Wai Tak; Qin, Jing

doi:10.1016/j.csbj.2020.06.033

Cited by 48 publications

(37 citation statements)

References 105 publications

(162 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…5We have performed extensive experimental evaluation to assess the feasibility of DL in tackling the proposed problem. (6) We have reported results that demonstrate the potential of DL in successfully tackling the problem of discriminating across SCGRNs. To the best of our knowledge, this work would set the foundation for advancing the biological understanding of various diseases and cellular mechanisms.…”

Section: Introductionmentioning

confidence: 81%

“…Recent advances in single-cell technologies have led to the generation of single-cell gene expression data, which help advanced computational methods to study the singlecell-derived gene regulatory networks (GRNs) [1][2][3][4][5][6][7][8][9]. By inferring GRNs, biologists would be able to get deeper insight into the working mechanism of cells, thereby improving their understanding of the mechanism underlying the regulation of cellular functions in various biological processes [10][11][12].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Discriminating the Single-cell Gene Regulatory Networks of Human Pancreatic Islets: A Novel Deep Learning Application

Turki

Taguchi

2020

Preprint

View full text Add to dashboard Cite

Analyzing single-cell pancreatic data would play an important role in understanding various metabolic diseases and health conditions. Due to the sparsity and noise present in such single-cell gene expression data, analyzing various functions related to the inference of gene regulatory networks, derived from single-cell data, remains difficult, thereby posing a barrier to the deepening of understanding of cellular metabolism. Since recent studies have led to the reliable inference of single-cell gene regulatory networks (SCGRNs), the challenge of discriminating between SCGRNs has now arisen. By accurately discriminating between SCGRNs (e.g., distinguishing SCGRNs of healthy pancreas from those of T2D pancreas), biologists would be able to annotate, organize, visualize, and identify common patterns of SCGRNs for metabolic diseases. Such annotated SCGRNs could play an important role in speeding up the process of building large data repositories. In this study, we aimed to contribute to the development of a novel deep learning (DL) application. First, we generated a dataset consisting of 224 SCGRNs belonging to both T2D and healthy pancreas and made it freely available. Next, we chose seven DL architectures, including VGG16, VGG19, Xception, ResNet50, ResNet101, DenseNet121, and DenseNet169, trained each of them on the dataset, and checked prediction based on a test set. We evaluated the DL architectures on an HP workstation platform with a single NVIDIA GeForce RTX 2080Ti GPU. Experimental results on the whole dataset, using several performance measures, demonstrated the superiority of VGG19 DL model in the automatic classification of SCGRNs, derived from the single-cell pancreatic data.

show abstract

Section: Introductionmentioning

confidence: 81%

Section: Introductionmentioning

confidence: 99%

Discriminating the Single-cell Gene Regulatory Networks of Human Pancreatic Islets: A Novel Deep Learning Application

Turki

Taguchi

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Elucidating transcriptional GRNs is critical to understanding the molecular mechanisms of cell differentiation in developmental and disease systems. In recent years, significant efforts have been made to incorporate multi-omic datasets into GRN models, but this has been a difficult endeavor (Hu et al, 2020). In this work, in addition to a number of publicly available Xenopus genomic datasets, we generated additional RNA-seq and ChIP-seq data.…”

Section: Discussionmentioning

confidence: 99%

“…For the current work, we wished to build a “mechanistic” GRN, so we sought to only find direct connections that engage cis -regulatory regions. This is extremely difficult in practice using only one type of data (reviewed in Hu et al, 2020). Some recent predictive algorithms use multi-omic data to build lists of putative functional enhancers (Sethi et al, 2020; Xiang et al, 2020), but they do not incorporate TF binding data to determine whether the TF can directly regulate these enhancers.…”

Section: Introductionmentioning

confidence: 99%

Uncovering the mesendoderm gene regulatory network through multi-omic data integration

Jansen

Paraiso

Zhou

et al. 2020

Preprint

View full text Add to dashboard Cite

Mesendodermal specification is one of the earliest events in embryogenesis, where cells first acquire distinct identities. Cell differentiation is a highly regulated process that involves the function of numerous transcription factors (TFs) and signaling molecules, which can be described with gene regulatory networks (GRNs). Cell differentiation GRNs are difficult to build because existing mechanistic methods are low-throughput, and high-throughput methods tend to be non-mechanistic. Additionally, integrating highly dimensional data comprised of more than two data types is challenging. Here, we use linked self-organizing maps to combine ChIP-seq/ATAC-seq with temporal, spatial and perturbation RNA-seq data from Xenopus tropicalis mesendoderm development to build a high resolution genome scale mechanistic GRN. We recovered both known and previously unsuspected TF-DNA/TF-TF interactions and validated through reporter assays. Our analysis provides new insights into transcriptional regulation of early cell fate decisions and provides a general approach to building GRNs using highly-dimensional multi-omic data sets.

show abstract

“…The feasibility problem is at the core of the modeling of many problems in various areas of mathematics and physical sciences, such as image recovery [11], wireless sensor networks localization [18], radiation therapy treatment planning [8] and gene regulatory network inference [17,31]. The convex feasibility problem (CFP), in which the involved functions are convex, has attracted a great deal of attention in the development of optimization algorithms and applications; see [6,11,33] and references therein.…”

Section: Introductionmentioning

confidence: 99%

The effect of deterministic noise on a quasi-subgradient method for quasi-convex feasibility problems

2020

J. Appl. Numer. Optim.

View full text Add to dashboard Cite

The quasi-convex feasibility problem (QFP), in which the involved functions are quasi-convex, is at the core of the modeling of many problems in various areas such as economics, finance and management science. In this paper, we consider an inexact incremental quasi-subgradient method to solve the QFP, in which an incremental control of component functions in the QFP is employed and the inexactness stems from computation error and noise arising from practical considerations and physical circumstances. Under the assumptions that the computation error and noise are deterministic and bounded and a Hölder condition on component functions in the QFP, we study the convergence property of the proposed inexact incremental quasi-subgradient method, and particularly, investigate the effect of the inexact terms on the incremental quasi-subgradient method when using the constant, diminishing and dynamic stepsize rules.

show abstract

Integration of single-cell multi-omics for gene regulatory network inference

Abstract: Graphical abstract

Cited by 48 publications

References 105 publications

Discriminating the Single-cell Gene Regulatory Networks of Human Pancreatic Islets: A Novel Deep Learning Application

Discriminating the Single-cell Gene Regulatory Networks of Human Pancreatic Islets: A Novel Deep Learning Application

Uncovering the mesendoderm gene regulatory network through multi-omic data integration

The effect of deterministic noise on a quasi-subgradient method for quasi-convex feasibility problems

Contact Info

Product

Resources

About