Journal Of Biomedical Semantics[JOURNAL]
Sun
200 papers
A prototype ETL pipeline that uses HL7 FHIR RDF resources when deploying pure functions to enrich knowledge graph patient data.
Ansari A, Conte M, Flynn A … +1 more , Paturkar A
J Biomed Semantics · 2025 Sep · PMID 40887611 · Full text
BACKGROUND: For clinical care and research, knowledge graphs with patient data can be enriched by extracting parameters from a knowledge graph and then using them as inputs to compute new patient features with pure funct...
BACKGROUND: For clinical care and research, knowledge graphs with patient data can be enriched by extracting parameters from a knowledge graph and then using them as inputs to compute new patient features with pure functions. Systematic and transparent methods for enriching knowledge graphs with newly computed patient features are of interest. When enriching the patient data in knowledge graphs this way, existing ontologies and well-known data resource standards can help promote semantic interoperability. RESULTS: We developed and tested a new data processing pipeline for extracting, computing, and returning newly computed results to a large knowledge graph populated with electronic health record and patient survey data. We show that RDF data resource types already specified by Health Level 7's FHIR RDF effort can be programmatically validated and then used by this new data processing pipeline to represent newly derived patient-level features. CONCLUSIONS: Knowledge graph technology can be augmented with standards-based semantic data processing pipelines for deploying and tracing the use of pure functions to derive new patient-level features from existing data. Semantic data processing pipelines enable research enterprises to report on new patient-level computations of interest with linked metadata that details the origin and background of every new computation.
Mapping between clinical and preclinical terminologies: eTRANSAFE's Rosetta stone approach.
van Mulligen EM, Parry R, van der Lei J … +1 more , Kors JA
J Biomed Semantics · 2025 Aug · PMID 40841963 · Full text
BACKGROUND: The eTRANSAFE project developed tools that support translational research. One of the challenges in this project was to combine preclinical and clinical data, which are coded with different terminologies and...
BACKGROUND: The eTRANSAFE project developed tools that support translational research. One of the challenges in this project was to combine preclinical and clinical data, which are coded with different terminologies and granularities, and are expressed as single pre-coordinated, clinical concepts and as combinations of preclinical concepts from different terminologies. This study develops and evaluates the Rosetta Stone approach, which maps combinations of preclinical concepts to clinical, pre-coordinated concepts, allowing for different levels of exactness of mappings. METHODS: Concepts from preclinical and clinical terminologies used in eTRANSAFE have been mapped to the Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT). SNOMED CT acts as an intermediary terminology that provides the semantics to bridge between pre-coordinated clinical concepts and combinations of preclinical concepts with different levels of granularity. The mappings from clinical terminologies to SNOMED CT were taken from existing resources, while mappings from the preclinical terminologies to SNOMED CT were manually created. A coordination template defines the relation types that can be explored for a mapping and assigns a penalty score that reflects the inexactness of the mapping. A subset of 60 pre-coordinated concepts was mapped both with the Rosetta Stone semantic approach and with a lexical term matching approach. Both results were manually evaluated. RESULTS: A total of 34,308 concepts from preclinical terminologies (Histopathology terminology, Standard for Exchange of Nonclinical Data (SEND) code lists, Mouse Adult Gross Anatomy Ontology) and a clinical terminology (MedDRA) were mapped to SNOMED CT as the intermediary bridging terminology. A terminology service has been developed that returns dynamically the exact and inexact mappings between preclinical and clinical concepts. On the evaluation set, the precision of the mappings from the terminology service was high (95%), much higher than for lexical term matching (22%). CONCLUSION: The Rosetta Stone approach uses a semantically rich intermediate terminology to map between pre-coordinated clinical concepts and a combination of preclinical concepts with different levels of exactness. The possibility to generate not only exact but also inexact mappings allows to relate larger amounts of preclinical and clinical data, which can be helpful in translational use cases.
BASIL DB: bioactive semantic integration and linking database.
Jackson D, Groth P, Harmouch H
J Biomed Semantics · 2025 Aug · PMID 40804424 · Full text
BACKGROUND: Bioactive compounds found in foods and plants can provide health benefits, including antioxidant and anti-inflammatory effects. Research into their role in disease prevention and personalized nutrition is exp...
BACKGROUND: Bioactive compounds found in foods and plants can provide health benefits, including antioxidant and anti-inflammatory effects. Research into their role in disease prevention and personalized nutrition is expanding, but challenges such as data complexity, inconsistent methods, and the rapid growth of scientific literature can hinder progress. To address these issues, we developed BASIL DB (BioActive Semantic Integration and Linking Database), a knowledge graph (KG) database that leverages natural language processing (NLP) techniques to streamline data organization and analysis. This automated approach offers greater scalability and comprehensiveness than traditional methods such as manual data curation and entry. CONSTRUCTION AND CONTENT: The process of constructing the BASIL DB is divided into four fundamental steps: data collection, data preprocessing, data extraction, and data integration. Data on bioactives and foods are sourced from structured databases. The relevant randomized controlled trials (RCTs) were extracted from PubMed. The data are then prepared by cleaning inconsistencies and structuring them for analysis. In the data extraction phase, NLP tools, including a large language model (LLM), are utilized to analyze clinical trials and extract data on bioactive compounds and their health impacts. The integration phase compiles these data into a knowledge graph, which consists of the entities Foods, Bioactives, and Health Conditions as nodes and their interactions as edges. To quantify the relationships/interactions between these entities, we generate a weight for each edge on the basis of empirical evidence and methodological rigor. UTILITY AND DISCUSSION: The BASIL DB incorporates 433 compounds, 40296 research papers, 7256 health effects, and 4197 food items. The database features query and visualization capabilities, including interactive graphs and custom filtering options, that showcase different aspects of the data. Users are able to explore the relationships between bioactives and health effects, enhancing both research efficiency and insight discovery. CONCLUSION: The BASIL DB is a knowledge graph database of bioactive compounds. This study provides a structured resource for exploring the relationships among bioactives, foods, and health outcomes, representing a step toward a more systematic and data-driven approach to understanding the health effects of bioactive compounds. Future work will focus on expanding the database and refining the utilized methods. Extending the BASIL DB will help bridge the gap between traditional and conventional approaches to nutrition, guiding future research in bioactive compound discovery and health optimization. AVAILABILITY: Users can access and explore the data via https://basil-db.github.io/info.html or fork and run the respective script via https://github.com/basil-db/script .
Semantic classification of Indonesian consumer health questions.
Hanami RN, Mahendra R, Wicaksono AF
J Biomed Semantics · 2025 Jul · PMID 40721829 · Full text
PURPOSE: Online consumer health forums serve as a way for the public to connect with medical professionals. While these medical forums offer a valuable service, online Question Answering (QA) forums can struggle to deliv...
PURPOSE: Online consumer health forums serve as a way for the public to connect with medical professionals. While these medical forums offer a valuable service, online Question Answering (QA) forums can struggle to deliver timely answers due to the limited number of available healthcare professionals. One way to solve this problem is by developing an automatic QA system that can provide patients with quicker answers. One key component of such a system could be a module for classifying the semantic type of a question. This would allow the system to understand the patient's intent and route them towards the relevant information. METHODS: This paper proposes a novel two-step approach to address the challenge of semantic type classification in Indonesian consumer health questions. We acknowledge the scarcity of Indonesian health domain data, a hurdle for machine learning models. To address this gap, we first introduce a novel corpus of annotated Indonesian consumer health questions. Second, we utilize this newly created corpus to build and evaluate a data-driven predictive model for classifying question semantic types. To enhance the trustworthiness and interpretability of the model's predictions, we employ an explainable model framework, LIME. This framework facilitates a deeper understanding of the role played by word-based features in the model's decision-making process. Additionally, it empowers us to conduct a comprehensive bias analysis, allowing for the detection of "semantic bias", where words with no inherent association with a specific semantic type disproportionately influence the model's predictions. RESULTS: The annotation process revealed moderate agreement between expert annotators. In addition, not all words with high LIME probability could be considered true characteristics of a question type. This suggests a potential bias in the data used and the machine learning models themselves. Notably, XGBoost, Naïve Bayes, and MLP models exhibited a tendency to predict questions containing the words "kanker" (cancer) and "depresi" (depression) as belonging to the DIAGNOSIS category. In terms of prediction performance, Perceptron and XGBoost emerged as the top-performing models, achieving the highest weighted average F1 scores across all input scenarios and weighting factors. Naïve Bayes performed best after balancing the data with Borderline SMOTE, indicating its promise for handling imbalanced datasets. CONCLUSION: We constructed a corpus of query semantics in the domain of Indonesian consumer health, containing 964 questions annotated with their corresponding semantic types. This corpus served as the foundation for building a predictive model. We further investigated the impact of disease-biased words on model performance. These words exhibited high LIME scores, yet lacked association with a specific semantic type. We trained models using datasets with and without these biased words and found no significant difference in model performance between the two scenarios, suggesting that the models might possess an ability to mitigate the influence of such bias during the learning process.
A fourfold pathogen reference ontology suite.
Beverley J, Babcock S, Benson C … +8 more , De Colle G, Cohen S, Diehl AD, Challa RANR, Mavrovich RA, Billig J, Huffman A, He Y
J Biomed Semantics · 2025 Jul · PMID 40635066 · Full text
BACKGROUND: Infectious diseases remain a critical global health challenge, and the integration of standardized ontologies plays a vital role in managing related data. The Infectious Disease Ontology (IDO) and its extensi...
BACKGROUND: Infectious diseases remain a critical global health challenge, and the integration of standardized ontologies plays a vital role in managing related data. The Infectious Disease Ontology (IDO) and its extensions, such as the Coronavirus Infectious Disease Ontology (CIDO), are essential for organizing and disseminating information related to infectious diseases. The COVID-19 pandemic highlighted the need for updating IDO and its virus-specific extensions. There is an additional need to update IDO extensions specific to bacteria, fungus, and parasite infectious diseases. METHODS: The "hub-and-spoke" methodology is adopted to generate pathogen-specific extensions of IDO: Virus Infectious Disease Ontology (VIDO), Bacteria Infectious Disease Ontology (BIDO), Mycosis Infectious Disease Ontology (MIDO), and Parasite Infectious Disease Ontology (PIDO). RESULTS: IDO is introduced before reporting on the scopes, major classes and relations, applications and extensions of IDO to VIDO, BIDO, MIDO, and PIDO. CONCLUSIONS: The creation of pathogen-specific reference ontologies advances modularization and reusability of infectious disease ontologies within the IDO ecosystem. Future work will focus on further refining these ontologies, creating new extensions, and developing application ontologies based on them, in line with ongoing efforts to standardize biological and biomedical terminologies for improved data sharing, quality, and analysis.
medicX-KG: a knowledge graph for pharmacists' drug information needs.
Farrugia L, Azzopardi LM, Debattista J … +1 more , Abela C
J Biomed Semantics · 2025 Jul · PMID 40597373 · Full text
The role of pharmacists is evolving from medicine dispensing to delivering comprehensive pharmaceutical services within multidisciplinary healthcare teams. Central to this shift is access to accurate, up-to-date medicina...
The role of pharmacists is evolving from medicine dispensing to delivering comprehensive pharmaceutical services within multidisciplinary healthcare teams. Central to this shift is access to accurate, up-to-date medicinal product information supported by robust data integration. Leveraging artificial intelligence and semantic technologies, Knowledge Graphs (KGs) uncover hidden relationships and enable data-driven decision-making. This paper presents medicX-KG, a pharmacist-oriented knowledge graph supporting clinical and regulatory decisions. It forms the semantic layer of the broader medicX platform, powering predictive and explainable pharmacy services. medicX-KG integrates data from three sources, including, the British National Formulary (BNF), DrugBank, and the Malta Medicines Authority (MMA) that addresses Malta's regulatory landscape and combines European Medicines Agency alignment with partial UK supply dependence. The KG tackles the absence of a unified national drug repository, reducing pharmacists' reliance on fragmented sources. Its design was informed by interviews with practising pharmacists to ensure real-world applicability. We detail the KG's construction, including data extraction, ontology design, and semantic mapping. Evaluation demonstrates that medicX-KG effectively supports queries about drug availability, interactions, adverse reactions, and therapeutic classes. Limitations, including missing detailed dosage encoding and real-time updates, are discussed alongside directions for future enhancements.
Unveiling differential adverse event profiles in vaccines via LLM text embeddings and ontology semantic analysis.
Wang Z, Li X, Zheng J … +1 more , He Y
J Biomed Semantics · 2025 May · PMID 40410898 · Full text
BACKGROUND: Vaccines are crucial for preventing infectious diseases; however, they may also be associated with adverse events (AEs). Conventional analysis of vaccine AEs relies on manual review and assignment of AEs to t...
BACKGROUND: Vaccines are crucial for preventing infectious diseases; however, they may also be associated with adverse events (AEs). Conventional analysis of vaccine AEs relies on manual review and assignment of AEs to terms in terminology or ontology, which is a time-consuming process and constrained in scope. This study explores the potential of using Large Language Models (LLMs) and LLM text embeddings for efficient and comprehensive vaccine AE analysis. RESULTS: We used Llama-3 LLM to extract AE information from FDA-approved vaccine package inserts for 111 licensed vaccines, including 15 influenza vaccines. Text embeddings were then generated for each vaccine's AEs using the nomic-embed-text and mxbai-embed-large models. Llama-3 achieved over 80% accuracy in extracting AE text from vaccine package inserts. To further evaluate the performance of text embedding, the vaccines were clustered using two clustering methods: (1) LLM text embedding-based clustering and (2) ontology-based semantic similarity analysis. The ontology-based method mapped AEs to the Human Phenotype Ontology (HPO) and Ontology of Adverse Events (OAE), with semantic similarity analyzed using Lin's method. Text embeddings were generated for each vaccine's AE description using the LLM nomic-embed-text and mxbai-embed-large models. Compared to the semantic similarity analysis, the LLM approach was able to capture more differential AE profiles. Furthermore, LLM-derived text embeddings were used to develop a Lasso logistic regression model to predict whether a vaccine is "Live" or "Non-Live". The term "Non-Live" refers to all vaccines that do not contain live organisms, including inactivated and mRNA vaccines. A comparative analysis showed that, despite similar clustering patterns, the nomic-embed-text model outperformed the other. It achieved 80.00% sensitivity, 83.06% specificity, and 81.89% accuracy in a 10-fold cross-validation. Many AE patterns, with examples demonstrated, were identified from our analysis with AE LLM embeddings. CONCLUSION: This study demonstrates the effectiveness of LLMs for automated AE extraction and analysis, and LLM text embeddings capture latent information about AEs, enabling more comprehensive knowledge discovery. Our findings suggest that LLMs demonstrate substantial potential for improving vaccine safety and public health research.
The SPHN Schema Forge - transform healthcare semantics from human-readable to machine-readable by leveraging semantic web technologies.
Touré V, Unni D, Krauss P … +5 more , Abdelwahed A, Buchhorn J, Hinderling L, Geiger TR, Österle S
J Biomed Semantics · 2025 May · PMID 40341005 · Full text
BACKGROUND: The Swiss Personalized Health Network (SPHN) adopted the Resource Description Framework (RDF), a core component of the Semantic Web technology stack, for the formal encoding and exchange of healthcare data in...
BACKGROUND: The Swiss Personalized Health Network (SPHN) adopted the Resource Description Framework (RDF), a core component of the Semantic Web technology stack, for the formal encoding and exchange of healthcare data in a medical knowledge graph. The SPHN RDF Schema defines the semantics on how data elements should be represented. While RDF is proven to be machine readable and interpretable, it can be challenging for individuals without specialized background to read and understand the knowledge represented in RDF. For this reason, the semantics described in the SPHN RDF Schema are primarily defined in a user-accessible tabular format, the SPHN Dataset, before being translated into its RDF representation. However, this translation process was previously manual, time-consuming and labor-intensive. RESULT: To automate and streamline the translation from tabular to RDF representation, the SPHN Schema Forge web service was developed. With a few clicks, this tool automatically converts an SPHN-compliant Dataset spreadsheet into an RDF schema. Additionally, it generates SHACL rules for data validation, an HTML visualization of the schema and SPARQL queries for basic data analysis. CONCLUSION: The SPHN Schema Forge significantly reduces the manual effort and time required for schema generation, enabling researchers to focus on more meaningful tasks such as data interpretation and analysis within the SPHN framework.
Sentences, entities, and keyphrases extraction from consumer health forums using multi-task learning.
Naufal T, Mahendra R, Wicaksono AF
J Biomed Semantics · 2025 May · PMID 40329333 · Full text
PURPOSE: Online consumer health forums offer an alternative source of health-related information for internet users seeking specific details that may not be readily available through articles or other one-way communicati...
PURPOSE: Online consumer health forums offer an alternative source of health-related information for internet users seeking specific details that may not be readily available through articles or other one-way communication channels. However, the effectiveness of these forums can be constrained by the limited number of healthcare professionals actively participating, which can impact response times to user inquiries. One potential solution to this issue is the integration of a semi-automatic system. A critical component of such a system is question processing, which often involves sentence recognition (SR), medical entity recognition (MER), and keyphrase extraction (KE) modules. We posit that the development of these three modules would enable the system to identify critical components of the question, thereby facilitating a deeper understanding of the question, and allowing for the re-formulation of more effective questions with extracted key information. METHODS: This work contributes to two key aspects related to these three tasks. First, we expand and publicly release an Indonesian dataset for each task. Second, we establish a baseline for all three tasks within the Indonesian language domain by employing transformer-based models with nine distinct encoder variations. Our feature studies revealed an interdependence among these three tasks. Consequently, we propose several multi-task learning (MTL) models, both in pairwise and three-way configurations, incorporating parallel and hierarchical architectures. RESULTS: Using F1-score at the chunk level, the inter-annotator agreements for SR, MER, and KE tasks were , and respectively. In single-task learning (STL) settings, the best performance for each task was achieved by different model, with obtained the highest average score. These results suggested that a larger model did not always perform better. We also found no indication of which ones between Indonesian and multilingual language models that generally performed better for our tasks. In pairwise MTL settings, we found that pairing tasks could outperform the STL baseline for all three tasks. Despite varying loss weights across our three-way MTL models, we did not identify a consistent pattern. While some configurations improved MER and KE performance, none surpassed the best pairwise MTL model for the SR task. CONCLUSION: We extended an Indonesian dataset for SR, MER, and KE tasks, resulted in 1, 173 labeled data points which splitted into 773 training instances, 200 validation instances, and 200 testing instances. We then used transformer-based models to set a baseline for all three tasks. Our MTL experiments suggested that additional information regarding the other two tasks could help the learning process for MER and KE tasks, while had only a small effect for SR task.
Semantics in action: a guide for representing clinical data elements with SNOMED CT.
Ehrsam J, Gaudet-Blavignac C, Mattei M … +2 more , Baumann M, Lovis C
J Biomed Semantics · 2025 Mar · PMID 40149003 · Full text
BACKGROUND: Clinical data is abundant, but meaningful reuse remains lacking. Semantic representation using SNOMED CT can improve research, public health, and quality of care. However, the lack of applied guidelines to in...
BACKGROUND: Clinical data is abundant, but meaningful reuse remains lacking. Semantic representation using SNOMED CT can improve research, public health, and quality of care. However, the lack of applied guidelines to industrialise the process hinders sustainability and reproducibility. This work describes a guide for semantic representation of data elements with SNOMED CT, addressing challenges encountered during its application. The representation of the institutional data warehouse started with the guidelines proposed by SNOMED International and other groups. However, the application at large scale of manual expert-driven representation led to the development of additional rules. RESULTS: An eight-rule step-by-step guide was developed iteratively through focus groups. Continuously refined by usage and growing coverage, they are tested in practice to ensure they achieve the desired outcome. All rules prioritize maintaining semantic accuracy, which is the main goal of our strategy. They are divided into four groups which apply to understanding the data correctly (Context), and to using SNOMED CT properly (Single concepts first, Approved post-coordination, Extending post-coordination). CONCLUSIONS: This work provides a practical framework for semantic representation using SNOMED CT, enabling greater accuracy and consistency by promoting a common method. While addressing challenges of large-scale implementation, the guide supports the drive from data centric models to a semantic centric approach, leveraging interoperability and more effective reuse of clinical data.
Standardizing free-text data exemplified by two fields from the Immune Epitope Database.
Duesing S, Bennett J, Overton JA … +2 more , Vita R, Peters B
J Biomed Semantics · 2025 Mar · PMID 40121509 · Full text
BACKGROUND: While unstructured data, such as free text, constitutes a large amount of publicly available biomedical data, it is underutilized in automated analyses due to the difficulty of extracting meaning from it. Nor...
BACKGROUND: While unstructured data, such as free text, constitutes a large amount of publicly available biomedical data, it is underutilized in automated analyses due to the difficulty of extracting meaning from it. Normalizing free-text data, i.e., removing inessential variance, enables the use of structured vocabularies like ontologies to represent the data and allow for harmonized queries over it. This paper presents an adaptable tool for free-text normalization and an evaluation of the application of this tool to two different fields curated from the literature in the Immune Epitope Database (IEDB): "age" and "data-location" (the part of a paper in which data was found). RESULTS: Free text entries for the database fields for subject age (4095 distinct values) and publication data-location (251,810 distinct values) in the IEDB were analyzed. Normalization was performed in three steps, namely character normalization, word normalization, and phrase normalization, using generalizable rules developed and applied with the tool presented in this manuscript. For the age dataset, in the character stage, the application of 21 rules resulted in 99.97% output validity; in the word stage, the application of 94 rules resulted in 98.06% output validity; and in the phrase stage, the application of 16 rules resulted in 83.81% output validity. For the data-location dataset, in the character stage, the application of 39 rules resulted in 99.99% output validity; in the word stage, the application of 187 rules resulted in 98.46% output validity; and in the phrase stage, the application of 12 rules resulted in 97.95% output validity. CONCLUSIONS: We developed a generalizable approach for normalization of free text as found in database fields with content on a specific topic. Creating and testing the rules took a one-time effort for a given field that can now be applied to data as it is being curated. The standardization achieved in two datasets tested produces significantly reduced variance in the content which enhances the findability and usability of that data, chiefly by improving search functionality and enabling linkages with formal ontologies.
Digital evolution: Novo Nordisk's shift to ontology-based data management.
Tan SZK, Baksi S, Bjerregaard TG … +9 more , Elangovan P, Gopalakrishnan TK, Hric D, Joumaa J, Li B, Rabbani K, Venkatesan SK, Valdez JD, Kuriakose SV
J Biomed Semantics · 2025 Mar · PMID 40121504 · Full text
The amount of biomedical data is growing, and managing it is increasingly challenging. While Findable, Accessible, Interoperable and Reusable (FAIR) data principles provide guidance, their adoption has proven difficult,...
The amount of biomedical data is growing, and managing it is increasingly challenging. While Findable, Accessible, Interoperable and Reusable (FAIR) data principles provide guidance, their adoption has proven difficult, especially in larger enterprises like pharmaceutical companies. In this manuscript, we describe how we leverage an Ontology-Based Data Management (OBDM) strategy for digital transformation in Novo Nordisk Research & Early Development. Here, we include both our technical blueprint and our approach for organizational change management. We further discuss how such an OBDM ecosystem plays a pivotal role in the organization's digital aspirations for data federation and discovery fuelled by artificial intelligence. Our aim for this paper is to share the lessons learned in order to foster dialogue with parties navigating similar waters while collectively advancing the efforts in the fields of data management, semantics and data driven drug discovery.
Enriched knowledge representation in biological fields: a case study of literature-based discovery in Alzheimer's disease.
Pu Y, Beck D, Verspoor K
J Biomed Semantics · 2025 Mar · PMID 40114255 · Full text
BACKGROUND: In Literature-based Discovery (LBD), Swanson's original ABC model brought together isolated public knowledge statements and assembled them to infer putative hypotheses via logical connections. Modern LBD stud...
BACKGROUND: In Literature-based Discovery (LBD), Swanson's original ABC model brought together isolated public knowledge statements and assembled them to infer putative hypotheses via logical connections. Modern LBD studies that scale up this approach through automation typically rely on a simple entity-based knowledge graph with co-occurrences and/or semantic triples as basic building blocks. However, our analysis of a knowledge graph constructed for a recent LBD system reveals limitations arising from such pairwise representations, which further negatively impact knowledge inference. Using LBD as the context and motivation in this work, we explore limitations of using pairwise relationships only as knowledge representation in knowledge graphs, and we identify impacts of these limitations on knowledge inference. We argue that enhanced knowledge representation is beneficial for biological knowledge representation in general, as well as for both the quality and the specificity of hypotheses proposed with LBD. RESULTS: Based on a systematic analysis of one co-occurrence-based LBD system focusing on Alzheimer's Disease, we identify 7 types of limitations arising from the exclusive use of pairwise relationships in a standard knowledge graph-including the need to capture more than two entities interacting together in a single event-and 3 types of negative impacts on knowledge inferred with the graph-Experimentally infeasible hypotheses, Literature-inconsistent hypotheses, and Oversimplified hypotheses explanations. We also present an indicative distribution of different types of relationships. Pairwise relationships are an essential component in representation frameworks for knowledge discovery. However, only 20% of discoveries are perfectly represented with pairwise relationships alone. 73% require a combination of pairwise relationships and nested relationships. The remaining 7% are represented with pairwise relationships, nested relationships, and hypergraphs. CONCLUSION: We argue that the standard entity pair-based knowledge graph, while essential for representing basic binary relations, results in important limitations for comprehensive biological knowledge representation and impacts downstream tasks such as proposing meaningful discoveries in LBD. These limitations can be mitigated by integrating more semantically complex knowledge representation strategies, including capturing collective interactions and allowing for nested entities. The use of more sophisticated knowledge representation will benefit biological fields with more expressive knowledge graphs. Downstream tasks, such as LBD, can benefit from richer representations as well, allowing for generation of implicit knowledge discoveries and explanations for disease diagnosis, treatment, and mechanism that are more biologically meaningful.
New and revised gene ontology biological process terms describe multiorganism interactions critical for understanding microbial pathogenesis and sequences of concern.
Godbold G, Proescher J, Gaudet P
J Biomed Semantics · 2025 Mar · PMID 40114175 · Full text
BACKGROUND: There is a new framework from the United States government for screening synthetic nucleic acids. Beginning in October of 2026, it calls for the screening of sequences 50 nucleotides or greater in length that...
BACKGROUND: There is a new framework from the United States government for screening synthetic nucleic acids. Beginning in October of 2026, it calls for the screening of sequences 50 nucleotides or greater in length that are known to contribute to pathogenicity or toxicity for humans, regardless of the taxa from which it originates. Distinguishing sequences that encode pathogenic and toxic functions from those that lack them is not simple. OBJECTIVES: Our project scope was to discern, describe, and catalog sequences involved in microbial pathogenesis from the scientific literature. We recognize a need for better terminology to designate pathogenic functions that are relevant across the entire range of existing parasites. METHODS: We canvassed publications investigating microbial pathogens of humans, other animals, and some plants to collect thousands of sequences that enable the exploitation of hosts. We compared sequences to each other, grouping them according to what host biological processes they subvert and the consequence(s) for the host. We developed terms to capture many of the varied pathogenic functions for sequences employed by parasitic microbes for host exploitation and applied these terms in a systematic manner to our dataset of sequences. RESULTS/CONCLUSIONS: The enhanced and expanded terms enable a quick and pertinent evaluation of a sequence's ability to endow a microbe with pathogenic function when they are appropriately applied to relevant sequences. This will allow providers of synthetic nucleic acids to rapidly assess sequences ordered by their customers for pathogenic capacity. This will help fulfill the new US government guidance.
Gene expression knowledge graph for patient representation and diabetes prediction.
Sousa RT, Paulheim H
J Biomed Semantics · 2025 Mar · PMID 40057806 · Full text
Diabetes is a worldwide health issue affecting millions of people. Machine learning methods have shown promising results in improving diabetes prediction, particularly through the analysis of gene expression data. While...
Diabetes is a worldwide health issue affecting millions of people. Machine learning methods have shown promising results in improving diabetes prediction, particularly through the analysis of gene expression data. While gene expression data can provide valuable insights, challenges arise from the fact that the number of patients in expression datasets is usually limited, and the data from different datasets with different gene expressions cannot be easily combined. This work proposes a novel approach to address these challenges by integrating multiple gene expression datasets and domain-specific knowledge using knowledge graphs, a unique tool for biomedical data integration, and to learn uniform patient representations for subjects contained in different incompatible datasets. Different strategies and KG embedding methods are explored to generate vector representations, serving as inputs for a classifier. Extensive experiments demonstrate the efficacy of our approach, revealing weighted F1-score improvements in diabetes prediction up to 13% when integrating multiple gene expression datasets and domain-specific knowledge about protein functions and interactions.
Expanding the concept of ID conversion in TogoID by introducing multi-semantic and label features.
Ikeda S, Aoki-Kinoshita KF, Chiba H … +10 more , Goto S, Hosoda M, Kawashima S, Kim JD, Moriya Y, Ohta T, Ono H, Takatsuki T, Yamamoto Y, Katayama T
J Biomed Semantics · 2025 Jan · PMID 39780290 · Full text
BACKGROUND: TogoID ( https://togoid.dbcls.jp/ ) is an identifier (ID) conversion service designed to link IDs across diverse categories of life science databases. With its ability to obtain IDs related in different seman...
BACKGROUND: TogoID ( https://togoid.dbcls.jp/ ) is an identifier (ID) conversion service designed to link IDs across diverse categories of life science databases. With its ability to obtain IDs related in different semantic relationships, a user-friendly web interface, and a regular automatic data update system, TogoID has been a valuable tool for bioinformatics. RESULTS: We have recently expanded TogoID's ability to represent semantics between datasets, enabling it to handle multiple semantic relationships within dataset pairs. This enhancement enables TogoID to distinguish relationships such as "glycans bind to proteins" or "glycans are processed by proteins" between glycans and proteins. Additional new features include the ability to display labels corresponding to database IDs, making it easier to interpret the relationships between the various IDs available in TogoID, and the ability to convert labels to IDs, extending the entry point for ID conversion. The implementation of URL parameters, which reproduces the state of TogoID's web application, allows users to share complex search results through a simple URL. CONCLUSIONS: These advancements improve TogoID's utility in bioinformatics, allowing researchers to explore complex ID relationships. By introducing the tool's multi-semantic and label features, TogoID expands the concept of ID conversion and supports more comprehensive and efficient data integration across life science databases.
FAIR Data Cube, a FAIR data infrastructure for integrated multi-omics data analysis.
Liao X, Ederveen THA, Niehues A … +11 more , de Visser C, Huang J, Badmus F, Doornbos C, Orlova Y, Kulkarni P, van der Velde KJ, Swertz MA, Brandt M, van Gool AJ, 't Hoen PAC
J Biomed Semantics · 2024 Dec · PMID 39732721 · Full text
MOTIVATION: We are witnessing an enormous growth in the amount of molecular profiling (-omics) data. The integration of multi-omics data is challenging. Moreover, human multi-omics data may be privacy-sensitive and can b...
MOTIVATION: We are witnessing an enormous growth in the amount of molecular profiling (-omics) data. The integration of multi-omics data is challenging. Moreover, human multi-omics data may be privacy-sensitive and can be misused to de-anonymize and (re-)identify individuals. Hence, most biomedical data is kept in secure and protected silos. Therefore, it remains a challenge to re-use these data without infringing the privacy of the individuals from which the data were derived. Federated analysis of Findable, Accessible, Interoperable, and Reusable (FAIR) data is a privacy-preserving solution to make optimal use of these multi-omics data and transform them into actionable knowledge. RESULTS: The Netherlands X-omics Initiative is a National Roadmap Large-Scale Research Infrastructure aiming for efficient integration of data generated within X-omics and external datasets. To facilitate this, we developed the FAIR Data Cube (FDCube), which adopts and applies the FAIR principles and helps researchers to create FAIR data and metadata, to facilitate re-use of their data, and to make their data analysis workflows transparent, and in the meantime ensure data security and privacy.
Dynamic Retrieval Augmented Generation of Ontologies using Artificial Intelligence (DRAGON-AI).
Toro S, Anagnostopoulos AV, Bello SM … +27 more , Blumberg K, Cameron R, Carmody L, Diehl AD, Dooley DM, Duncan WD, Fey P, Gaudet P, Harris NL, Joachimiak MP, Kiani L, Lubiana T, Munoz-Torres MC, O'Neil S, Osumi-Sutherland D, Puig-Barbe A, Reese JT, Reiser L, Robb SM, Ruemping T, Seager J, Sid E, Stefancsik R, Weber M, Wood V, Haendel MA, Mungall CJ
J Biomed Semantics · 2024 Oct · PMID 39415214 · Full text
BACKGROUND: Ontologies are fundamental components of informatics infrastructure in domains such as biomedical, environmental, and food sciences, representing consensus knowledge in an accurate and computable form. Howeve...
BACKGROUND: Ontologies are fundamental components of informatics infrastructure in domains such as biomedical, environmental, and food sciences, representing consensus knowledge in an accurate and computable form. However, their construction and maintenance demand substantial resources and necessitate substantial collaboration between domain experts, curators, and ontology experts. We present Dynamic Retrieval Augmented Generation of Ontologies using AI (DRAGON-AI), an ontology generation method employing Large Language Models (LLMs) and Retrieval Augmented Generation (RAG). DRAGON-AI can generate textual and logical ontology components, drawing from existing knowledge in multiple ontologies and unstructured text sources. RESULTS: We assessed performance of DRAGON-AI on de novo term construction across ten diverse ontologies, making use of extensive manual evaluation of results. Our method has high precision for relationship generation, but has slightly lower precision than from logic-based reasoning. Our method is also able to generate definitions deemed acceptable by expert evaluators, but these scored worse than human-authored definitions. Notably, evaluators with the highest level of confidence in a domain were better able to discern flaws in AI-generated definitions. We also demonstrated the ability of DRAGON-AI to incorporate natural language instructions in the form of GitHub issues. CONCLUSIONS: These findings suggest DRAGON-AI's potential to substantially aid the manual ontology construction process. However, our results also underscore the importance of having expert curators and ontology editors drive the ontology generation process.
MeSH2Matrix: combining MeSH keywords and machine learning for biomedical relation classification based on PubMed.
Turki H, Dossou BFP, Emezue CC … +5 more , Owodunni AT, Hadj Taieb MA, Ben Aouicha M, Ben Hassen H, Masmoudi A
J Biomed Semantics · 2024 Oct · PMID 39354632 · Full text
Biomedical relation classification has been significantly improved by the application of advanced machine learning techniques on the raw texts of scholarly publications. Despite this improvement, the reliance on large ch...
Biomedical relation classification has been significantly improved by the application of advanced machine learning techniques on the raw texts of scholarly publications. Despite this improvement, the reliance on large chunks of raw text makes these algorithms suffer in terms of generalization, precision, and reliability. The use of the distinctive characteristics of bibliographic metadata can prove effective in achieving better performance for this challenging task. In this research paper, we introduce an approach for biomedical relation classification using the qualifiers of co-occurring Medical Subject Headings (MeSH). First of all, we introduce MeSH2Matrix, our dataset consisting of 46,469 biomedical relations curated from PubMed publications using our approach. Our dataset includes a matrix that maps associations between the qualifiers of subject MeSH keywords and those of object MeSH keywords. It also specifies the corresponding Wikidata relation type and the superclass of semantic relations for each relation. Using MeSH2Matrix, we build and train three machine learning models (Support Vector Machine [SVM], a dense model [D-Model], and a convolutional neural network [C-Net]) to evaluate the efficiency of our approach for biomedical relation classification. Our best model achieves an accuracy of 70.78% for 195 classes and 83.09% for five superclasses. Finally, we provide confusion matrix and extensive feature analyses to better examine the relationship between the MeSH qualifiers and the biomedical relations being classified. Our results will hopefully shed light on developing better algorithms for biomedical ontology classification based on the MeSH keywords of PubMed publications. For reproducibility purposes, MeSH2Matrix, as well as all our source codes, are made publicly accessible at https://github.com/SisonkeBiotik-Africa/MeSH2Matrix .
Annotation of epilepsy clinic letters for natural language processing.
Fonferko-Shadrach B, Strafford H, Jones C … +10 more , Khan RA, Brown S, Edwards J, Hawken J, Shrimpton LE, White CP, Powell R, Sawhney IMS, Pickrell WO, Lacey AS
J Biomed Semantics · 2024 Sep · PMID 39277770 · Full text
BACKGROUND: Natural language processing (NLP) is increasingly being used to extract structured information from unstructured text to assist clinical decision-making and aid healthcare research. The availability of expert...
BACKGROUND: Natural language processing (NLP) is increasingly being used to extract structured information from unstructured text to assist clinical decision-making and aid healthcare research. The availability of expert-annotated documents for the development and validation of NLP applications is limited. We created synthetic clinical documents to address this, and to validate the Extraction of Epilepsy Clinical Text version 2 (ExECTv2) NLP pipeline. METHODS: We created 200 synthetic clinic letters based on hospital outpatient consultations with epilepsy specialists. The letters were double annotated by trained clinicians and researchers according to agreed guidelines. We used the annotation tool, Markup, with an epilepsy concept list based on the Unified Medical Language System ontology. All annotations were reviewed, and a gold standard set of annotations was agreed and used to validate the performance of ExECTv2. RESULTS: The overall inter-annotator agreement (IAA) between the two sets of annotations produced a per item F1 score of 0.73. Validating ExECTv2 using the gold standard gave an overall F1 score of 0.87 per item, and 0.90 per letter. CONCLUSION: The synthetic letters, annotations, and annotation guidelines have been made freely available. To our knowledge, this is the first publicly available set of annotated epilepsy clinic letters and guidelines that can be used for NLP researchers with minimum epilepsy knowledge. The IAA results show that clinical text annotation tasks are difficult and require a gold standard to be arranged by researcher consensus. The results for ExECTv2, our automated epilepsy NLP pipeline, extracted detailed epilepsy information from unstructured epilepsy letters with more accuracy than human annotators, further confirming the utility of NLP for clinical and research applications.
About
- Frequency
- Sun
- Papers found
- 200
- RSS feed
- Subscribe