Graph Curvature for Differentiating Cancer Networks.
Ontology highlight
ABSTRACT:
SUBMITTER: Sandhu R
PROVIDER: S-EPMC4500997 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Cancer has been a leading cause of death in the United States with significant health care costs. Accurate prediction of cancers at an early stage and understanding the genomic mechanisms that drive cancer development are vital to the improvement of treatment outcomes and survival rates, thus resulting in significant social and economic impacts. Attempts have been made to classify cancer types with machine learning techniques during the past two decades and deep learning approaches more recently. In this paper, we established four models with graph convolutional neural network (GCNN) that use unstructured gene expressions as inputs to classify different tumor and non-tumor samples into their designated 33 cancer types or as normal. Four GCNN models based on a co-expression graph, co-expression+singleton graph, protein-protein interaction (PPI) graph, and PPI+singleton graph have been designed and implemented. They were trained and tested on combined 10,340 cancer samples and 731 normal tissue samples from The Cancer Genome Atlas (TCGA) dataset. The established GCNN models achieved excellent prediction accuracies (89.9-94.7%) among 34 classes (33 cancer types and a normal group). In silico gene-perturbation experiments were performed on four models based on co-expression graph, co-expression+singleton, PPI graph, and PPI+singleton graphs. The co-expression GCNN model was further interpreted to identify a total of 428 markers genes that drive the classification of 33 cancer types and normal. The concordance of differential expressions of these markers between the represented cancer type and others are confirmed. Successful classification of cancer types and a normal group regardless of normal tissues' origin suggested that the identified markers are cancer-specific rather than tissue-specific. Novel GCNN models have been established to predict cancer types or normal tissue based on gene expression profiles. We demonstrated the results from the TCGA dataset that these models can produce accurate classification (above 94%), using cancer-specific markers genes. The models and the source codes are publicly available and can be readily adapted to the diagnosis of cancer and other diseases by the data-driven modeling research community.
| S-EPMC7799442 | biostudies-literature
Project description:BackgroundIt is often the case that only a portion of the underlying network structure is observed in real-world settings. However, as most network analysis methods are built on a complete network structure, the natural questions to ask are: (a) how well these methods perform with incomplete network structure, (b) which structural observation and network analysis method to choose for a specific task, and (c) is it beneficial to complete the missing structure.MethodsIn this paper, we consider the incomplete network structure as one random sampling instance from a complete graph, and we choose graph neural networks (GNNs), which have achieved promising results on various graph learning tasks, as the representative of network analysis methods. To identify the robustness of GNNs under graph sampling scenarios, we systemically evaluated six state-of-the-art GNNs under four commonly used graph sampling methods.ResultsWe show that GNNs can still be applied on single static networks under graph sampling scenarios, and simpler GNN models are able to outperform more sophisticated ones in a fairly experimental procedure. More importantly, we find that completing the sampled subgraph does improve the performance of downstream tasks in most cases; however, completion is not always effective and needs to be evaluated for a specific dataset. Our code is available at https://github.com/weiqianglg/evaluate-GNNs-under-graph-sampling.
| S-EPMC9044246 | biostudies-literature
Project description:Cancer complexome comprises a heterogeneous and multifactorial milieu that varies in cytology, physiology, signaling mechanisms and response to therapy. The combined framework of network theory and spectral graph theory along with the multilayer analysis provides a comprehensive approach to analyze the proteomic data of seven different cancers, namely, breast, oral, ovarian, cervical, lung, colon and prostate. Our analysis demonstrates that the protein-protein interaction networks of the normal and the cancerous tissues associated with the seven cancers have overall similar structural and spectral properties. However, few of these properties implicate unsystematic changes from the normal to the disease networks depicting difference in the interactions and highlighting changes in the complexity of different cancers. Importantly, analysis of common proteins of all the cancer networks reveals few proteins namely the sensors, which not only occupy significant position in all the layers but also have direct involvement in causing cancer. The prediction and analysis of miRNAs targeting these sensor proteins hint towards the possible role of these proteins in tumorigenesis. This novel approach helps in understanding cancer at the fundamental level and provides a clue to develop promising and nascent concept of single drug therapy for multiple diseases as well as personalized medicine.
| S-EPMC5290734 | biostudies-literature
Project description:Networks are widely used as a tool for describing diverse real complex systems and have been successfully applied to many fields. The distance between networks is one of the most fundamental concepts for properly classifying real networks, detecting temporal changes in network structures, and effectively predicting their temporal evolution. However, this distance has rarely been discussed in the theory of complex networks. Here, we propose a graph distance between networks based on a Laplacian matrix that reflects the structural and dynamical properties of networked dynamical systems. Our results indicate that the Laplacian-based graph distance effectively quantifies the structural difference between complex networks. We further show that our approach successfully elucidates the temporal properties underlying temporal networks observed in the context of face-to-face human interactions.
| S-EPMC5057156 | biostudies-literature
Project description:Graph representations provide an elegant solution to capture and analyze complex molecular mechanisms in the cell. Co-expression networks are undirected graph representations of transcriptional co-behavior indicating (co-)regulations, functional modules or even physical interactions between the corresponding gene products. The growing avalanche of available RNA sequencing (RNAseq) data fuels the construction of such networks, which are usually stored in relational databases like most other biological data. Inferring linkage by recursive multiple-join statements, however, is computationally expensive and complex to design in relational databases. In contrast, graph databases store and represent complex interconnected data as nodes, edges and properties, making it fast and intuitive to query and analyze relationships. While graph-based database technologies are on their way from a fringe domain to going mainstream, there are only a few studies reporting their application to biological data. We used the graph database management system Neo4j to store and analyze co-expression networks derived from RNAseq data from The Cancer Genome Atlas. Comparing co-expression in tumors versus healthy tissues in six cancer types revealed significant perturbation tracing back to erroneous or rewired gene regulation. Applying centrality, community detection and pathfinding graph algorithms uncovered the destruction or creation of central nodes, modules and relationships in co-expression networks of tumors. Given the speed, accuracy and straightforwardness of managing these densely connected networks, we conclude that graph databases are ready for entering the arena of biological data.
| S-EPMC7731929 | biostudies-literature
Project description:The network embedding task is to represent a node in a network as a low-dimensional vector while incorporating the topological and structural information. Most existing approaches solve this problem by factorizing a proximity matrix, either directly or implicitly. In this work, we introduce a network embedding method from a new perspective, which leverages Modern Hopfield Networks (MHN) for associative learning. Our network learns associations between the content of each node and that node's neighbors. These associations serve as memories in the MHN. The recurrent dynamics of the network make it possible to recover the masked node, given that node's neighbors. Our proposed method is evaluated on different benchmark datasets for downstream tasks such as node classification, link prediction, and graph coarsening. The results show competitive performance compared to the common matrix factorization techniques and deep learning based methods.
| S-EPMC9713410 | biostudies-literature
Project description:Exponential random graph models (ERGMs), also known as p* models, have been utilized extensively in the social science literature to study complex networks and how their global structure depends on underlying structural components. However, the literature on their use in biological networks (especially brain networks) has remained sparse. Descriptive models based on a specific feature of the graph (clustering coefficient, degree distribution, etc.) have dominated connectivity research in neuroscience. Corresponding generative models have been developed to reproduce one of these features. However, the complexity inherent in whole-brain network data necessitates the development and use of tools that allow the systematic exploration of several features simultaneously and how they interact to form the global network architecture. ERGMs provide a statistically principled approach to the assessment of how a set of interacting local brain network features gives rise to the global structure. We illustrate the utility of ERGMs for modeling, analyzing, and simulating complex whole-brain networks with network data from normal subjects. We also provide a foundation for the selection of important local features through the implementation and assessment of three selection approaches: a traditional p-value based backward selection approach, an information criterion approach (AIC), and a graphical goodness of fit (GOF) approach. The graphical GOF approach serves as the best method given the scientific interest in being able to capture and reproduce the structure of fitted brain networks.
| S-EPMC3102079 | biostudies-other
Project description:This manuscript describes the experimental observation of vasculogenesis in chick embryos by means of network analysis. The formation of the vascular network was observed in the area opaca of embryos from 40 to 55 h of development. In the area opaca endothelial cell clusters self-organize as a primitive and approximately regular network of capillaries. The process was observed by bright-field microscopy in control embryos and in embryos treated with Bevacizumab (Avastin®), an antibody that inhibits the signalling of the vascular endothelial growth factor (VEGF). The sequence of images of the vascular growth were thresholded, and used to quantify the forming network in control and Avastin-treated embryos. This characterization is made by measuring vessels density, number of cell clusters and the largest cluster density. From the original images, the topology of the vascular network was extracted and characterized by means of the usual network metrics such as: the degree distribution, average clustering coefficient, average short path length and assortativity, among others. This analysis allows to monitor how the largest connected cluster of the vascular network evolves in time and provides with quantitative evidence of the disruptive effects that Avastin has on the tree structure of vascular networks.
| S-EPMC5882691 | biostudies-other
Project description:Biological networks change dynamically as protein components are synthesized and degraded. Understanding the time-dependence and, in a multicellular organism, tissue-dependence of a network leads to insight beyond a view that collapses time-varying interactions into a single static map. Conventional algorithms are limited to analyzing evolving networks by reducing them to a series of unrelated snapshots.Here we introduce an approach that groups proteins according to shared interaction patterns through a dynamical hierarchical stochastic block model. Protein membership in a block is permitted to evolve as interaction patterns shift over time and space, representing the spatial organization of cell types in a multicellular organism. The spatiotemporal evolution of the protein components are inferred from transcript profiles, using Arabidopsis root development (5 tissues, 3 temporal stages) as an example.The new model requires essentially no parameter tuning, out-performs existing snapshot-based methods, identifies protein modules recruited to specific cell types and developmental stages, and could have broad application to social networks and other similar dynamic systems.
| S-EPMC2799515 | biostudies-literature
Project description:We study the glycosylation processes that convert initially toxic substrates to nutritionally valuable metabolites in the flavonoid biosynthesis pathway of tomato (Solanum lycopersicum) seedlings. To estimate the reaction rates we use ordinary differential equations (ODEs) to model the enzyme kinetics. A popular choice is to use a system of linear ODEs with constant kinetic rates or to use Michaelis-Menten kinetics. In reality, the catalytic rates, which are affected among other factors by kinetic constants and enzyme concentrations, are changing in time and with the approaches just mentioned, this phenomenon cannot be described. Another problem is that, in general these kinetic coefficients are not always identifiable. A third problem is that, it is not precisely known which enzymes are catalyzing the observed glycosylation processes. With several hundred potential gene candidates, experimental validation using purified target proteins is expensive and time consuming. We aim at reducing this task via mathematical modeling to allow for the pre-selection of most potential gene candidates. In this article we discuss a fast and relatively simple approach to estimate time varying kinetic rates, with three favorable properties: firstly, it allows for identifiable estimation of time dependent parameters in networks with a tree-like structure. Secondly, it is relatively fast compared to usually applied methods that estimate the model derivatives together with the network parameters. Thirdly, by combining the metabolite concentration data with a corresponding microarray data, it can help in detecting the genes related to the enzymatic processes. By comparing the estimated time dynamics of the catalytic rates with time series gene expression data we may assess potential candidate genes behind enzymatic reactions. As an example, we show how to apply this method to select prominent glycosyltransferase genes in tomato seedlings.
| S-EPMC5036115 | biostudies-literature