Journal of Biomedical Semantics最新文献

Current animal protection laws require replacement of animal experiments with alternative methods, whenever such methods are suitable to reach the intended scientific objective. However, searching for alternative methods in the scientific literature is a time-consuming task that requires careful screening of an enormously large number of experimental biomedical publications. The identification of potentially relevant methods, e.g. organ or cell culture models, or computer simulations, can be supported with text mining tools specifically built for this purpose. Such tools are trained (or fine tuned) on relevant data sets labeled by human experts. We developed the GoldHamster corpus, composed of 1,600 PubMed (Medline) articles (titles and abstracts), in which we manually identified the used experimental model according to a set of eight labels, namely: "in vivo", "organs", "primary cells", "immortal cell lines", "invertebrates", "humans", "in silico" and "other" (models). We recruited 13 annotators with expertise in the biomedical domain and assigned each article to two individuals. Four additional rounds of annotation aimed at improving the quality of the annotations with disagreements in the first round. Furthermore, we conducted various machine learning experiments based on supervised learning to evaluate the corpus for our classification task. We obtained more than 7,000 document-level annotations for the above labels. After the first round of annotation, the inter-annotator agreement (kappa coefficient) varied among labels, and ranged from 0.42 (for "others") to 0.82 (for "invertebrates"), with an overall score of 0.62. All disagreements were resolved in the subsequent rounds of annotation. The best-performing machine learning experiment used the PubMedBERT pre-trained model with fine-tuning to our corpus, which gained an overall f-score of 0.83. We obtained a corpus with high agreement for all labels, and our evaluation demonstrated that our corpus is suitable for training reliable predictive models for automatic classification of biomedical literature according to the used experimental models. Our SMAFIRA - "Smart feature-based interactive" - search tool ( https://smafira.bf3r.de ) will employ this classifier for supporting the retrieval of alternative methods to animal experiments. The corpus is available for download ( https://doi.org/10.5281/zenodo.7152295 ), as well as the source code ( https://github.com/mariananeves/goldhamster ) and the model ( https://huggingface.co/SMAFIRA/goldhamster ).

Background: This paper proposes Cyrus, a new transparency evaluation framework, for Open Knowledge Extraction (OKE) systems. Cyrus is based on the state-of-the-art transparency models and linked data quality assessment dimensions. It brings together a comprehensive view of transparency dimensions for OKE systems. The Cyrus framework is used to evaluate the transparency of three linked datasets, which are built from the same corpus by three state-of-the-art OKE systems. The evaluation is automatically performed using a combination of three state-of-the-art FAIRness (Findability, Accessibility, Interoperability, Reusability) assessment tools and a linked data quality evaluation framework, called Luzzu. This evaluation includes six Cyrus data transparency dimensions for which existing assessment tools could be identified. OKE systems extract structured knowledge from unstructured or semi-structured text in the form of linked data. These systems are fundamental components of advanced knowledge services. However, due to the lack of a transparency framework for OKE, most OKE systems are not transparent. This means that their processes and outcomes are not understandable and interpretable. A comprehensive framework sheds light on different aspects of transparency, allows comparison between the transparency of different systems by supporting the development of transparency scores, gives insight into the transparency weaknesses of the system, and ways to improve them. Automatic transparency evaluation helps with scalability and facilitates transparency assessment. The transparency problem has been identified as critical by the European Union Trustworthy Artificial Intelligence (AI) guidelines. In this paper, Cyrus provides the first comprehensive view of transparency dimensions for OKE systems by merging the perspectives of the FAccT (Fairness, Accountability, and Transparency), FAIR, and linked data quality research communities.

Results: In Cyrus, data transparency includes ten dimensions which are grouped in two categories. In this paper, six of these dimensions, i.e., provenance, interpretability, understandability, licensing, availability, interlinking have been evaluated automatically for three state-of-the-art OKE systems, using the state-of-the-art metrics and tools. Covid-on-the-Web is identified to have the highest mean transparency.

Conclusions: This is the first research to study the transparency of OKE systems that provides a comprehensive set of transparency dimensions spanning ethics, trustworthy AI, and data quality approaches to transparency. It also demonstrates how to perform automated transparency evaluation that combines existing FAIRness and linked data quality assessment tools for the first time. We show that state-of-the-art OKE systems vary in the transparency of the linked data generated and that these differences can be automatically quantified leading to potential

Background: Predicting gene-disease associations typically requires exploring diverse sources of information as well as sophisticated computational approaches. Knowledge graph embeddings can help tackle these challenges by creating representations of genes and diseases based on the scientific knowledge described in ontologies, which can then be explored by machine learning algorithms. However, state-of-the-art knowledge graph embeddings are produced over a single ontology or multiple but disconnected ones, ignoring the impact that considering multiple interconnected domains can have on complex tasks such as gene-disease association prediction.

Results: We propose a novel approach to predict gene-disease associations using rich semantic representations based on knowledge graph embeddings over multiple ontologies linked by logical definitions and compound ontology mappings. The experiments showed that considering richer knowledge graphs significantly improves gene-disease prediction and that different knowledge graph embeddings methods benefit more from distinct types of semantic richness.

Conclusions: This work demonstrated the potential for knowledge graph embeddings across multiple and interconnected biomedical ontologies to support gene-disease prediction. It also paved the way for considering other ontologies or tackling other tasks where multiple perspectives over the data can be beneficial. All software and data are freely available.

With the capacity to produce and record data electronically, Scientific research and the data associated with it have grown at an unprecedented rate. However, despite a decent amount of data now existing in an electronic form, it is still common for scientific research to be recorded in an unstructured text format with inconsistent context (vocabularies) which vastly reduces the potential for direct intelligent analysis. Research has demonstrated that the use of semantic technologies such as ontologies to structure and enrich scientific data can greatly improve this potential. However, whilst there are many ontologies that can be used for this purpose, there is still a vast quantity of scientific terminology that does not have adequate semantic representation. A key area for expansion identified by the authors was the pharmacokinetic/pharmacodynamic (PK/PD) domain due to its high usage across many areas of Pharma. As such we have produced a set of these terms and other bioassay related terms to be incorporated into the BioAssay Ontology (BAO), which was identified as the most relevant ontology for this work. A number of use cases developed by experts in the field were used to demonstrate how these new ontology terms can be used, and to set the scene for the continuation of this work with a look to expanding this work out into further relevant domains. The work done in this paper was part of Phase 1 of the SEED project (Semantically Enriching electronic laboratory notebook (eLN) Data).

Motivation: Phenotypes are observable characteristics of an organism and they can be highly variable. Information about phenotypes is collected in a clinical context to characterize disease, and is also collected in model organisms and stored in model organism databases where they are used to understand gene functions. Phenotype data is also used in computational data analysis and machine learning methods to provide novel insights into disease mechanisms and support personalized diagnosis of disease. For mammalian organisms and in a clinical context, ontologies such as the Human Phenotype Ontology and the Mammalian Phenotype Ontology are widely used to formally and precisely describe phenotypes. We specifically analyze axioms pertaining to phenotypes of collections of entities within a body, and we find that some of the axioms in phenotype ontologies lead to inferences that may not accurately reflect the underlying biological phenomena.

Results: We reformulate the phenotypes of collections of entities using an ontological theory of collections. By reformulating phenotypes of collections in phenotypes ontologies, we avoid potentially incorrect inferences pertaining to the cardinality of these collections. We apply our method to two phenotype ontologies and show that the reformulation not only removes some problematic inferences but also quantitatively improves biological data analysis.

Background: Clinical decision support systems have been widely deployed to guide healthcare decisions on patient diagnosis, treatment choices, and patient management through evidence-based recommendations. These recommendations are typically derived from clinical practice guidelines created by clinical specialties or healthcare organizations. Although there have been many different technical approaches to encoding guideline recommendations into decision support systems, much of the previous work has not focused on enabling system generated recommendations through the formalization of changes in a guideline, the provenance of a recommendation, and applicability of the evidence. Prior work indicates that healthcare providers may not find that guideline-derived recommendations always meet their needs for reasons such as lack of relevance, transparency, time pressure, and applicability to their clinical practice.

Results: We introduce several semantic techniques that model diseases based on clinical practice guidelines, provenance of the guidelines, and the study cohorts they are based on to enhance the capabilities of clinical decision support systems. We have explored ways to enable clinical decision support systems with semantic technologies that can represent and link to details in related items from the scientific literature and quickly adapt to changing information from the guidelines, identifying gaps, and supporting personalized explanations. Previous semantics-driven clinical decision systems have limited support in all these aspects, and we present the ontologies and semantic web based software tools in three distinct areas that are unified using a standard set of ontologies and a custom-built knowledge graph framework: (i) guideline modeling to characterize diseases, (ii) guideline provenance to attach evidence to treatment decisions from authoritative sources, and (iii) study cohort modeling to identify relevant research publications for complicated patients.

Conclusions: We have enhanced existing, evidence-based knowledge by developing ontologies and software that enables clinicians to conveniently access updates to and provenance of guidelines, as well as gather additional information from research studies applicable to their patients' unique circumstances. Our software solutions leverage many well-used existing biomedical ontologies and build upon decades of knowledge representation and reasoning work, leading to explainable results.

The current rise of Open Science and Reproducibility in the Life Sciences requires the creation of rich, machine-actionable metadata in order to better share and reuse biological digital resources such as datasets, bioinformatics tools, training materials, etc. For this purpose, FAIR principles have been defined for both data and metadata and adopted by large communities, leading to the definition of specific metrics. However, automatic FAIRness assessment is still difficult because computational evaluations frequently require technical expertise and can be time-consuming. As a first step to address these issues, we propose FAIR-Checker, a web-based tool to assess the FAIRness of metadata presented by digital resources. FAIR-Checker offers two main facets: a "Check" module providing a thorough metadata evaluation and recommendations, and an "Inspect" module which assists users in improving metadata quality and therefore the FAIRness of their resource. FAIR-Checker leverages Semantic Web standards and technologies such as SPARQL queries and SHACL constraints to automatically assess FAIR metrics. Users are notified of missing, necessary, or recommended metadata for various resource categories. We evaluate FAIR-Checker in the context of improving the FAIRification of individual resources, through better metadata, as well as analyzing the FAIRness of more than 25 thousand bioinformatics software descriptions.

Background: The Findable, Accessible, Interoperable and Reusable(FAIR) Principles explicitly require the use of FAIR vocabularies, but what precisely constitutes a FAIR vocabulary remains unclear. Being able to define FAIR vocabularies, identify features of FAIR vocabularies, and provide assessment approaches against the features can guide the development of vocabularies.

Results: We differentiate data, data resources and vocabularies used for FAIR, examine the application of the FAIR Principles to vocabularies, align their requirements with the Open Biomedical Ontologies principles, and propose FAIR Vocabulary Features. We also design assessment approaches for FAIR vocabularies by mapping the FVFs with existing FAIR assessment indicators. Finally, we demonstrate how they can be used for evaluating and improving vocabularies using exemplary biomedical vocabularies.

Conclusions: Our work proposes features of FAIR vocabularies and corresponding indicators for assessing the FAIR levels of different types of vocabularies, identifies use cases for vocabulary engineers, and guides the evolution of vocabularies.

Background: Drug-drug interaction (DDI) information retrieval (IR) is an important natural language process (NLP) task from the PubMed literature. For the first time, active learning (AL) is studied in DDI IR analysis. DDI IR analysis from PubMed abstracts faces the challenges of relatively small positive DDI samples among overwhelmingly large negative samples. Random negative sampling and positive sampling are purposely designed to improve the efficiency of AL analysis. The consistency of random negative sampling and positive sampling is shown in the paper.

Results: PubMed abstracts are divided into two pools. Screened pool contains all abstracts that pass the DDI keywords query in PubMed, while unscreened pool includes all the other abstracts. At a prespecified recall rate of 0.95, DDI IR analysis precision is evaluated and compared. In screened pool IR analysis using supporting vector machine (SVM), similarity sampling plus uncertainty sampling improves the precision over uncertainty sampling, from 0.89 to 0.92 respectively. In the unscreened pool IR analysis, the integrated random negative sampling, positive sampling, and similarity sampling improve the precision over uncertainty sampling along, from 0.72 to 0.81 respectively. When we change the SVM to a deep learning method, all sampling schemes consistently improve DDI AL analysis in both screened pool and unscreened pool. Deep learning has significant improvement of precision over SVM, 0.96 vs. 0.92 in screened pool, and 0.90 vs. 0.81 in the unscreened pool, respectively.

Conclusions: By integrating various sampling schemes and deep learning algorithms into AL, the DDI IR analysis from literature is significantly improved. The random negative sampling and positive sampling are highly effective methods in improving AL analysis where the positive and negative samples are extremely imbalanced.

The majority of available datasets in open government data are statistical. They are widely published by various governments to be used by the public and data consumers. However, most open government data portals do not provide the five-star Linked Data standard datasets. The published datasets are isolated from one another while conceptually connected. This paper constructs a knowledge graph for the disease-related datasets of a Canadian government data portal, Nova Scotia Open Data. We leveraged the Semantic Web technologies to transform the disease-related datasets into Resource Description Framework (RDF) and enriched them with semantic rules. An RDF data model using the RDF Cube vocabulary was designed in this work to develop a graph that adheres to best practices and standards, allowing for expansion, modification and flexible re-use. The study also discusses the lessons learned during the cross-dimensional knowledge graph construction and integration of open statistical datasets from multiple sources.