Using semantics for representing experimental protocols.

J Biomed Semantics. 2017 Nov 13;8(1):52

Authors: Giraldo O, García A, López F, Corcho O

Abstract
BACKGROUND: An experimental protocol is a sequence of tasks and operations executed to perform experimental research in biological and biomedical areas, e.g. biology, genetics, immunology, neurosciences, virology. Protocols often include references to equipment, reagents, descriptions of critical steps, troubleshooting and tips, as well as any other information that researchers deem important for facilitating the reusability of the protocol. Although experimental protocols are central to reproducibility, the descriptions are often cursory. There is the need for a unified framework with respect to the syntactic structure and the semantics for representing experimental protocols.
RESULTS: In this paper we present "SMART Protocols ontology", an ontology for representing experimental protocols. Our ontology represents the protocol as a workflow with domain specific knowledge embedded within a document. We also present the S ample I nstrument R eagent O bjective (SIRO) model, which represents the minimal common information shared across experimental protocols. SIRO was conceived in the same realm as the Patient Intervention Comparison Outcome (PICO) model that supports search, retrieval and classification purposes in evidence based medicine. We evaluate our approach against a set of competency questions modeled as SPARQL queries and processed against a set of published and unpublished protocols modeled with the SP Ontology and the SIRO model. Our approach makes it possible to answer queries such as Which protocols use tumor tissue as a sample.
CONCLUSION: Improving reporting structures for experimental protocols requires collective efforts from authors, peer reviewers, editors and funding bodies. The SP Ontology is a contribution towards this goal. We build upon previous experiences and bringing together the view of researchers managing protocols in their laboratory work. Website: https://smartprotocols.github.io/ .

PMID: 29132408 [PubMed - in process]

SSEL-ADE: A semi-supervised ensemble learning framework for extracting adverse drug events from social media.

Artif Intell Med. 2017 Oct 27;:

Authors: Liu J, Zhao S, Wang G

Abstract
With the development of Web 2.0 technology, social media websites have become lucrative but under-explored data sources for extracting adverse drug events (ADEs), which is a serious health problem. Besides ADE, other semantic relation types (e.g., drug indication and beneficial effect) could hold between the drug and adverse event mentions, making ADE relation extraction - distinguishing ADE relationship from other relation types - necessary. However, conducting ADE relation extraction in social media environment is not a trivial task because of the expertise-dependent, time-consuming and costly annotation process, and the feature space's high-dimensionality attributed to intrinsic characteristics of social media data. This study aims to develop a framework for ADE relation extraction using patient-generated content in social media with better performance than that delivered by previous efforts. To achieve the objective, a general semi-supervised ensemble learning framework, SSEL-ADE, was developed. The framework exploited various lexical, semantic, and syntactic features, and integrated ensemble learning and semi-supervised learning. A series of experiments were conducted to verify the effectiveness of the proposed framework. Empirical results demonstrate the effectiveness of each component of SSEL-ADE and reveal that our proposed framework outperforms most of existing ADE relation extraction methods The SSEL-ADE can facilitate enhanced ADE relation extraction performance, thereby providing more reliable support for pharmacovigilance. Moreover, the proposed semi-supervised ensemble methods have the potential of being applied to effectively deal with other social media-based problems.

PMID: 29111222 [PubMed - as supplied by publisher]

The OMA orthology database in 2018: retrieving evolutionary relationships among all domains of life through richer web and programmatic interfaces.

Nucleic Acids Res. 2017 Nov 02;:

Authors: Altenhoff AM, Glover NM, Train CM, Kaleb K, Warwick Vesztrocy A, Dylus D, de Farias TM, Zile K, Stevenson C, Long J, Redestig H, Gonnet GH, Dessimoz C

Abstract
The Orthologous Matrix (OMA) is a leading resource to relate genes across many species from all of life. In this update paper, we review the recent algorithmic improvements in the OMA pipeline, describe increases in species coverage (particularly in plants and early-branching eukaryotes) and introduce several new features in the OMA web browser. Notable improvements include: (i) a scalable, interactive viewer for hierarchical orthologous groups; (ii) protein domain annotations and domain-based links between orthologous groups; (iii) functionality to retrieve phylogenetic marker genes for a subset of species of interest; (iv) a new synteny dot plot viewer; and (v) an overhaul of the programmatic access (REST API and semantic web), which will facilitate incorporation of OMA analyses in computational pipelines and integration with other bioinformatic resources. OMA can be freely accessed at https://omabrowser.org.

PMID: 29106550 [PubMed - as supplied by publisher]

Open chemistry: RESTful web APIs, JSON, NWChem and the modern web application.

J Cheminform. 2017 Oct 30;9(1):55

Authors: Hanwell MD, de Jong WA, Harris CJ

Abstract
An end-to-end platform for chemical science research has been developed that integrates data from computational and experimental approaches through a modern web-based interface. The platform offers an interactive visualization and analytics environment that functions well on mobile, laptop and desktop devices. It offers pragmatic solutions to ensure that large and complex data sets are more accessible. Existing desktop applications/frameworks were extended to integrate with high-performance computing resources, and offer command-line tools to automate interaction-connecting distributed teams to this software platform on their own terms. The platform was developed openly, and all source code hosted on the GitHub platform with automated deployment possible using Ansible coupled with standard Ubuntu-based machine images deployed to cloud machines. The platform is designed to enable teams to reap the benefits of the connected web-going beyond what conventional search and analytics platforms offer in this area. It also has the goal of offering federated instances, that can be customized to the sites/research performed. Data gets stored using JSON, extending upon previous approaches using XML, building structures that support computational chemistry calculations. These structures were developed to make it easy to process data across different languages, and send data to a JavaScript-based web client.

PMID: 29086154 [PubMed]

Electronic lab notebooks: can they replace paper?

J Cheminform. 2017 May 24;9(1):31

Authors: Kanza S, Willoughby C, Gibbins N, Whitby R, Frey JG, Erjavec J, Zupančič K, Hren M, Kovač K

Abstract
Despite the increasingly digital nature of society there are some areas of research that remain firmly rooted in the past; in this case the laboratory notebook, the last remaining paper component of an experiment. Countless electronic laboratory notebooks (ELNs) have been created in an attempt to digitise record keeping processes in the lab, but none of them have become a 'key player' in the ELN market, due to the many adoption barriers that have been identified in previous research and further explored in the user studies presented here. The main issues identified are the cost of the current available ELNs, their ease of use (or lack of it) and their accessibility issues across different devices and operating systems. Evidence suggests that whilst scientists willingly make use of generic notebooking software, spreadsheets and other general office and scientific tools to aid their work, current ELNs are lacking in the required functionality to meet the needs of the researchers. In this paper we present our extensive research and user study results to propose an ELN built upon a pre-existing cloud notebook platform that makes use of accessible popular scientific software and semantic web technologies to help overcome the identified barriers to adoption.

PMID: 29086051 [PubMed]

A Knowledge-Modeling Approach to Integrate Multiple Clinical Practice Guidelines to Provide Evidence-Based Clinical Decision Support for Managing Comorbid Conditions.

J Med Syst. 2017 Oct 26;41(12):193

Authors: Abidi S

Abstract
Clinical management of comorbidities is a challenge, especially in a clinical decision support setting, as it requires the safe and efficient reconciliation of multiple disease-specific clinical procedures to formulate a comorbid therapeutic plan that is both effective and safe for the patient. In this paper we pursue the integration of multiple disease-specific Clinical Practice Guidelines (CPG) in order to manage co-morbidities within a computerized Clinical Decision Support System (CDSS). We present a CPG integration framework-termed as COMET (Comorbidity Ontological Modeling & ExecuTion) that manifests a knowledge management approach to model, computerize and integrate multiple CPG to yield a comorbid CPG knowledge model that upon execution can provide evidence-based recommendations for handling comorbid patients. COMET exploits semantic web technologies to achieve (a) CPG knowledge synthesis to translate a paper-based CPG to disease-specific clinical pathways (CP) that include specialized co-morbidity management procedures based on input from domain experts; (b) CPG knowledge modeling to computerize the disease-specific CP using a Comorbidity CPG ontology; (c) CPG knowledge integration by aligning multiple ontologically-modeled CP to develop a unified comorbid CPG knowledge model; and (e) CPG knowledge execution using reasoning engines to derive CPG-mediated recommendations for managing patients with comorbidities. We present a web-accessible COMET CDSS that provides family physicians with CPG-mediated comorbidity decision support to manage Atrial Fibrillation and Chronic Heart Failure. We present our qualitative and quantitative analysis of the knowledge content and usability of COMET CDSS.

PMID: 29076113 [PubMed - in process]

Graph-Based Semantic Web Service Composition for Healthcare Data Integration.

J Healthc Eng. 2017;2017:4271273

Authors: Arch-Int N, Arch-Int S, Sonsilphong S, Wanchai P

Abstract
Within the numerous and heterogeneous web services offered through different sources, automatic web services composition is the most convenient method for building complex business processes that permit invocation of multiple existing atomic services. The current solutions in functional web services composition lack autonomous queries of semantic matches within the parameters of web services, which are necessary in the composition of large-scale related services. In this paper, we propose a graph-based Semantic Web Services composition system consisting of two subsystems: management time and run time. The management-time subsystem is responsible for dependency graph preparation in which a dependency graph of related services is generated automatically according to the proposed semantic matchmaking rules. The run-time subsystem is responsible for discovering the potential web services and nonredundant web services composition of a user's query using a graph-based searching algorithm. The proposed approach was applied to healthcare data integration in different health organizations and was evaluated according to two aspects: execution time measurement and correctness measurement.

PMID: 29065602 [PubMed - in process]

Best Paper Selection.

Yearb Med Inform. 2017 Aug;26(1):137-138

Authors:

Abstract
Lin FP, Pokorny A, Teng C, Dear R, Epstein RJ. Computational prediction of multidisciplinary team decision-making for adjuvant breast cancer drug therapies: a machine learning approach. BMC Cancer 2016 Dec 1;16(1):929 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5131452/ Marco-Ruiz L, Pedrinaci C, Maldonado JA, Panziera L, Chen R, Bellika JG. Publication, discovery and interoperability of Clinical Decision Support Systems: A Linked Data approach. J Biomed Inform 2016 Aug;62:243-64 http://www.sciencedirect.com/science/article/pii/S153204641630065X?via%3Dihub McEvoy DS, Sittig DF, Hickman TT, Aaron S, Ai A, Amato M, Bauer DW, Fraser GM, Harper J, Kennemer A, Krall MA, Lehmann CU, Malhotra S, Murphy DR, O'Kelley B, Samal L, Schreiber R, Singh H, Thomas EJ, Vartian CV, Westmorland J, McCoy AB, Wright A. Variation in high-priority drug-drug interaction alerts across institutions and electronic health records. J Am Med Inform Assoc 2017 Mar 1;24(2):331-8 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5391726/ Zamborlini V, Hoekstra R, Da Silveira M, Pruski C, ten Teije A, van Harmelen F. Inferring recommendation interactions in clinical guidelines. Semantic Web 2016;7(4):421-46 https://www.google.de/url?sa=t&rct=j&q=&esrc=s&source=web&cd=3&cad=rja&uact=8&ved=0ahUKEwin39e8r77VAhXEaFAKHeLkAC0QFgg_MAI&url=http%3A%2F%2Fwww.semantic-web-journal.net%2Fsystem%2Ffiles%2Fswj891.pdf&usg=AFQjCNF7CEXY49F929iQL09sRbGCl2Lc2A.

PMID: 29063554 [PubMed - in process]

Contributions from the 2016 Literature on Clinical Decision Support.

Yearb Med Inform. 2017 Aug;26(1):133-137

Authors: Koutkias V, Bouaud J

Abstract
Objectives: To summarize recent research and select the best papers published in 2016 in the field of computerized clinical decision support for the Decision Support section of the IMIA yearbook. Methods: A literature review was performed by searching two bibliographic databases for papers related to clinical decision support systems (CDSSs). The aim was to identify a list of candidate best papers from the retrieved papers that were then peer-reviewed by external reviewers. A consensus meeting of the IMIA editorial team finally selected the best papers on the basis of all reviews and section editor evaluation. Results: Among the 1,145 retrieved papers, the entire review process resulted in the selection of four best papers. The first paper describes machine learning models used to predict breast cancer multidisciplinary team decisions and compares them with two predictors based on guideline knowledge. The second paper introduces a linked-data approach for publication, discovery, and interoperability of CDSSs. The third paper assessed the variation in high-priority drug-drug interaction (DDI) alerts across 14 Electronic Health Record systems, operating in different institutions in the US. The fourth paper proposes a generic framework for modeling multiple concurrent guidelines and detecting their recommendation interactions using semantic web technologies. Conclusions: The process of identifying and selecting best papers in the domain of CDSSs demonstrated that the research in this field is very active concerning diverse dimensions, such as the types of CDSSs, e.g. guideline-based, machine-learning-based, knowledge-fusion-based, etc., and addresses challenging areas, such as the concurrent application of multiple guidelines for comorbid patients, the resolution of interoperability issues, and the evaluation of CDSSs. Nevertheless, this process also showed that CDSSs are not yet fully part of the digitalized healthcare ecosystem. Many challenges remain to be faced with regard to the evidence of their output, the dissemination of their technologies, as well as their adoption for better and safer healthcare delivery.

PMID: 29063553 [PubMed - in process]

A two-staged approach to developing and evaluating an ontology for delivering personalized education to diabetic patients.

Inform Health Soc Care. 2017 Oct 16;:1-16

Authors: Quinn S, Bond R, Nugent C

Abstract
Ontologies are often used in biomedical and health domains to provide a concise and consistent means of attributing meaning to medical terminology. While they are novices in terms of ontology engineering, the evaluation of an ontology by domain specialists provides an opportunity to enhance its objectivity, accuracy, and coverage of the domain itself. This paper provides an evaluation of the viability of using ontology engineering novices to evaluate and enrich an ontology that can be used for personalized diabetic patient education. We describe a methodology for engaging healthcare and information technology specialists with a range of ontology engineering tasks. We used 87.8% of the data collected to validate the accuracy of our ontological model. The contributions also enabled a 16% increase in the class size and an 18% increase in object properties. Furthermore, we propose that ontology engineering novices can make valuable contributions to ontology development. Application-specific evaluation of the ontology using a semantic-web-based architecture is also discussed.

PMID: 29035605 [PubMed - as supplied by publisher]

Opinion Mining for Educational Video Lectures.

Adv Exp Med Biol. 2017;989:235-243

Authors: Kravvaris D, Kermanidis KL

Abstract
The search for relevant educational videos is a time consuming process for the users. Furthermore, the increasing demand for educational videos intensifies the problem and calls for the users to utilize whichever information is offered by the hosting web pages, and choose the most appropriate one. This research focuses on the classification of user views, based on the comments on educational videos, into positive or negative ones. The aim is to give users a picture of the positive and negative comments that have been recorded, so as to provide a qualitative view of the final selection at their disposal. The present paper's innovation is the automatic identification of the most important words of the verbal content of the video lectures and the filtering of the comments based on them, thus limiting the comments to the ones that have a substantial semantic connection with the video content.

PMID: 28971431 [PubMed - in process]

BioCarian: search engine for exploratory searches in heterogeneous biological databases.

BMC Bioinformatics. 2017 Oct 02;18(1):435

Authors: Zaki N, Tennakoon C

Abstract
BACKGROUND: There are a large number of biological databases publicly available for scientists in the web. Also, there are many private databases generated in the course of research projects. These databases are in a wide variety of formats. Web standards have evolved in the recent times and semantic web technologies are now available to interconnect diverse and heterogeneous sources of data. Therefore, integration and querying of biological databases can be facilitated by techniques used in semantic web. Heterogeneous databases can be converted into Resource Description Format (RDF) and queried using SPARQL language. Searching for exact queries in these databases is trivial. However, exploratory searches need customized solutions, especially when multiple databases are involved. This process is cumbersome and time consuming for those without a sufficient background in computer science. In this context, a search engine facilitating exploratory searches of databases would be of great help to the scientific community.
RESULTS: We present BioCarian, an efficient and user-friendly search engine for performing exploratory searches on biological databases. The search engine is an interface for SPARQL queries over RDF databases. We note that many of the databases can be converted to tabular form. We first convert the tabular databases to RDF. The search engine provides a graphical interface based on facets to explore the converted databases. The facet interface is more advanced than conventional facets. It allows complex queries to be constructed, and have additional features like ranking of facet values based on several criteria, visually indicating the relevance of a facet value and presenting the most important facet values when a large number of choices are available. For the advanced users, SPARQL queries can be run directly on the databases. Using this feature, users will be able to incorporate federated searches of SPARQL endpoints. We used the search engine to do an exploratory search on previously published viral integration data and were able to deduce the main conclusions of the original publication. BioCarian is accessible via http://www.biocarian.com .
CONCLUSIONS: We have developed a search engine to explore RDF databases that can be used by both novice and advanced users.

PMID: 28969593 [PubMed - in process]

MetSigDis: a manually curated resource for the metabolic signatures of diseases.

Brief Bioinform. 2017 Aug 22;:

Authors: Cheng L, Yang H, Zhao H, Pei X, Shi H, Sun J, Zhang Y, Wang Z, Zhou M

Abstract
Complex diseases cannot be understood only on the basis of single gene, single mRNA transcript or single protein but the effect of their collaborations. The combination consequence in molecular level can be captured by the alterations of metabolites. With the rapidly developing of biomedical instruments and analytical platforms, a large number of metabolite signatures of complex diseases were identified and documented in the literature. Biologists' hardship in the face of this large amount of papers recorded metabolic signatures of experiments' results calls for an automated data repository. Therefore, we developed MetSigDis aiming to provide a comprehensive resource of metabolite alterations in various diseases. MetSigDis is freely available at http://www.bio-annotation.cn/MetSigDis/. By reviewing hundreds of publications, we collected 6849 curated relationships between 2420 metabolites and 129 diseases across eight species involving Homo sapiens and model organisms. All of these relationships were used in constructing a metabolite disease network (MDN). This network displayed scale-free characteristics according to the degree distribution (power-law distribution with R2 = 0.909), and the subnetwork of MDN for interesting diseases and their related metabolites can be visualized in the Web. The common alterations of metabolites reflect the metabolic similarity of diseases, which is measured using Jaccard index. We observed that metabolite-based similar diseases are inclined to share semantic associations of Disease Ontology. A human disease network was then built, where a node represents a disease, and an edge indicates similarity of pair-wise diseases. The network validated the observation that linked diseases based on metabolites should have more overlapped genes.

PMID: 28968812 [PubMed - as supplied by publisher]

An automated tool for obtaining QSAR-ready series of compounds using semantic web technologies.

Bioinformatics. 2017 Sep 07;:

Authors: López-Massaguer O, Sanz F, Pastor M

Abstract
Summary: We describe an application (Collector) for obtaining series of compounds annotated with bioactivity data, ready to be used for the development of quantitative structure-activity relationships (QSAR) models. The tool extracts data from the 'Open Pharmacological Space' (OPS) developed by the Open PHACTS project, using as input a valid name of the biological target. Collector uses the OPS ontologies for expanding the query using all known target synonyms and extracts compounds with bioactivity data against the target from multiple sources. The extracted data can be filtered to retain only drug-like compounds and the bioactivities can be automatically summarised to assign a single value per compound, yielding data ready to be used for QSAR modeling. The data obtained is locally stored facilitating the traceability and auditability of the process. Collector was used successfully for the development of models for toxicity endpoints within the eTOX project.
Availability and implementation: The software is available at http://phi.upf.edu/collector . The source code is located at https://github.com/phi-grib/Collector and is free for use under the GPL3 license. The web version is hosted at http://collector.upf.edu /.
Contact: manuel.pastor@upf.edu.
Supplementary information: Supplementary data are available at Bioinformatics online.

PMID: 28968713 [PubMed - as supplied by publisher]

Analysis and visualization of disease courses in a semantically-enabled cancer registry.

J Biomed Semantics. 2017 Sep 29;8(1):46

Authors: Esteban-Gil A, Fernández-Breis JT, Boeker M

Abstract
BACKGROUND: Regional and epidemiological cancer registries are important for cancer research and the quality management of cancer treatment. Many technological solutions are available to collect and analyse data for cancer registries nowadays. However, the lack of a well-defined common semantic model is a problem when user-defined analyses and data linking to external resources are required. The objectives of this study are: (1) design of a semantic model for local cancer registries; (2) development of a semantically-enabled cancer registry based on this model; and (3) semantic exploitation of the cancer registry for analysing and visualising disease courses.
RESULTS: Our proposal is based on our previous results and experience working with semantic technologies. Data stored in a cancer registry database were transformed into RDF employing a process driven by OWL ontologies. The semantic representation of the data was then processed to extract semantic patient profiles, which were exploited by means of SPARQL queries to identify groups of similar patients and to analyse the disease timelines of patients. Based on the requirements analysis, we have produced a draft of an ontology that models the semantics of a local cancer registry in a pragmatic extensible way. We have implemented a Semantic Web platform that allows transforming and storing data from cancer registries in RDF. This platform also permits users to formulate incremental user-defined queries through a graphical user interface. The query results can be displayed in several customisable ways. The complex disease timelines of individual patients can be clearly represented. Different events, e.g. different therapies and disease courses, are presented according to their temporal and causal relations.
CONCLUSION: The presented platform is an example of the parallel development of ontologies and applications that take advantage of semantic web technologies in the medical field. The semantic structure of the representation renders it easy to analyse key figures of the patients and their evolution at different granularity levels.

PMID: 28962670 [PubMed - in process]

SciLite: a platform for displaying text-mined annotations as a means to link research articles with biological data.

Wellcome Open Res. 2016;1:25

Authors: Venkatesan A, Kim JH, Talo F, Ide-Smith M, Gobeill J, Carter J, Batista-Navarro R, Ananiadou S, Ruch P, McEntyre J

Abstract
The tremendous growth in biological data has resulted in an increase in the number of research papers being published. This presents a great challenge for scientists in searching and assimilating facts described in those papers. Particularly, biological databases depend on curators to add highly precise and useful information that are usually extracted by reading research articles. Therefore, there is an urgent need to find ways to improve linking literature to the underlying data, thereby minimising the effort in browsing content and identifying key biological concepts.   As part of the development of Europe PMC, we have developed a new platform, SciLite, which integrates text-mined annotations from different sources and overlays those outputs on research articles. The aim is to aid researchers and curators using Europe PMC in finding key concepts more easily and provide links to related resources or tools, bridging the gap between literature and biological data.

PMID: 28948232 [PubMed]

ANALYTiC: An Active Learning System for Trajectory Classification.

IEEE Comput Graph Appl. 2017;37(5):28-39

Authors: Soares Junior A, Renso C, Matwin S

Abstract
The increasing availability and use of positioning devices has resulted in large volumes of trajectory data. However, semantic annotations for such data are typically added by domain experts, which is a time-consuming task. Machine-learning algorithms can help infer semantic annotations from trajectory data by learning from sets of labeled data. Specifically, active learning approaches can minimize the set of trajectories to be annotated while preserving good performance measures. The ANALYTiC web-based interactive tool visually guides users through this annotation process.

PMID: 28945577 [PubMed - in process]

Logistic Model to Support Service Modularity for the Promotion of Reusability in a Web Objects-Enabled IoT Environment.

Sensors (Basel). 2017 Sep 22;17(10):

Authors: Kibria MG, Ali S, Jarwar MA, Kumar S, Chong I

Abstract
Due to a very large number of connected virtual objects in the surrounding environment, intelligent service features in the Internet of Things requires the reuse of existing virtual objects and composite virtual objects. If a new virtual object is created for each new service request, then the number of virtual object would increase exponentially. The Web of Objects applies the principle of service modularity in terms of virtual objects and composite virtual objects. Service modularity is a key concept in the Web Objects-Enabled Internet of Things (IoT) environment which allows for the reuse of existing virtual objects and composite virtual objects in heterogeneous ontologies. In the case of similar service requests occurring at the same, or different locations, the already-instantiated virtual objects and their composites that exist in the same, or different ontologies can be reused. In this case, similar types of virtual objects and composite virtual objects are searched and matched. Their reuse avoids duplication under similar circumstances, and reduces the time it takes to search and instantiate them from their repositories, where similar functionalities are provided by similar types of virtual objects and their composites. Controlling and maintaining a virtual object means controlling and maintaining a real-world object in the real world. Even though the functional costs of virtual objects are just a fraction of those for deploying and maintaining real-world objects, this article focuses on reusing virtual objects and composite virtual objects, as well as discusses similarity matching of virtual objects and composite virtual objects. This article proposes a logistic model that supports service modularity for the promotion of reusability in the Web Objects-enabled IoT environment. Necessary functional components and a flowchart of an algorithm for reusing composite virtual objects are discussed. Also, to realize the service modularity, a use case scenario is studied and implemented.

PMID: 28937590 [PubMed - in process]

The Adverse Drug Reactions from Patient Reports in Social Media Project: Five Major Challenges to Overcome to Operationalize Analysis and Efficiently Support Pharmacovigilance Process.

JMIR Res Protoc. 2017 Sep 21;6(9):e179

Authors: Bousquet C, Dahamna B, Guillemin-Lanne S, Darmoni SJ, Faviez C, Huot C, Katsahian S, Leroux V, Pereira S, Richard C, Schück S, Souvignet J, Lillo-Le Louët A, Texier N

Abstract
BACKGROUND: Adverse drug reactions (ADRs) are an important cause of morbidity and mortality. Classical Pharmacovigilance process is limited by underreporting which justifies the current interest in new knowledge sources such as social media. The Adverse Drug Reactions from Patient Reports in Social Media (ADR-PRISM) project aims to extract ADRs reported by patients in these media. We identified 5 major challenges to overcome to operationalize the analysis of patient posts: (1) variable quality of information on social media, (2) guarantee of data privacy, (3) response to pharmacovigilance expert expectations, (4) identification of relevant information within Web pages, and (5) robust and evolutive architecture.
OBJECTIVE: This article aims to describe the current state of advancement of the ADR-PRISM project by focusing on the solutions we have chosen to address these 5 major challenges.
METHODS: In this article, we propose methods and describe the advancement of this project on several aspects: (1) a quality driven approach for selecting relevant social media for the extraction of knowledge on potential ADRs, (2) an assessment of ethical issues and French regulation for the analysis of data on social media, (3) an analysis of pharmacovigilance expert requirements when reviewing patient posts on the Internet, (4) an extraction method based on natural language processing, pattern based matching, and selection of relevant medical concepts in reference terminologies, and (5) specifications of a component-based architecture for the monitoring system.
RESULTS: Considering the 5 major challenges, we (1) selected a set of 21 validated criteria for selecting social media to support the extraction of potential ADRs, (2) proposed solutions to guarantee data privacy of patients posting on Internet, (3) took into account pharmacovigilance expert requirements with use case diagrams and scenarios, (4) built domain-specific knowledge resources embeding a lexicon, morphological rules, context rules, semantic rules, syntactic rules, and post-analysis processing, and (5) proposed a component-based architecture that allows storage of big data and accessibility to third-party applications through Web services.
CONCLUSIONS: We demonstrated the feasibility of implementing a component-based architecture that allows collection of patient posts on the Internet, near real-time processing of those posts including annotation, and storage in big data structures. In the next steps, we will evaluate the posts identified by the system in social media to clarify the interest and relevance of such approach to improve conventional pharmacovigilance processes based on spontaneous reporting.

PMID: 28935617 [PubMed]

PIBAS FedSPARQL: a web-based platform for integration and exploration of bioinformatics datasets.

J Biomed Semantics. 2017 Sep 20;8(1):42

Authors: Djokic-Petrovic M, Cvjetkovic V, Yang J, Zivanovic M, Wild DJ

Abstract
BACKGROUND: There are a huge variety of data sources relevant to chemical, biological and pharmacological research, but these data sources are highly siloed and cannot be queried together in a straightforward way. Semantic technologies offer the ability to create links and mappings across datasets and manage them as a single, linked network so that searching can be carried out across datasets, independently of the source. We have developed an application called PIBAS FedSPARQL that uses semantic technologies to allow researchers to carry out such searching across a vast array of data sources.
RESULTS: PIBAS FedSPARQL is a web-based query builder and result set visualizer of bioinformatics data. As an advanced feature, our system can detect similar data items identified by different Uniform Resource Identifiers (URIs), using a text-mining algorithm based on the processing of named entities to be used in Vector Space Model and Cosine Similarity Measures. According to our knowledge, PIBAS FedSPARQL was unique among the systems that we found in that it allows detecting of similar data items. As a query builder, our system allows researchers to intuitively construct and run Federated SPARQL queries across multiple data sources, including global initiatives, such as Bio2RDF, Chem2Bio2RDF, EMBL-EBI, and one local initiative called CPCTAS, as well as additional user-specified data source. From the input topic, subtopic, template and keyword, a corresponding initial Federated SPARQL query is created and executed. Based on the data obtained, end users have the ability to choose the most appropriate data sources in their area of interest and exploit their Resource Description Framework (RDF) structure, which allows users to select certain properties of data to enhance query results.
CONCLUSIONS: The developed system is flexible and allows intuitive creation and execution of queries for an extensive range of bioinformatics topics. Also, the novel "similar data items detection" algorithm can be particularly useful for suggesting new data sources and cost optimization for new experiments. PIBAS FedSPARQL can be expanded with new topics, subtopics and templates on demand, rendering information retrieval more robust.

PMID: 28931422 [PubMed - in process]