Near linear time algorithm to detect community structures in large-scale networks

Social Sensing of the Imbalance of Urban and Regional Development in China Through the Population Migration Network around Spring Festival

Regional development differences are a universal problem in the economic development process of countries around the world. In recent decades, China has experienced rapid urban development since the implementation of the reform and opening-up policy. However, development differs across regions, triggering the migration of laborers from underdeveloped areas to developed areas. The interaction between regional development differences and Spring Festival has formed the world’s largest cyclical migration phenomenon, Spring Festival travel. Studying the migration pattern from public spatiotemporal behavior can contribute to understanding the differences in regional development. This paper proposes a geospatial network analytical framework to quantitatively characterize the imbalance of urban/regional development based on Spring Festival travel from the perspectives of complex network science and geospatial science. Firstly, the urban development difference is explored based on the intercity population flow difference ratio, PageRank algorithm, and attractiveness index. Secondly, the community detection method and rich-club coefficient are applied to further observe the spatial interactions between cities. Finally, the regional importance index and attractiveness index are used to reveal the regional development imbalance. The methods and findings can be used for urban planning, poverty alleviation, and population studies.

Deconvolute individual genomes from metagenome sequences through short read clustering

Metagenome assembly from short next-generation sequencing data is a challenging process due to its large scale and computational complexity. Clustering short reads by species before assembly offers a unique opportunity for parallel downstream assembly of genomes with individualized optimization. However, current read clustering methods suffer either false negative (under-clustering) or false positive (over-clustering) problems. Here we extended our previous read clustering software, SpaRC, by exploiting statistics derived from multiple samples in a dataset to reduce the under-clustering problem. Using synthetic and real-world datasets we demonstrated that this method has the potential to cluster almost all of the short reads from genomes with sufficient sequencing coverage. The improved read clustering in turn leads to improved downstream genome assembly quality.

Identifying Communities in Dynamic Networks Using Information Dynamics

Identifying communities in dynamic networks is essential for exploring the latent network structures, understanding network functions, predicting network evolution, and discovering abnormal network events. Many dynamic community detection methods have been proposed from different viewpoints. However, identifying the community structure in dynamic networks is very challenging due to the difficulty of parameter tuning, high time complexity and detection accuracy decreasing as time slices increase. In this paper, we present a dynamic community detection framework based on information dynamics and develop a dynamic community detection algorithm called DCDID (dynamic community detection based on information dynamics), which uses a batch processing technique to incrementally uncover communities in dynamic networks. DCDID employs the information dynamics model to simulate the exchange of information among nodes and aims to improve the efficiency of community detection by filtering out the unchanged subgraph. To illustrate the effectiveness of DCDID, we extensively test it on synthetic and real-world dynamic networks, and the results demonstrate that the DCDID algorithm is superior to the representative methods in relation to the quality of dynamic community detection.

Cold Start Problem Alleviation in a Research Paper Recommendation System Using the Random Walk Approach on a Heterogeneous User-Paper Graph

Recommendation approaches generally fail to recommend newly-published papers as relevant, owing to the lack of prior information about the said papers and, more particularly, problems associated with cold starts. It would appear, to all intents and purposes, that researchers currently interact more on social networks than they normally would in academic circles, and relationships of a purely academic nature have witnessed a paradigm shift, in keeping with this new trend. In existing paper recommendation methods, the social interaction factor has yet to play a pivotal role. The authors propose a social network-based research paper recommendation method, that alleviates cold start problems by incorporating users' social interaction, as well as topical relevancy, among assorted papers in the Mendeley academic social network using a novel approach, random walk Ergodic Markov Chain. The system yields improved results after cold start alleviation, compared with the existing system.

ALEPH: a network-oriented approach for the generation of fragment-based libraries and for structure interpretation

The analysis of large structural databases reveals general features and relationships among proteins, providing useful insight. A different approach is required to characterize ubiquitous secondary-structure elements, where flexibility is essential in order to capture small local differences. The ALEPH software is optimized for the analysis and the extraction of small protein folds by relying on their geometry rather than on their sequence. The annotation of the structural variability of a given fold provides valuable information for fragment-based molecular-replacement methods, in which testing alternative model hypotheses can succeed in solving difficult structures when no homology models are available or are successful. ARCIMBOLDO_BORGES combines the use of composite secondary-structure elements as a search model with density modification and tracing to reveal the rest of the structure when both steps are successful. This phasing method relies on general fold libraries describing variations around a given pattern of β-sheets and helices extracted using ALEPH. The program introduces characteristic vectors defined from the main-chain atoms as a way to describe the geometrical properties of the structure. ALEPH encodes structural properties in a graph network, the exploration of which allows secondary-structure annotation, decomposition of a structure into small compact folds, generation of libraries of models representing a variation of a given fold and finally superposition of these folds onto a target structure. These functions are available through a graphical interface designed to interactively show the results of structure manipulation, annotation, fold decomposition, clustering and library generation. ALEPH can produce pictures of the graphs, structures and folds for publication purposes.

Density-based Approach with Dual Optimization for Tracking Community Structure of Increasing Social Networks

The rapid evolution of social networks in recent years has focused the attention of researchers to find adequate solutions for the management of these networks. For this purpose, several efficient algorithms dedicated to the tracking and the rapid detection of the community structure have been proposed. In this paper, we propose a novel density-based approach with dual optimization for tracking community structure of increasing social networks. These networks are part of dynamic networks evolving by adding nodes with their links. The local optimization of the density makes it possible to reduce the resolution limit problem generated by the optimization of the modularity. The presented algorithm is incremental with a relatively low algorithmic complexity, making it efficient and faster. To demonstrate the effectiveness of our method, we test it on social networks of the real world. The experimental results show the performance and efficiency of our algorithm measured in terms of modularity density, modularity, normalized mutual information, number of communities discovered, running time and stability of communities.

Optimizing Variational Graph Autoencoder for Community Detection with Dual Optimization

Variational Graph Autoencoder (VGAE) has recently gained traction for learning representations on graphs. Its inception has allowed models to achieve state-of-the-art performance for challenging tasks such as link prediction, rating prediction, and node clustering. However, a fundamental flaw exists in Variational Autoencoder (VAE)-based approaches. Specifically, merely minimizing the loss of VAE increases the deviation from its primary objective. Focusing on Variational Graph Autoencoder for Community Detection (VGAECD) we found that optimizing the loss using the stochastic gradient descent often leads to sub-optimal community structure especially when initialized poorly. We address this shortcoming by introducing a dual optimization procedure. This procedure aims to guide the optimization process and encourage learning of the primary objective. Additionally, we linearize the encoder to reduce the number of learning parameters. The outcome is a robust algorithm that outperforms its predecessor.

A Feasible Community Detection Algorithm for Multilayer Networks

As a more complicated network model, multilayer networks provide a better perspective for describing the multiple interactions among social networks in real life. Different from conventional community detection algorithms, the algorithms for multilayer networks can identify the underlying structures that contain various intralayer and interlayer relationships, which is of significance and remains a challenge. In this paper, aiming at the instability of the label propagation algorithm (LPA), an improved label propagation algorithm based on the SH-index (SH-LPA) is proposed. By analyzing the characteristics and deficiencies of the H-index, the SH-index is presented as an index to evaluate the importance of nodes, and the stability of the SH-LPA algorithm is verified by a series of experiments. Afterward, considering the deficiency of the existing multilayer network aggregation model, we propose an improved multilayer network aggregation model that merges two networks into a weighted single-layer network. Finally, considering the influence of the SH-index and the weight of the edge of the weighted network, a community detection algorithm (MSH-LPA) suitable for multilayer networks is exhibited in terms of the SH-LPA algorithm, and the superiority of the mentioned algorithm is verified by experimental analysis.

Detecting coalitions by optimally partitioning signed networks of political collaboration

We propose new mathematical programming models for optimal partitioning of a signed graph into cohesive groups. To demonstrate the approach’s utility, we apply it to identify coalitions in US Congress since 1979 and examine the impact of polarized coalitions on the effectiveness of passing bills. Our models produce a globally optimal solution to the NP-hard problem of minimizing the total number of intra-group negative and inter-group positive edges. We tackle the intensive computations of dense signed networks by providing upper and lower bounds, then solving an optimization model which closes the gap between the two bounds and returns the optimal partitioning of vertices. Our substantive findings suggest that the dominance of an ideologically homogeneous coalition (i.e. partisan polarization) can be a protective factor that enhances legislative effectiveness.

Community Detection Based on a Preferential Decision Model

The research on complex networks is a hot topic in many fields, among which community detection is a complex and meaningful process, which plays an important role in researching the characteristics of complex networks. Community structure is a common feature in the network. Given a graph, the process of uncovering its community structure is called community detection. Many community detection algorithms from different perspectives have been proposed. Achieving stable and accurate community division is still a non-trivial task due to the difficulty of setting specific parameters, high randomness and lack of ground-truth information. In this paper, we explore a new decision-making method through real-life communication and propose a preferential decision model based on dynamic relationships applied to dynamic systems. We apply this model to the label propagation algorithm and present a Community Detection based on Preferential Decision Model, called CDPD. This model intuitively aims to reveal the topological structure and the hierarchical structure between networks. By analyzing the structural characteristics of complex networks and mining the tightness between nodes, the priority of neighbor nodes is chosen to perform the required preferential decision, and finally the information in the system reaches a stable state. In the experiments, through the comparison of eight comparison algorithms, we verified the performance of CDPD in real-world networks and synthetic networks. The results show that CDPD not only has better performance than most recent algorithms on most datasets, but it is also more suitable for many community networks with ambiguous structure, especially sparse networks.

Rough Net Approach for Community Detection Analysis in Complex Networks

Rough set theory has many interesting applications in circumstances characterized by vagueness. In this paper, the applications of rough set theory in community detection analysis are discussed based on the Rough Net definition. We will focus the application of Rough Net on community detection validity in both monoplex and multiplex networks. Also, the topological evolution estimation between adjacent layers in dynamic networks is discussed and a new community interaction visualization approach combining both complex network representation and Rough Net definition is adopted to interpret the community structure. We provide some examples that illustrate how the Rough Net definition can be used to analyze the properties of the community structure in real-world networks, including dynamic networks.

Applications of Network Analysis in Biomedicine

The abundance of high-throughput data and technical refinements in graph theories have allowed network analysis to become an effective approach for various medical fields. This chapter introduces co-expression, Bayesian, and regression-based network construction methods, which are the basis of network analysis. Various methods in network topology analysis are explained, along with their unique features and applications in biomedicine. Furthermore, we explain the role of network embedding in reducing the dimensionality of networks and outline several popular algorithms used by researchers today. Current literature has implemented different combinations of topology analysis and network embedding techniques, and we outline several studies in the fields of genetic-based disease prediction, drug-target identification, and multi-level omics integration.

Pharmacogenomic network analysis of the gene-drug interaction landscape underlying drug disposition

In recent decades the identification of pharmacogenomic gene-drug associations has evolved tremendously. Despite this progress, a major fraction of the heritable inter-individual variability remains elusive. Higher-dimensional phenomena, such as gene-gene-drug interactions, in which variability in multiple genes synergizes to precipitate an observable phenotype have been suggested to account at least for part of this missing heritability. However, the identification of such intricate relationships remains difficult partly because of analytical challenges associated with the complexity explosion of the problem. To facilitate the identification of such combinatorial pharmacogenetic associations, we here propose a network analysis strategy. Specifically, we analyzed the landscape of drug metabolizing enzymes and transporters for 100 top selling drugs as well as all compounds with pharmacogenetic germline labels or dosing guidelines. Based on this data, we calculated the posterior probabilities that gene i is involved in metabolism, transport or toxicity of a given drug under the condition that another gene j is involved for all pharmacogene pairs (i, j). Interestingly, these analyses revealed significant patterns between individual genes and across pharmacogene families that provide insights into metabolic interactions. To visualize the gene-drug interaction landscape, we use multidimensional scaling to collapse this similarity matrix into a two-dimensional network. We suggest that Euclidian distance between nodes can inform about the likelihood of epistatic interactions and thus might provide a useful tool to reduce the search space and facilitate the identification of combinatorial pharmacogenomic associations.

Chaotic memetic algorithm and its application for detecting community structure in complex networks

Community structure is one of the most important topological characteristics of complex networks. Detecting the community structure is a highly challenging problem in analyzing complex networks and it has high significance for understanding the function and organization of complex networks. A wide range of algorithms for this problem uses the maximization of a quality function called modularity. In this paper, a Chaotic Memetic Algorithm is proposed and used to solve the problem of the community structure detection in complex networks. In the proposed algorithm, the combination of the genetic algorithm (global search) and a dedicated local search is used to search the solution space. In addition, to improve the convergence speed and efficiency, in both global search and local search processes, instead of random numbers, chaotic numbers are used. By using chaotic numbers, the population diversity is preserved and it prevents from falling in the local optimum. The experiments on both real-world and synthetic benchmark networks indicate that the proposed algorithm is effective compared with state-of-the-art algorithms.

Multi-Type Node Detection in Network Communities

Patterns of connectivity among nodes on networks can be revealed by community detection algorithms. The great significance of communities in the study of clustering patterns of nodes in different systems has led to the development of various methods for identifying different node types on diverse complex systems. However, most of the existing methods identify only either disjoint nodes or overlapping nodes. Many of these methods rarely identify disjunct nodes, even though they could play significant roles on networks. In this paper, a new method, which distinctly identifies disjoint nodes (node clusters), disjunct nodes (single node partitions) and overlapping nodes (nodes binding overlapping communities), is proposed. The approach, which differs from existing methods, involves iterative computation of bridging centrality to determine nodes with the highest bridging centrality value. Additionally, node similarity is computed between the bridge-node and its neighbours, and the neighbours with the least node similarity values are disconnected. This process is sustained until a stoppage criterion condition is met. Bridging centrality metric and Jaccard similarity coefficient are employed to identify bridge-nodes (nodes at cut points) and the level of similarity between the bridge-nodes and their direct neighbours respectively. Properties that characterise disjunct nodes are equally highlighted. Extensive experiments are conducted with artificial networks and real-world datasets and the results obtained demonstrate efficiency of the proposed method in distinctly detecting and classifying multi-type nodes in network communities. This method can be applied to vast areas such as examination of cell interactions and drug designs, disease control in epidemics, dislodging organised crime gangs and drug courier networks, etc.

Enhancing Personalized Recommendation by Implicit Preference Communities Modeling

Recommender systems aim to capture user preferences and provide accurate recommendations to users accordingly. For each user, there usually exist others with similar preferences, and a collection of users may also have similar preferences with each other, thus forming a community. However, such communities may not necessarily be explicitly given, and the users inside the same communities may not know each other; they are formally defined and named Implicit Preference Communities (IPCs) in this article. By enriching user preferences with the information of other users in the communities, the performance of recommender systems can also be enhanced.

Historical explicit ratings are a good resource to construct the IPCs of users but is usually sparse. Meanwhile, user preferences are easily affected by their social connections, which can be jointly used for IPC modeling with the ratings. However, this imposes two challenges for model design. First, the rating and social domains are heterogeneous; thus, it is challenging to coordinate social information and rating behaviors for a same learning task. Therefore, transfer learning is a good strategy for IPC modeling. Second, the communities are not explicitly labeled, and existing supervised learning approaches do not fit the requirement of IPC modeling. As co-clustering is an effective unsupervised learning approach for discovering block structures in high-dimensional data, it is a cornerstone for discovering the structure of IPCs.

In this article, we propose a recommendation model with Implicit Preference Communities from user ratings and social connections. To tackle the unsupervised learning limitation, we design a Bayesian probabilistic graphical model to capture the IPC structure for recommendation. Meanwhile, following the spirit of transfer learning, both rating behaviors and social connections are introduced into the model by parameter sharing. Moreover, Gibbs sampling-based algorithms are proposed for parameter inferences of the models. Furthermore, to meet the need for online scenarios when the data arrive sequentially as a stream, a novel online sampling-based parameter inference algorithm for recommendation is proposed. To the best of our knowledge, this is the first attempt to propose and formally define the concept of IPC.

DeepLink: A novel link prediction framework based on deep learning

Recently, link prediction has attracted more attention from various disciplines such as computer science, bioinformatics and economics. In link prediction, numerous information such as network topology, profile information and user-generated contents are considered to discover missing links between nodes. Whereas numerous previous researches had focused on the structural features of the networks for link prediction, recent studies have shown more interest in profile and content information, too. So, some of these researches combine structural and content information. However, some issues such as scalability and feature engineering need to be investigated to solve a few remaining problems. Moreover, most of the previous researches are presented only for undirected and unweighted networks. In this article, a novel link prediction framework named ‘DeepLink’ is presented, which is based on deep learning techniques. While deep learning has the advantage of extracting automatically the best features for link prediction, many other link prediction algorithms need manual feature engineering. Moreover, in the proposed framework, both structural and content information are employed. The framework is capable of using different structural feature vectors that are prepared by various link prediction methods. It learns all proximity orders that are presented on a network during the structural feature learning. We have evaluated the effectiveness of DeepLink on two real social network datasets, Telegram and irBlogs. On both datasets, the proposed framework outperforms several other structural and hybrid approaches for link prediction.

Interactive Multiresolution Visualization of Cellular Network Processes

Visualization plays a central role in the analysis of biochemical network models to identify patterns that arise from reaction dynamics and perform model exploratory analysis. To facilitate these analyses, we developed PyViPR, a visualization tool that generates static and dynamic representations of biochemical network processes within a Python-based environment. PyViPR embeds network visualizations within Jupyter notebooks, thus enabling integration with modeling, simulation, and analysis workflows. To present the capabilities of PyViPR, we explore execution mechanisms of extrinsic apoptosis in HeLa cells. We show that community-detection algorithms identify groups of molecular species that capture key biological functions and ease exploration of the apoptosis network. We then show how different kinetic parameter sets that fit the experimental data equally well exhibit significantly different signal-execution dynamics as the system progresses toward mitochondrial outer-membrane permeabilization. Therefore, PyViPR aids the conceptual understanding of dynamic network processes and accelerates hypothesis generation for further testing and validation.

Community Detection Method Based on Node Density, Degree Centrality, and K-Means Clustering in Complex Network

Community detection in networks plays a key role in understanding their structures, and the application of clustering algorithms in community detection tasks in complex networks has attracted intensive attention in recent years. In this paper, based on the definition of uncertainty of node community belongings, the node density is proposed first. After that, the DD (the combination of node density and node degree centrality) is proposed for initial node selection in community detection. Finally, based on the DD and k-means clustering algorithm, we proposed a community detection approach, the density-degree centrality-jaccard-k-means method (DDJKM). The DDJKM algorithm can avoid the problem of random selection of initial cluster centers in conventional k-means clustering algorithms, so that isolated nodes will not be selected as initial cluster centers. Additionally, DDJKM can reduce the iteration times in the clustering process and the over-short distances between the initial cluster centers can be avoided by calculating the node similarity. The proposed method is compared with state-of-the-art algorithms on synthetic networks and real-world networks. The experimental results show the effectiveness of the proposed method in accurately describing the community. The results also show that the DDJKM is practical a approach for the detection of communities with large network datasets.

STS-NLSP: A Network-Based Label Space Partition Method for Predicting the Specificity of Membrane Transporter Substrates Using a Hybrid Feature of Structural and Semantic Similarity

Membrane transport proteins play crucial roles in the pharmacokinetics of substrate drugs, the drug resistance in cancer and are vital to the process of drug discovery, development and anti-cancer therapeutics. However, experimental methods to profile a substrate drug against a panel of transporters to determine its specificity are labor intensive and time consuming. In this article, we aim to develop an in silico multi-label classification approach to predict whether a substrate can specifically recognize one of the 13 categories of drug transporters ranging from ATP-binding cassette to solute carrier families using both structural fingerprints and chemical ontologies information of substrates. The data-driven network-based label space partition (NLSP) method was utilized to construct the model based on a hybrid of similarity-based feature by the integration of 2D fingerprint and semantic similarity. This method builds predictors for each label cluster (possibly intersecting) detected by community detection algorithms and takes union of label sets for a compound as final prediction. NLSP lies into the ensembles of multi-label classifier category in multi-label learning field. We utilized Cramér's V statistics to quantify the label correlations and depicted them via a heatmap. The jackknife tests and iterative stratification based cross-validation method were adopted on a benchmark dataset to evaluate the prediction performance of the proposed models both in multi-label and label-wise manner. Compared with other powerful multi-label methods, ML-kNN, MTSVM, and RAkELd, our multi-label classification model of NLPS-RF (random forest-based NLSP) has proven to be a feasible and effective model, and performed satisfactorily in the predictive task of transporter-substrate specificity. The idea behind NLSP method is intriguing and the power of NLSP remains to be explored for the multi-label learning problems in bioinformatics. The benchmark dataset, intermediate results and python code which can fully reproduce our experiments and results are available at https://github.com/dqwei-lab/STS.

Vienna Graph Clustering

This paper serves as a user guide to the Vienna graph clustering framework. We review our general memetic algorithm, VieClus, to tackle the graph clustering problem. A key component of our contribution are natural recombine operators that employ ensemble clusterings as well as multi-level techniques. Lastly, we combine these techniques with a scalable communication protocol, producing a system that is able to compute high-quality solutions in a short amount of time. After giving a description of the algorithms employed, we establish the connection of the graph clustering problem to protein-protein interaction networks and moreover give a description on how the software can be used, what file formats are expected, and how this can be used to find functional groups in protein-protein interaction networks.

A new algorithm for detecting communities in social networks based on content and structure information

Purpose

The purpose of this paper is to present an algorithm for detecting communities in social networks.

Design/methodology/approach

The majority of existing methods of community detection in social networks are based on structural information, and they neglect the content information. In this paper, the authors propose a novel approach that combines the content and structure information to discover more meaningful communities in social networks. To integrate the content information in the process of community detection, the authors propose to exploit the texts involved in social networks to identify the users’ topics of interest. These topics are detected based on the statistical and semantic measures, which allow us to divide the users into different groups so that each group represents a distinct topic. Then, the authors perform links analysis in each group to discover the users who are highly interconnected (communities).

Findings

To validate the performance of the approach, the authors carried out a set of experiments on four real life data sets, and they compared their method with classical methods that ignore the content information.

Originality/value

The experimental results demonstrate that the quality of community structure is improved when we take into account the content and structure information during the procedure of community detection.

Differential network enrichment analysis reveals novel lipid pathways in chronic kidney disease

MOTIVATION

Functional enrichment testing methods can reduce data comprising hundreds of altered biomolecules to smaller sets of altered biological 'concepts' that help generate testable hypotheses. This study leveraged differential network enrichment analysis methodology to identify and validate lipid subnetworks that potentially differentiate chronic kidney disease (CKD) by severity or progression.

RESULTS

We built a partial correlation interaction network, identified highly connected network components, applied network-based gene-set analysis to identify differentially enriched subnetworks, and compared the subnetworks in patients with early-stage versus late-stage CKD. We identified two subnetworks 'triacylglycerols' and 'cardiolipins-phosphatidylethanolamines (CL-PE)' characterized by lower connectivity, and a higher abundance of longer polyunsaturated triacylglycerols in patients with severe CKD (stage ≥4) from the Clinical Phenotyping Resource and Biobank Core. These finding were replicated in an independent cohort, the Chronic Renal Insufficiency Cohort. Using an innovative method for elucidating biological alterations in lipid networks, we demonstrated alterations in triacylglycerols and cardiolipins-phosphatidylethanolamines that precede the clinical outcome of end-stage kidney disease by several years.

AVAILABILITY AND IMPLEMENTATION

A complete list of NetGSA results in HTML format can be found at http://metscape.ncibi.org/netgsa/12345-022118/cric_cprobe/022118/results_cric_cprobe/main.html. The DNEA is freely available at https://github.com/wiggie/DNEA. Java wrapper leveraging the cytoscape.js framework is available at http://js.cytoscape.org.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

ATC-NLSP: Prediction of the Classes of Anatomical Therapeutic Chemicals Using a Network-Based Label Space Partition Method

Anatomical Therapeutic Chemical (ATC) classification system proposed by the World Health Organization is a widely accepted drug classification scheme in both academic and industrial realm. It is a multilabeling system which categorizes drugs into multiple classes according to their therapeutic, pharmacological, and chemical attributes. In this study, we adopted a data-driven network-based label space partition (NLSP) method for prediction of ATC classes of a given compound within the multilabel learning framework. The proposed method ATC-NLSP is trained on the similarity-based features such as chemical–chemical interaction and structural and fingerprint similarities of a compound to other compounds belonging to the different ATC categories. The NLSP method trains predictors for each label cluster (possibly intersecting) detected by community detection algorithms and takes the ensemble labels for a compound as final prediction. Experimental evaluation based on the jackknife test on the benchmark dataset demonstrated that our method has boosted the absolute true rate, which is the most stringent evaluation metrics in this study, from 0.6330 to 0.7497, in comparison to the state-of-the-art approaches. Moreover, the community structures of the label relation graph were detected through the label propagation method. The advantage of multilabel learning over the single-label models was shown by label-wise analysis. Our study indicated that the proposed method ATC-NLSP, which adopts ideas from network research community and captures the correlation of labels in a data driven manner, is the top-performing model in the ATC prediction task. We believed that the power of NLSP remains to be unleashed for the multilabel learning tasks in drug discovery. The source codes are freely available at https://github.com/dqwei-lab/ATC.

OmicsNet: a web-based tool for creation and visual analysis of biological networks in 3D space

Biological networks play increasingly important roles in omics data integration and systems biology. Over the past decade, many excellent tools have been developed to support creation, analysis and visualization of biological networks. However, important limitations remain: most tools are standalone programs, the majority of them focus on protein-protein interaction (PPI) or metabolic networks, and visualizations often suffer from 'hairball' effects when networks become large. To help address these limitations, we developed OmicsNet - a novel web-based tool that allows users to easily create different types of molecular interaction networks and visually explore them in a three-dimensional (3D) space. Users can upload one or multiple lists of molecules of interest (genes/proteins, microRNAs, transcription factors or metabolites) to create and merge different types of biological networks. The 3D network visualization system was implemented using the powerful Web Graphics Library (WebGL) technology that works natively in most major browsers. OmicsNet supports force-directed layout, multi-layered perspective layout, as well as spherical layout to help visualize and navigate complex networks. A rich set of functions have been implemented to allow users to perform coloring, shading, topology analysis, and enrichment analysis. OmicsNet is freely available at http://www.omicsnet.ca.

Community Detection on Networks with Ricci Flow

Many complex networks in the real world have community structures - groups of well-connected nodes with important functional roles. It has been well recognized that the identification of communities bears numerous practical applications. While existing approaches mainly apply statistical or graph theoretical/combinatorial methods for community detection, in this paper, we present a novel geometric approach which  enables us to borrow powerful classical geometric methods and properties. By considering networks as geometric objects and communities in a network as a geometric decomposition, we apply curvature and discrete Ricci flow, which have been used to decompose smooth manifolds with astonishing successes in mathematics, to break down communities in networks. We  tested our method on networks with ground-truth community structures, and experimentally confirmed the effectiveness of this geometric approach.

Label propagation method based on bi-objective optimization for ambiguous community detection in large networks

Community detection is of great significance because it serves as a basis for network research and has been widely applied in real-world scenarios. It has been proven that label propagation is a successful strategy for community detection in large-scale networks and local clustering coefficient can measure the degree to which the local nodes tend to cluster together. In this paper, we try to optimize two objects about the local clustering coefficient to detect community structure. To avoid the trend that merges too many nodes into a large community, we add some constraints on the objectives. Through the experiments and comparison, we select a suitable strength for one constraint. Last, we merge two objectives with linear weighting into a hybrid objective and use the hybrid objective to guide the label update in our proposed label propagation algorithm. We perform amounts of experiments on both artificial and real-world networks. Experimental results demonstrate the superiority of our algorithm in both modularity and speed, especially when the community structure is ambiguous.

A Critical Comparison of Pipelines for Structural Brain Network Analysis

The human brain could be understood as a vast network composed of interconnected regions forming hierarchical and overlapping subnetworks. Cortical thickness (CT) correlations, as measure of structural connectedness, can be transformed into structural networks. Those can be analyzed via cluster detection algorithms to investigate their organization. An analysis pipeline from CT to links, networks, clusters and beyond is composed of a lot of consecutive reasoned or just arbitrary steps. How much can different pipeline components alter the result? Which step is to be considered most influential? In order to give a sufficient answer, we critically compare 96 different pipelines. The results of this study are to some extent surprising as the choice of a specific CT correlation and correction procedure can lead to more diverse results than the decision between taking only absolute CT correlations or ignoring all negative ones. Even more crucial, exemplary cluster detectors were found to pair-wisely correlate from r = 0.98 to even r = -0.20 on the same data. Thus, a summary of multiple detector results with different but suited properties is highly advisable until a theory based neuroscientific recommendation for the best approach will be found.

Reconstruction and inference of the Lactococcus lactis MG1363 gene co-expression network

Lactic acid bacteria are Gram-positive bacteria used throughout the world in many industrial applications for their acidification, flavor and texture formation attributes. One of the species, Lactococcus lactis, is employed for the production of fermented milk products like cheese, buttermilk and quark. It ferments lactose to lactic acid and, thus, helps improve the shelf life of the products. Many physiological and transcriptome studies have been performed in L. lactis in order to comprehend and improve its biotechnological assets. Using large amounts of transcriptome data to understand and predict the behavior of biological processes in bacterial or other cell types is a complex task. Gene networks enable predicting gene behavior and function in the context of transcriptionally linked processes. We reconstruct and present the gene co-expression network (GCN) for the most widely studied L. lactis strain, MG1363, using publicly available transcriptome data. Several methods exist to generate and judge the quality of GCNs. Different reconstruction methods lead to networks with varying structural properties, consequently altering gene clusters. We compared the structural properties of the MG1363 GCNs generated by five methods, namely Pearson correlation, Spearman correlation, GeneNet, Weighted Gene Co-expression Network Analysis (WGCNA), and Sparse PArtial Correlation Estimation (SPACE). Using SPACE, we generated an L. lactis MG1363 GCN and assessed its quality using modularity and structural and biological criteria. The L. lactis MG1363 GCN has structural properties similar to those of the gold-standard networks of Escherichia coli K-12 and Bacillus subtilis 168. We showcase that the network can be used to mine for genes with similar expression profiles that are also generally linked to the same biological process.

Next Generation Networks: Featuring the Potential Role of Emerging Applications in Translational Oncology

Nowadays, networks are pervasively used as examples of models suitable to mathematically represent and visualize the complexity of systems associated with many diseases, including cancer. In the cancer context, the concept of network entropy has guided many studies focused on comparing equilibrium to disequilibrium (i.e., perturbed) conditions. Since these conditions reflect both structural and dynamic properties of network interaction maps, the derived topological characterizations offer precious support to conduct cancer inference. Recent innovative directions have emerged in network medicine addressing especially experimental omics approaches integrated with a variety of other data, from molecular to clinical and also electronic records, bioimaging etc. This work considers a few theoretically relevant concepts likely to impact the future of applications in personalized/precision/translational oncology. The focus goes to specific properties of networks that are still not commonly utilized or studied in the oncological domain, and they are: controllability, synchronization and symmetry. The examples here provided take inspiration from the consideration of metastatic processes, especially their progression through stages and their hallmark characteristics. Casting these processes into computational frameworks and identifying network states with specific modular configurations may be extremely useful to interpret or even understand dysregulation patterns underlying cancer, and associated events (onset, progression) and disease phenotypes.