Heterogeneous Data Resources Research Articles

Predicting protein and pathway associations for understudied dark kinases using pattern-constrained knowledge graph embedding.

The 534 protein kinases encoded in the human genome constitute a large druggable class of proteins that include both well-studied and understudied "dark" members. Accurate prediction of dark kinase functions is a major bioinformatics challenge. Here, we employ a graph mining approach that uses the evolutionary and functional context encoded in knowledge graphs (KGs) to predict protein and pathway associations for understudied kinases. We propose a new scalable graph embedding approach, RegPattern2Vec, which employs regular pattern constrained random walks to sample diverse aspects of node context within a KG flexibly. RegPattern2Vec learns functional representations of kinases, interacting partners, post-translational modifications, pathways, cellular localization, and chemical interactions from a kinase-centric KG that integrates and conceptualizes data from curated heterogeneous data resources. By contextualizing information relevant to prediction, RegPattern2Vec improves accuracy and efficiency in comparison to other random walk-based graph embedding approaches. We show that the predictions produced by our model overlap with pathway enrichment data produced using experimentally validated Protein-Protein Interaction (PPI) data from both publicly available databases and experimental datasets not used in training. Our model also has the advantage of using the collected random walks as biological context to interpret the predicted protein-pathway associations. We provide high-confidence pathway predictions for 34 dark kinases and present three case studies in which analysis of meta-paths associated with the prediction enables biological interpretation. Overall, RegPattern2Vec efficiently samples multiple node types for link prediction on biological knowledge graphs and the predicted associations between understudied kinases, pseudokinases, and known pathways serve as a conceptual starting point for hypothesis generation and testing.

Construction and application of Chinese breast cancer knowledge graph based on multi-source heterogeneous data.

The knowledge graph is a critical resource for medical intelligence. The general medical knowledge graph tries to include all diseases and contains much medical knowledge. However, it is challenging to review all the triples manually. Therefore the quality of the knowledge graph can not support intelligence medical applications. Breast cancer is one of the highest incidences of cancer at present. It is urgent to improve the efficiency of breast cancer diagnosis and treatment through artificial intelligence technology and improve the postoperative health status of breast cancer patients. This paper proposes a framework to construct a breast cancer knowledge graph from heterogeneous data resources in response to this demand. Specifically, this paper extracts knowledge triple from clinical guidelines, medical encyclopedias and electronic medical records. Furthermore, the triples from different data resources are fused to build a breast cancer knowledge graph (BCKG). Experimental results demonstrate that BCKG can support knowledge-based question answering, breast cancer postoperative follow-up and healthcare, and improve the quality and efficiency of breast cancer diagnosis, treatment and management.

Design of an English Web-based Teaching Resource Sharing Platform based on Mobile Web Technology

Thanks to the booming technology of computers and multimedia, student-centered online teaching resource platforms have become an important way for students to learn. However, English teaching resource platforms at the present stage fail to effectively integrate the massive and scattered learning resources. Based on this, the study proposes an English online teaching resource sharing platform based on mobile Web technology, using the SOAP protocol to deploy heterogeneous data resources as Web services to achieve interchangeability between heterogeneous resources. In addition, to enhance the efficient use of learning resources by students, the study proposes a hybrid algorithm based on collaborative filtering algorithm and sequential pattern mining algorithm to achieve personalized sequential recommendation for students. The results show that the platform created by the study exhibits excellent performance in terms of resource transfer capability, achieves efficient teaching resource sharing in a short response time and also shows that the proposed recommendation algorithm is highly accurate.

RIDAB: Electronic medical record-integrated real world data platform for predicting and summarizing interactions in biomedical research from heterogeneous data resources

Background and objective: With the advent of bioinformatics, biological databases have been constructed to computerize data. Biological systems can be described as interactions and relationships between elements constituting the systems, and they are organized in various biomedical open databases. These open databases have been used in approaches to predict functional interactions such as protein-protein interactions (PPI), drug-drug interactions (DDI) and disease-disease relationships (DDR). However, just combining interaction data has limited effectiveness in predicting the complex relationships occurring in a whole context. Each contributing source contains information on each element in a specific field of knowledge but there is a lack of inter-disciplinary insight in combining them.Methods: In this study, we propose the RWD Integrated platform for Discovering Associations in Biomedical research (RIDAB) to predict interactions between biomedical entities. RIDAB is established as a graph network to construct a platform that predicts the interactions of target entities. Biomedical open database is combined with EMRs each representing a biomedical network and a real-world data. To integrate databases from different domains to build the platform, mapping of the vocabularies was required. In addition, the appropriate structure of the network and the graph embedding method to be used were needed to be selected to fit the tasks.Results: The feasibility of the platform was evaluated using node similarity and link prediction for drug repositioning task, a commonly used task for biomedical network. In addition, we compared the US Food and Drug Administration (FDA)-approved repositioned drugs with the predicted result. By integrating EMR database with biomedical networks, the platform showed increased f1 score in predicting repositioned drugs, from 45.62% to 57.26%, compared to platforms based on biomedical networks alone.Conclusions: This study demonstrates that the elements of biomedical research findings can be reflected by integrating EMR data with open-source biomedical networks. In addition, showed the feasibility of using the established platform to represent the integration of biomedical networks and reflected the relationship between real world networks.

High-quality gene/disease embedding in a multi-relational heterogeneous graph after a joint matrix/tensor decomposition

MotivationNode embedding of biological entity network has been widely investigated for the downstream application scenarios. To embed full semantics of gene and disease, a multi-relational heterogeneous graph is considered in a scenario where uni-relation between gene/disease and other heterogeneous entities are abundant while multi-relation between gene and disease is relatively sparse. After introducing this novel graph format, it is illuminative to design a specific data integration algorithm to fully capture the graph information and bring embeddings with high quality. ResultsFirst, a typical multi-relational triple dataset was introduced, which carried significant association between gene and disease. Second, we curated all human genes and diseases in seven mainstream datasets and constructed a large-scale gene-disease network, which compromising 163,024 nodes and 25,265,607 edges, and relates to 27,165 genes, 2,665 diseases, 15,067 chemicals, 108,023 mutations, 2,363 pathways, and 7.732 phenotypes. Third, we proposed a Joint Decomposition of Heterogeneous Matrix and Tensor (JDHMT) model, which integrated all heterogeneous data resources and obtained embedding for each gene or disease. Forth, a visualized intrinsic evaluation was performed, which investigated the embeddings in terms of interpretable data clustering. Furthermore, an extrinsic evaluation was performed in the form of linking prediction. Both intrinsic and extrinsic evaluation results showed that JDHMT model outperformed other eleven state-of-the-art (SOTA) methods which are under relation-learning, proximity-preserving or message-passing paradigms. Finally, the constructed gene-disease network, embedding results and codes were made available. Data and Codes AvailabilityThe constructed massive gene-disease network is available at: https://hzaubionlp.com/heterogeneous-biological-network/. The codes are available at: https://github.com/bionlp-hzau/JDHMT.

Boosting Climate Analysis With Semantically Uplifted Knowledge Graphs

Nowadays, the fast expansion of heterogeneous climate data resources accessible on the Internet has led to substantial data fragmentation on the web. For example, station-based sensor data from different sources are likely to be interrelated but may be stored in disparate formats, such as <monospace>CSV</monospace>, <monospace>JSON</monospace>, and <monospace>XML</monospace>. To address the data isolation problem, several semantically uplifted knowledge graphs are proposed for climate data exchange. While these knowledge graphs improve data interoperability, the advancement in multisource data interchange is limited to data included inside knowledge graphs. As a result, the exclusive interoperability of current climatic knowledge graphs hampers the flow of data into typical climate analysis workflows in contexts, where analytical models often need data in nonknowledge graph formats. This article addresses this issue by focusing on enhancing climate analysis workflows within the context of the Python machine learning environment, with a preference for tabular data. We propose an analysis workflow able to automatically integrate remote climate knowledge graph data with local tabular data so as to enhance the data usability with respect to certain climate analysis tasks. To underscore the importance of our study, we illustrate how the workflow streamlines the access to multisource climatic variables in the Python environment from a semantic perspective. The additional knowledge graph data have the potential to augment local datasets in the climate domain, as evidenced by an improvement in accuracy of up to 10&#x0025; for machine learning geared on rainfall detection.

HKGB: An Inclusive, Extensible, Intelligent, Semi-auto-constructed Knowledge Graph Framework for Healthcare with Clinicians’ Expertise Incorporated

Health knowledge graph provides an ideal technical means to integrate heterogeneous data resources and enhance knowledge-based services. There are many challenges for the construction of health knowledge graph such as complex concepts and relationships, various medical standards, heterogeneous data structures, poor data quality, highly accurate and interpretable services, etc.In this paper, firstly, we propose Health Knowledge Graph Builder (HKGB), an end-to-end platform which could be used to construct disease-specific and extensible health knowledge graphs from multiple sources. Secondly, we analyze the capabilities and requirements of clinicians, design the tasks to involve the clinicians and implement a clinician-in-the-loop toolset to integrate the clinicians prior knowledge into the construction of health knowledge graphs. Thirdly, we design an extensible mechanism to add new diseases to an existing knowledge graph. Fourthly, we present a quantitative effort estimation algorithm to quantitatively evaluate the effort of clinicians during the construction, and use it to calculate the workloads such as 44.27 person days for knee osteoarthritis domain. Finally, we have developed several knowledge graph based tools to facilitate real applications.

Research on Construction Technology of Multi Heterogeneous Data Resource Graph of Power Grid Corporation

The development of new-generation artificial intelligence technologies such as deep learning, knowledge graphing, and enhanced learning is driving the “Internet + Smart Energy” into a new era of “Internet of Energy.” The data structure, type, and format of the data between the main body of the energy and power system, various departments of the enterprise, and various types of users are all constructed at different times using different standards. The data is huge and complex. Establishing a company-level data center for power grid companies to resolve the standardized management and fast and reliable exchange of heterogeneous data under massive data is an opportunity and a challenge for the company to build an energy Internet. As the core foundation of integrating heterogeneous data resources of power grid, data resource graph can provide effective support for the management of heterogeneous data of power grid enterprises under the energy Internet. From the multi-dimensional perspective of data modeling, resource management, data navigation, learning cognition, database, this paper focuses on the diversified and heterogeneous data resources of power grid companies, and explores from the specific technical aspects of data ontology modeling, data naming and identification, data relationship mining, data fusion and exchange technology, aiming to provide technical support and reference for power grid companies to build data resource graph.

Knowledge Service Model of Port Supply Chain Enterprise Based on Ontology

Under the background of the development of port industry and information age, with the help of the knowledge service theory system and ontology technology to build a smart port supply chain knowledge service model to provide a personalized, intelligent, and diversified knowledge-based service system platform solution to port supply chain enterprises, which is of great significance to realization of port supply chain transformation and upgrading and intelligent integrated operation. Based on the analysis of the demand for knowledge service and the research status of knowledge service in port supply chain during the development and operation of port supply chain, this paper uses ontology technology to build domain ontology knowledge base, which is used to dismantle and integrate the massive digital resources in port supply chain, integrate various multi-source heterogeneous data resources, and standardize the form of knowledge sharing organization. On the basis of this, the paper carries on the calculation and reasoning experiment to the port supply chain ontology. The experiment shows that the ontology technology has good effectiveness and superiority in the knowledge representation and knowledge reasoning of constructing the port supply chain knowledge service system model.

Multimodal Analytics to Understand Self-Regulation Process of Cognitive and Behavioral Strategies in Real-World Learning

Recent studies suggest that learning “how to learn” is important because learners must be self-regulated to take more responsibility for their own learning processes, meta-cognitive control, and other generative learning thoughts and behaviors. The mechanism that enables a learner to self-regulate his/her learning strategies has been actively studied in classroom settings, but has seldom been studied in the area of real-world learning in out-of-school settings (e.g., environmental learning in nature). A feature of real-world learning is that a learner's cognition of the world is updated by his/her behavior to investigate the world, and vice versa. This paper models the mechanism of real-world learning for executing and self-regulating a learner's cognitive and behavioral strategies to self-organize his/her internal knowledge space. Furthermore, this paper proposes multimodal analytics to integrate heterogeneous data resources of the cognitive and behavioral features of real-world learning, to structure and archive the time series of strategies occurring through learner-environment interactions, and to assess how learning should be self-regulated for better understanding of the world. Our analysis showed that (1) intellectual achievements are built by self-regulating learning to chain the execution of cognitive and behavioral strategies, and (2) a clue to predict learning outcomes in the world is analyzing the quantity and frequency of strategies that a learner uses and self-regulates. Assessment based on these findings can encourage a learner to reflect and improve his/her way of learning in the world.

A Novel HDF‐Based Data Compression and Integration Approach to Support BIM‐GIS Practical Applications

Constructing a fully mapped virtual world is the premise of establishing the digital twin system; thus, the integration of BIM (Building Information Modeling) and GIS (Geographic Information System) constitutes a fundamental part of the mature digital twin. Although quite a few theoretical unified data models of BIM and GIS integration have been presented in precedent research, the practical web‐based applications and software support for real‐world city information modeling are still difficult to achieve. One of the challenges is storage inefficiency. It thence leads to burdens in exchange and analysis, which hugely impede the realization of virtual‐real fusion. To address that issue, in this research, we contribute to exploring an HDF‐ (Hierarchical Data Format‐) based, innovative, and synthesized scheme with three significant technical processes. First, data reorganization trims the original data with efficient redundancy elimination and reordering for IFC‐SPF (IFC STEP Physical File) and XML‐encoded CityGML (City Geography Markup Language). Next, bidirectional transformation methods for BIM and GIS modeling data, images, and analytical data into HDF are proposed. They retain the entities and relationships in modeling data and can further improve the compactness and accessibility by ultimately 60%–80% which saves 497,612 KB from 565,152 KB in the test of ZhongChun transformation substation. Finally, data aggregation enhances the bond of the integrated model and heterogeneous data resources from the transformed HDF files. The case studies show that the approach proposed in this paper could reach high efficiency for practicability of the BIM + GIS integration model. This light‐weight integration method can further improve the front‐end service responsiveness in digital twin applications.

Research on Cluster Analysis Method of Heterogeneous Data Resources Based on FCM

Research on Cluster Analysis Method of Heterogeneous Data Resources Based on FCM

Virtual Research Environment Integrating Heterogeneous Data Resources for Materials Science and Engineering

Virtual Research Environment Integrating Heterogeneous Data Resources for Materials Science and Engineering

FACTORBASE: multi-relational structure learning with SQL all the way

FactorBase is a new SQL-based framework that leverages a relational database management system to support multi-relational model discovery. A multi-relational statistical model provides an integrated analysis of the heterogeneous and interdependent data resources in the database. We adopt the BayesStore design philosophy: Statistical models are stored and managed as first-class citizens inside a database (Wang et al., in: PVLDB, pp 340–351, 2008). Whereas previous systems like BayesStore support multi-relational inference, FactorBase supports multi-relational learning. A case study on six benchmark databases evaluates how our system supports a challenging machine learning application, namely learning a first-order Bayesian network model for an entire database. Model learning in this setting has to examine a large number of potential statistical associations across data tables. Our implementation shows how the SQL constructs in FactorBase facilitate the fast, modular, and reliable development of scalable model learning systems.

Generative Adversarial Networks Based Heterogeneous Data Integration and Its Application for Intelligent Power Distribution and Utilization

Heterogeneous characteristics of a big data system for intelligent power distribution and utilization have already become more and more prominent, which brings new challenges for the traditional data analysis technologies and restricts the comprehensive management of distribution network assets. In order to solve the problem that heterogeneous data resources of power distribution systems are difficult to be effectively utilized, a novel generative adversarial networks (GANs) based heterogeneous data integration method for intelligent power distribution and utilization is proposed. In the proposed method, GANs theory is introduced to expand the distribution of completed data samples. Then, a so-called peak clustering algorithm is proposed to realize the finite open coverage of the expanded sample space, and repair those incomplete samples to eliminate the heterogeneous characteristics. Finally, in order to realize the integration of the heterogeneous data for intelligent power distribution and utilization, the well-trained discriminator model of GANs is employed to check the restored data samples. The simulation experiments verified the validity and stability of the proposed heterogeneous data integration method, which provides a novel perspective for the further data quality management of power distribution systems.

A Spatio-Temporal Enhanced Metadata Model for Interdisciplinary Instant Point Observations in Smart Cities

Due to the incomprehensive and inconsistent description of spatial and temporal information for city data observed by sensors in various fields, it is a great challenge to share the massive, multi-source and heterogeneous interdisciplinary instant point observation data resources. In this paper, a spatio-temporal enhanced metadata model for point observation data sharing was proposed. The proposed Data Meta-Model (DMM) focused on the spatio-temporal characteristics and formulated a ten-tuple information description structure to provide a unified and spatio-temporal enhanced description of the point observation data. To verify the feasibility of the point observation data sharing based on DMM, a prototype system was established, and the performance improvement of Sensor Observation Service (SOS) for the instant access and insertion of point observation data was realized through the proposed MongoSOS, which is a Not Only SQL (NoSQL) SOS based on the MongoDB database and has the capability of distributed storage. For example, the response time of the access and insertion for navigation and positioning data can be realized at the millisecond level. Case studies were conducted, including the gas concentrations monitoring for the gas leak emergency response and the smart city public vehicle monitoring based on BeiDou Navigation Satellite System (BDS) used for recording the dynamic observation information. The results demonstrated the versatility and extensibility of the DMM, and the spatio-temporal enhanced sharing for interdisciplinary instant point observations in smart cities.

Analysis of Heterogeneous Data Integration and Document Clustering method in Digital Library

This paper proposes a hierarchical organization framework model of heterogeneous data integration and resource utilization of digital library. The model is divided into metadata layer, ontology layer, link data layer and application layer from top to bottom. Aiming at the drawbacks of the traditional document clustering methods, an improved LDA method is proposed to cluster the shared subject documents of the same category. The results show that the retrieval time of the proposed linked data organization framework model of digital library is much smaller than that of the traditional model, and the search response time is reduced by 56.3%. The establishment of the linked data organization framework model of digital library can greatly increase the interconnection of distributed heterogeneous information and make the data source more easily crawled by search engines. TC-LDA algorithm has the highest retrieval accuracy and the best stability. The time consumption of the five algorithms is almost the same, thus it hard to get the algorithm with advantage of time-consuming. The improved LDA text subject clustering algorithm has more advantages than the traditional text clustering method, which is obtained from the analysis of clustering accuracy and time consuming.

Progress in Biomedical Knowledge Discovery: A 25-year Retrospective.

We sought to explore, via a systematic review of the literature, the state of the art of knowledge discovery in biomedical databases as it existed in 1992, and then now, 25 years later, mainly focused on supervised learning. We performed a rigorous systematic search of PubMed and latent Dirichlet allocation to identify themes in the literature and trends in the science of knowledge discovery in and between time periods and compare these trends. We restricted the result set using a bracket of five years previous, such that the 1992 result set was restricted to articles published between 1987 and 1992, and the 2015 set between 2011 and 2015. This was to reflect the current literature available at the time to researchers and others at the target dates of 1992 and 2015. The search term was framed as: Knowledge Discovery OR Data Mining OR Pattern Discovery OR Pattern Recognition, Automated. A total 538 and 18,172 documents were retrieved for 1992 and 2015, respectively. The number and type of data sources increased dramatically over the observation period, primarily due to the advent of electronic clinical systems. The period 1992- 2015 saw the emergence of new areas of research in knowledge discovery, and the refinement and application of machine learning approaches that were nascent or unknown in 1992. Over the 25 years of the observation period, we identified numerous developments that impacted the science of knowledge discovery, including the availability of new forms of data, new machine learning algorithms, and new application domains. Through a bibliometric analysis we examine the striking changes in the availability of highly heterogeneous data resources, the evolution of new algorithmic approaches to knowledge discovery, and we consider from legal, social, and political perspectives possible explanations of the growth of the field. Finally, we reflect on the achievements of the past 25 years to consider what the next 25 years will bring with regard to the availability of even more complex data and to the methods that could be, and are being now developed for the discovery of new knowledge in biomedical data.

Process Materials Scientific Data for Intelligent Service Using a Dataspace Model

Nowadays, materials scientific data come from lab experiments, simulations, individual archives, enterprise and internet in all scales and formats. The data flood has outpaced our capability to process, manage, analyze, and provide intelligent services. Extracting valuable information from the huge data ocean is necessary for improving the quality of domain services. The most acute information management challenges today stem from organizations relying on amounts of diverse, interrelated data sources, but having no way to manage the dataspaces in an integrated, user-demand driven and services convenient way. Thus, we proposed the model of Virtual DataSpace (VDS) in materials science field to organize multi-source and heterogeneous data resources and offer services on the data in place without losing context information. First, the concept and theoretical analysis are described for the model. Then the methods for construction of the model is proposed based on users’ interests. Furthermore, the dynamic evolution algorithm of VDS is analyzed using the user feedback mechanism. Finally, we showed its efficiency for intelligent, real-time, on-demand services in the field of materials engineering.

Deception Detection in Cyber Conflicts

Deception is a strategy that has been widely used in cyber conflicts. How to detect deception in a timely manner is always a challenge, especially for a cyber commander who is at the point of making decisions with respect to the actual target to go after, the exact location of the target, the starting and ending time of a cyber operation, the type of cyber operation, the way of launching the cyber operation, and the amount of resources and support needed. It is absolutely important for a cyber commander to know for sure that he/she is not deceived by an adversary so he/she will be able to make right decisions. Varied solutions do exist. However, they are either too narrow or too broad. The solutions represented by signature technology are narrow in scope, so that they are not capable of dealing with the deception that they have not handled before. The solutions represented by behavioral analysis are relatively broad, so that they require extra time to re-adjust their focuses, incorporate contextual information, and combine heterogeneous data resources in order to get to what is exactly needed. In addition, the use of contexts in analysis is at random and not in a systematic way in most cases. Even when contexts are included in analysis, their relations with the relevant events are not well explored in all these solutions. To address these issues, this paper proposes a new strategic and systematic solution applying the Operational-Level Cybersecurity Strategy Formation Framework. This new solution employs purpose analysis, contextual analysis, and risk analysis. A case study is provided to test the effectiveness of this solution in detecting deception in a timely manner. The benefits and limitations of this solution are discussed. The capabilities of the Operational-Level Cybersecurity Strategy Formation Framework are evidently proved via this use case.