Network Reconstruction Methods Research Articles

Exploring the Molecular Terrain: A Survey of Analytical Methods for Biological Network Analysis

Biological systems, characterized by their complex interplay of symmetry and asymmetry, operate through intricate networks of interacting molecules, weaving the elaborate tapestry of life. The exploration of these networks, aptly termed the “molecular terrain”, is pivotal for unlocking the mysteries of biological processes and spearheading the development of innovative therapeutic strategies. This review embarks on a comprehensive survey of the analytical methods employed in biological network analysis, focusing on elucidating the roles of symmetry and asymmetry within these networks. By highlighting their strengths, limitations, and potential applications, we delve into methods for network reconstruction, topological analysis with an emphasis on symmetry detection, and the examination of network dynamics, which together reveal the nuanced balance between stable, symmetrical configurations and the dynamic, asymmetrical shifts that underpin biological functionality. This review equips researchers with a multifaceted toolbox designed to navigate and decipher biological networks’ intricate, balanced landscape, thereby advancing our understanding and manipulation of complex biological systems. Through this detailed exploration, we aim to foster significant advancements in biological network analysis, paving the way for novel therapeutic interventions and a deeper comprehension of the molecular underpinnings of life.

Physics constrained unsupervised deep learning for rapid, high resolution scanning coherent diffraction reconstruction

By circumventing the resolution limitations of optics, coherent diffractive imaging (CDI) and ptychography are making their way into scientific fields ranging from X-ray imaging to astronomy. Yet, the need for time consuming iterative phase recovery hampers real-time imaging. While supervised deep learning strategies have increased reconstruction speed, they sacrifice image quality. Furthermore, these methods’ demand for extensive labeled training data is experimentally burdensome. Here, we propose an unsupervised physics-informed neural network reconstruction method, PtychoPINN, that retains the factor of 100-to-1000 speedup of deep learning-based reconstruction while improving reconstruction quality by combining the diffraction forward map with real-space constraints from overlapping measurements. In particular, PtychoPINN gains a factor of 4 in linear resolution and an 8 dB improvement in PSNR while also accruing improvements in generalizability and robustness. This blend of performance and computational efficiency offers exciting prospects for high-resolution real-time imaging in high-throughput environments such as X-ray free electron lasers (XFELs) and diffraction-limited light sources.

OR20-03 Leptin-mediated Regulation Of Gene Regulatory Networks In Gonadotropes

Abstract Disclosure: J. Banik: None. A. Lagasse: None. A. Haney: None. S. Byrum: None. U. Boehm: None. G.V. Childs: None. M.C. MacNicol: None. A.M. MacNicol: None. A.K. Odle: None. The female reproductive system is energetically expensive and requires tight control of the hypothalamic-pituitary-gonadal (HPG) axis to promote gonadal priming and ovulation. Thus, a crosstalk between the metabolic and reproductive systems exists to regulate the rate-limiting steps of reproduction. Leptin is an adipokine hormone that is produced and secreted proportionally from white fat cells, and leptin receptors (Lepr) are present in the hypothalamus, pituitary, and gonads. Leptin binding to hypothalamic LepR functions as a sensor of nutritional status and, thus, orchestrates energy expenditure during reproductive events. We hypothesized that leptin is crucial to influence fertility in females via differential gene regulation during the estrus cycle in pituitary gonadotropes. To test this hypothesis, we utilized Cre-LoxP technology to selectively ablate leptin receptors within female gonadotropes (CreGnRHR+/- Leprfl/fl TdTomato+/+, referred to as “Gon-Lepr-null”) and performed single-cell RNA-sequencing (scRNA-seq) to identify leptin-dependent targets within the gonadotrope transcriptome. We observed a significant decrease in cell percentage within the gonadotrope cluster, and differential analysis reported a significant decrease in Fshb expression in the Lepr-null mutant gonadotropes. Moreover, the lack of leptin signaling in gonadotropes also caused a shift in the lactotrope-specific transcript signature in the Gon-Lepr-null mutants. We employed SCENIC, a computational method for simultaneous gene regulatory network reconstruction and cell-state identification from single-cell RNA-seq data, to delineate altered upstream regulators contributing to the reduction of Fshb expression in gonadotropes and the shift in the lactotrope transcriptome signature in Gon-Lepr-null mutants versus control animals. Regulons are co-regulated gene sets that share binding sites for a common transcription factor driver, and we identified 381 and 399 regulons specific to controls and mutants, respectively. Examination of the gonadotrope regulons revealed Gata2, Nhlh2, NeuroD1, and Sox11 to be drivers of Fshb expression in control animals only. Differential expression analysis showed significant downregulation of Gata2 and Sox11 in Lepr-null mutant gonadotropes, suggesting Fshb is a leptin-dependent target of Gata2 and Sox11. Moreover, Gata2, Nhlh2, NeuroD1, and Sox11 target 117 genes in controls and 263 genes in mutants, implying a more restricted ability of Gata2, Nhlh2, NeuroD1, and/or Sox11 to target gene expression in the presence of leptin signaling in controls, as an abrogation of leptin signaling leads to an expansion of the regulatory network in Lepr-null mutant gonadotropes. Overall, our analysis reveals how leptin signaling modulates the gonadotrope transcriptome to optimize pituitary reproductive functions at the molecular level. Presentation: Saturday, June 17, 2023

Reconstructing networks via discrete state dynamical data: A mini-review

The inference of network structure from dynamic data is one of the most challenging scientific problems in network science. To address this issue, researchers have proposed various approaches regarding different types of dynamical data. Since many real evolution processes or social phenomena can be described by discrete state dynamical systems, such as the spreading of epidemic, the evolution of opinions, and the cooperation behaviors, network reconstruction methods driven by discrete state dynamical data were also widely studied. In this letter, we provide a mini-review of recent progresses for reconstructing networks based on discrete state dynamical data. These studies encompass network reconstruction problems where the dynamical processes are known, as well as those where the dynamics are unknown, and extend to the reconstruction of higher-order networks. Finally, we discuss the remaining challenges in this field.

Assessing and mitigating fire sales risk under partial information

We consider the problem of assessing and mitigating fire sales risk for banks under partial information. Using data from the European Banking Authority's stress tests, we consider the matrix of asset holdings of different banks. We first analyse fire sales risk under both full and partial information using different matrix reconstruction methods. We then investigate how well some policy interventions aimed at mitigating fire sales risk perform if they are applied based on only partial information. We find that even under partial information, using suitable network reconstruction methods to decide on policy interventions can significantly mitigate risk from fire sales. Furthermore, we show that some interventions based on reconstructed networks significantly outperform ad hoc methods that decide on interventions only based on the size of an institution and do not account for overlapping portfolios.

Research on Road Network Partitioning Considering the Coupling of Network Connectivity and Traffic Attributes

The urban road network is a large and complex system characterized by significant heterogeneity arising from different spatial structures and traffic demands. To facilitate effective management and control, it is necessary to partition the road network into homogeneous sub-areas. In this regard, we aim to propose a hybrid method for partitioning sub-areas with intra-area homogeneity, inter-area heterogeneity, and similar sizes, called CSDRA. It is specifically designed for bidirectional road networks with segment weights that encompass traffic flow, speed, or roadside facility evaluation. Based on community detection and spectral clustering, this proposed method comprises four main modules: initial partition, partitioning of large sub-areas, reassignment of small sub-areas, and boundary adjustment. In the preliminary partitioning work, we also design a road network reconstruction method which further helps to enhance the intra-area homogeneity and inter-area heterogeneity of partitioning results. Furthermore, to align with the requirement for comparable work units in practical traffic management and control, we control the similarity in the size of sub-areas by enforcing upper and lower bound constraints on the size of the sub-areas. We verify the outperformance of the proposed method by an experiment on the partitioning of an urban road network in Guangzhou, China, where we employ sidewalk barrier-free score data as segment weights. The results demonstrate the effectiveness of both the road network reconstruction method and the CSDRA proposed in this paper, as they significantly improve the partitioning outcomes compared with other methods using different evaluation indicators corresponding to the partitioning objectives. Finally, we investigate the influence of constraint parameters on the evaluation indicator. Our findings indicate that appropriately configuring these constraint parameters can effectively minimize sub-region size variations while having minimal impact on other aspects.

Urban waterlogging control: A novel method to urban drainage pipes reconstruction, systematic and automated

Reconstruction of the drainage system is an important measure for urban waterlogging control. For the drainage system of the community, factors such as upstream pipeline water capacity and downstream bottleneck pipeline are often neglected in the process of network reconstruction. Only the network in the waterlogged area is reformed, which is lack of systematicness, and may lead to the failure of waterlogging control. To solve this problem, the Storm Water Management Model (SWMM 5.1) is used to analyze the rationality of the current pipe network reconstruction methods using three indicators: the maximum overflow depth, the maximum overflow volume, and the conduit surcharge. And a new reconstruction method for drainage pipe networks is developed by R programming. The results show that the current pipe network reconstruction method is still insufficient to achieve the goal of eliminating node overflow. For different rainfall conditions, there are still existing low-risk areas, with maximum overflow depth can reach up to 0.15 m and maximum overflow volume can reach up to 7.12 m3. The novel developed drainage pipe network reconstruction method (optimizing pipe network) can effectively identify the bottleneck pipes, and by repeatedly expanding the bottleneck pipes, the goal of node overflow can be achieved under a given rainfall event.

MCPNet: a parallel maximum capacity-based genome-scale gene network construction framework.

Gene network reconstruction from gene expression profiles is a compute- and data-intensive problem. Numerous methods based on diverse approaches including mutual information, random forests, Bayesian networks, correlation measures, as well as their transforms and filters such as data processing inequality, have been proposed. However, an effective gene network reconstruction method that performs well in all three aspects of computational efficiency, data size scalability, and output quality remains elusive. Simple techniques such as Pearson correlation are fast to compute but ignore indirect interactions, while more robust methods such as Bayesian networks are prohibitively time consuming to apply to tens of thousands of genes. We developed maximum capacity path (MCP) score, a novel maximum-capacity-path-based metric to quantify the relative strengths of direct and indirect gene-gene interactions. We further present MCPNet, an efficient, parallelized gene network reconstruction software based on MCP score, to reverse engineer networks in unsupervised and ensemble manners. Using synthetic and real Saccharomyces cervisiae datasets as well as real Arabidopsis thaliana datasets, we demonstrate that MCPNet produces better quality networks as measured by AUPRC, is significantly faster than all other gene network reconstruction software, and also scales well to tens of thousands of genes and hundreds of CPU cores. Thus, MCPNet represents a new gene network reconstruction tool that simultaneously achieves quality, performance, and scalability requirements. Source code freely available for download at https://doi.org/10.5281/zenodo.6499747 and https://github.com/AluruLab/MCPNet, implemented in C++ and supported on Linux.

Landscape and perturbation of enhancer-driven core transcription regulatory circuits in cancer

Enhancers are emerging as critical regulatory regions in regulating gene expression across diverse tissues and cell types. Perturbation of enhancer-driven transcriptional regulatory circuits has been observed in cancer and other human complex diseases. Systematic analyses of the landscape of core enhancer- or super-enhancer-driven regulatory circuits (CRCs) will provide novel insights into the regulation of gene expression. In this study, Feng et al. have identified the CRCs in large cell/tissue samples.1Feng C. Song C. Jiang Y. Zhao J. Zhang J. Wang Y. Yin M. Zhu J. Ai B. Wang Q. et al.Landscape and significance of human super enhancer-driven core transcription regulatory circuitry.Mol. Ther. Nucleic Acids. 2023; https://doi.org/10.1016/j.omtn.2023.03.014Abstract Full Text Full Text PDF Scopus (0) Google Scholar The authors analyzed the sequence conservation, CRC activity, and genome binding affinity for common transcription factors (TFs), moderate TFs, and specific TFs, which exhibited distinct biological features. Moreover, network analysis highlighted the potential as prognostic biomarkers of the CRC module in cancer. A user-friendly resource named CRCdb (http://www.licpathway.net/crcdb/index.html) was developed for aiding analysis of CRCs. The transcriptional activity of a gene is usually regulated by the crosstalk among enhancers and various cis-regulatory elements bound by TFs and RNA binding proteins. Recent developments of high-throughput sequencing technologies have generated valuable multiple-omics data resources (Figure 1A), which accelerated the studies of CRCs in diverse tissues and complex diseases contexts. TRANSFAC is widely used for identification of TF-gene binding and ChIPBase has been developed with >10,000 curated ChIP-seq datasets. In addition, enhancers and super-enhancers are usually identified based on the H3K27ac and H3K4me1 signals. The Encyclopedia of DNA Elements Project and Roadmap Epigenomics Project provide rich histone modification datasets across diverse tissues and cell types. Moreover, the development of biological methods (e.g., Hi-C, 3C, and ChIA-PET) to investigate the 3D chromatin organization is pivotal for understanding the enhancer-gene interactions.2Salviato E. Djordjilović V. Hariprakash J.M. Tagliaferri I. Pal K. Ferrari F. Leveraging three-dimensional chromatin architecture for effective reconstruction of enhancer-target gene regulatory interactions.Nucleic Acids Res. 2021; 49: e97Crossref PubMed Scopus (1) Google Scholar However, these experimental data are generally considered to be tissue- or cell-type specific. Increasing omics data allows genome-wide identification of the CRCs constituted by enhancers, TFs, and genes, which would be a valuable resource in biomedical research. The increases of high-throughput sequencing data have provided foundational resources for modeling the CRCs across diverse tissues and complex diseases. Experimental determination of the CRCs is time-consuming and laborious. Thus, numerous computational methods have attempted to map the CRCs by efforts to integrate global information regarding these resources (Figure 1A). CRC mapper was developed to construct the core regulatory circuitry models across human cell types.3Saint-André V. Federation A.J. Lin C.Y. Abraham B.J. Reddy J. Lee T.I. Bradner J.E. Young R.A. Models of human core transcriptional regulatory circuitries.Genome Res. 2016; 26: 385-396Crossref PubMed Google Scholar The python package Coltron (https://pypi.python.org/pypi/coltron) has also been developed to identify CRCs by integrating H3K27ac ChIP-seq and ATAC-seq data. FIMO is widely used for scanning TF motifs in gene sequences. Moreover, SCENIC is a recently developed computational method for simultaneous gene regulatory network reconstruction and cell-state identification from single-cell RNA-seq data.4Aibar S. González-Blas C.B. Moerman T. Huynh-Thu V.A. Imrichova H. Hulselmans G. Rambow F. Marine J.C. Geurts P. Aerts J. et al.SCENIC: single-cell regulatory network inference and clustering.Nat. Methods. 2017; 14: 1083-1086Crossref PubMed Scopus (1493) Google Scholar These computational methods for constructing core circuitry models should prove valuable tools for further investigating CRCs in healthy and diseased contexts. In this study, Feng et al. identified the CRCs and core TFs by integrating the results of CRC mapper and Coltron,1Feng C. Song C. Jiang Y. Zhao J. Zhang J. Wang Y. Yin M. Zhu J. Ai B. Wang Q. et al.Landscape and significance of human super enhancer-driven core transcription regulatory circuitry.Mol. Ther. Nucleic Acids. 2023; https://doi.org/10.1016/j.omtn.2023.03.014Abstract Full Text Full Text PDF Scopus (0) Google Scholar generating a comprehensive landscape of CRCs driven by super-enhancers across diverse tissues and cell types. However, the landscape of CRCs across diverse cancer types is still largely unknown. The CRCs are under intricate regulation in physiological conditions but could go awry upon genome instability caused by genetic and epigenetic alterations. A detailed understanding of the molecular mechanisms of CRC perturbations in cancer still remains an important question. In the past decade, thousands of genomic mutations have been identified by high-throughput sequencing technologies in a variety of cancer patients. A large number of genomic mutations and structural alterations were observed in enhancers, TFs, and target genes (Figure 1B). Moreover, copy number variations may impact the activities of a variety of oncogenic or tumor-suppressive pathways by perturbing the CRCs in cancer. For example, Xiao et al. have performed an integrative analysis of the enhancer-centered regulatory circuit perturbations in gliomas and revealed the potential CRC biomarkers.5Xiao J. Jin X. Zhang C. Zou H. Chang Z. Han N. Li X. Zhang Y. Li Y. Systematic analysis of enhancer regulatory circuit perturbation driven by copy number variations in malignant glioma.Theranostics. 2021; 11: 3060-3073Crossref PubMed Google Scholar DNA methylation is the most widely studied epigenetic regulation (Figure 1B), which could also drive the tissue-specific enhancer basal transcription and target gene expression in human cancers.6Pan X. Li X. Sun J. Xiong Z. Hu H. Ning S. Zhi H. Enhancer methylation dynamics drive core transcriptional regulatory circuitry in pan-cancer.Oncogene. 2022; 41: 3474-3484Crossref PubMed Scopus (1) Google Scholar Gene expressions are regulated by the complex model of CRCs, represented as “nodes” and “edges” in the regulatory network model, respectively. Genetic and epigenetic alterations not only perturbed the nodes but also exhibited edge-specific alterations (edgetic). The edgetic alterations of CRCs might improve our understanding of gene expression regulation in cancer. The gene regulatory network has been observed to be perturbed by genetic and epigenetic variations,7Li Y. McGrail D.J. Xu J. Mills G.B. Sahni N. Yi S. Gene regulatory network perturbation by genetic and epigenetic variation.Trends Biochem. Sci. 2018; 43: 576-592Abstract Full Text Full Text PDF PubMed Scopus (11) Google Scholar,8Li Y. Zhang Y. Li X. Yi S. Xu J. Gain-of-Function mutations: an emerging advantage for cancer biology.Trends Biochem. Sci. 2019; 44: 659-674Abstract Full Text Full Text PDF PubMed Scopus (26) Google Scholar such as genomic mutations and DNA methylation. Genomic mutations and DNA methylation can regulate gene expression by gain or loss of the binding of transcription factor(s) to DNA (Figure 1B). Such efforts have already been initiated in cancer for understanding the edgetic perturbations of CRCs. The global landscape of DNA methylation-mediated transcriptional dysregulation across 22 human cancer types has been portrayed recently,9Wang Z. Yin J. Zhou W. Bai J. Xie Y. Xu K. Zheng X. Xiao J. Zhou L. Qi X. et al.Complex impact of DNA methylation on transcriptional dysregulation across 22 human cancer types.Nucleic Acids Res. 2020; 48: 2287-2302Crossref PubMed Scopus (20) Google Scholar and a network module that consisted of methylation-sensitive TFs with prognostic potential was identified. Moreover, regulatory network and pathway perturbations analyses help prioritizing cancer driver mutations and genes.10Li Y. Burgman B. Khatri I.S. Pentaparthi S.R. Su Z. McGrail D.J. Li Y. Wu E. Eckhardt S.G. Sahni N. Yi S.S. e-MutPath: computational modeling reveals the functional landscape of genetic mutations rewiring interactome networks.Nucleic Acids Res. 2021; 49: e2Crossref PubMed Scopus (5) Google Scholar Feng et al. also identified the core TFs in tissue-specific CRC networks as potential biomarkers, which have regulatory potential for cancer immunotherapy.1Feng C. Song C. Jiang Y. Zhao J. Zhang J. Wang Y. Yin M. Zhu J. Ai B. Wang Q. et al.Landscape and significance of human super enhancer-driven core transcription regulatory circuitry.Mol. Ther. Nucleic Acids. 2023; https://doi.org/10.1016/j.omtn.2023.03.014Abstract Full Text Full Text PDF Scopus (0) Google Scholar Functional characterization of the node and edgetic effects of genetic and epigenetic variants on CRCs will undoubtedly facilitate our understanding of the molecular mechanism of cancer, which will help identifying biomarkers for clinical diagnosis and therapy. In conclusion, the findings of Feng et al. provided a valuable resource for investigating the CRCs across diverse tissues and cell types. Comprehensive analysis of the enhancer-TF-gene regulatory circuits across diverse tissue/cell types and cancers may thus help better understanding of cancer-associated genetic and epigenetic alterations, leading to potential CRC-directed therapeutic interventions in cancer. This work was supported by the National Natural Science Foundation of China (32170676, 32060152, 31970646), Marshal Initiative Funding of Hainan Medical University (JBGS202103), Bioinformatics for Major Diseases Science Innovation Group of Hainan Medical University, and Heilongjiang Touyan Innovation Team Program. The authors declare no financial interest.

Topological properties of reconstructed credit networks and banking systemic risk

Financial bipartite networks provide channels for contagion risks and their topological properties determine financial stability. We enrich the bipartite network reconstruction methods proposed by Ramadiah et al. (2020) and extend them to the Chinese banking system. By comparing the reproducibility of the real credit market and the corresponding systemic risk, the impact of topological properties for different reconstructed bipartite networks on financial stability is analyzed. The empirical evidence shows that network reconstruction methods based on maximum entropy ensembles capture more properties in the real credit network. It also highlights that the different systemic risk level is mainly contributed by the topological properties based on common exposures. These analyses for topological properties provide regulatory insights for systemic risk prevention. It shows that reducing credit similarity across banks while increasing credit diversification in different sectors helps to control systemic risk. The results imply the possibility of increasing financial stability through the macro-regulation of the credit market structure.

Rumor source localization in social networks based on infection potential energy

The location technology of information sources in social networks is a major factor in exploring the means of information propagation. In this context, most existing methods ignore the direction of infected nodes and fail to make full use of the diffusion information, resulting in poor identification of source localization. To address such problems, a novel source location method based on infection potential energy is proposed. Its methodology consists of several steps: Firstly, a network reconstruction method is suggested, based on infection potential energy, to make the constructed information diffusion path more accurate. Afterwards, a network pruning method is identified to reduce the search space of candidate sources. Finally, considering the minor differences in the Gaussian density values of multiple nodes and the tendency of the rumor to spread, a distance centrality method is proposed. Experiments in real networks show that the suggested method achieves a better location performance.

Learning the structure of the mTOR protein signaling pathway from protein phosphorylation data

Statistical learning of the structures of cellular networks, such as protein signaling pathways, is a topical research field in computational systems biology. To get the most information out of experimental data, it is often required to develop a tailored statistical approach rather than applying one of the off-the-shelf network reconstruction methods. The focus of this paper is on learning the structure of the mTOR protein signaling pathway from immunoblotting protein phosphorylation data. Under two experimental conditions eleven phosphorylation sites of eight key proteins of the mTOR pathway were measured at ten non-equidistant time points. For the statistical analysis we propose a new advanced hierarchically coupled non-homogeneous dynamic Bayesian network (NH-DBN) model, and we consider various data imputation methods for dealing with non-equidistant temporal observations. Because of the absence of a true gold standard network, we propose to use predictive probabilities in combination with a leave-one-out cross validation strategy to objectively cross-compare the accuracies of different NH-DBN models and data imputation methods. Finally, we employ the best combination of model and data imputation method for predicting the structure of the mTOR protein signaling pathway.

Collaborative Fault Recovery and Network Reconstruction Method for Cyber-physical-systems Based on Double Layer Optimization

Collaborative Fault Recovery and Network Reconstruction Method for Cyber-physical-systems Based on Double Layer Optimization

Reconstruction of international energy trade networks with given marginal data: A comparative analysis

The energy commodity plays a significant role in economic development and national security. It is important for various countries to capture the linkages of the international energy trade network and avoid the occurrence of systemic risk. However, the granular data on trade network is often lacking, and instead, the network has to be reconstructed from partial data. In this paper, we compare seven network reconstruction methods by applying them to 16 types of energy trade data extracted from UN-Comtrade. To this end, first we present the topological structures and compute the dependency characteristics for these energy trade networks. Then, we conduct a horse race among different network reconstruction methods. The methods are ranked by comparing their abilities to reproduce the network structures and bilateral weights. Our findings show that Cimi is the winner across all 16 energy trade networks in terms of link-based similarity measures. In addition, the fitness models (Cimi and Musm) tend to perform best at reconstructing the weight matrix. These findings will aid in the accurate disclosure of latent international energy trade relations when only aggregated export and import figures are available, allowing systemic risks to be appropriately assessed.

Evolutionary Multitasking Multilayer Network Reconstruction

Due to the multilayer nature of real-world systems, the problem of inferring multilayer network structures from nonlinear and complex dynamical systems is prominent in many fields, including engineering, biological, physical, and computer sciences. Many network reconstruction methods have been proposed to address this problem, but none of them consider the similarities among network reconstruction tasks at different component layers, which are inspired by topology correlations and dynamic couplings among different component layers. This article develops an evolutionary multitasking multilayer network reconstruction framework to make use of the correlations among different component layers to improve the reconstruction performance; we refer to this framework as EM2MNR. In EM2MNR, the multilayer network reconstruction problem is first established as a multitasking multilayer network reconstruction problem, where the goal of each task is to reconstruct the network structure of a component layer. In addition, multitasking multilayer network reconstruction problems are high dimensional, but existing evolutionary multitasking algorithms may have poor performance when dealing with optimization problems with a high-dimensional search space. Inspired by the sparsity of multilayer networks, EM2MNR employs the restricted Boltzmann machine to extract low effective features from the original decision space and then decides whether to conduct knowledge transfer on these features. To verify the performance of EM2MNR, this article also designs a test suite for multilayer network reconstruction problems. The experimental results demonstrate the significant improvement obtained by the proposed EM2MNR framework on 96 multilayer network reconstruction problems.

Network inference from perturbation time course data

Networks underlie much of biology from subcellular to ecological scales. Yet, understanding what experimental data are needed and how to use them for unambiguously identifying the structure of even small networks remains a broad challenge. Here, we integrate a dynamic least squares framework into established modular response analysis (DL-MRA), that specifies sufficient experimental perturbation time course data to robustly infer arbitrary two and three node networks. DL-MRA considers important network properties that current methods often struggle to capture: (i) edge sign and directionality; (ii) cycles with feedback or feedforward loops including self-regulation; (iii) dynamic network behavior; (iv) edges external to the network; and (v) robust performance with experimental noise. We evaluate the performance of and the extent to which the approach applies to cell state transition networks, intracellular signaling networks, and gene regulatory networks. Although signaling networks are often an application of network reconstruction methods, the results suggest that only under quite restricted conditions can they be robustly inferred. For gene regulatory networks, the results suggest that incomplete knockdown is often more informative than full knockout perturbation, which may change experimental strategies for gene regulatory network reconstruction. Overall, the results give a rational basis to experimental data requirements for network reconstruction and can be applied to any such problem where perturbation time course experiments are possible.

Deep USRNet Reconstruction Method Based on Combined Attention Mechanism

Single image super-resolution (SISR) based on deep learning is a key research problem in the field of computer vision. However, existing super-resolution reconstruction algorithms often improve the quality of image reconstruction through a single network depth, ignoring the problems of reconstructing image texture structure and easy overfitting of network training. Therefore, this paper proposes a deep unfolding super-resolution network (USRNet) reconstruction method under the integrating channel attention mechanism, which is expected to improve the image resolution and restore the high-frequency information of the image. Thus, the image appears sharper. First, by assigning different weights to features, focusing on more important features and suppressing unimportant features, the details such as image edges and textures are better recovered, and the generalization ability is improved to cope with more complex scenes. Then, the CA (Channel Attention) module is added to USRNet, and the network depth is increased to better express high-frequency features; multi-channel mapping is introduced to extract richer features and enhance the super-resolution reconstruction effect of the model. The experimental results show that the USRNet with integrating channel attention has a faster convergence rate, is not prone to overfitting, and can be converged after 10,000 iterations; the average peak signal-to-noise ratios on the Set5 and Set12 datasets after the side length enlarged by two times are, respectively, 32.23 dB and 29.72 dB, and are dramatically improved compared with SRCNN, SRMD, PAN, and RCAN. The algorithm can generate high-resolution images with clear outlines, and the super-resolution effect is better.

Reconstruction of complex network from time series data based on graph attention network and Gumbel Softmax

It is a challenging practical problem to infer the network structure from measurable time series data. Recently, with the rapid development of graph deep learning, Zhang et al. [Appl. Netw. Sci. 4, 110 (2019)] applied graph neural network to the field of network reconstruction and proposed Gumbel Graph Network. In this paper, a graph deep learning network reconstruction method based on graph attention network and Gumbel Softmax (GAT-GS) is proposed, which can realize high accuracy network reconstruction and node state prediction of discrete and continuous systems. The GAT-GS model is designed based on the dynamic equation of nodes. It consists of two parts: a network structure learner to reconstruct a more real rather than functionally connected networks, based on Gumbel Softmax sampling to generate network structures; and a node state learner using graph attention networks to learn the state evolution of nodes, with the introduction of Laplacian matrix and adjacency matrix for better adaptation to diffusion coupling and unidirectional coupling systems. This model is trained to dynamically adjust the network adjacency matrix and attention coefficients to obtain the network structure and predict the node state. Experimental results show that the GAT-GS model has high reconstruction accuracy, strong robustness and high universality. It can be applied to various kinds of dynamic systems, including Coupled Map Lattice model and Lorenz system, can deal with time series data from regular to complete chaos, can reconstruct various kinds of complex networks, including regular network, Barabási–Albert network and Watts–Strogatz small world network, and it can also reconstruct networks from small scale to large scale with higher computational efficiency.

A Super-resolution Reconstruction Method for Underwater Fish Images with Feedback Networks

<p>Video surveillance is commonly used for production process monitoring in aquaculture. Because underwater video images are prone to blurring and unclear detail texture, this paper proposes a super-resolution network reconstruction method with a feedback network. The reconstruction effect is enhanced by a feedback network in the process of mapping low-resolution images to high-resolution images, which is implemented with a constrained recurrent neural network (RNN) to process deep feedback information. However, the shallow features are fed to the feedback net-work module to generate deeper features through multiple upsampling and downsampling and progressive refinement, which give the network structure an early reconstruction capability and are conducive to more realistically reconstructing high-resolution images. A course learning strategy is introduced to make the network applicable to more complex tasks and improve its robust-ness. We construct a training set of 800 images and validation and test sets of 10 images each using images of marine net fish as the research object. The method of this paper is validated on the public dataset Set14 and a self-built dataset. The proposed method outperforms other methods in both subjective and objective evaluations on the public and self-built datasets. Good foundation for high-definition monitoring of aquaculture is laid. </p> <p> </p>

Research on Data-Driven Distribution Network Planning Method

With the development of the intelligent and interactive power system, the elements of distribution network planning continue to increase. The distribution network connects the transmission system and individuals, directly affects the individual’s power consumption experience, and is a key link in the power system. A reasonable planning scheme can not only improve the power supply capacity and reliability of the distribution network but also fully apply the data of each system in the distribution network to realize the optimal planning of the medium-voltage distribution network driven by data. Firstly, this paper constructs the CIM model and the distribution network topology model and establishes the wiring pattern recognition feature library. The network reconstruction and planning method research was carried out for the target line, and a typical operation scenario of the distribution network was generated. At the same time, based on the time period network loss index, the distribution network reconfiguration optimization model and distribution network expansion planning model are established, and the solution method of the distribution network reconstruction and expansion planning model is expounded. A reconstruction optimization scheme with the best overall network loss performance is in the network operation scenario. The experimental results of the final example show that based on the proposed time period network loss index, the overall operation loss of the distribution network in a period can be calculated more accurately, and the optimized planning scheme is more suitable for the load power consumption characteristics of the region, and the method has certain feasibility.