Graph theory analysis reveals how sickle cell disease impacts neural networks of patients with more severe disease.
Ontology highlight
ABSTRACT:
SUBMITTER: Case M
PROVIDER: S-EPMC6411610 | biostudies-literature | 2019
REPOSITORIES: biostudies-literature
Publications
Graph theory analysis reveals how sickle cell disease impacts neural networks of patients with more severe disease.
Case Michelle M Shirinpour Sina S Vijayakumar Vishal V Zhang Huishi H Datta Yvonne Y Nelson Stephen S Pergami Paola P Darbari Deepika S DS Gupta Kalpna K He Bin B
NeuroImage. Clinical 20181114
Sickle cell disease (SCD) is a hereditary blood disorder associated with many life-threatening comorbidities including cerebral stroke and chronic pain. The long-term effects of this disease may therefore affect the global brain network which is not clearly understood. We performed graph theory analysis of functional networks using non-invasive fMRI and high resolution EEG on thirty-one SCD patients and sixteen healthy controls. Resting state data were analyzed to determine differences between c ...[more]
Similar Datasets
Project description:MotivationDisease gene prioritization consists in identifying genes that are likely to be involved in the mechanisms of a given disease, providing a ranking of such genes. Recently, the research community has used computational methods to uncover unknown gene-disease associations; these methods range from combinatorial to machine learning-based approaches. In particular, during the last years, approaches based on deep learning have provided superior results compared to more traditional ones. Yet, the problem with these is their inherent black-box structure, which prevents interpretability.ResultsWe propose a new methodology for disease gene discovery, which leverages graph-structured data using graph neural networks (GNNs) along with an explainability phase for determining the ranking of candidate genes and understanding the model's output. Our approach is based on a positive-unlabeled learning strategy, which outperforms existing gene discovery methods by exploiting GNNs in a non-black-box fashion. Our methodology is effective even in scenarios where a large number of associated genes need to be retrieved, in which gene prioritization methods often tend to lose their reliability.Availability and implementationThe source code of XGDAG is available on GitHub at: https://github.com/GiDeCarlo/XGDAG. The data underlying this article are available at: https://www.disgenet.org/, https://thebiogrid.org/, https://doi.org/10.1371/journal.pcbi.1004120.s003, and https://doi.org/10.1371/journal.pcbi.1004120.s004.
| S-EPMC10421968 | 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:In accordance with the physiological networks that underlie it, human cognition is characterized by both the segregation and interdependence of a number of cognitive domains. Cognition itself, therefore, can be conceptualized as a network of functions. A network approach to cognition has previously revealed topological differences in cognitive profiles between healthy and disease populations. The present study, therefore, used graph theory to determine variation in cognitive profiles across healthy aging and cognitive impairment. A comprehensive neuropsychological test battery was administered to 415 participants. This included three groups of healthy adults aged 18-39 (n = 75), 40-64 (n = 75), and 65 and over (n = 70) and three patient groups with either amnestic (n = 75) or non-amnestic (n = 60) mild cognitive impairment or Alzheimer's type dementia (n = 60). For each group, cognitive networks were created reflective of test-to-test covariance, in which nodes represented cognitive tests and edges reflected statistical inter-nodal significance (p < 0.05). Network metrics were derived using the Brain Connectivity Toolbox. Network-wide clustering, local efficiency and global efficiency of nodes showed linear differences across the stages of aging, being significantly higher among older adults when compared with younger groups. Among patients, these metrics were significantly higher again when compared with healthy older controls. Conversely, average betweenness centralities were highest in middle-aged participants and lower among older adults and patients. In particular, compared with controls, patients demonstrated a distinct lack of centrality in the domains of semantic processing and abstract reasoning. Network composition in the amnestic mild cognitive impairment group was similar to the network of Alzheimer's dementia patients. Using graph theoretical methods, this study demonstrates that the composition of cognitive networks may be measurably altered by the aging process and differentially impacted by pathological cognitive impairment. Network alterations characteristic of Alzheimer's disease in particular may occur early and be distinct from alterations associated with differing types of cognitive impairment. A shift in centrality between domains may be particularly relevant in identifying cognitive profiles indicative of underlying disease. Such techniques may contribute to the future development of more sophisticated diagnostic tools for neurodegenerative disease.
| S-EPMC8311855 | biostudies-literature
Project description:Graph neural networks (GNNs) have been widely used in various graph analysis tasks. As the graph characteristics vary significantly in real-world systems, given a specific scenario, the architecture parameters need to be tuned carefully to identify a suitable GNN. Neural architecture search (NAS) has shown its potential in discovering the effective architectures for the learning tasks in image and language modeling. However, the existing NAS algorithms cannot be applied efficiently to GNN search problem because of two facts. First, the large-step exploration in the traditional controller fails to learn the sensitive performance variations with slight architecture modifications in GNNs. Second, the search space is composed of heterogeneous GNNs, which prevents the direct adoption of parameter sharing among them to accelerate the search progress. To tackle the challenges, we propose an automated graph neural networks (AGNN) framework, which aims to find the optimal GNN architecture efficiently. Specifically, a reinforced conservative controller is designed to explore the architecture space with small steps. To accelerate the validation, a novel constrained parameter sharing strategy is presented to regularize the weight transferring among GNNs. It avoids training from scratch and saves the computation time. Experimental results on the benchmark datasets demonstrate that the architecture identified by AGNN achieves the best performance and search efficiency, comparing with existing human-invented models and the traditional search methods.
| S-EPMC9714572 | biostudies-literature
Project description:Deep learning has been applied to magnetic resonance imaging (MRI) for a variety of purposes, ranging from the acceleration of image acquisition and image denoising to tissue segmentation and disease diagnosis. Convolutional neural networks have been particularly useful for analyzing MRI data due to the regularly sampled spatial and temporal nature of the data. However, advances in the field of brain imaging have led to network- and surface-based analyses that are often better represented in the graph domain. In this analysis, we propose a general purpose cortical segmentation method that, given resting-state connectivity features readily computed during conventional MRI pre-processing and a set of corresponding training labels, can generate cortical parcellations for new MRI data. We applied recent advances in the field of graph neural networks to the problem of cortical surface segmentation, using resting-state connectivity to learn discrete maps of the human neocortex. We found that graph neural networks accurately learn low-dimensional representations of functional brain connectivity that can be naturally extended to map the cortices of new datasets. After optimizing over algorithm type, network architecture, and training features, our approach yielded mean classification accuracies of 79.91% relative to a previously published parcellation. We describe how some hyperparameter choices including training and testing data duration, network architecture, and algorithm choice affect model performance.
| S-EPMC8739886 | biostudies-literature
Project description:Inferring molecular structure from Nuclear Magnetic Resonance (NMR) measurements requires an accurate forward model that can predict chemical shifts from 3D structure. Current forward models are limited to specific molecules like proteins and state-of-the-art models are not differentiable. Thus they cannot be used with gradient methods like biased molecular dynamics. Here we use graph neural networks (GNNs) for NMR chemical shift prediction. Our GNN can model chemical shifts accurately and capture important phenomena like hydrogen bonding induced downfield shift between multiple proteins, secondary structure effects, and predict shifts of organic molecules. Previous empirical NMR models of protein NMR have relied on careful feature engineering with domain expertise. These GNNs are trained from data alone with no feature engineering yet are as accurate and can work on arbitrary molecular structures. The models are also efficient, able to compute one million chemical shifts in about 5 seconds. This work enables a new category of NMR models that have multiple interacting types of macromolecules.
| S-EPMC8372537 | biostudies-literature
Project description:Graph layout algorithms used in network visualization represent the first and the most widely used tool to unveil the inner structure and the behavior of complex networks. Current network visualization software relies on the force-directed layout (FDL) algorithm, whose high computational complexity makes the visualization of large real networks computationally prohibitive and traps large graphs into high energy configurations, resulting in hard-to-interpret "hairball" layouts. Here we use Graph Neural Networks (GNN) to accelerate FDL, showing that deep learning can address both limitations of FDL: it offers a 10 to 100 fold improvement in speed while also yielding layouts which are more informative. We analytically derive the speedup offered by GNN, relating it to the number of outliers in the eigenspectrum of the adjacency matrix, predicting that GNNs are particularly effective for networks with communities and local regularities. Finally, we use GNN to generate a three-dimensional layout of the Internet, and introduce additional measures to assess the layout quality and its interpretability, exploring the algorithm's ability to separate communities and the link-length distribution. The novel use of deep neural networks can help accelerate other network-based optimization problems as well, with applications from reaction-diffusion systems to epidemics.
| S-EPMC10030870 | biostudies-literature
Project description:BackgroundAlthough a large body of knowledge about both brain structure and function has been gathered over the last decades, we still have a poor understanding of their exact relationship. Graph theory provides a method to study the relation between network structure and function, and its application to neuroscientific data is an emerging research field. We investigated topological changes in large-scale functional brain networks in patients with Alzheimer's disease (AD) and frontotemporal lobar degeneration (FTLD) by means of graph theoretical analysis of resting-state EEG recordings. EEGs of 20 patients with mild to moderate AD, 15 FTLD patients, and 23 non-demented individuals were recorded in an eyes-closed resting-state. The synchronization likelihood (SL), a measure of functional connectivity, was calculated for each sensor pair in 0.5-4 Hz, 4-8 Hz, 8-10 Hz, 10-13 Hz, 13-30 Hz and 30-45 Hz frequency bands. The resulting connectivity matrices were converted to unweighted graphs, whose structure was characterized with several measures: mean clustering coefficient (local connectivity), characteristic path length (global connectivity) and degree correlation (network 'assortativity'). All results were normalized for network size and compared with random control networks.ResultsIn AD, the clustering coefficient decreased in the lower alpha and beta bands (p < 0.001), and the characteristic path length decreased in the lower alpha and gamma bands (p < 0.05) compared to controls. In FTLD no significant differences with controls were found in these measures. The degree correlation decreased in both alpha bands in AD compared to controls (p < 0.05), but increased in the FTLD lower alpha band compared with controls (p < 0.01).ConclusionWith decreasing local and global connectivity parameters, the large-scale functional brain network organization in AD deviates from the optimal 'small-world' network structure towards a more 'random' type. This is associated with less efficient information exchange between brain areas, supporting the disconnection hypothesis of AD. Surprisingly, FTLD patients show changes in the opposite direction, towards a (perhaps excessively) more 'ordered' network structure, possibly reflecting a different underlying pathophysiological process.
| S-EPMC2736175 | biostudies-literature
Project description:The brain map project aims to map out the neuron connections of the human brain. Even with all of the wirings mapped out, the global and physical understandings of the function and behavior are still challenging. Hopfield quantified the learning and memory process of symmetrically connected neural networks globally through equilibrium energy. The energy basins of attractions represent memories, and the memory retrieval dynamics is determined by the energy gradient. However, the realistic neural networks are asymmetrically connected, and oscillations cannot emerge from symmetric neural networks. Here, we developed a nonequilibrium landscape-flux theory for realistic asymmetrically connected neural networks. We uncovered the underlying potential landscape and the associated Lyapunov function for quantifying the global stability and function. We found the dynamics and oscillations in human brains responsible for cognitive processes and physiological rhythm regulations are determined not only by the landscape gradient but also by the flux. We found that the flux is closely related to the degrees of the asymmetric connections in neural networks and is the origin of the neural oscillations. The neural oscillation landscape shows a closed-ring attractor topology. The landscape gradient attracts the network down to the ring. The flux is responsible for coherent oscillations on the ring. We suggest the flux may provide the driving force for associations among memories. We applied our theory to rapid-eye movement sleep cycle. We identified the key regulation factors for function through global sensitivity analysis of landscape topography against wirings, which are in good agreements with experiments.
| S-EPMC3831465 | biostudies-literature
Project description:Similarities on the cellular and neurochemical composition of the amygdaloid subnuclei suggests their clustering into subunits that exhibit unique functional organization. The topological principle of community structure has been used to identify functional subnetworks in neuroimaging data that reflect the brain effective organization. Here we used modularity to investigate the organization of the amygdala using resting state functional magnetic resonance imaging (rsfMRI) data. Our goal was to determine whether such topological organization would reliably reflect the known neurobiology of individual amygdaloid nuclei, allowing for human imaging studies to accurately reflect the underlying neurobiology. Modularity analysis identified amygdaloid elements consistent with the main anatomical subdivisions of the amygdala that embody distinct functional and structural properties. Additionally, functional connectivity pathways of these subunits and their correlation with task-induced amygdala activation revealed distinct functional profiles consistent with the neurobiology of the amygdala nuclei. These modularity findings corroborate the structure-function relationship between amygdala anatomical substructures, supporting the use of network analysis techniques to generate biologically meaningful partitions of brain structures.
| S-EPMC5663902 | biostudies-other