Ontology Mapping Research Articles

A hybrid framework with large language models for rare disease phenotyping.

Rare diseases pose significant challenges in diagnosis and treatment due to their low prevalence and heterogeneous clinical presentations. Unstructured clinical notes contain valuable information for identifying rare diseases, but manual curation is time-consuming and prone to subjectivity. This study aims to develop a hybrid approach combining dictionary-based natural language processing (NLP) tools with large language models (LLMs) to improve rare disease identification from unstructured clinical reports. We propose a novel hybrid framework that integrates the Orphanet Rare Disease Ontology (ORDO) and the Unified Medical Language System (UMLS) to create a comprehensive rare disease vocabulary. SemEHR, a dictionary-based NLP tool, is employed to extract rare disease mentions from clinical notes. To refine the results and improve accuracy, we leverage various LLMs, including LLaMA3, Phi3-mini, and domain-specific models like OpenBioLLM and BioMistral. Different prompting strategies, such as zero-shot, few-shot, and knowledge-augmented generation, are explored to optimize the LLMs' performance. The proposed hybrid approach demonstrates superior performance compared to traditional NLP systems and standalone LLMs. LLaMA3 and Phi3-mini achieve the highest F1 scores in rare disease identification. Few-shot prompting with 1-3 examples yields the best results, while knowledge-augmented generation shows limited improvement. Notably, the approach uncovers a significant number of potential rare disease cases not documented in structured diagnostic records, highlighting its ability to identify previously unrecognized patients. The hybrid approach combining dictionary-based NLP tools with LLMs shows great promise for improving rare disease identification from unstructured clinical reports. By leveraging the strengths of both techniques, the method demonstrates superior performance and the potential to uncover hidden rare disease cases. Further research is needed to address limitations related to ontology mapping and overlapping case identification, and to integrate the approach into clinical practice for early diagnosis and improved patient outcomes.

ChatGeoAI: Enabling Geospatial Analysis for Public through Natural Language, with Large Language Models

Large Language Models (LLMs) such as GPT, BART, and Gemini stand at the forefront of Generative Artificial Intelligence, showcasing remarkable prowess in natural language comprehension and task execution. This paper proposes a novel framework developed on the foundation of Llama 2, aiming to bridge the gap between natural language queries and executable code for geospatial analyses within the PyQGIS environment. It empowers non-expert users to leverage GIS technology without requiring deep knowledge of geospatial programming or tools. Through cutting-edge Natural Language Processing (NLP) techniques, including tailored entity recognition and ontology mapping, the framework accurately interprets user intents and translates them into specific GIS operations. Integration of geospatial ontologies enriches semantic comprehension, ensuring precise alignment between user descriptions, geospatial datasets, and geospatial analysis tasks. A code generation module empowered by Llama 2 converts these interpretations into PyQGIS scripts, enabling the execution of geospatial analysis and results visualization. Rigorous testing across a spectrum of geospatial analysis tasks, with incremental complexity, evaluates the framework and the performance of such a system, with LLM at its core. The proposed system demonstrates proficiency in handling various geometries, spatial relationships, and attribute queries, enabling accurate and efficient analysis of spatial datasets. Moreover, it offers robust error-handling mechanisms and supports tasks related to map styling, visualization, and data manipulation. However, it has some limitations, such as occasional struggles with ambiguous attribute names and aliases, which leads to potential inaccuracies in the filtering and retrieval of features. Despite these limitations, the system presents a promising solution for applications integrating LLMs into GIS and offers a flexible and user-friendly approach to geospatial analysis.

A multi-strategy ontology mapping method based on cost-sensitive SVM

As the core of ontology integration, the task of ontology mapping is to find the semantic relationship between ontologies. Nevertheless, most existing ontology mapping methods only rely ontext information to calculate entity similarity, thereby disregarding semantic nuances and necessitating substantial manual intervention. Therefore, this paper introduces an ontology mapping method. Based on the traditional ontology mapping method, the process employs a deep learning model to mine the semantic information of entity concepts, entity properties and ontology structure to obtain the embedding vector. We use the similarity mechanism to calculate the similarity between different embedding vectors, and combine the similarity values obtained from multiple strategy entities into a similarity matrix. The similarity matrix serves as input to the support vector machine (SVM), and the ontology mapping problem is finally transformed into a binary classification problem. However, since the number of mapped pairs is much larger than the number of non-mapped pairs, the number of positive samples in the data set is much smaller than the number of negative samples. Therefore, based on the traditional SVM, the paper adopts cost-sensitive strategy to deal with the class imbalance problem. In comparative evaluations against contemporary ontology mapping techniques, our method demonstrates a noteworthy 5.0% enhancement in recall and a 3.0% improvement in F1 score when tested on both public benchmark datasets and domain-specific datasets.

Completing the Completeness Measure: the MIDS Specification

The need to rapidly digitise millions of specimens in natural history collections has seen the development of a staged approach for data capture by institutions that have been carrying out mass digitisation projects. The cost and difficulty of transcribing labels associated with specimens has necessitated an approach that prioritises parts of the data based on research and curatorial requirements as well as ease of transcription and methodology available. This approach means that there is currently a wide variation in the completeness of data capture and imaging of specimens within and between collections. The Biodiversity Information Standards (TDWG) Minimum Information about a Digital Specimen (MIDS) specification has been designed to provide a framework for measuring and monitoring the completeness of the data transcribed from the specimen and the presence of an image or other media file. This framework enables a consistent and standardised approach to the calculation of the level of digitisation of specimens within a collection and, by extension/extrapolation, to the collection itself. Four levels of digitisation have been defined in the MIDS specification including a pre-digitisation level. These have been developed to correspond to practical requirements and existing large-scale digitisation programmes. MIDS level 0 (Bare): A bare or skeletal record making the association between an identifier of a physical specimen and its digital representation, allowing for unambiguous attachment of all other information. MIDS level 1 (Basic): A basic record of specimen information enabling basic discoverability as well as how the user is permitted to use the data. MIDS level 2 (Regular): A regular level of information including data that have been agreed over time as essential for most scientific purposes. MIDS level 3 (Extended): An extended level of information about a specimen including identifiers enabling connections to be made to other data present or known about the specimen. The scope of MIDS does not directly include the quality of data entered. Instead, MIDS can be seen as a tool to support the continuing improvement of data access and quality. It provides guidance for prioritising the data to be captured as well as recommendations for data standards and mapping structures. Here we present the progress in the development of the MIDS specification and its implementation. The MIDS elements for each of the four levels have now been defined and a draft version is available here. A machine-readable mapping to Darwin Core and ABCD has been compiled following the Simple Standard for Sharing Ontological Mappings (SSSOM). The differing data relevances and priorities for different disciplines have been recognised and the inclusion of required elements at each level is discipline specific (biology, palaeontology and geology). In addition, MIDS level scores have been increasingly implemented in existing specimen management systems, allowing an evaluation of the levels achieved in various contexts. There are two implementations of MIDS calculators that have been developed and are available to test. One, developed at the Meise Botanic Garden, uses a zipped Global Biodiversity Information Facility (GBIF) annotated archive (a commonly used GBIF download format based on Darwin Core Archive) and is available here. The other, developed at The Natural History Museum London, interacts directly with the GBIF API and is available here. We encourage users to try these and provide feedback to the TDWG MIDS Task Group.

Retraction Note: A weighted graph-oriented ontology matching algorithm for enhancing ontology mapping and alignment in semantic web

Retraction Note: A weighted graph-oriented ontology matching algorithm for enhancing ontology mapping and alignment in semantic web

P05-50 Using ontology map and physiological map to improve predictive models for kidney toxicity

P05-50 Using ontology map and physiological map to improve predictive models for kidney toxicity

An Enhanced Technology for Ontology Mapping

The process of defining content from different ontologies is time-consuming, tedious and error-prone. To solve these problems, new methods for ontology comparison have been developed. This process focuses on the integration of ontologies for various applications, but also requires maintaining the integrity of the integrated ontologies. The concept ontology associated with integration is designed to be more efficient, accurate and useful. You can combine these two and compete together to increase accuracy. Comparing this approach with existing methods should provide greater accuracy and efficiency in ontology comparison.

Going Beyond Surface Language: An Exploratory Evaluation of Nursing Ontology Mappings.

A range of approaches have been used to develop and evaluate terminology mapping. In seeking to enhance existing methods this exploratory feasibility study examined a small subset of existing equivalency mappings between the International Classification for Nursing Practice and SNOMED CT. To identify potential inconsistencies in allocation, comparisons were made for each concept in each equivalency mapping, through a manual review of a) compositionality and specificity of asserted and inherited relationships, and b) ancestors through to root. There were similarities and several differences across the mappings which were both structural and definitional in nature. In order to demonstrate practical utility, the approach piloted in the present study might benefit from scaling up and a degree of automation. However, the study has demonstrated it is both feasible and potentially useful when evaluating terminology mapping to go beyond the surface language of mapped terms, and to consider the deeper definitional features of the underlying concepts.

Advancing Ontology Alignment in the Labor Market: Combining Large Language Models with Domain Knowledge

One of the approaches to help the demand and supply problem in the labor market domain is to change from degree-based hiring to skill-based hiring. The link between occupations, degrees and skills is captured in domain ontologies such as ESCO in Europe and O*NET in the US. Several countries are also building or extending these ontologies. The alignment of the ontologies is important, as it should be clear how they all relate. Aligning two ontologies by creating a mapping between them is a tedious task to do manually, and with the rise of generative large language models like GPT-4, we explore how language models and domain knowledge can be combined in the matching of the instances in the ontologies and in finding the specific relation between the instances (mapping refinement). We specifically focus on the process of updating a mapping, but the methods could also be used to create a first-time mapping. We compare the performance of several state-of-the-art methods such as GPT-4 and fine-tuned BERT models on the mapping between ESCO and O*NET and ESCO and CompetentNL (the Dutch variant) for both ontology matching and mapping refinement. Our findings indicate that: 1) Match-BERT-GPT, an integration of BERT and GPT, performs best in ontology matching, while 2) TaSeR outperforms GPT-4, albeit marginally, in the task of mapping refinement. These results show that domain knowledge is still important in ontology alignment, especially in the updating of a mapping in our use cases in the labor domain.

Diabetic Drug ontology mapping for individual Diabetic Person and predict Insulin Dosage on Daily Basis

Managing diabetes requires a personalized treatment plan based on the patient's health records and drug usage effectively. In this paper, we have proposed accurate prediction of insulin dosage for diabetic patients daily by using ontology mapping with deep learning recurrent neural network models such as long short-term memory (LSTM), Gated recurrent unit( GRU), and Bidirectional long short-term memory(BiLSTM). The patient's information is arranged in a structured format. The structured ontology data provides a meaningful connection between patients' personal information, physical activity, insulin intake, carbohydrate intake and glucose level. The structured data is beneficial to take decisions effectively to recommend the insulin dosage level daily to avoid a sudden decrease in sugar level. The proposed LSTM model outperforms well on insulin prediction compared to GRU and BiLSTM models. The proposed model is very effective for diabetic personal care and improves patient outcomes and quality of life.

RMDEASD: Integrating Rule Mining and Deep Learning for Enhanced Aspect-Based Sentiment Analysis Across Diverse Domains

The rapidly evolving landscape of Aspect-Based Sentiment Analysis (ABSA) in the realm of natural language processing necessitates innovative approaches to comprehend and interpret the intricate nature of sentiments expressed in textual data. Traditional ABSA methods have often struggled with the nuanced sentiments inherent in various textual sources, limited in their ability to adapt to domain-specific vernacular and context. This study introduces a novel approach that synergizes rule mining with advanced deep learning techniques, aiming to address these limitations and enhance the precision and contextual understanding in sentiment analysis. Our proposed model integrates rule-based systems with deep learning Transformers, a method recognized for its effectiveness in extracting structured, domain-specific insights. This integration results in a significant enhancement in the model's ability to capture nuanced sentiments, as demonstrated by an 8.5% increase in aspect-based sentiment analysis precision and an 8.3% improvement in accuracy over existing methods. The model employs a combination of techniques including Bi-LSTM, BiGRU-CRF with RNNs, and ontology mapping operations, forming a Hybrid Multi-Level Architecture that effectively captures both sequential data relationships and semantic context. Additionally, the model incorporates Cross-Domain Transfer Learning, utilizing BERT-based pre-trained models with added layers for contextual semantics, which has shown notable generalization capabilities across various domains. Furthermore, this study refines evaluation parameters, tailoring metrics such as domain-specific accuracy, recall, and precision to more accurately assess model performance in particular domains. This is especially pertinent in our analysis of Twitter datasets specific to industries like finance and healthcare. The inclusion of Temporal Dynamics and Aspect Summarization, using techniques like the VARMAx process, provides insights into the evolution of sentiments and aspects over time, an aspect crucial for longitudinal sentiment analysis. The comprehensive testing of our model on diverse spatial and temporal datasets reveals not only improved precision and accuracy in sentiment analysis but also a reduction in delay, demonstrating its efficiency and responsiveness. The study's findings indicate that our approach could significantly impact fields reliant on sentiment analysis, such as market analysis, public opinion research, and social media monitoring, providing a more nuanced and accurate understanding of consumer sentiments and trends. This paper's contribution lies in its innovative amalgamation of rule-based and deep learning techniques, tailored evaluation metrics, and its emphasis on temporal dynamics, setting a new precedent in the field of ABSA and opening avenues for further research and application in real-world scenarios.

Translating nanoEHS data using EPA NaKnowBase and the resource description framework.

The U.S. Federal Government has supported the generation of extensive amounts of nanomaterials and related nano Environmental Health and Safety (nanoEHS) data, there is a need to make these data available to stakeholders. With recent efforts, a need for improved interoperability, translation, and sustainability of Federal nanoEHS data in the United States has been realized. The NaKnowBase (NKB) is a relational database containing experimental results generated by the EPA Office of Research and Development (ORD) regarding the actions of engineered nanomaterials on environmental and biological systems. Through the interaction of the National Nanotechnology Initiative's Nanotechnology Environmental Health Implications (NEHI) Working Group, and the Database and Informatics Interest Group (DIIG), a U.S. Federal nanoEHS Consortium has been formed. The primary goal of this consortium is to establish a "common language" for nanoEHS data that aligns with FAIR data standards. A second goal is to overcome nomenclature issues inherent to nanomaterials data, ultimately allowing data sharing and interoperability across the diverse U.S. Federal nanoEHS data compendium, but also in keeping a level of consistency that will allow interoperability with U.S. and European partners. The most recent version of the EPA NaKnowBase (NKB) has been implemented for semantic integration. Computational code has been developed to use each NKB record as input, modify and filter table data, and subsequently output each modified record to a Research Description Framework (RDF). To improve the accuracy and efficiency of this process the EPA has created the OntoSearcher tool. This tool partially automates the ontology mapping process, thereby reducing onerous manual curation. Here we describe the efforts of the US EPA in promoting FAIR data standards for Federal nanoEHS data through semantic integration, as well as in the development of NAMs (computational tools) to facilitate these improvements for nanoEHS data at the Federal partner level.

Development and application of Chinese medical ontology for diabetes mellitus

ObjectiveTo develop a Chinese Diabetes Mellitus Ontology (CDMO) and explore methods for constructing high-quality Chinese biomedical ontologies.Materials and methodsWe used various data sources, including Chinese clinical practice guidelines, expert consensus, literature, and hospital information system database schema, to build the CDMO. We combined top-down and bottom-up strategies and integrated text mining and cross-lingual ontology mapping. The ontology was validated by clinical experts and ontology development tools, and its application was validated through clinical decision support and Chinese natural language medical question answering.ResultsThe current CDMO consists of 3,752 classes, 182 fine-grained object properties with hierarchical relationships, 108 annotation properties, and over 12,000 mappings to other well-known medical ontologies in English. Based on the CDMO and clinical practice guidelines, we developed 200 rules for diabetes diagnosis, treatment, diet, and medication recommendations using the Semantic Web Rule Language. By injecting ontology knowledge, CDMO enhances the performance of the T5 model on a real-world Chinese medical question answering dataset related to diabetes.ConclusionCDMO has fine-grained semantic relationships and extensive annotation information, providing a foundation for medical artificial intelligence applications in Chinese contexts, including the construction of medical knowledge graphs, clinical decision support systems, and automated medical question answering. Furthermore, the development process incorporated natural language processing and cross-lingual ontology mapping to improve the quality of the ontology and improved development efficiency. This workflow offers a methodological reference for the efficient development of other high-quality Chinese as well as non-English medical ontologies.

An ontological approach for representing declarative mapping languages

Knowledge Graphs are currently created using an assortment of techniques and tools: ad hoc code in a programming language, database export scripts, OpenRefine transformations, mapping languages, etc. Focusing on the latter, the wide variety of use cases, data peculiarities, and potential uses has had a substantial impact in how mappings have been created, extended, and applied. As a result, a large number of languages and their associated tools have been created. In this paper, we present the Conceptual Mapping ontology, that is designed to represent the features and characteristics of existing declarative mapping languages to construct Knowledge Graphs. This ontology is built upon the requirements extracted from experts experience, a thorough analysis of the features and capabilities of current mapping languages presented as a comparative framework; and the languages’ limitations discussed by the community and denoted as Mapping Challenges. The ontology is evaluated to ensure that it meets these requirements and has no inconsistencies, pitfalls or modelling errors, and is publicly available online along with its documentation and related resources.

Mapping Insights from News Articles to Tackle Low Birth Rate and Parenthood in Finland

The aim of this study is to explore how parenthood and birth rate is manifested in Finnish society and citizens as revealed by automated mining of news articles from Finland News API. Several levels of analysis were conducted using natural language processing and text mining techniques to unfold relevant insights from the collected News API. This includes surface-level analysis, word frequency-based analysis, topic-based analysis, and health ontology mapping. In total, 1621 news articles were selected and analyzed from the collected dataset. The surface-level analysis revealed the capacity of imminent health researchers to gain public audience and interest. Content-based analysis revealed the importance of family, employment, and health issues. Topical analysis stressed on the dominance of family issues during corona time, followed by public services and employment issues. Finally, the health ontology mapping revealed the quasi dominance of mental health and development disorders concerns. The research work provides a general framework for analyzing unstructured text to extract useful insights that can help policymakers to positively impact the existing policy in health and social policy development.

CMAT: ClinVar Mapping and Annotation Toolkit.

Semantic ontology mapping of clinical descriptors with disease outcome is essential. ClinVar is a key resource for human variation with known clinical significance. We present CMAT, a software toolkit and curation protocol for accurately enriching ClinVar releases with disease ontology associations and complex functional consequences. The software and ontology mappings can be obtained from: https://github.com/EBIvariation/CMAT.

Exploration of Innovative Practical Path of Party Building Work in Colleges and Universities Based on Cognitive Mapping Construction

Abstract This paper combines knowledge meta-extraction and knowledge fusion to construct a cognitive mapping model of party building work in colleges and universities, and the system contains four subsystems: data resource management, mapping ontology modeling, mapping construction, and mapping application. The content of the cognitive mapping is further optimized through the continuous collection, supplementation and improvement of subject knowledge data and the deduction, inference, induction and integration of party-building work using the cognitive mapping data model. After cognitive arbitrariness, the P-values of party-building organizational strength, intelligent party-building, branch activities, and organizational security are all less than 0.5, with significant positive effects. In the work dimension, the scores can reach 97 and 95. The number of participants in party-building organizational activities exceeded 500 after the innovation and even reached a maximum of 900. The results of the study can provide specific practical guidance for party-building work in colleges and universities, which can help them achieve better results in party-building work.

Design ofthe formalized andintegrated Alzheimer's Disease Ontology andits application inretrieving textual data via text mining.

As one of the leading causes for dementia in the population, it is imperative that we discern exactly why Alzheimer's disease (AD) has a strong molecular association with beta-amyloid and tau. Although a clear understanding about etiology and pathogenesis of AD remains unsolved, scientists worldwide have dedicated significant efforts to discovering the molecular interactions linked to the pathological characteristics and potential treatments. Knowledge representations, such as domain ontologies encompassing our current understanding about AD, could greatly assist and contribute to disease research. This paper describes the construction and application of the integrated Alzheimer's Disease Ontology (ADO), combining selected concepts from the former version of the ADO and the Alzheimer's Disease Mapping Ontology (ADMO). In addition to the existing entities available from these knowledge models, essential knowledge about AD from public sources, such as newly discovered risk factor genes and novel treatments, was also integrated. The ADO can also be leveraged in text mining scenarios given that it is conceptually enriched with domain-specific knowledge as well as their relations. The integrated ADO consists of 39 855 total axioms. The ontology covers many aspects of the AD domain, including risk factor genes, clinical features, treatments and experimental models. The ontology complies with the Open Biological and Biomedical Ontology principles and was accepted by the foundry. In this paper, we illustrate the role of the presented ontology in extracting textual information from the SCAIView database and key measures in an ADO-based corpus. Database URL: https://academic.oup.com/database.

"Revealing the genetic arsenal of Bacillus firmus TNAU1: Unleashing nematicidal and plant growth promotion traits"

Bacillus firmus is a promising nematicidal bacterium that also confers plant growth promotion, nutrient acquisition and antimicrobial activities. In the present study, attempts were made for whole genome sequencing of B. firmus TNAU1 isolated from the rhizosphere region of cucumber. The results confirmed that the isolate was B. firmus which contained a single circular genome of 5,370,919 bp (5.3 Mb) in length with an average GC content of 41.16 %. Annotation was performed using PATRIC tool to explore the subsystem analysis, specialty genes, Enzyme Commission (EC) numbers, Gene Ontology (GO) mappings, KEGG pathways of B. firmus TNAU1. A total of 5804 coding sequence (CDS) genes that encode proteins were predicted based on the KEGG and clusters of orthologous groups (COGs) database. Comparative genomic analysis was performed to discover the unique features and their relationship with other available B. firmus strains. Blastp analysis revealed that TNAU 1 genome assemblies had 26 homologs corresponding to nematode-virulent proteases and various genes responsible for plant growth promotion which includes indole acetic acid (IAA) production, nitrate transport, phosphorus and potassium solubilization. Four secondary metabolite biosynthetic clusters encoding antibiotics and siderophore production were confirmed through comparative genomics. B. firmus TNAU1 was evaluated for its antagonistic activity against root-knot nematode Meloidogyne incognita of tomato. The results exhibited that B. firmus inhibited the egg hatching and mortality of juveniles by 96% over control under in vitro conditions and greenhouse experiments confirmed that the TNAU1 strain not only had the potential to suppress the soil and root population of M. incognita (70% reduction over control), but also triggered the plant growth parameters of tomato.

Context-based refinement of mappings in evolving life science ontologies

BackgroundBiomedical computational systems benefit from ontologies and their associated mappings. Indeed, aligned ontologies in life sciences play a central role in several semantic-enabled tasks, especially in data exchange. It is crucial to maintain up-to-date alignments according to new knowledge inserted in novel ontology releases. Refining ontology mappings in place, based on adding concepts, demands further research.ResultsThis article studies the mapping refinement phenomenon by proposing techniques to refine a set of established mappings based on the evolution of biomedical ontologies. In our first analysis, we investigate ways of suggesting correspondences with the new ontology version without applying a matching operation to the whole set of ontology entities. In the second analysis, the refinement technique enables deriving new mappings and updating the semantic type of the mapping beyond equivalence. Our study explores the neighborhood of concepts in the alignment process to refine mapping sets.ConclusionExperimental evaluations with several versions of aligned biomedical ontologies were conducted. Those experiments demonstrated the usefulness of ontology evolution changes to support the process of mapping refinement. Furthermore, using context in ontological concepts was effective in our techniques.