Mercedes Argüello Casteleiro

Clinical practice guidelines: A case study of combining OWL-S, OWL, and SWRL

As the number of available Web services increases there is a growing demand to realise complex business processes by combining and reusing available Web services. In this context, the Ontology Web Language for Services (OWL-S) can be used to specify semantic types of the input and output data of a Web service and its functionality. This paper uses OWL-S to describe Web services and takes advantage of a XML syntax based on the OWL Web Ontology Language to encode OWL domain ontology fragments and SWRL rule fragments as the inputs and outputs of Web services. The approach presented outlines the use of the OWLs XML presentation syntax to obtain Web services that provide reasoning support and easily deal with facts and rules. To validate the proposal, the research has focused on Clinical Practice Guidelines (GLs) related to the biomedical field. This paper highlights the benefits and drawbacks found when applying the approach to obtain Web services that are intended to be used in clinical decision-making and rely on GLs. As an example of use, this paper concentrates on a services-based application for diagnosis and clinical management of Diabetic Retinopathy, where the end-users are health professionals who are not familiarized with Semantic Web technologies.

The Proteasix Ontology

BackgroundThe Proteasix Ontology (PxO) is an ontology that supports the Proteasix tool; an open-source peptide-centric tool that can be used to predict automatically and in a large-scale fashion in silico the proteases involved in the generation of proteolytic cleavage fragments (peptides)MethodsThe PxO re-uses parts of the Protein Ontology, the three Gene Ontology sub-ontologies, the Chemical Entities of Biological Interest Ontology, the Sequence Ontology and bespoke extensions to the PxO in support of a series of roles: 1. To describe the known proteases and their target cleaveage sites. 2. To enable the description of proteolytic cleaveage fragments as the outputs of observed and predicted proteolysis. 3. To use knowledge about the function, species and cellular location of a protease and protein substrate to support the prioritisation of proteases in observed and predicted proteolysis.ResultsThe PxO is designed to describe the biological underpinnings of the generation of peptides. The peptide-centric PxO seeks to support the Proteasix tool by separating domain knowledge from the operational knowledge used in protease prediction by Proteasix and to support the confirmation of its analyses and results.AvailabilityThe Proteasix Ontology may be found at: http://bioportal.bioontology.org/ontologies/PXO. This ontology is free and open for use by everyone.

A collaborative workflow for building ontologies: A case study in the biomedical field

Much medical knowledge is contained within available literature, such as clinical guidelines and protocols. Recently, an interest has been developed in automatic content extraction to construct ontologies of this knowledge to make it more widely available. With groups of domain experts distributed geographically, and the growing amount of medical literature, an important challenge is to develop collaborative workflows to support ways for domain experts to contribute in the ontology learning process. This paper presents a collaborative workflow for ontology learning based on coupling an Ontology Learning Tool (OntoLancs) with and Ontology engineer (Protégé) to provide semi-automatic support for text mining and a collaborative tool to model formal ontologies. The work presented in this paper was evaluated with a case study on a Clinical Practice Guideline of Diabetic Retinopathy. The major benefits of coupling OntoLancs with Protégé are: a) a higher level of automation in the creation of domain ontologies and models, and b) strengthened communication and information exchange among domain experts that are physically distributed. Validations of user experiences indicate the applicability of our approach.

A case study on sepsis using PubMed and Deep Learning for ontology learning

We investigate the application of distributional semantics models for facilitating unsupervised extraction of biomedical terms from unannotated corpora. Term extraction is used as the first step of an ontology learning process that aims to (semi-)automatic annotation of biomedical concepts and relations from more than 300K PubMed titles and abstracts. We experimented with both traditional distributional semantics methods such as Latent Semantic Analysis (LSA) and Latent Dirichlet Allocation (LDA) as well as the neural language models CBOW and Skip-gram from Deep Learning. The evaluation conducted concentrates on sepsis, a major life-threatening condition, and shows that Deep Learning models outperform LSA and LDA with much higher precision.

Prediction of Proteases Involved in Peptide Generation

Clinical proteomics has led to the identification of a substantial number of disease-associated peptides and protein fragments in several conditions such as cancer, kidney, or cardiovascular diseases. In silico prediction tools that can facilitate linking of identified peptide biomarkers to predicted protease activity might therefore significantly contribute to the understanding of pathophysiological mechanisms of these diseases. Proteasix is an open-source, peptide-centric tool that can be used to predict in silico the proteases involved in naturally occurring peptide generation. From an input peptide list, Proteasix allows for automatic cleavage site reconstruction and protease associations.

Using Semantic Web Technologies to Underpin the SNOMED CT Query Language

SNOMED International is working on a query language specification for SNOMED CT, which we call here SCTQL. SNOMED CT is the leading terminology for use in Electronic Health Records (EHRs). SCTQL can contribute to effective retrieval and reuse of clinical information within EHRs. This paper analyses the functional capabilities needed for SCTQL and proposes two implementations that rely on ontological representations of SNOMED CT: one based on the W3C SPARQL 1.1 query language and another based on the OWL API. The paper reports the performance and correctness of both implementations as well as highlights their benefits and drawbacks.

Computable Declarative Representation of Clinical Assessment Scales in EHRs

Clinical assessment scales, such as the Glasgow coma scale, are a core part of Electronic Health Records (EHRs). However, fully representing them in an OWL ontology is challenging: In particular, the determination of a score from patients observations and clinical findings requires forms of aggregation and addition which are either tedious in OWL 2 or merely impractical due to combinatorial explosion. To solve this problem, we propose to separate the representation of the structure and content of an assessment scale from its enactment with the former being captured in OWL 2 and the latter being determined by a SPARQL query. The paper reports the results of a systematic review of 104 well-established clinical assessment scales along with the performance of the SPARQL queries proposed when executed with the query engine ARQ for Jena over HL7 CDA level three documents.