Ontology Graph Research Articles

Применение графов знаний для клинического мониторинга процесса лечения

Patient condition monitoring is essential at every stage of the treatment and diagnostic process. During treatment, the key tasks of monitoring include evaluating the effectiveness of treatment strategies and ensuring safety, specifically by avoiding complications and adverse effects from medications, procedures, or their combinations. To enhance doctor-patient interactions and improve treatment quality, intelligent monitoring tools are needed. These tools must use patient data and formalized knowledge of the subject area to identify which observations, at specific times, can indicate any deviation of the patient's condition from expected outcomes.This study aims to develop an ontology that formalizes the knowledge necessary for selecting and explaining monitoring parameters throughout treatment. Key concept rela-tionships that address the challenges of monitoring patient conditions during treatment are identified, leading to an on-tological graph for a specific class of medical monitoring issues. The study describes a method for building knowledge graphs applicable to various diseases and a reasoning process to identify unexpected conditions. A process of reasoning and the resulting recommendation is presented. This approach establishes a foundation for a decision support system tailored to this class of problems, where monitoring parameters can be adapted according to treatment stage, patient condition, and individual characteristics.

Visual Data and Pattern Analysis for Smart Education: A Robust DRL-Based Early Warning System for Student Performance Prediction

Artificial Intelligence (AI) and Deep Reinforcement Learning (DRL) have revolutionised e-learning by creating personalised, adaptive, and secure environments. However, challenges such as privacy, bias, and data limitations persist. E-FedCloud aims to address these issues by providing more agile, personalised, and secure e-learning experiences. This study introduces E-FedCloud, an AI-assisted, adaptive e-learning system that automates personalised recommendations and tracking, thereby enhancing student performance. It employs federated learning-based authentication to ensure secure and private access for both course instructors and students. Intelligent Software Agents (ISAs) evaluate weekly student engagement using the Shannon Entropy method, classifying students into either engaged or not-engaged clusters. E-FedCloud utilises weekly engagement status, demographic information, and an innovative DRL-based early warning system, specifically ID2QN, to predict the performance of not-engaged students. Based on these predictions, the system categorises students into three groups: risk of dropping out, risk of scoring lower in the final exam, and risk of failing the end exam. It employs a multi-disciplinary ontology graph and an attention-based capsule network for automated, personalised recommendations. The system also integrates performance tracking to enhance student engagement. Data are securely stored on a blockchain using the LWEA encryption method.

Introducing a multipliable BOM-based automatic definition of information retrieval in plant engineering

AbstractThe complexity of process plants and the growing demand for digitalization require efficient and accurate information retrieval throughout the lifecycle phases of a process plant. This paper discusses the concept of instantiation and introduces a method for identifying and multiplying required information in plant engineering using scalable so-called Instantiation Blocks linked to the Bill of Material. Core functionality, an ontology graph and a user interface based on Python and React are developed to demonstrate the implementation of the framework and validate its effectiveness in practice.

ПРОБЛЕМИ І РОЛЬ ОНТОЛОГІЧНОЇ ІНЖЕНЕРІЇ У ФОРМУВАННІ ІНДУСТРІЇ ЗНАНЬ З ПОЗИЦІЙ ДОСЛІДНОГО ПРОЄКТУВАННЯ

The article discusses models and mechanisms of transdisciplinary research in the perspective of creating clusters of disciplinary convergence and scientific theories, formal representation of knowledge, and the formation of the knowledge industry using a unified ontology engineering devkit. Special attention is focused on the possibilities of research-related design for the creation of new knowledge and technologies. A conceptual analysis of ontology engineering is conducted, indicating the importance and effectiveness of applying ontology knowledge and mechanisms in solving user tasks. The domain ontology, its ontology graph, and their essential differences and advantages from owl ontologies are examined in depth. An example of the application of task ontology to the design of programmable microchip computing devices is proposed. Keywords: knowledge industry, ontology engineering, transdisciplinary research, convergence clusters, research-related design, new knowledge and technologies, domain ontology, ontology graph, task ontology.

Restricting the Spurious Growth of Knowledge Graphs by Using Ontology Graphs

Restricting the Spurious Growth of Knowledge Graphs by Using Ontology Graphs

Planteome 2024 Update: Reference Ontologies and Knowledgebase for Plant Biology.

The Planteome project (https://planteome.org/) provides a suite of reference and crop-specific ontologies and an integrated knowledgebase of plant genomics data. The plant genomics data in the Planteome has been obtained through manual and automated curation and sourced from more than 40 partner databases and resources. Here, we report on updates to the Planteome reference ontologies, namely, the Plant Ontology (PO), Trait Ontology (TO), the Plant Experimental Conditions Ontology (PECO), and integration of species/crop-specific vocabularies from our partners, the Crop Ontology (CO) into the TO ontology graph. Currently, 11 CO vocabularies are integrated into the Planteome with the addition of yam, sorghum, and potato since 2018. In addition, the size of the annotation database has increased by 34%, and the number of bioentities (genes, proteins, etc.) from 125 plant taxa has increased by 72%. We developed new tools to facilitate user requests and improvements to the CO vocabularies, and to allow fast searching and browsing of PO terms and definitions. These enhancements and future changes to automate the TO-CO mappings and knowledge discovery tools ensure that the Planteome will continue to be a valuable resource for plant biology.

Global Ontology Entities Embeddings

Ontologies are among the most widely used types of knowledge representation formalisms. The application of deep learning techniques in the field of ontology engineering has reinforced the need to learn and generate representations of ontological data. This allows ontologies to be exploited by such models, and thus automate various ontology engineering tasks, where most of the existing tools and machine learning approaches require a numerical feature vectors associated with each concept. This paper outlines a novel approach for learning global ontology entities embeddings by exploiting the structure and the various taxonomic and semantic relationships present in ontologies, taking into account all the information present in the ontological graph and carried by the OWL/RDF triples. Thus, producing global ontology entities embeddings capturing the global ontological graph semantics and similarities enclosed in the source ontology. Three different neural network models have been proposed based on two architectures: multi-input and multi-output, trained using the contrastive estimation technique. The evaluation on OWL/RDF ontologies and word semantic similarity tasks using various graph and WordNet based similarity measures, show that our approach yields competitive results outperforming the state-of-the-art ontology and word embedding models.

KAMPNet: multi-source medical knowledge augmented medication prediction network with multi-level graph contrastive learning

BackgroundsPredicting medications is a crucial task in intelligent healthcare systems, aiding doctors in making informed decisions based on electronic medical records (EMR). However, medication prediction faces challenges due to complex relations within heterogeneous medical data. Existing studies primarily focus on the supervised mining of hierarchical relations between homogeneous codes in medical ontology graphs, such as diagnosis codes. Few studies consider the valuable relations, including synergistic relations between medications, concurrent relations between diseases, and therapeutic relations between medications and diseases from historical EMR. This limitation restricts prediction performance and application scenarios.MethodsTo address these limitations, we propose KAMPNet, a multi-sourced medical knowledge augmented medication prediction network. KAMPNet captures diverse relations between medical codes using a multi-level graph contrastive learning framework. Firstly, unsupervised graph contrastive learning with a graph attention network encoder captures implicit relations within homogeneous medical codes from the medical ontology graph, generating knowledge augmented medical code embedding vectors. Then, unsupervised graph contrastive learning with a weighted graph convolutional network encoder captures correlative relations between homogeneous or heterogeneous medical codes from the constructed medical codes relation graph, producing relation augmented medical code embedding vectors. Finally, the augmented medical code embedding vectors, along with supervised medical code embedding vectors, are fed into a sequential learning network to capture temporal relations of medical codes and predict medications for patients.ResultsExperimental results on the public MIMIC-III dataset demonstrate the superior performance of our KAMPNet model over several baseline models, as measured by Jaccard, F1 score, and PR-AUC for medication prediction.ConclusionsOur KAMPNet model can effectively capture the valuable relations between medical codes inherent in multi-sourced medical knowledge using the proposed multi-level graph contrastive learning framework. Moreover, The multi-channel sequence learning network facilitates capturing temporal relations between medical codes, enabling comprehensive patient representations for downstream tasks such as medication prediction.

Deep Ontology Alignment Using a Natural Language Processing Approach for Automatic M2M Translation in IIoT.

The technical capabilities of modern Industry 4.0 and Industry 5.0 are vast and growing exponentially daily. The present-day Industrial Internet of Things (IIoT) combines manifold underlying technologies that require real-time interconnection and communication among heterogeneous devices. Smart cities are established with sophisticated designs and control of seamless machine-to-machine (M2M) communication, to optimize resources, costs, performance, and energy distributions. All the sensory devices within a building interact to maintain a sustainable climate for residents and intuitively optimize the energy distribution to optimize energy production. However, this encompasses quite a few challenges for devices that lack a compatible and interoperable design. The conventional solutions are restricted to limited domains or rely on engineers designing and deploying translators for each pair of ontologies. This is a costly process in terms of engineering effort and computational resources. An issue persists that a new device with a different ontology must be integrated into an existing IoT network. We propose a self-learning model that can determine the taxonomy of devices given their ontological meta-data and structural information. The model finds matches between two distinct ontologies using a natural language processing (NLP) approach to learn linguistic contexts. Then, by visualizing the ontological network as a knowledge graph, it is possible to learn the structure of the meta-data and understand the device's message formulation. Finally, the model can align entities of ontological graphs that are similar in context and structure.Furthermore, the model performs dynamic M2M translation without requiring extra engineering or hardware resources.

Patient Clustering for Vital Organ Failure Using ICD Code With Graph Attention.

Heart failure, respiratory failure and kidney failure are three severe organ failures (OF) that have high mortalities and are most prevalent in intensive care units. The objective of this work is to offer insights into OF clustering from the aspects of graph neural networks and diagnosis history. This paper proposes a neural network-based pipeline to cluster three types of organ failure patients by incorporating embedding pre-train using an ontology graph of the International Classification of Diseases (ICD) codes. We employ an autoencoder-based deep clustering architecture jointly trained with a K-means loss, and a non-linear dimension reduction is performed to obtain patient clusters on the MIMIC-III dataset. The clustering pipeline shows superior performance on a public-domain image dataset. On the MIMIC-III dataset, it discovers two distinct clusters that exhibit different comorbidity spectra which can be related to the severity of diseases. The proposed pipeline is compared with several other clustering models and shows superiority. Our proposed pipeline gives stable clusters, however, they do not correspond to the type of OF which indicates these OF share significant hidden characteristics in diagnosis. These clusters can be used to signal possible complications and severity of illness and aid personalised treatment. We are the first to apply an unsupervised approach to offer insights from a biomedical engineering perspective on these three types of organ failure, and publish the pre-trained embeddings for future transfer learning.

Integrative Technology for Creating Electronic Educational Resources

To increase the efficiency of using ontologies in the educational process, we have developed the Ontos.xyz resource, which consists of an ontograph editor and a viewer that allows displaying both individual EERs and their collections. The editor allows creating an ontograph that describes the structure of the EER, as well as the ability to assign to each node a context of all types supported by the browser including html-pages, web 2.0 resources, etc. The EER built-in this way allows the integration of data from different sources with the ability to adapt to the conditions of any subject area, regardless of its specifics.
 Thus, the digital competencies of the EER creators remain relevant, since they do not need to learn new software resources to work with individual ontology concepts (“ontograph nodes”).
 As a result of our research, we have developed a technology for using the ontological approach to create an EER. For its implementation, the Ontos.xyz resource was developed, which is an ontological graph editor. The ontograph allows for the primary visualization of the EER structure, interpreting its structural elements as nodes (vertices) of the graph, and displaying the logic of transitions between structural elements in the form of directed links. With such an approach, the ontology is some kind of aggregator that ensures the integration of the semantic and technological approaches. Building an EER using the ontological approach requires appropriate technological support in terms of description languages, models, software tools, and systems.
 The software proposed solution, in contrast to its functional counterparts, focuses on use in the educational process.

Specimen, biological structure, and spatial ontologies in support of a Human Reference Atlas

The Human Reference Atlas (HRA) is defined as a comprehensive, three-dimensional (3D) atlas of all the cells in the healthy human body. It is compiled by an international team of experts who develop standard terminologies that they link to 3D reference objects, describing anatomical structures. The third HRA release (v1.2) covers spatial reference data and ontology annotations for 26 organs. Experts access the HRA annotations via spreadsheets and view reference object models in 3D editing tools. This paper introduces the Common Coordinate Framework (CCF) Ontology v2.0.1 that interlinks specimen, biological structure, and spatial data, together with the CCF API that makes the HRA programmatically accessible and interoperable with Linked Open Data (LOD). We detail how real-world user needs and experimental data guide CCF Ontology design and implementation, present CCF Ontology classes and properties together with exemplary usage, and report on validation methods. The CCF Ontology graph database and API are used in the HuBMAP portal, HRA Organ Gallery, and other applications that support data queries across multiple, heterogeneous sources.

Improving building occupant comfort through a digital twin approach: A Bayesian network model and predictive maintenance method

This study introduces a Bayesian network model to evaluate the comfort levels of occupants of two non-residential Norwegian buildings based on data collected from satisfaction surveys and building performance parameters. A Digital Twin approach is proposed to integrate building information modeling (BIM) with real-time sensor data, occupant feedback, and a probabilistic model of occupant comfort to detect and predict HVAC issues that may impact comfort. The study also uses 200000 points as historical data of various sensors to understand the previous building systems’ behavior. The study also presents new methods for using BIM as a visualization platform and for predictive maintenance to identify and address problems in the HVAC system. For predictive maintenance, nine machine learning algorithms were evaluated using metrics such as ROC, accuracy, F1-score, precision, and recall, where Extreme Gradient Boosting (XGB) was the best algorithm for prediction. XGB is on average 2.5% more accurate than Multi-Layer Perceptron (MLP), and up to 5% more accurate than the other models. Random Forest is around 96% faster than XGBoost while being relatively easier to implement. The paper introduces a novel method that utilizes several standards to determine the remaining useful life of HVAC, leading to a potential increase in its lifetime by at least 10% and resulting in significant cost savings. The result shows that the most important factors that affect occupant comfort are poor air quality, lack of natural light, and uncomfortable temperature. To address the challenge of applying these methods to a wide range of buildings, the study proposes a framework using ontology graphs to integrate data from different systems, including FM, CMMS, BMS, and BIM. This study’s results provide insight into the factors that influence occupant comfort, help to expedite identifying equipment malfunctions and point towards potential solutions, leading to more sustainable and energy-efficient buildings.

Assessment of GO-Based Protein Interaction Affinities in the Large-Scale Human-Coronavirus Family Interactome.

SARS-CoV-2 is a novel coronavirus that replicates itself via interacting with the host proteins. As a result, identifying virus and host protein-protein interactions could help researchers better understand the virus disease transmission behavior and identify possible COVID-19 drugs. The International Committee on Virus Taxonomy has determined that nCoV is genetically 89% compared to the SARS-CoV epidemic in 2003. This paper focuses on assessing the host-pathogen protein interaction affinity of the coronavirus family, having 44 different variants. In light of these considerations, a GO-semantic scoring function is provided based on Gene Ontology (GO) graphs for determining the binding affinity of any two proteins at the organism level. Based on the availability of the GO annotation of the proteins, 11 viral variants, viz., SARS-CoV-2, SARS, MERS, Bat coronavirus HKU3, Bat coronavirus Rp3/2004, Bat coronavirus HKU5, Murine coronavirus, Bovine coronavirus, Rat coronavirus, Bat coronavirus HKU4, Bat coronavirus 133/2005, are considered from 44 viral variants. The fuzzy scoring function of the entire host-pathogen network has been processed with ~180 million potential interactions generated from 19,281 host proteins and around 242 viral proteins. ~4.5 million potential level one host-pathogen interactions are computed based on the estimated interaction affinity threshold. The resulting host-pathogen interactome is also validated with state-of-the-art experimental networks. The study has also been extended further toward the drug-repurposing study by analyzing the FDA-listed COVID drugs.

PFresGO: an attention mechanism-based deep-learning approach for protein annotation by integrating gene ontology inter-relationships.

The rapid accumulation of high-throughput sequence data demands the development of effective and efficient data-driven computational methods to functionally annotate proteins. However, most current approaches used for functional annotation simply focus on the use of protein-level information but ignore inter-relationships among annotations. Here, we established PFresGO, an attention-based deep-learning approach that incorporates hierarchical structures in Gene Ontology (GO) graphs and advances in natural language processing algorithms for the functional annotation of proteins. PFresGO employs a self-attention operation to capture the inter-relationships of GO terms, updates its embedding accordingly and uses a cross-attention operation to project protein representations and GO embedding into a common latent space to identify global protein sequence patterns and local functional residues. We demonstrate that PFresGO consistently achieves superior performance across GO categories when compared with 'state-of-the-art' methods. Importantly, we show that PFresGO can identify functionally important residues in protein sequences by assessing the distribution of attention weightings. PFresGO should serve as an effective tool for the accurate functional annotation of proteins and functional domains within proteins. PFresGO is available for academic purposes at https://github.com/BioColLab/PFresGO. Supplementary data are available at Bioinformatics online.

Automatic schema construction of electrical graph data platform based on multi-source relational data models

Data storage and management in power systems usually adopt relational databases. However, the relational database requires ample storage space and has low data retrieval and query efficiency. An electrical graph data platform can describe the complicated relationships between concepts and entities involved in power systems with the form of an association graph, which provides a better ability to organize, manage, and apply massive amounts of information. Since the construction of the top-level ontology model or schema for a specific field graph data platform is cumbersome, complex, and generally requires lots of association analysis and expert system intervention, it is insufficiently automated, time-consuming, and unable to cope with large-scale electric power knowledge. This paper proposes a method for automatically constructing the schema of an electrical graph data platform, which uses the diverse table structure information from the relational database and SQL language descriptions to extract ontologies to form the ontology candidate set automatically. Then the method utilizes ontology clustering and disambiguation to initial an ontology graph model and automatically update ontology and relationship expressions. Meanwhile, the model layering is used to construct a hierarchical model based on different business needs, and the schema optimization is applied according to expert comments.

TANGO: A GO-Term Embedding Based Method for Protein Semantic Similarity Prediction.

We aim to quantitatively predict protein semantic similarities (PSS), which is vital to making biological discoveries. Previously, researchers commonly exploited Gene Ontology (GO) graphs (containing standardized hierarchically-organized GO terms for annotating distinct protein attributes) to learn GO term embeddings (vector representations) for quantifying protein attribute similarities and aggregate these embeddings to form protein embeddings for similarity measurement. However, two key properties of GO terms and annotated proteins are not yet well-explored by these learning-based methods: (1) taxonomy relations between GO terms; (2) GO terms' different contributions in describing protein semantics. In this paper, we propose TANGO, a new framework composed of a TAxoNomy-aware embedding module and an aggreGatiOn module. Our Embedding Module encodes taxonomic information into GO term embeddings by incorporating GO term topological distances in the GO graph hierarchy. Hence, distances between GO term embeddings can be used to more accurately measure shared meanings between correlated protein attributes. Our Aggregation Module automatically determines the contributions of GO terms when merging into the target protein embeddings, by mining GO term concept dependency relations in the GO graph and correlations in protein annotations. We conduct extensive experiments on several public datasets. On two PSS metrics, our new method significantly outperforms known methods by a large margin.

Local-to-Global Framework for Multi-target Frame Identification

Frame identification is a crucial and challenging task in frame semantic parsing, where the objective is to determine the most appropriate frame for a given target within its context. Existing approaches typically classify each target individually, overlooking the potential interactions among different targets. To address these limitations, we propose a novel two-step prediction framework that encompasses both local and global perspectives for target identification. Additionally, we leverage the frame ontology graph to enhance the interactions among multiple targets by incorporating rich frame ontology knowledge. Moreover, we introduce a dynamic masking strategy during model training. This strategy encourages our model to adopt a global view during prediction, avoiding local optimization. Experimental results demonstrate the superiority of our model compared to previous approaches on FrameNet1.5, and it achieves competitive performance on FrameNet1.7. Furthermore, supplementary experiments and analyses provide additional evidence of the effectiveness of our proposed model.

Digital Twin framework for automated fault source detection and prediction for comfort performance evaluation of existing non-residential Norwegian buildings

Numerous buildings fall short of expectations regarding occupant satisfaction, sustainability, or energy efficiency. In this paper, the performance of buildings in terms of occupant comfort is evaluated using a probabilistic model based on Bayesian networks (BNs). The BN model is founded on an in-depth analysis of satisfaction survey responses and a thorough study of building performance parameters. This study also presents a user-friendly visualization compatible with BIM to simplify data collecting in two case studies from Norway with data from 2019 to 2022. This paper proposes a novel Digital Twin approach for incorporating building information modeling (BIM) with real-time sensor data, occupants’ feedback, a probabilistic model of occupants’ comfort, and HVAC faults detection and prediction that may affect occupants’ comfort. New methods for using BIM as a visualization platform, as well as a predictive maintenance method to detect and anticipate problems in the HVAC system, are also presented. These methods will help decision-makers improve the occupants’ comfort conditions in buildings. However, due to the intricate interaction between numerous equipment and the absence of data integration among FM systems, CMMS, BMS, and BIM data are integrated in this paper into a framework utilizing ontology graphs to generalize the Digital Twin framework so it can be applied to many buildings. The results of this study can aid decision-makers in the facility management sector by offering insight into the aspects that influence occupant comfort, speeding up the process of identifying equipment malfunctions, and pointing toward possible solutions.

A dialogue system based on ontology automatically built through a natural language text analysis

An integrated approach is created to the development of natural-language dialogue systems driven by an ontological graph database. Ontology here has a defined regular structure that contains typed semantic relationships between concepts, as well as related contexts, which may also have a multilevel structure and additional typing. The ontology is created automatically due to the semantic analysis of a natural language using a specially developed original software, which is set up to work with inflected languages, in particular Ukrainian. The ontology description is serialized in OWL format. To work as part of the dialog system, the ontology is transferred to the graph database Neo4j. The Cypher language is used for formal queries. The original phrases of the user are subject to a special method of semantic analysis, which determines the type of formal query to the database. The essence of the analysis is that the text of the user phrase goes through a series of checks. Based on their results, a set of basic templates for formal requests is determined, as well as additional constructions that are attached to the basic template. Some of the checks may also return the notion of substitution to certain specified positions of the formal query. Formal queries can return both contexts and lists of ontology concepts. In addition to concepts, queries can also return information about specific semantic predicates that connect them, which simplifies the synthesis of natural language responses. The synthesis of answers is based on special templates, the choice of which is directly related to the corresponding template of the formal query.