269 results found
Zhang X, Zhang J, Sun K, et al., 2019, Integrated Multi-omics Analysis Using Variational Autoencoders: Application to Pan-cancer Classification
© 2019 IEEE. Omics data are normally high dimensional with large number of molecular features and relatively small number of available samples with clinical labels. The 'curse of dimensionality' makes it challenging to train a machine learning model using high dimensional omics data like DNA methylation and gene expression profiles. Here we propose an end-to-end deep learning model called OmiVAE to extract low dimensional features and classify samples from multi-omics data. OmiVAE combines the basic structure of variational autoencoders with a classifier to achieve task-oriented feature extraction and multi-class classification. The training procedure of OmiVAE is comprised of an unsupervised phase and a supervised phase. During the unsupervised phase, a hierarchical cluster structure of samples can be automatically formed without the need for labels. And in the supervised phase, OmiVAE achieved an average accuracy of 97.49% after 10-fold cross-validation among 33 tumour types and normal samples, which shows better performance than existing methods. The integrated model learned from multi-omics datasets outperformed those using only one type of omics data, which indicates that the complementary information from different omics datatypes provides useful insights for biomedical tasks like cancer classification.
Zhang J, Zhang X, Sun K, et al., 2019, Unsupervised Annotation of Phenotypic Abnormalities via Semantic Latent Representations on Electronic Health Records, 2019 IEEE International Conference on Bioinformatics and Biomedicine
Wang Y, Li Q, Liu L, et al., 2019, TeraVR empowers precise reconstruction of complete 3-D neuronal morphology in the whole brain, Nature Communications, Vol: 10, ISSN: 2041-1723
Neuron morphology is recognized as a key determinant of cell type, yet the quantitative profiling of a mammalian neuron's complete three-dimensional (3-D) morphology remains arduous when the neuron has complex arborization and long projection. Whole-brain reconstruction of neuron morphology is even more challenging as it involves processing tens of teravoxels of imaging data. Validating such reconstructions is extremely laborious. We develop TeraVR, an open-source virtual reality annotation system, to address these challenges. TeraVR integrates immersive and collaborative 3-D visualization, interaction, and hierarchical streaming of teravoxel-scale images. Using TeraVR, we have produced precise 3-D full morphology of long-projecting neurons in whole mouse brains and developed a collaborative workflow for highly accurate neuronal reconstruction.
Bai L, Liang J, Du H, et al., 2019, An Information-Theoretical Framework for Cluster Ensemble, IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, Vol: 31, Pages: 1464-1477, ISSN: 1041-4347
Zhang J, Lertvittayakumjorn P, Guo Y, 2019, Integrating semantic knowledge to tackle zero-shot text classification, 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Insufficient or even unavailable training data of emerging classes is a bigchallenge of many classification tasks, including text classification.Recognising text documents of classes that have never been seen in the learningstage, so-called zero-shot text classification, is therefore difficult and onlylimited previous works tackled this problem. In this paper, we propose atwo-phase framework together with data augmentation and feature augmentation tosolve this problem. Four kinds of semantic knowledge (word embeddings, classdescriptions, class hierarchy, and a general knowledge graph) are incorporatedinto the proposed framework to deal with instances of unseen classeseffectively. Experimental results show that each and the combination of the twophases achieve the best overall accuracy compared with baselines and recentapproaches in classifying real-world texts under the zero-shot scenario.
Pavlidis S, Monast C, Loza MJ, et al., 2019, I_MDS: an inflammatory bowel disease molecular activity score to classify patients with differing disease-driving pathways and therapeutic response to anti-TNF treatment, PLoS Computational Biology, Vol: 15, ISSN: 1553-734X
Crohn's disease and ulcerative colitis are driven by both common and distinct underlying mechanisms of pathobiology. Both diseases, exhibit heterogeneity underscored by the variable clinical responses to therapeutic interventions. We aimed to identify disease-driving pathways and classify individuals into subpopulations that differ in their pathobiology and response to treatment. We applied hierarchical clustering of enrichment scores derived from gene set variation analysis of signatures representative of various immunological processes and activated cell types, to a colonic biopsy dataset that included healthy volunteers, Crohn's disease and ulcerative colitis patients. Patient stratification at baseline or after anti-TNF treatment in clinical responders and non-responders was queried. Signatures with significantly different enrichment scores were identified using a general linear model. Comparisons to healthy controls were made at baseline in all participants and then separately in responders and non-responders. Fifty-nine percent of the signatures were commonly enriched in both conditions at baseline, supporting the notion of a disease continuum within ulcerative colitis and Crohn's disease. Signatures included T cells, macrophages, neutrophil activation and poly:IC signatures, representing acute inflammation and a complex mix of potential disease-driving biology. Collectively, identification of significantly enriched signatures allowed establishment of an inflammatory bowel disease molecular activity score which uses biopsy transcriptomics as a surrogate marker to accurately track disease severity. This score separated diseased from healthy samples, enabled discrimination of clinical responders and non-responders at baseline with 100% specificity and 78.8% sensitivity, and was validated in an independent data set that showed comparable classification. Comparing responders and non-responders separately at baseline to controls, 43% and 70% of signatures were enri
Arcucci R, McIlwraith D, Guo YK, 2019, Scalable Weak Constraint Gaussian Processes, Pages: 111-125, ISSN: 0302-9743
© 2019, Springer Nature Switzerland AG. A Weak Constraint Gaussian Process (WCGP) model is presented to integrate noisy inputs into the classical Gaussian Process predictive distribution. This follows a Data Assimilation approach i.e. by considering information provided by observed values of a noisy input in a time window. Due to the increased number of states processed from real applications and the time complexity of GP algorithms, the problem mandates a solution in a high performance computing environment. In this paper, parallelism is explored by defining the parallel WCGP model based on domain decomposition. Both a mathematical formulation of the model and a parallel algorithm are provided. We prove that the parallel implementation preserves the accuracy of the sequential one. The algorithm’s scalability is further proved to be where p is the number of processors.
Liao B, Zhang J, Wu C, et al., 2018, Deep sequence learning with auxiliary information for traffic prediction, Publisher: arXiv
Predicting traffic conditions from online route queries is a challenging task as there are many complicated interactions over the roads and crowds involved. In this paper, we intend to improve traffic prediction by appropriate integration of three kinds of implicit but essential factors encoded in auxiliary information. We do this within an encoder-decoder sequence learning framework that integrates the following data: 1) offline geographical and social attributes. For example, the geographical structure of roads or public social events such as national celebrations; 2) road intersection information. In general, traffic congestion occurs at major junctions; 3) online crowd queries. For example, when many online queries issued for the same destination due to a public performance, the traffic around the destination will potentially become heavier at this location after a while. Qualitative and quantitative experiments on a real-world dataset from Baidu have demonstrated the effectiveness of our framework.
Yang G, Yu S, Hao D, et al., 2018, DAGAN: deep de-aliasing generative adversarial networks for fast compressed sensing MRI reconstruction, IEEE Transactions on Medical Imaging, Vol: 37, Pages: 1310-1321, ISSN: 0278-0062
Compressed Sensing Magnetic Resonance Imaging (CS-MRI) enables fast acquisition, which is highly desirable for numerous clinical applications. This can not only reduce the scanning cost and ease patient burden, but also potentially reduce motion artefacts and the effect of contrast washout, thus yielding better image quality. Different from parallel imaging based fast MRI, which utilises multiple coils to simultaneously receive MR signals, CS-MRI breaks the Nyquist-Shannon sampling barrier to reconstruct MRI images with much less required raw data. This paper provides a deep learning based strategy for reconstruction of CS-MRI, and bridges a substantial gap between conventional non-learning methods working only on data from a single image, and prior knowledge from large training datasets. In particular, a novel conditional Generative Adversarial Networks-based model (DAGAN) is proposed to reconstruct CS-MRI. In our DAGAN architecture, we have designed a refinement learning method to stabilise our U-Net based generator, which provides an endto-end network to reduce aliasing artefacts. To better preserve texture and edges in the reconstruction, we have coupled the adversarial loss with an innovative content loss. In addition, we incorporate frequency domain information to enforce similarity in both the image and frequency domains. We have performed comprehensive comparison studies with both conventional CSMRI reconstruction methods and newly investigated deep learning approaches. Compared to these methods, our DAGAN method provides superior reconstruction with preserved perceptual image details. Furthermore, each image is reconstructed in about 5 ms, which is suitable for real-time processing.
Takahashi K, Pavlidis S, Ng Kee Kwong F, et al., 2018, Sputum proteomics and airway cell transcripts of current and ex-smokers with severe asthma in U-BIOPRED: an exploratory analysis, European Respiratory Journal, Vol: 51, ISSN: 0903-1936
Background: Severe asthma patients with a significant smoking history have airflow obstruction with reported neutrophilia. We hypothesise that multi1omic analysis will enable the definition of smoking and ex1smoking severe asthma molecular phenotypes.Methods The U1BIOPRED severe asthma patients containing current1smokers (CSA), ex1smokers (ESA), non1smokers (NSA) and healthy non1smokers (NH) was examined. Blood and sputum cell counts, fractional exhaled nitric oxide and spirometry were obtained. Exploratory proteomic analysis of sputum supernatants and transcriptomic analysis of bronchial brushings, biopsies and sputum cells was performed. Results Colony stimulating factor (CSF)2 protein levels were increased in CSA sputum supernatants with azurocidin 1, neutrophil elastase and CXCL8 upregulated in ESA. Phagocytosis and innate immune pathways were associated with neutrophilic inflammation in ESA. Gene Set Variation Analysis of bronchial epithelial cell transcriptome from CSA showed enrichment of xenobiotic metabolism, oxidative stress and endoplasmic reticulum stress compared to other groups. CXCL5 and matrix metallopeptidase 12 genes were upregulated in ESA and the epithelial protective genes, mucin 2 and cystatin SN, were downregulated. Conclusion Despite little difference in clinical characteristics, CSA were distinguishable from ESA subjects at the sputum proteomic level with CSA having increased CSF2 expression and ESA patients showed sustained loss of epithelial barrier processes.
Dong H, Wu C, Wei Z, et al., 2018, Dropping Activation Outputs With Localized First-Layer Deep Network for Enhancing User Privacy and Data Security, IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, Vol: 13, Pages: 662-670, ISSN: 1556-6013
Bai L, Liang J, Du H, et al., 2018, A novel community detection algorithm based on simplification of complex networks, KNOWLEDGE-BASED SYSTEMS, Vol: 143, Pages: 58-64, ISSN: 0950-7051
Kuo C-HS, Liu C-Y, Pavlidis S, et al., 2018, Unique immune gene expression Patterns in Bronchoalveolar lavage and Tumor adjacent non-neoplastic lung Tissue in non-small cell lung cancer, FRONTIERS IN IMMUNOLOGY, Vol: 9, ISSN: 1664-3224
Li K, Liu F, Dong H, et al., 2018, A DEEP LEARNING PLATFORM FOR DIABETES BIG DATA ANALYSIS, Publisher: MARY ANN LIEBERT, INC, Pages: A116-A116, ISSN: 1520-9156
Yang X, Pan W, Guo Y, 2017, Sparse Bayesian classification and feature selection for biological expression data with high correlations, PLOS ONE, Vol: 12, ISSN: 1932-6203
Oehmichen A, Guitton F, Sun K, et al., 2017, eTRIKS analytical environment: A modular high performance framework for medical data analysis, 2017 IEEE International Conference on Big Data (BIGDATA), Pages: 353-360
Supratak A, Dong H, Wu C, et al., 2017, DeepSleepNet: A Model for Automatic Sleep Stage Scoring Based on Raw Single-Channel EEG, IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, Vol: 25, Pages: 1998-2008, ISSN: 1534-4320
Bai L, Cheng X, Liang J, et al., 2017, Fast density clustering strategies based on the k-means algorithm, PATTERN RECOGNITION, Vol: 71, Pages: 375-386, ISSN: 0031-3203
NCD Risk Factor Collaboration NCD-RisC, Bentham J, NCD Risk Factor Collaboration NCD-RisC, 2017, Worldwide trends in body-mass index, underweight, overweight, and obesity from 1975 to 2016: a pooled analysis of 2416 population-based measurement studies in 128·9 million children, adolescents, and adults., Lancet, Vol: 390, Pages: 2627-2642, ISSN: 0140-6736
BACKGROUND: Underweight, overweight, and obesity in childhood and adolescence are associated with adverse health consequences throughout the life-course. Our aim was to estimate worldwide trends in mean body-mass index (BMI) and a comprehensive set of BMI categories that cover underweight to obesity in children and adolescents, and to compare trends with those of adults. METHODS: We pooled 2416 population-based studies with measurements of height and weight on 128·9 million participants aged 5 years and older, including 31·5 million aged 5-19 years. We used a Bayesian hierarchical model to estimate trends from 1975 to 2016 in 200 countries for mean BMI and for prevalence of BMI in the following categories for children and adolescents aged 5-19 years: more than 2 SD below the median of the WHO growth reference for children and adolescents (referred to as moderate and severe underweight hereafter), 2 SD to more than 1 SD below the median (mild underweight), 1 SD below the median to 1 SD above the median (healthy weight), more than 1 SD to 2 SD above the median (overweight but not obese), and more than 2 SD above the median (obesity). FINDINGS: Regional change in age-standardised mean BMI in girls from 1975 to 2016 ranged from virtually no change (-0·01 kg/m(2) per decade; 95% credible interval -0·42 to 0·39, posterior probability [PP] of the observed decrease being a true decrease=0·5098) in eastern Europe to an increase of 1·00 kg/m(2) per decade (0·69-1·35, PP>0·9999) in central Latin America and an increase of 0·95 kg/m(2) per decade (0·64-1·25, PP>0·9999) in Polynesia and Micronesia. The range for boys was from a non-significant increase of 0·09 kg/m(2) per decade (-0·33 to 0·49, PP=0·6926) in eastern Europe to an increase of 0·77 kg/m(2) per decade (0·50-1·06, PP>0·9999) in Polynesia and Micronesia. Tre
Wang Z, Xiao D, Fang F, et al., 2017, Model identification of reduced order fluid dynamics systems using deep learning, International Journal for Numerical Methods in Fluids, Vol: 86, Pages: 255-268, ISSN: 0271-2091
This paper presents a novel model reduction method: deep learning reduced order model, which is based on proper orthogonal decomposition and deep learning methods. The deep learning approach is a recent technological advancement in the field of artificial neural networks. It has the advantage of learning the nonlinear system with multiple levels of representation and predicting data. In this work, the training data are obtained from high fidelity model solutions at selected time levels. The long short-term memory network is used to construct a set of hypersurfaces representing the reduced fluid dynamic system. The model reduction method developed here is independent of the source code of the full physical system.The reduced order model based on deep learning has been implemented within an unstructured mesh finite element fluid model. The performance of the new reduced order model is evaluated using 2 numerical examples: an ocean gyre and flow past a cylinder. These results illustrate that the CPU cost is reduced by several orders of magnitude whilst providing reasonable accuracy in predictive numerical modelling.
Dong H, Supratak A, Pan W, et al., 2017, Mixed neural network approach for temporal sleep stage classification, IEEE Transactions on Neural Systems and Rehabilitation Engineering, Vol: 26, Pages: 324-333, ISSN: 1534-4320
This paper proposes a practical approach to addressing limitations posed by using of single-channel electroencephalography (EEG) for sleep stage classification. EEG-based characterizations of sleep stage progression contribute the diagnosis and monitoring of the many pathologies of sleep. Several prior reports explored ways of automating the analysis of sleep EEG and of reducing the complexity of the data needed for reliable discrimination of sleep stages at lower cost in the home. However, these reports have involved recordings from electrodes placed on the cranial vertex or occiput, which are both uncomfortable and difficult to position. Previous studies of sleep stage scoring that used only frontal electrodes with a hierarchical decision tree motivated this paper, in which we have taken advantage of rectifier neural network for detecting hierarchical features and long short-term memory (LSTM) network for sequential data learning to optimize classification performance with single-channel recordings. After exploring alternative electrode placements, we found a comfortable configuration of a single-channel EEG on the forehead and have shown that it can be integrated with additional electrodes for simultaneous recording of the electrooculogram (EOG). Evaluation of data from 62 people (with 494 hours sleep) demonstrated better performance of our analytical algorithm than is available from existing approaches with vertex or occipital electrode placements. Use of this recording configuration with neural network deconvolution promises to make clinically indicated home sleep studies practical.
Hekking PP, Loza MJ, Pavlidis S, et al., 2017, Pathway discovery using transcriptomic profiles in adult-onset severe asthma, Journal of Allergy and Clinical Immunology, Vol: 141, Pages: 1280-1290, ISSN: 1097-6825
RationaleAdult-onset severe asthma is characterized by highly symptomatic disease despite high intensity asthma treatments. Understanding of the underlying pathways of this heterogeneous disease needed for the development of targeted treatments. Gene Set Variation Analysis (GSVA) is a statistical technique to identify gene profiles in heterogeneous samples.ObjectiveTo identify gene profiles associated with adult-onset severe asthma.MethodsThis was a cross-sectional, observational study in which adult patients with adult-onset of asthma (defined as starting at ≥18yrs old) as compared to childhood-onset severe asthma (<18 yrs) were selected from the U-BIOPRED cohort. Gene expression was assessed on the total RNA of induced sputum (n=83), nasal brushings (n=41), and endobronchial brushings (n=65) and biopsies (n=47) (Affymetrix HT HG-U133+ PM). GSVA was used to identify differentially enriched pre-defined gene signatures of leukocyte lineage, inflammatory and induced lung injury pathways.ResultsSignificant differentially enriched gene signatures in patients with adult-onset as compared to childhood-onset severe asthma were identified in nasal brushings (5 signatures), sputum (3 signatures) and endobronchial brushings (6 signatures). Signatures associated with eosinophilic airway inflammation, mast cells and group 3 innate lymphoid cells (ILC3) were more enriched in adult-onset severe asthma, whereas signatures associated with induced lung injury were less enriched in adult-onset severe asthma.ConclusionsAdult-onset severe asthma is characterized by inflammatory pathways involving eosinophils, mast cells and ILC3s. These pathways could represent useful targets for the treatment of adult-onset severe asthma.
Nie L, Yang X, Matthews PM, et al., 2017, Inferring functional connectivity in fMRI using minimum partial correlation, International Journal of Automation and Computing, Vol: 14, Pages: 371-385, ISSN: 1751-8520
Functional connectivity has emerged as a promising approach to study the functional organisation of the brain and to define features for prediction of brain state. The most widely used method for inferring functional connectivity is Pearson-s correlation, but it cannot differentiate direct and indirect effects. This disadvantage is often avoided by computing the partial correlation between two regions controlling all other regions, but this method suffers from Berkson-s paradox. Some advanced methods, such as regularised inverse covariance, have been applied. However, these methods usually depend on some parameters. Here we propose use of minimum partial correlation as a parameter-free measure for the skeleton of functional connectivity in functional magnetic resonance imaging (fMRI). The minimum partial correlation between two regions is the minimum of absolute values of partial correlations by controlling all possible subsets of other regions. Theoretically, there is a direct effect between two regions if and only if their minimum partial correlation is non-zero under faithfulness and Gaussian assumptions. The elastic PC-algorithm is designed to efficiently approximate minimum partial correlation within a computational time budget. The simulation study shows that the proposed method outperforms o thers in most cases and its application is illustrated using a resting-state fMRI dataset from the human connectome project.
Pavlidis S, Guo Y, Sun K, et al., 2017, Comparison between bronchial and nasal brushings gene expression in the u-biopred cohort, International Conference of the American-Thoracic-Society (ATS), Publisher: American Thoracic Society, ISSN: 1073-449X
Rossios C, Pavlidis S, Hoda U, et al., 2017, Sputum transcriptomics reveal upregulation of IL-1 receptor family members in patients with severe asthma, Journal of Allergy and Clinical Immunology, Vol: 141, Pages: 560-570, ISSN: 1097-6825
BACKGROUND: Sputum analysis in asthmatic patients is used to define airway inflammatory processes and might guide therapy. OBJECTIVE: We sought to determine differential gene and protein expression in sputum samples from patients with severe asthma (SA) compared with nonsmoking patients with mild/moderate asthma. METHODS: Induced sputum was obtained from nonsmoking patients with SA, smokers/ex-smokers with severe asthma, nonsmoking patients with mild/moderate asthma (MMAs), and healthy nonsmoking control subjects. Differential cell counts, microarray analysis of cell pellets, and SOMAscan analysis of sputum analytes were performed. CRID3 was used to inhibit the inflammasome in a mouse model of SA. RESULTS: Eosinophilic and mixed neutrophilic/eosinophilic inflammation were more prevalent in patients with SA compared with MMAs. Forty-two genes probes were upregulated (>2-fold) in nonsmoking patients with severe asthma compared with MMAs, including IL-1 receptor (IL-1R) family and nucleotide-binding oligomerization domain, leucine-rich repeat and pyrin domain containing 3 (NRLP3) inflammasome members (false discovery rate < 0.05). The inflammasome proteins nucleotide-binding oligomerization domain, leucine rich repeat and pyrin domain containing 1 (NLRP1), NLRP3, and nucleotide-binding oligomerization domain (NOD)-like receptor C4 (NLRC4) were associated with neutrophilic asthma and with sputum IL-1β protein levels, whereas eosinophilic asthma was associated with an IL-13-induced TH2 signature and IL-1 receptor-like 1 (IL1RL1) mRNA expression. These differences were sputum specific because no activation of NLRP3 or enrichment of IL-1R family genes in bronchial brushings or biopsy specimens in patients with SA was observed. Expression of NLRP3 and of the IL-1R family genes was validated in the Airway Disease Endotyping for Personalized Therapeutics cohort. Inflammasome inhibition using CRID3 prevented airway hyperresponsiveness and airway inflammati
Bai L, Cheng X, Liang J, et al., 2017, Fast graph clustering with a new description model for community detection, INFORMATION SCIENCES, Vol: 388, Pages: 37-47, ISSN: 0020-0255
Kuo C-HS, Pavlidis S, Loza M, et al., 2017, T-helper cell type 2 (Th2) and non-Th2 molecular phenotypes of asthma using sputum transcriptomics in U-BIOPRED, European Respiratory Journal, Vol: 49, ISSN: 0903-1936
Asthma is characterised by heterogeneous clinical phenotypes. Our objective was to determine molecular phenotypes of asthma by analysing sputum cell transcriptomics from 104 moderate-to-severe asthmatic subjects and 16 nonasthmatic subjects.After filtering on the differentially expressed genes between eosinophil- and noneosinophil-associated sputum inflammation, we used unbiased hierarchical clustering on 508 differentially expressed genes and gene set variation analysis of specific gene sets.We defined three transcriptome-associated clusters (TACs): TAC1 (characterised by immune receptors IL33R, CCR3 and TSLPR), TAC2 (characterised by interferon-, tumour necrosis factor-α- and inflammasome-associated genes) and TAC3 (characterised by genes of metabolic pathways, ubiquitination and mitochondrial function). TAC1 showed the highest enrichment of gene signatures for interleukin-13/T-helper cell type 2 (Th2) and innate lymphoid cell type 2. TAC1 had the highest sputum eosinophilia and exhaled nitric oxide fraction, and was restricted to severe asthma with oral corticosteroid dependency, frequent exacerbations and severe airflow obstruction. TAC2 showed the highest sputum neutrophilia, serum C-reactive protein levels and prevalence of eczema. TAC3 had normal to moderately high sputum eosinophils and better preserved forced expiratory volume in 1 s. Gene–protein coexpression networks from TAC1 and TAC2 extended this molecular classification.We defined one Th2-high eosinophilic phenotype TAC1, and two non-Th2 phenotypes TAC2 and TAC3, characterised by inflammasome-associated and metabolic/mitochondrial pathways, respectively.
Molina-Solana MJ, Guo Y, Birch D, 2017, Improving data exploration in graphs with fuzzy logic and large-scale visualisation, Applied Soft Computing, Vol: 53, Pages: 227-235, ISSN: 1872-9681
This work presents three case-studies of how fuzzy logic can be combined with large-scale immersive visualisation to enhance the process of graph sensemaking, enabling interactive fuzzy filtering of large global views of graphs. The aim is to provide users a mechanism to quickly identify interesting nodes for further analysis. Fuzzy logic allows a flexible framework to ask human-like curiosity-driven questions over the data, and visualisation allows its communication and understanding. Together, these two technologies successfully empower novices and experts to a faster and deeper understanding of the underlying patterns in big datasets compared to traditional means in a desktop screen with crisp queries. Among other examples, we provide evidence of how these two technologies successfully enable the identification of relevant transaction patterns in the Bitcoin network.
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.