Anita Burgun

NON-LEXICAL APPROACHES TO IDENTIFYING ASSOCIATIVE RELATIONS IN THE GENE ONTOLOGY

The Gene Ontology (GO) is a controlled vocabulary widely used for the annotation of gene products. GO is organized in three hierarchies for molecular functions, cellular components, and biological processes but no relations are provided among terms across hierarchies. The objective of this study is to investigate three non-lexical approaches to identifying such associative relations in GO and compare them among themselves and to lexical approaches. The three approaches are: computing similarity in a vector space model, statistical analysis of co-occurrence of GO terms in annotation databases, and association rule mining. Five annotation databases (FlyBase, the Human subset of GOA, MGI, SGD, and WormBase) are used in this study. A total of 7,665 associations were identified by at least one of the three non-lexical approaches. Of these, 12% were identified by more than one approach. While there are almost 6,000 lexical relations among GO terms, only 203 associations were identified by both non-lexical and lexical approaches. The associations identified in this study could serve as the starting point for adding associative relations across hierarchies to GO, but would require manual curation. The application to quality assurance of annotation databases is also discussed.

Investigating subsumption in SNOMED CT: An exploration into large description logic-based biomedical terminologies

OBJECTIVE Formalisms based on one or other flavor of description logic (DL) are sometimes put forward as helping to ensure that terminologies and controlled vocabularies comply with sound ontological principles. The objective of this paper is to study the degree to which one DL-based biomedical terminology (SNOMED CT) does indeed comply with such principles. MATERIALS AND METHODS We defined seven ontological principles (for example: each class must have at least one parent, each class must differ from its parent) and examined the properties of SNOMED CT classes with respect to these principles. RESULTS Our major results are 31% of these classes have a single child; 27% have multiple parents; 51% do not exhibit any differentiae between the description of the parent and that of the child. CONCLUSIONS The applications of this principles to quality assurance for ontologies are discussed and suggestions are made for dealing with the phenomenon of multiple inheritance. The advantages and limitations of our approach are also discussed.

Translational research platforms integrating clinical and omics data: a review of publicly available solutions

The rise of personalized medicine and the availability of high-throughput molecular analyses in the context of clinical care have increased the need for adequate tools for translational researchers to manage and explore these data. We reviewed the biomedical literature for translational platforms allowing the management and exploration of clinical and omics data, and identified seven platforms: BRISK, caTRIP, cBio Cancer Portal, G-DOC, iCOD, iDASH and tranSMART. We analyzed these platforms along seven major axes. (1) The community axis regrouped information regarding initiators and funders of the project, as well as availability status and references. (2) We regrouped under the information content axis the nature of the clinical and omics data handled by each system. (3) The privacy management environment axis encompassed functionalities allowing control over data privacy. (4) In the analysis support axis, we detailed the analytical and statistical tools provided by the platforms. We also explored (5) interoperability support and (6) system requirements. The final axis (7) platform support listed the availability of documentation and installation procedures. A large heterogeneity was observed in regard to the capability to manage phenotype information in addition to omics data, their security and interoperability features. The analytical and visualization features strongly depend on the considered platform. Similarly, the availability of the systems is variable. This review aims at providing the reader with the background to choose the platform best suited to their needs. To conclude, we discuss the desiderata for optimal translational research platforms, in terms of privacy, interoperability and technical features.

Big Data and machine learning in radiation oncology: State of the art and future prospects

Precision medicine relies on an increasing amount of heterogeneous data. Advances in radiation oncology, through the use of CT Scan, dosimetry and imaging performed before each fraction, have generated a considerable flow of data that needs to be integrated. In the same time, Electronic Health Records now provide phenotypic profiles of large cohorts of patients that could be correlated to this information. In this review, we describe methods that could be used to create integrative predictive models in radiation oncology. Potential uses of machine learning methods such as support vector machine, artificial neural networks, and deep learning are also discussed.

Adverse Drug Reaction Identification and Extraction in Social Media: A Scoping Review

Background The underreporting of adverse drug reactions (ADRs) through traditional reporting channels is a limitation in the efficiency of the current pharmacovigilance system. Patients’ experiences with drugs that they report on social media represent a new source of data that may have some value in postmarketing safety surveillance. Objective A scoping review was undertaken to explore the breadth of evidence about the use of social media as a new source of knowledge for pharmacovigilance. Methods Daubt et al’s recommendations for scoping reviews were followed. The research questions were as follows: How can social media be used as a data source for postmarketing drug surveillance? What are the available methods for extracting data? What are the different ways to use these data? We queried PubMed, Embase, and Google Scholar to extract relevant articles that were published before June 2014 and with no lower date limit. Two pairs of reviewers independently screened the selected studies and proposed two themes of review: manual ADR identification (theme 1) and automated ADR extraction from social media (theme 2). Descriptive characteristics were collected from the publications to create a database for themes 1 and 2. Results Of the 1032 citations from PubMed and Embase, 11 were relevant to the research question. An additional 13 citations were added after further research on the Internet and in reference lists. Themes 1 and 2 explored 11 and 13 articles, respectively. Ways of approaching the use of social media as a pharmacovigilance data source were identified. Conclusions This scoping review noted multiple methods for identifying target data, extracting them, and evaluating the quality of medical information from social media. It also showed some remaining gaps in the field. Studies related to the identification theme usually failed to accurately assess the completeness, quality, and reliability of the data that were analyzed from social media. Regarding extraction, no study proposed a generic approach to easily adding a new site or data source. Additional studies are required to precisely determine the role of social media in the pharmacovigilance system.

Unsupervised,corpus-based method for extending a biomedical terminology

Objectives: To automatically extend downwards an existing biomedical terminology using a corpus and both lexical and terminological knowledge. Methods: Adjectival modifiers are removed from terms extracted from the corpus (three million noun phrases extracted from MEDLINE), and demodified terms are searched for in the terminology (UMLS Metathesaurus, restricted to disorders and procedures). A phrase from MEDLINE becomes a candidate term in the Metathesaurus if the following two requirements are met: 1) a demodified term created from this phrase is found in the terminology and 2) the modifiers removed to create the demodified term also modify existing terms from the terminology, for a given semantic category. A manual review of a sample of candidate terms was performed. Results: Out of the 3 million simple phrases randomly extracted from MEDLINE, 125,000 new terms were identified for inclusion in the UMLS. 83% of the 1000 terms reviewed manually were associated with a relevant UMLS concept. Discussion: The limitations of this approach are discussed, as well as adaptation and generalization issues.

A unified structural/terminological interoperability framework based on LexEVS: application to TRANSFoRm

Objective Biomedical research increasingly relies on the integration of information from multiple heterogeneous data sources. Despite the fact that structural and terminological aspects of interoperability are interdependent and rely on a common set of requirements, current efforts typically address them in isolation. We propose a unified ontology-based knowledge framework to facilitate interoperability between heterogeneous sources, and investigate if using the LexEVS terminology server is a viable implementation method. Materials and methods We developed a framework based on an ontology, the general information model (GIM), to unify structural models and terminologies, together with relevant mapping sets. This allowed a uniform access to these resources within LexEVS to facilitate interoperability by various components and data sources from implementing architectures. Results Our unified framework has been tested in the context of the EU Framework Program 7 TRANSFoRm project, where it was used to achieve data integration in a retrospective diabetes cohort study. The GIM was successfully instantiated in TRANSFoRm as the clinical data integration model, and necessary mappings were created to support effective information retrieval for software tools in the project. Conclusions We present a novel, unifying approach to address interoperability challenges in heterogeneous data sources, by representing structural and semantic models in one framework. Systems using this architecture can rely solely on the GIM that abstracts over both the structure and coding. Information models, terminologies and mappings are all stored in LexEVS and can be accessed in a uniform manner (implementing the HL7 CTS2 service functional model). The system is flexible and should reduce the effort needed from data sources personnel for implementing and managing the integration.

Phenome-Wide Association Studies on a Quantitative Trait: Application to TPMT Enzyme Activity and Thiopurine Therapy in Pharmacogenomics

Phenome-Wide Association Studies (PheWAS) investigate whether genetic polymorphisms associated with a phenotype are also associated with other diagnoses. In this study, we have developed new methods to perform a PheWAS based on ICD-10 codes and biological test results, and to use a quantitative trait as the selection criterion. We tested our approach on thiopurine S-methyltransferase (TPMT) activity in patients treated by thiopurine drugs. We developed 2 aggregation methods for the ICD-10 codes: an ICD-10 hierarchy and a mapping to existing ICD-9-CM based PheWAS codes. Eleven biological test results were also analyzed using discretization algorithms. We applied these methods in patients having a TPMT activity assessment from the clinical data warehouse of a French academic hospital between January 2000 and July 2013. Data after initiation of thiopurine treatment were analyzed and patient groups were compared according to their TPMT activity level. A total of 442 patient records were analyzed representing 10,252 ICD-10 codes and 72,711 biological test results. The results from the ICD-9-CM based PheWAS codes and ICD-10 hierarchy codes were concordant. Cross-validation with the biological test results allowed us to validate the ICD phenotypes. Iron-deficiency anemia and diabetes mellitus were associated with a very high TPMT activity (p = 0.0004 and p = 0.0015, respectively). We describe here an original method to perform PheWAS on a quantitative trait using both ICD-10 diagnosis codes and biological test results to identify associated phenotypes. In the field of pharmacogenomics, PheWAS allow for the identification of new subgroups of patients who require personalized clinical and therapeutic management.

UMLF: a unified medical lexicon for French.

Lexical resources for medical language, such as lists of words with inflectional and derivational information, are publicly available for the English lantuate with the UMLS Specialist Lexicon. The goal of the UMLF project is to pool and unify existing resources and to add extensively to them by exploiting medical terminologies and corpora, resulting in a Unified Medical Lexicon for French. We present here the current status of the project.

Assessing the consistency of a biomedical terminology through lexical knowledge

OBJECTIVE We investigate the use of adjectival modification as a way of assessing the systematic use of linguistic phenomena to represent similar lexical or semantic features in the constituent terms of a vocabulary. METHODS Terms consisting of one or more adjectival modifiers followed by a head noun are selected from disease and procedure terms in SNOMED. Frequently co-occurring adjectival modifiers are systematically combined with the contexts (i.e., terms minus modifier) of each modifier. The existence of these combinations is checked in both SNOMED and the entire UMLS Metathesaurus; the term corresponding to the context alone is similarly checked. Relationships among terms sharing a context and between each of these terms and their context are studied. RESULTS Four pairs of modifiers were studied: (acute, chronic), (unilateral, bilateral), (primary, secondary), and (acquired, congenital). The numbers of contexts studied for each pair ranged from 73 to 974. The percentage of contexts associated with both modifiers ranged from 5 to 50% in SNOMED and from 10 to 60% in UMLS. The presence of the context term varied from 31 to 64% in SNOMED and from 43 to 79% in UMLS. Finally, 172 occurrences (9%) of synonymy between a modified term and the context term were found in SNOMED. One hundred and forty-five such occurrences (8%) were found in the entire Metathesaurus.