@conference {344, title = {W14-02: Systematizing Definitions in Ontologies}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, address = {Corvallis, Oregon, USA}, abstract = {

In this talk, I will present a methodological proposal to systematize textual and logical definitions in ontologies. I will use as a case study definitions of social entities from the Ontology of Medically Related Social Entities (OMRSE). The goal is to show how this method can simplify and accelerate the definition writing process.

}, keywords = {definition templates, definitions, logical definitions, ontologies, textual definitions}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {Sepp{\"a}l{\"a}, Selja} } @conference {343, title = {W14-01: Uncovering Definition Coverage in the OBO Foundry Ontologies}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, address = {Corvallis, Oregon, USA}, abstract = {

Definitions, both logical and textual, are an essential part of ontologies. Textual definitions help human users disambiguate and regularize their understanding and use of ontology terms to achieve intra- and inter-personal consistency and avoid errors, for example, when annotating scientific data, integrating databases with an ontology, or importing terms into other ontologies. Logical definitions are needed, among other things, for checking the consistency of the ontology and carrying out inferences, for example, over data that has been annotated with ontology terms. Despite the best efforts of ontology developers, it is not uncommon to see missing definitions. While the OBO Foundry explicitly states that its member ontologies should have a substantial fraction of their terms defined, these ontologies still often lack one or both kinds of definitions. Statistics on definition coverage in the OBO Foundry ontologies are scarce and it is difficult to tell what effectively constitutes a substantial fraction of terms in an ontology. In the present work, we examine the coverage of textual and logical definitions throughout the OBO Foundry ontologies in order to uncover the big picture and to give more detailed insight into logical definitions in these ontologies. We have found that textual definition coverage is reasonably good over the OBO Foundry ontologies (66\%), but that the core ontologies exhibit a higher definition coverage (86\%) than the non-core ones (64\%). Logical definitions follow a similar trend, but with lower values {\textemdash} overall, the OBO Foundry has a 30\% coverage, while core ontologies are better covered (53\%) than non-core ones (28\%).

}, keywords = {definition coverage, logical definitions, OBO Foundry, ontology, textual definitions}, url = {http://ceur-ws.org/Vol-1747/IP16_ICBO2016.pdf}, author = {Schlegel, Daniel R. and Selja Sepp{\"a}l{\"a} and Elkin, Peter L.} } @conference {364, title = {W12-06: Evolution of Floral Form: The potential of ontologies across diverse plant lineages}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

TBA

}, keywords = {evo-devo, flower development, fusion, morphological evolution, petaloidy, Zingiberales}, author = {Chelsea Specht} } @conference {W14-03, title = {W12-04: The Plant Phenology Ontology for Phenological Data Integration}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Plant phenology the timing of life-cycle events, such as flowering or leafing-out has cascading effects on multiple levels of biological organization, from individuals to ecosystems. Despite the importance of understanding phenology for managing biodiversity and ecosystem services, we are not currently able to address continent-scale phenological responses to anticipated climatic changes. This is not because we lack relevant data. Rather, the problem is that the disparate organizations producing large-scale phenology data are using non-standardized terminologies and metrics during data collection and data processing. Here, we preview the Plant Phenology Ontology, which will provide the standardized vocabulary necessary for annotation of phenological data. We are aggregating, annotating, and analyzing the most significant phenological data sets in the USA and Europe for broad temporal, geographic, and taxonomic analyses of how phenology is changing in relation to climate change.

}, url = {http://icbo2016.cgrb.oregonstate.edu/sites/default/files/W14-03_ICBO2016.pdf}, author = {Brian J. Stucky and John Deck and Ellen Denny and Robert P. Guralnick and Ramona L. Walls and Jennifer Yost} } @conference {W14-02, title = {W12-03: The Biological Collections Ontology for linking traditional and contemporary biodiversity data}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Biodiversity data comes from many sources, ranging from museum specimens to field surveys to genomic sequences. Domain specific standards provide vocabularies for many types of these data, but they do not fully support integrating data across methods, scales, and domains. The Biological Collections Ontology (BCO) was designed to bridge the terminology gap between traditional museum-based specimen collections and more contemporary environmental sampling methods, such as metagenomic sequencing, by providing a logically defined set of terms for biodiversity that map to standards such as the Darwin Core and Minimum Information for any Sequence. The BCO is expanding to encompass observational biodiversity data such as field surveys and taxonomic inventories. A key design principle of the BCO is to clearly distinguish the different types of processes involved in biodiversity data collection along with the inputs and outputs of those processes. The BCO has applications to plant biodiversity studies for linking herbarium specimens to sequence data, connecting trait data to specimens, and describing survey data.

}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {Ramona Walls and Rob Guralnick} } @conference {363, title = {W12-02: TraitBank: semantic integration of biodiversity data from diverse sources}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Easy access to large amounts of biodiversity data has the potential to transform research across the life sciences. However, most of the data generated so far are not easily integrated or repurposed due to a lack of standardization in how scientists talk about the characteristics of organisms, how they describe the context of their observations, and how they document the methods with which the data were collected. TraitBank (eol.org/traitbank) addresses this impediment by linking information aggregated from diverse sources to community-developed ontologies and controlled vocabularies. These post hoc annotations help to organize distributed, heterogeneous knowledge into a lightweight, scalable semantic framework supporting retrieval and reuse for a variety of applications, ranging from large-scale synthetic analyses of biodiversity to linked data products and hands-on data science in the classroom. The TraitBank data store currently holds over 11 million measurements and facts for more than 1.7 million taxa including animals, plants, fungi, and microbes. These data are mobilized from major biodiversity information systems (e.g., International Union for Conservation of Nature, Ocean Biogeographic Information System, Paleobiology Database), open literature repositories (e.g., Dryad, Ecological Archives, Pangaea), label data from natural history collections, and legacy/unpublished data sets. TraitBank subject coverage \ is very broad ranging from distribution, ecology, and life history to morphology and physiology. Data can be downloaded via CSV files or a JSON-LD service. Reuse and redistribution with attribution to the original data sources is encouraged. TraitBank complements taxon or subject-specific knowledge management systems by filling gaps (both in taxonomic and trait space), by recruiting new types of data (e.g., from text-mining, citizen-science, and specimen data digitization efforts) and by integrating knowledge across the entire tree of life and multiple scientific domains. The emerging semantic framework will facilitate data discovery, support queries across data sets, and advance data integration and exchange among projects, thus making more biodiversity data available for use in scientific and policy-oriented applications.

}, author = {Katja Schulz and Jennifer Hammock} } @conference {362, title = {W12-01: Some Challenges in Working with Biodiversity Ontologies}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, address = {Corvallis, OR}, abstract = {

We have faced a number of ontology-related challenges in developing our botanical knowledge portal, which uses Semantic Mediawiki (SMW) to store and display structured data extracted from the Flora of North America (FNA), and to integrate this data with an open biodiversity knowledge graph. We will describe some of the challenges that we have overcome, and some that we continue to struggle with. These include issues with representing and integrating data about phenotypes, habitats, phenology, and establishment means (native vs. introduced). We will also describe the structure of our biodiversity knowledge graph, and invite collaboration in its continued construction.

}, author = {Joel Sachs and Hong Cui and James Macklin} } @conference {W11-07, title = {W11-07: IC3-Foods: An infrastructure for the next generation internet of food systems, food, and health.}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {IC3-FOODS, The International Conference/Consortium/Center for Food Ontology, Operability, Data and Semantics, is a new effort at UC Davis, assembling ontological and semantic infrastructure components for next generation internet of food and health. It consists of 3 specific efforts: i) The International Conference for FOODS assembles stakeholders desiring to integrate data and informatics systems currently residing along the Environment<=>Ag<=>Food<=>Diet<=>Health knowledge spectrum, into the: ii) International Consortium of FOODS, which maintains membership of representative stakeholders from academia, industry and (non-)governmental organizations to guide research priorities and development trajectories carried out by: iii) The International Center for FOODS, whose mission consists of hosting the IConference--FOODS, administering the I-Consortium-FOODS, and designing, assembling, and coordinating ontological and infrastructure underpinnings for the emerging semantic web of ag, food, diet, and health.}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {Matthew Lange} } @conference {W11-06, title = {W11-06: FoodON Use cases: Caution! Food Allergies Ahead}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {Millions of people worldwide live with food allergies, including all those at risk for life-threatening anaphylaxis. The lack of a standardized food vocabulary impacts food source risk assessment, food hazard control, consistent food allergy policy implementation and food-allergy research. The Canadian Healthy Infant Longitudinal Study (CHILD) examines causal factors of asthma and allergy during childhood development. The development of FoodON will benefit food allergy research by standardizing food descriptors across child cohorts, enable the correlation of food antigens with biological causation of immune response, and streamline guidelines for parents.}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {Emma Griffiths} } @conference {W11-05, title = {W11-05: Food safety and infectious disease}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {Globalization of food manufacturing, distribution and consumption require food microbiology testing programs to perform high-throughput pathogen diagnostics within a short time frame. Whole-genome sequencing (WGS) can now assemble and type bacterial genomes in near real-time with improved resolution, making WGS a viable diagnostic tool during foodborne illness outbreak investigations. However, genomic data must be combined with epidemiological, clinical, laboratory and other health care data (contextual data) to be meaningfully interpreted for actionable interventions. Canada{\textquoteright}s Integrated Rapid Infectious Disease Analysis (IRIDA) project includes the development of a Genomic Epidemiology Application Ontology (GenEpiO), with the development of standardized food vocabulary as a priority area. Standardized food descriptors are essential for data sharing between public health agencies and health responders, accreditation and reproducibility of WGS pipelines, source attribution and risk assessment.}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {William Hsiao} } @conference {W11-04, title = {W11-04: Food composition: Understanding what gives food its colour, taste and aroma}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {Data on the composition of foods are essential for a diversity of purposes. It provides detailed sets of information on the nutritionally important components such as proteins, carbohydrates, vitamins and minerals. In this talk, we will describe our approach to employ ontologies to identify food components in recipes described in natural language. By combining several public data sources, we link the food components to chemical compounds and their physiological and pathological effects.}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {Miguel Garcia} } @conference {W11-03, title = {W11-03: Sustainable food systems and food in ecosystems}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {This brief talk will outline the need for a global food ontology to flexibly represent food across human and natural ecosystems. From an anthropocentric point of view, the sustainability and resilience of the global food system - including the sustainability of ecosystems and human-made networks which support it - should be closely interlinked with entities which realise food roles and the global policy objectives to secure food supply for all. From a more "natural" point of view, a truly global food ontology should be flexible enough to link taxa (including humans) to their consumers via the simultaneous realisation of prey, detrital, and food roles. This feature would provide a semantic basis to model food webs and, in combination with compositional inventories, nutritional profiles for ecoinformatics. These anthropogenic and natural perspectives will inevitably converge as a biospheric representation of trophic patterns emerges, a process which a flexible food ontology can greatly accelerate. Vitally, these aims will require coordination across multiple established and emerging ontologies to be feasible in the long term and a number of potential synergies with the Environment Ontology, the Agronomy Ontology, and the Sustainable Development Goal Interface Ontology will be proposed.}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {Pier Luigi Buttigieg} } @conference {W11-02, title = {W11-02: International Efforts in Creating Food Vocabularies}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {A standardised system for classifying and describing food makes it easier to compare data from different sources and perform more detailed types of data analyses. As such, there have been many agency-specific, project-specific and international efforts to create food vocabularies fit for different purposes. Here we describe the different existing and ongoing efforts.}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {Robert Hoehndorf and Matthew Lange} } @conference {W11-01, title = {W11-01: Why we Need Food Ontology}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {The need to represent knowledge about food is central to many fields such as health, food safety, nutrition, food allergy, sustainable development, trade, ecosystems etc. Academic, national, provincial and departmental databases are all silos of food terminology and data models. Several resources and standards exist for indexing food descriptors however their content and architecture are not semantically and logically coherent. Here we present a unified approach to developing a Farm-to-Fork food ontology which will facilitate data sharing and interoperability between different health, regulatory, development and research communities worldwide.}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {Damion Dooley} } @conference {W05-07, title = {W05-07: Ontology-based literature mining of E. coli vaccine-associated gene interaction networks}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {Pathogenic Escherichia coli infections cause various diseases in humans and many animal species. While extensive E. coli vaccine research has been conducted, we are still unable to fully protect ourselves against E. coli infections. In this study, we first extended the Vaccine Ontology (VO) to semantically represent various E. coli vaccines and genes used in the vaccine development. We also normalized E. coli gene names compiled from the annotations of various E. coli strains. The Interaction Network Ontology (INO) includes various interaction-related keywords useful for literature mining. Using VO, INO, and normalized E. coli gene names, we applied an ontology- based SciMiner literature mining strategy to mine all PubMed abstracts and retrieve E. coli vaccine-associated gene interactions. Using vaccine-related abstracts, our study identified 11,350 sentences that contain 88 unique INO interaction types and at least two out of 1,781 unique E. coli genes. From this big network, a sub-network that contains 5 E. coli vaccine genes, 62 other E. coli genes, and 25 INO interaction types were also identified. A centrality analysis of these gene interaction networks identified top ranked E. coli genes and INO interaction types. Our INO hierarchical classification also provided an effective way to identify and study the relations and patterns among the 25 interaction types.}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {Junguk Hur and Arzucan Ozgur and Edison Ong and Yongqun He} } @conference {W05-06, title = {W05-06: Hierarchical Sentiment Analysis on HPV Vaccines Related Tweets Using Machine Learning Based Approaches}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {In order to figure out the reasons behind the low HPV vaccine coverage and come up with corresponding strategies to improve vaccine uptake, understand public opinions on HPV vaccines would be of great help. As a precious and rich data source to analyze public opinions, Twitter is now attracting more attention from medical informatics researchers. In order to use machine learning based methods to automatically track and analyze rapidly-growing HPV vaccine related public opinions on Twitter, we first collected and manually annotated 6,000 related tweets as a gold standard. In order to model the possible sentiments especially the negative sentiments over HPV vaccine on Twitter, a preliminary ontology for hierarchical sentiment classification was built as the annotation scheme. A Kappa annotation agreement at 0.851 was reached. Different features (word n-grams, POS and word clusters) were extracted. Experiments were conducted to test the performance of the different combinations features sets on different levels of classification tasks. Macro F scores at 0.8043 and 0.7552 were reached for top-level classification and finest level classification respectively. The limitations and challenges were also discussed. Our results and analysis indicate that it is feasible to do hierarchical classification tasks on HPV vaccine related tweets using machine learning approaches.}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {Jingcheng Du and Jun Xu and Hsingyi Song and Xiangyu Liu and Cui Tao} } @conference {W05-05, title = {W05-05: Co-occurrence Analysis of Adverse Events for Typhoid Fever Vaccines}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {Salmonella enterica serotype Typhi is considered as one of the high-priority potential bioterrorism agents by the Center for Disease Control and Prevention (CDC). Vaccines against Typhi can help with the prophylaxis against typhoid fever. However, little effort has been conducted for post-market safety monitoring of typhoid fever vaccines. In this paper, we proposed a novel network-based computational approach to investigate the co-occurrence relationships among adverse events reported after typhoid fever vaccine (TYP). We focused on association data that were recorded in the Vaccine Adverse Event Reporting System (VAERS) between 1990 and 2014. First, we extracted and summarized adverse event (AE) information from TYP related reports in the VAERS database using Resource Description Framework (RDF). Then, we applied a series of network approaches to the AE co-occurrence network to identify potential associations among these AEs. Specifically, we (1) constructed an AE co-occurrence network after the typhoid fever vaccines; (2) calculated network properties of AE co-occurrence network; (3) identified condensed subnetworks in AE co-occurrence network; and (4) compared MedDRA terms associated with AEs in each subnetwork. We observed that (1) AE co-occurrence network shares the same scale-free network property as other biological networks and social networks; (2) AEs clustered in one subnetwork are usually enriched in certain MedDRA terms.}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {Yuji Zhang and Jingcheng Du and Cui Tao} } @conference {W05-04, title = {W05-04: LAERTES: An open scalable architecture for linking pharmacovigilance evidence sources with clinical data}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {Integrating multiple sources of pharmacovigilance evidence has the potential to advance the science of safety signal detection and evaluation. Consistent with these results, there has been a recent call for more research on how to integrate multiple disparate evidence sources while making the evidence computable from a knowledge representation perspective (i.e., semantic enrichment). Existing frameworks integrating various sources provide some of the input needed for combinatorial signal detection. However, none have been specifically designed to support both regulatory and clinical use cases, nor developed using an open architecture allowing interested scientists to easily add new sources. This paper discusses the architecture and functionality of a system called Large-scale Adverse Effects Related to Treatment Evidence Standardization (LAERTES). LAERTES provides an open and scalable architecture for linking evidence sources relevant to investigating the association of drugs with health outcomes of interest (HOIs). Standard terminologies/ontologies are used to represent different entities. For example, drugs and HOIs are represented respectively using RxNorm and SNOMED-CT. At the time of this writing, six evidence sources have been loaded into LAERTES. Also, a prototype evidence exploration user interface and set of Web API services are available. This system operates within a larger software environment provided by the OHDSI clinical research framework.}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {Richard D. Boyce and Erica A. Voss and Vojtech Huser and Lee Evans and Christian Reich and Jon D. Duke and Nicholas P. Tatonetti and Michel Dumontier and Manfred Hauben and Magnus Wallberg and Lili Peng and Sara Dempster and Yongqun He and Anthony G. Sena and Patrick B. Ryan} } @conference {W05-03, title = {W05-03: Modulated Evaluation Metrics for Drug-Based Ontologies}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {Our review of randomly selected biomedical ontologies from the National Center for Biomedical Ontology Bioportal showed that majority of the ontologies hosted did not have any documented evidence of formal ontology evaluation. The review points to the need to address this gap, if the ontology research community were to continually produce and maintain high-quality datasets for a wide-range of applications and research endeavors. As a result, this research presents a method to accurately evaluate specific domain ontologies using a semiotic framework that is delineated by the following parts {\textendash} syntactic, semantic, pragmatic, and social. Thusly, we propose the following, 1) whether a semiotic-based approach for ontology evaluation can provide meaningful assessment for biomedical ontologies and 2) if this approach can provide a more accurate assessment of the overall quality of an ontology. We applied this evaluation framework on drug-based ontologies and tailored the metric suite based on features of the drug ontologies. The results of our effort produced a customized metric for drug based ontologies, and also revelations specific to drug ontologies that may offer prescriptions for improvement {\textendash} better selection, consistency, and expressiveness of terms and labels. While ontology evaluation may be a neglected sub-field in ontology research, this study can offer a feasible direction for further research for biomedical ontologies.}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {Muhammad Amith and Cui Tao} } @conference {W05-02, title = {W05-02: Therapeutic Indications and Other Use-case-driven Updates in the Drug Ontology}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {The Drug Ontology (DrOn) is a an OWL2-based representation of drug products and their ingredients, mechanisms of action, strengths, and dose forms, as well as of packaged drug products as represented by United States National Drug Codes (NDCs) [1-3]. The primary goal of DrOn is to support analyses of large, drug-related datasets such as pharmacy claims and EHR data.}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {William R. Hogan and Josh Hanna and Amanda Hicks and Samira Amirova and Baxter Bramblett and Matthew Diller and Rodel Enderez and Timothy Modzelewski and Mirela Vasconcelos and Chris Delcher} } @conference {W05-01, title = {W05-01: On Prescribing Drug Prescriptions}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {n/a}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {Ryeyan Taseen and Jean-Francois Ethier and Adrien Barton} } @conference {W04-05, title = {W04-05: OntONeo: The Obstetric and Neonatal Ontology}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

OntONeo is an ontology for the obstetric and neonatal domain, which has been created to provide a consensus representation of salient electronic health record (EHR) data and in order to serve interoperability of the associated data and information systems. Regardless of medical specialty, in general, every EHR deal with data about the entities involved in a health care appointment. We observed the existence at least three actors: health care facility, the physician, and the patient. Besides dealing with the social entities that participating in a health care appointment, we must also deal with the characteristics that define them and the events that are involved. Here, we demonstrate the utility of ontologies of social entities in the obstetric and neonatal domain. We present how OntONeo is dealing with the material entities who perform or participates in a health care encounter. The definition of these actors plus their related characteristics and events will also contribute to turning on the interoperability of information among EHR from different specialties. OntONeo is being developed with an approach based on ontological realism and the principles of OBO Foundry, including reuse of reference ontologies. Among our reusable ontologies, we can mention for instance the OMRSE, d-acts, PATO and OBI.

}, url = {http://ceur-ws.org/Vol-1747/IT403_ICBO2016.pdf}, author = {F. Farinelli and M.B. Almeida} } @conference {W04-04, title = {W04-04: Who{\textquoteright}s paying and who{\textquoteright}s graying? The organizations and roles associated with insurance policies, funding agencies, and national census data}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {Many social roles are necessarily related to organizations. Employee roles and primary insured roles are just a few examples. However, the relations between such roles and organizations have yet to be systematically worked out in the context of BFO-based ontologies. As an initial step toward developing such a systematic representation, we present use-case driven representations connecting roles to organizations in the context of insurance policies, scientific grants, and U.S. National Census data in OWL/RDF.}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {A. Hicks and W.R. Hogan} } @conference {W04-03, title = {W04-03: An ontological study of healthcare corporations and their social entities}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {Healthcare corporations have a primary goal to provide high-quality health care to those who seek its assistance. The quality and safety of care provided by a healthcare corporation depends on many factors involving both medical and business decisions. One crucial factor in healthcare corporations function is the information management mainly performed through information systems, which process information for both clinical decision making and for fulfilling internal and external legal obligations. In this lecture, we propose a sketch of an ontology-based model for healthcare corporations with the aim of facilitating the coordination of the information systems involved in either medical or management activities. In order to accomplish this, we focus on three efforts: i) to shed some light on the ontological status of corporations; ii) to clarify the relations that exist between the corporation as whole and both its members and units; iii) to explain how an corporation administers its duties and responsibilities on behalf of people who compose it.}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {M.B. Almeida} } @conference {W04-02, title = {W04-02: Relations between Institutional Roles and Deontic Roles in Biomedical Organizations}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {Doctors, nurses, surgeons, and other healthcare professionals are bearers of institutional roles (e.g. physician role), and it is common to think of these roles as having deontic powers as parts. This is reflected in sentences like: "Part of my job involves an obligation to oversee patient care" and "Doctors at this hospital have the following privileges...". The Document Act Ontology (d-acts; http://purl.obolibrary.rog/obo/iao/d-acts.owl) enables us to represent how deontic powers are created by document acts. Deontic powers are realizable entities that we treat as deontic roles (e.g. obligor role). This means deontic powers are roles themselves. In this talk, we turn to the question of the relationships between institutional roles and deontic roles. We propose that institutional roles can have deontic roles as parts. We illustrate how different kinds of deontic powers give rise to different parthood relations, and we conclude by arguing that such relations can better capture the nature of organizational structure than the traditional reliance on institutional roles alone.}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {Otte J.N. and Brochhausen M.} } @conference {W04-01, title = {W04-01: Ontology of the Organigram}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {Basic Formal Ontology (BFO) is a domain-neutral top-level ontology designed to serve as the starting point for development of domain ontologies designed to support the consistent annotation not only of scientific research data but also of data arising through clinical practice, hospital administration, and regulatory oversight. In each of these areas data are generated relating to what are called deontic entities {\textendash} obligations, duties, contracts, permissions, consents, licenses, and so forth. I will sketch how we can understand entities of these sorts within the BFO framework.}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {B. Smith} } @conference {360, title = {W01-05: Uncertainty analysis and visualization in Large-Scale Vector Fields}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, address = {Corvallis, Oregon, USA}, abstract = {

Vector fields are omnipresent in science, engineering, and medicine. Due to the big-data nature of simulated vector field data, uncertainty in the data can lead to difficulties in their physical interpretations. In this talk, we will describe how Morse-decomposition can serve as a means to quantify and control the uncertainty in the data.

}, keywords = {Big data, data uncertainty, data visualization}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {Eugene Zhang} } @conference {350, title = {W01-04: Telling a genome{\textquoteright}s story graphically}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, address = {Corvallis, Oregon, USA}, abstract = {

Scientific research is inherently a collaborative task; a dialog among different researchers to reach a consensus understanding of the underlying biology. Information graphics facilitate this dialog because humans are visually wired and can absorb well-executed graphics more quickly than they can absorb the written word or columns of numbers. Visual representations communicate complex ideas quickly and clearly.

This talk will briefly introduce basic principles of designing interactive graphics, with examples from the genomics community illustrating various points. It will also discuss the lessons learned with our own annotation tools: PAINT{\textemdash}a phylogenetically based functional annotation tool (https://github.com/geneontology/paint) , Apollo{\textemdash}a genomic feature editor designed to support structural annotation of gene models (http://genomearchitect.org/),\  and Noctua{\textemdash}a biological-process model builder designed for describing the functional roles of gene products (http://noctua.berkeleybop.org/).

In addition to the graphical elements we summarize the requirements that enable any annotation tool to meet the needs of the research community, including: Real time updates to allow geographically dispersed researchers to conduct joint efforts; Parallel chat mechanisms; Maintaining an evidence trail for all assertions; Well supported history mechanisms and browsing of past versions; Providing different levels of permissions; Facilitating publication; Responsiveness to users{\textquoteright} requests; Documentation and dedicated resources for training and support.

}, keywords = {BIG-data, data visualization, genome, ontology}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {Suzanna Lewis} } @conference {358, title = {W01-03: Computer Vision for Next Generation Phenomics and Tree of Life}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, address = {Corvallis, Oregon, USA}, abstract = {

To build the Tree of Life, scientists collect data on all heritable features {\textendash} both genotypes (e.g., DNA sequences) and phenotypes (e.g., anatomy, behavior, physiology) for all living and extinct species.\  The collection of phenomic data for tree-building has lagged far behind the collection of genomic data. Advances in computer vision have the potential to change this situation. In this talk, I will present a computer vision system developed in our lab for extending phenomic matrices, and in this way\ building the Tree of Life.\ Rows of a phenomic matrix represent images of specimens belonging to various species of interest, and columns represent scores of their phenomic characters. Given a\ phenomic matrix where only few rows are manually annotated with character scores, our vision system extends the matrix row-wise by populating missing character scores of the remaining species in the matrix. The talk will present our experimental results on scoring phenomic characters in images of bat skulls, nematocysts, and leaves, available in the Morphobank and Bisque data repositories.

}, keywords = {Bisque data repository, data visualization, Morphobank, Phenotypes, Tree of Life}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {Sinisa Todorovic} } @conference {359, title = {W01-02: Topology-Driven Data Visualization of Large-Scale Tensor Fields}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, address = {Corvallis, Oregon, USA}, abstract = {

Spatial-temporally varying simulation data sets are growing at a scale that traditional\ visualization techniques are inadequate to handle. In this talk, we review topology-driven techniques which focus on extracting the key (topological) features in 3D symmetric tensor fields, which can provide a more compact visualization of the data.

}, keywords = {data visualization, tensor fields, topology}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {Yue Zhang} } @conference {361, title = {W01-01: Big Data Visual Analysis}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, address = {Corvallis, Oregon, USA}, abstract = {

We live in an era in which the creation of new data is growing exponentially such\ that every two days we create as much new data as we\ did from the beginning of\ mankind until the year 2003. One of the greatest scientific challenges of the 21st\ century is to effectively\ understand and make use of the vast amount of information\ being produced. Visual data analysis will be among our most important tools\ to\ understand such large and often complex data. In this talk, I will present state-of-the-art visualization techniques, applied to important Big Data problems in science, engineering, and\ medicine.

}, keywords = {BIG-data, data visualization}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {Christopher Johnson} } @conference {IT705, title = {IT705: A Realist Representation of Social Identity Data}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Social identities merit special treatment in realist ontologies. Their ontological status is unsettled, so we should model them in a manner that is agnostic with respect to their ontological status. Nevertheless, there is a clear criterion for determining whether a specific person has a particular identity, namely, whether that person asserts that they do. This social act forms the basis for a realist representation, not of social identities themselves, but of data about social identities. We report the representation of social identities in the Ontology of Medically Related Social Entities and show that it supports data integration and retrieval.

}, url = {http://ceur-ws.org/Vol-1747/IT705_ICBO2016.pdf}, author = {Amanda Hicks} } @conference {IT704, title = {IT704: Representation of parts within the Foundational Model of Anatomy ontology}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

As biomedical ontologies grow in size and complexity it is crucial to develop methods for detecting inconsistencies within ontologies. The Foundational Model of Anatomy (FMA) ontology represents knowledge of human anatomy, with structural organization provided by class and part relationships. Using a manual audit, I identify types of inconsistencies arising from class and regional part relationships for regions of the body and the parts of organs. Inconsistencies arise from both explicitly declared relationships and relationships that are implied by the lexical constructs of class names. The purpose of this work is to propose methods of structural organization and lexical consistency that will make the FMA more compatible with computational auditing and increase its usability.

}, url = {http://ceur-ws.org/Vol-1747/IT704_ICBO2016.pdf}, author = {Melissa Clarkson} } @conference {IT703, title = {IT703: Semantic Digitization of Experimental Data in Biological Sciences}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

A major bulk of published experimental data, referred to as {\^O}Gold Standard{\~O} data, is available in a format that cannot be easily accessed by computers unless effectively curated. Most curation techniques bank on mining the text for information. Here we propose and demonstrate the efficacy of curating the experimental data itself. The data models facilitate digitization of the every aspect of the information associated with the experimental data. The models utilize several universally accepted ontologies as well as in-house developed alphanumeric notations for digitizing different aspect of the data. The data models have sufficient flexibility to address the extensive variability in experimental data. They have a very generic nature and can be used to curate and digitize experimental data from any organism. The digitized data is easily stored in a relational database management system and can thus be rapidly searched and integrated. These models have been successfully used to digitize data from over 20,000 experiments spanning over 500 research articles on rice biology. The entire dataset is available as a database entitled {\^O}Manually Curated Database of Rice Proteins{\~O} at www.genomeindia.org/biocuration.

}, url = {http://ceur-ws.org/Vol-1747/IT703_ICBO2016.pdf}, author = {Saurabh Raghuvanshi} } @conference {IT702, title = {IT702: To MIREOT or not to MIREOT? A case study of the impact of using MIREOT in the Experimental Factor Ontology (EFO)}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

MIREOT is a mechanism for the selective re-use of individual ontology classes in other ontologies. Designed to minimise effort and to support orthogonality, it is now in widespread use. The consequences for ontology integrity and automated reasoning of using the MIREOT mechanism have so far not been fully assessed. In this paper, we perform an analysis of the Experimental Factor Ontology (EFO), an ontology which uses the MIREOT process to gather classes from a large range of other ontologies. Our study examines the effect of combining EFO with the ontologies it references by actually importing them into the EFO. We then evaluate the consistency and status of the combined ontologies. Through our investigation, we reveal that EFO in combination with all its referenced ontologies is logically inconsistent. Furthermore, when EFO is individually combined with many of the ontologies it references, we find a large number of unsatisfiable classes. These results demonstrate a potential problem within a major ontological ecosystem, and reveals possible disadvantages to the use of the MIREOT system for developing ontologies.

}, url = {http://ceur-ws.org/Vol-1747/IT702_ICBO2016.pdf}, author = {Luke Slater and Georgios Gkoutos and Paul Schofield and Robert Hoehndorf} } @conference {IT701, title = {IT701: A Quality-Assurance Study of ChEBI}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Ontologies are important components of many health-information systems. The Chemical Entities of Biological Interest (ChEBI) ontology has become a standard reference for chemicals appearing in biological contexts. As such, assuring the quality of its content is imperative. In fact, ChEBI has a dedicated Web page at which errors and inconsistencies in its concepts can be reported. A study of the correctness of a random sample of ChEBI concepts is carried out. The results show that quite a large number of ChEBI concepts suffer from some kind of problematic modeling. For example, we found that 15.5\% of the sample concepts exhibited severe errors of commission, including incorrect hierarchical (is a) and lateral relationships. Errors of omission were also prevalent. The overall results of our quality-assurance (QA) study are presented. Suggestions for enhancing the QA processes in place for ChEBI are discussed.

}, url = {http://ceur-ws.org/Vol-1747/IT701_ICBO2016.pdf}, author = {Hasan Yumak and Ling Chen and Michael Halper and Ling Zheng and Yehoshua Perl and Gai Elhanan} } @conference {IT606, title = {IT606: Measuring the importance of annotation granularity to the detection of semantic similarity between phenotype profiles}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Inphenotypeannotationscuratedfromthebiolog-icalandmedicalliterature,considerablehumaneffortmustbeinvestedtoselectontologicalclassesthatcapturetheexpressivityoftheoriginalnaturallanguagedescriptions,andannotationgranularitycanalsoentailhighercomputationalcostsforpartic-ularreasoningtasks.Docoarseannotationsforcertainapplications?Here,wemeasurehowannotationgranularityaffectsthestatisticalbehaviorofsemanticsimilaritymetrics.Weusearandomizeddatasetofphenotypeprdrawnfrom57,051taxon-phenotypeannotationsinthePhenoscapeKnowledgebase.WecomparedqueryprhavingvariableproportionsofmatchingphenotypestosubjectdatabaseprusingbothpairwiseandgroupwiseJaccard(edge-based)andResnik(node-based)semanticsimilaritymetrics,andcomparedstatisticalperformanceforthreedifferentlevelsofannotationgranularity:entitiesalone,entitiesplusattributes,andentitiesplusqualities(withimplicitattributes).Allfourmetricsexaminedshowedmoreextremevaluesthanexpectedbychancewhenapproximatelyhalftheannotationsmatchedbetweenthequeryandsubjectprwithamoresuddendeclineforpairwisestatisticsandamoregradualoneforthegroupwisestatistics.Annotationgranularityhadanegligibleeffectonthepositionofthethresholdatwhichmatchescouldbediscriminatedfromnoise.Theseresultssuggestthatcoarseannotationsofphenotypes,atthelevelofentitieswithorwithoutattributes,maybetoidentifyphenotypeprwithstatisticallysemanticsimilarity.

}, url = {http://ceur-ws.org/Vol-1747/IT606_ICBO2016.pdf}, author = {Prashanti Manda and James P. Balhoff and Todd J. Vision} } @conference {IT605, title = {IT605: SEPIO: A Semantic Model for the Integration and Analysis of Scientific Evidence}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

The Scientific Evidence and Provenance Information Ontology (SEPIO) was developed to support the description of evidence and provenance information for scientific claims. The core model represents the relationships between claims, their lines of evidence, and the data items that comprise this evidence, as well as the methods, tools, and agents involved in the creation of these artifacts. SEPIO was initially developed to support the data integration and analysis efforts of the Monarch Initiative, where it provides a unified and computable representation of evidence and provenance metadata for genotype-phenotype associations aggregated across diverse model organism and clinical genetics databases. However, additional requirements were collected from diverse community partners in an effort to provide a shared community standard, with a core model that is domain independent and extensible to represent any type of claim and its associated evidence. In this report we describe the structure and principles behind the SEPIO model, and review its applications in support of data integration, curation, knowledge discovery, and manual and computational evaluation of scientific claims. The SEPIO ontology can be found at http://github.com/monarch-initiative/SEPIO-ontology/blob/master/src/ontology/sepio.owl.

}, url = {http://ceur-ws.org/Vol-1747/IT605_ICBO2016.pdf}, author = {Matthew Brush and Kent Shefchek and Melissa Haendel} } @conference {IT604, title = {IT604: Qualitative causal analyses of biosimulation models}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

We describe an approach for performing qualita-tive, systems-level causal analyses on biosimulation models that leverages semantics-based modeling formats, formal ontology, and automated inference. The approach allows users to quickly investigate how a qualitative perturbation to an element within a model{\~O}s network (an increment or decrement) propagates throughout the modeled system. To support such analyses, we must interpret and annotate the semantics of the models, includ-ing both the physical properties modeled and the dependencies that relate them. We build from prior work understanding the semantics of biological properties, but here, we focus on the se-mantics for dependencies, which provide the critical knowledge necessary for causal analysis of biosimulation models. We de-scribe augmentations to the Ontology of Physics for Biology, via OWL axioms and SWRL rules, and demonstrate that a reasoner can then infer how an annotated model{\~O}s physical properties influence each other in a qualitative sense. Our goal is to provide researchers with a tool that helps bring the systems-level network dynamics of biosimulation models into perspective, thus facilitat-ing model development, testing, and application.

}, url = {http://ceur-ws.org/Vol-1747/IT604_ICBO2016.pdf}, author = {Maxwell Neal and John Gennari and Daniel Cook} } @conference {IT603, title = {IT603: Improving the Semantics of Drug Prescriptions with a Realist Ontology}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Electronic prescriptions are supported as a means to reduce adverse drug events, but the ambiguities and overspecificities of prescription semantics along with their lack of standardization reduce adoption, limit interoperability and are potential sources of error. Ontologies in the OBO Foundry, founded on realist methodology, have been successful in fostering the logical, scientifically accurate data standards that the domain of drug prescriptions is currently in need of. This paper illustrates some problems regarding the structuration of current electronic prescriptions, and demonstrates how the Prescription of Drugs Ontology (PDRO) addresses these issues with improved semantics founded on OBO and realist principles. PDRO reuses classes and object properties from IAO, OBI, OGMS, OMRSE and DRON, introducing new entities within its scope and proposing entities within those of its imported domains that may be useful to other health care and information artifact-related ontologies in the OBO Foundry. PDRO aims at improving the semantics of drug prescriptions and prospectively enabling the interoperability of prescription data.

}, url = {http://ceur-ws.org/Vol-1747/IT603_ICBO2016.pdf}, author = {Jean-Francois Ethier and Ryeyan Taseen and Luc Lavoie and Adrien Barton} } @conference {IT602, title = {IT602: A Semantic Web Representation of Entire Populations}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Accurately representing demographic realities is a critical component in creating useful, agent-based epidemiological models of infectious disease. Synthetic ecosystems are generated from Census data microsamples in a statistically-sound manner to maintain population-level demographic characteristics. These highly detailed representations of populations are the basis of many advanced simulations of infectious disease epidemics. Creating a standard, machine-readable representation of synthetic ecosystem data would enable easier use and integration with epidemic simulator software. Here we describe an ontology-based representation in Resource Description Framework (RDF) and Web Ontology Language (OWL) of version 1.0 of the 2010 U.S. Synthetic Population database by RTI International. Our representation draws upon applicable classes from several reference ontologies, including the Ontology of Medically Related Social Entities (OMRSE). After failing to find suitable ontological representations of several key data elements in the Synthetic Population dataset, we created new classes in OMRSE for representing employment status, employee roles, workplaces, residences, households, and age measurements. We loaded a test RDF dataset (structured according to ontologies in OWL) of synthetic individuals into a commercial triple store (Stardog) and validated the representation with SPARQL queries.

}, url = {http://ceur-ws.org/Vol-1747/IT602_ICBO2016.pdf}, author = {Daniel Welch and Amanda Hicks and Josh Hanna and William Hogan} } @conference {IT601, title = {IT601: Identifying Missing Hierarchical Relations in SNOMED CT from Logical Definitions Based on the Lexical Features of Concept Names}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Objectives. To identify missing hierarchical relations in SNOMED CT from logical definitions based on the lexical features of concept names. Methods. We first create logical definitions from the lexical features of concept names, which we represent in OWL EL. We infer hierarchical (subClassOf) relations among these concepts using the ELK reasoner. Finally, we compare the hierarchy obtained from lexical features to the original SNOMED CT hierarchy. We review the differences manually for evaluation purposes. Results. Applied to 15,833 disorder and procedure concepts, our approach identified 559 potentially missing hierarchical relations, of which 78\% were deemed valid. Conclusions. This lexical approach to quality assurance is easy to implement, efficient and scalable.

}, url = {http://ceur-ws.org/Vol-1747/IT601_ICBO2016.pdf}, author = {Olivier Bodenreider} } @conference {IT507, title = {IT507: Natural Language Definitions for the Leukemia Knowledge Domain}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

The creation of natural definitions is a phase of any methodology to build formal ontologies. In order to reach formal definitions, one should first create natural language definitions according to sound principles. We gather a set of principles available in literature and organize them in a list of stages that one can use to create good definitions in natural language. In order to test the set of principles, we conducted a case study in which we create definitions in the domain of cancer, more specifically, definitions for acute myeloid leukemia. After creating and validating the definition of this specific kind of leukemia, we offer remarks about the experiment.

}, url = {http://ceur-ws.org/Vol-1747/IT507_ICBO2016.pdf}, author = {AD De Souza and MB Almeida} } @conference {IT506, title = {IT506: An Ontological Framework for Representing Topological Information in Human Anatomy}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Medical ontologies have been a focus of constant attention in recent years as one of the fundamental techniques and knowledge bases for clinical decision support applications. In this paper, we discuss the description framework of our anatomy ontology with a focus on representing topological information, which is required for anatomical reasoning in clinical decision support applications. Our framework has major advantages over preceding studies with respect to: (1) representations of branching sequence; (2) combined representation of relevant knowledge with the use of {\`O}general structural component{\'O}; and (3) cooperation with the disease and abnormality ontologies.

}, url = {http://ceur-ws.org/Vol-1747/IT506_ICBO2016.pdf}, author = {Takeshi Imai and Emiko Shinohara and Masayuki Kajino and Ryota Sakurai and Kazuhiko Ohe and Kouji Kozaki and Riichiro Mizoguchi} } @conference {IT505, title = {IT505: Towards a Standard Ontology Metadata Model}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Bio-ontologies are becoming increasingly important in semantic alignment for data integration, information exchange, and semantic interoperability. Due to the large number of emerging bio-ontologies, it is challenging for ontology for their applications. Therefore, it is important to have a consistent terminology metadata model and a resource for discovering appropriate ontologies or other resource for use in annotating data. This paper aims to seek a common, shareable, and comprehensive method to create, disseminate, and consume metadata about terminology resources.

}, url = {http://ceur-ws.org/Vol-1747/IT505_ICBO2016.pdf}, author = {Hua Min and Stuart Turner and Sherri de Coronado and Brian Davis and Trish Whetzel and Robert R. Freimuth and Harold R. Solbrig and Richard Kiefer and Michael Riben and Grace A. Stafford and Lawrence Wright and Riki Ohira} } @conference {IT504, title = {IT504: OOSTT: a Resource for Analyzing the Organizational Structures of Trauma Centers and Trauma Systems}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Organizational structures of healthcare organiza-tions has increasingly become a focus of medical research. In the CAF{\'E} project we aim to provide a web-service enabling ontol-ogy-driven comparison of the organizational characteristics of trauma centers and trauma systems. Trauma remains one of the biggest challenges to healthcare systems worldwide. Research has demonstrated that coordinated efforts like trauma systems and trauma centers are key components of addressing this chal-lenge. Evaluation and comparison of these organizations is es-sential. However, this research challenge is frequently com-pounded by the lack of a shared terminology and the lack of ef-fective information technology solutions for assessing and com-paring these organizations. In this paper we present the Ontol-ogy of Organizational Structures of Trauma systems and Trauma centers (OOSTT) that provides the ontological founda-tion to CAF{\'E}{\textquoteright}s web-based questionnaire infrastructure. We present the usage of the ontology in relation to the questionnaire and provide the methods that were used to create the ontology.

}, url = {http://ceur-ws.org/Vol-1747/IT504_ICBO2016.pdf}, author = {Joseph Utecht and John Judkins and Terra Colvin Jr. and J. Neil Otte and Nicholas Rogers and Robert Rose and Maria Alvi and Amanda Hicks and Jane Ball and Stephen M. Bowman and Robert T. Maxson and Rosemary Nabaweesi and Rohit Pradhan and Nels D. Sanddal and M. Eduard Tudoreanu and Robert Winchell and Mathias Brochhausen} } @conference {IT503, title = {IT503: Malaria study data integration and information retrieval based on OBO Foundry ontologies}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

The International Centers of Excellence in Malaria Research (ICEMR) projects involve studies to understand the epidemiology and transmission patterns of malaria in different geographic regions. Two major challenges of integrating data across these projects are: (1) standardization of highly heterogeneous epidemiologic data collected by various ICEMR projects; (2) provision of user-friendly search strategies to identify and retrieve information of interest from the very complex ICEMR data. We pursued an ontology-based strategy to address these challenges. We utilized and contributed to the Open Biological and Biomedical Ontologies to generate a consistent semantic representation of three different ICEMR data dictionaries that included ontology term mappings to data fields and allowed values. This semantic representation of ICEMR data served to guide data loading into a relational database and presentation of the data on web pages in the form of search filters that reveal relationships specified in the ontology and the structure of the underlying data. This effort resulted in the ability to use a common logic for storing and display of data on study participants, their clinical visits, and epidemiological information on their living conditions (dwelling) and geographic location. Users of the Plasmodium Genomics Resource, PlasmoDB, accessing the ICEMR data will be able to search for participants based on environmental factors such as type of dwelling, location or mosquito biting rate, characteristics such as age at enrollment, relevant genotypes or gender and visit data such as laboratory findings, diagnoses, malaria medications, symptoms, and other factors.

}, url = {http://ceur-ws.org/Vol-1747/IT503_ICBO2016.pdf}, author = {Jie Zheng and Jashon Cade and Brian Brunk and David Roos and Chris Stoeckert and San James and Emmanuel Arinaitwe and Bryan Greenhouse and Grant Dorsey and Steven Sullivan and Jane Carlton and Gabriel Carrasco-Escobar and Dionicia Gamboa and Paula Maguina-Mercedes and Joseph Vinetz} } @conference {IT502, title = {IT502: Visualizing the {\textquotedblleft}Big Picture{\textquotedblright} of Change in NCIt{\textquoteright}s Biological Processes}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

The National Cancer Institute thesaurus (NCIt) is a large and complex ontology. NCIt is frequently updated; a new release is made available approximately every month. Tracking structural changes in NCIt is important for the editors of its content. In this paper we describe a methodology and tool using diff partial-area taxonomies to visually summarize structural changes between two NCIt releases. Diff partial-area taxonomies provide a comprehensible view of the overall impact of the changes. This methodology is illustrated using the Biological Process hierarchy. Specifically, we illustrate how diff partial-area taxonomies reflect change that occurred due to major restructuring of this hierarchy between September 2004 and December 2004. During this time the hierarchy nearly doubled in size and a large portion of the classes were extensively modified. Several kinds of change patterns are identified and discussed.

}, url = {http://ceur-ws.org/Vol-1747/IT502_ICBO2016.pdf}, author = {Yehoshua Perl and Christopher Ochs and Sherri de Coronado and Nicole Thomas} } @conference {IT501, title = {IT501: A Descriptive Delta for Identifying Changes in SNOMED CT}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

SNOMED CT is a large and complex medical terminology. Thousands of editing operations are applied to its content for each new release. Understanding what changed in a release is important for the end user and SNOMED CT editors. Each SNOMED CT release comes with release notes that provide a brief description of the changes that occurred and a set of delta files that identify individual changes in the content. The release notes are brief and changes to thousands of concepts may be described in a few sentences, whereas the delta files contain tens of thousands of individual changes. To better identify how SNOMED CT content changes between releases we introduce a methodology of creating a descriptive delta that captures the editing operations that were applied to SNOMED CT content in a given release in a more comprehensible form. We use this methodology to analyze editing operations that were part of a recent remodeling effort of the Congenital disease and Infectious disease subhierarchies in the large Clinical finding hierarchy.

}, url = {http://ceur-ws.org/Vol-1747/IT501_ICBO2016.pdf}, author = {Christopher Ochs and Yehoshua Perl and Gai Elhanan and James Case} } @conference {IT407, title = {IT407: Annotating germplasm to Planteome reference ontologies}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

An expected use case of plant phenotype ontologies will be the identification of germplasm containing particular traits of interest. If phenotype data from experiments is annotated using ontologies, it makes sense to include annotations to that germplasm source. A lack of standardized data formatting reduces the utility of these data. Standardizing germplasm data, including links to germplasm databases, or distribution locations improves collaboration, and benefits both researchers and the scientific community as a whole. All plant traits contained in the Planteome reference ontologies are searchable, and interconnected through relationships in the ontology. All data annotated to these reference ontologies will be displayed, shareable, and computable through the Planteome website (www.planteome.org) and APIs. This manuscript will discuss the advantages of standardizing germplasm trait annotation, and the semi-automated process developed to achieve such standardization.

}, url = {http://ceur-ws.org/Vol-1747/IT407_ICBO2016.pdf}, author = {Austin Meier and Laurel Cooper and Justin Elser and Pankaj Jaiswal and Marie-Ang{\'e}lique Laporte} } @conference {IT406, title = {IT406-IP35: The Planteome Project}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

The Planteome project is a centralized online plant informatics portal which provides semantic integration of widely diverse datasets with the goal of plant improvement. Traditional plant breeding methods for crop improvement may be combined with next-generation analysis methods and automated scoring of traits and phenotypes to develop improved varieties. The Planteome project (www.planteome.org) develops and hosts a suite of reference ontologies for plants associated with a growing corpus of genomics data. Data annotations linking phenotypes and germplasm to genomics resources are achieved by data transformation and mapping species-specific controlled vocabularies to the reference ontologies. Analysis and annotation tools are being developed to facilitate studies of plant traits, phenotypes, diseases, gene function and expression and genetic diversity data across a wide range of plant species. The project database and the online resources provide researchers tools to search and browse and access remotely via APIs for semantic integration in annotation tools and data repositories providing resources for plant biology, breeding, genomics and genetics.

}, url = {http://ceur-ws.org/Vol-1747/IT406-IP35_ICBO2016.pdf}, author = {Laurel Cooper and Austin Meier and Justin Elser and Justin Preece and Xu Xu and Ryan Kitchen and Botong Qu and Eugene Zhang and Sinisa Todorovic and Pankaj Jaiswal and Marie-Ang{\'e}lique Laporte and Elizabeth Arnaud and Seth Carbon and Chris Mungall and Barry Smith and Georgios Gkoutos and John Doonan} } @conference {IT405, title = {IT405: Building Concordant Ontologies for Drug Discovery}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

n this study we demonstrate how we interconnect three different ontologies, the BioAssay Ontology (BAO), LINCS Information FramEwork ontology (LIFEo), and the Drug Target Ontology (DTO). The three ontologies are built and maintained for three different projects: BAO for the BioAssay Ontology Project, LIFEo for the Library of Integrated Network-Based Cellular Signatures (LINCS) project, and DTO for the Illuminating the Druggable Genome (IDG) project. DTO is a new ontology that aims to formally describe drug target knowledge relevant to drug discovery. LIFEo is an application ontology to describe information in the LIFE software system. BAO is a highly accessed NCBO ontology; it has been extended formally to describe several LINCS assays. The three ontologies use the same principle architecture that allows for re-use and easy integration of ontology modules and instance data. Using the formal definitions in DTO, LIFEo, and BAO and data from various resources one can quickly identify disease-relevant and tissue- specific genes, proteins, and prospective small molecules. We show a simple use case example demonstrating knowledge-based linking of life science data with the potential to empower drug discovery.

}, url = {http://ceur-ws.org/Vol-1747/IT405_ICBO2016.pdf}, author = {Hande K{\"u}{\c c}{\"u}k-Mcginty and Saurabh Metha and Yu Lin and Nooshin Nabizadeh and Vasileios Stathias and Dusica Vidovic and Amar Koleti and Christopher Mader and Jianbin Duan and Ubbo Visser and Stephan Schurer} } @conference {IT404, title = {IT404: Ten simple rules for biomedical ontology development}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Biomedical ontology development is often a time and resource consuming endeavor. To maximize efficiency of the process, we present a set of 10 simple rules covering basic technical requirements such as scoping and versioning, while considering additional elements such as licensing and community engagement. When applied, the rules will help avoid common pitfalls and jump-start ontology building.

}, url = {http://ceur-ws.org/Vol-1747/IT404_ICBO2016.pdf}, author = {Melanie Courtot and James Malone and Chris Mungall} } @conference {IT403, title = {IT403: OntONeo: The Obstetric and Neonatal Ontology}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

This paper presents the Obstetric and Neonatal Ontology (OntONeo). This ontology has been created to provide a consensus representation of salient electronic health record (EHR) data and to serve interoperability of the associated data and information systems. More generally, it will serve interoperability of clinical and translational data, for example deriving from genomics disciplines and from clinical trials. Interoperability of EHR data is important to ensuring continuity of care during the prenatal and postnatal periods for both mother and child. As a strategy to advance such interoperability we use an approach based on ontological realism and on the ontology development principles of the Open Biomedical Ontologies Foundry, including reuse of reference ontologies wherever possible. We describe the structure and coverage domain of OntONeo and the process of creating and maintaining the ontology.

}, url = {http://ceur-ws.org/Vol-1747/IT403_ICBO2016.pdf}, author = {Fernanda Farinelli and Mauricio Almeida and Peter Elkin and Barry Smith} } @conference {IT402, title = {IT402: Enhancing the Human Phenotype Ontology for Use by the Layperson}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

In rare or undiagnosed diseases, physicians rely upon genotype and phenotype information in order to compare abnormalities to other known cases and to inform diagnoses. Patients are often the best sources of information about their symptoms and phenotypes. The Human Phenotype Ontology (HPO) contains over 12,000 terms describing abnormal human phenotypes. However, the labels and synonyms in the HPO primarily use medical terminology, which can be difficult for patients and their families to understand. In order to make the HPO more accessible to non-medical experts, we systematically added new synonyms using non-expert terminology (i.e., layperson terms) to the existing HPO classes or tagged existing synonyms as layperson. As a result, the HPO contains over 6,000 classes with layperson synonyms.

}, url = {http://ceur-ws.org/Vol-1747/IT402_ICBO2016.pdf}, author = {Nicole Vasilevsky and Mark Engelstad and Erin Foster and Chris Mungall and Peter Robinson and Sebastian K{\"o}hler and Melissa Haendel} } @conference {IT401, title = {IT401: An analysis of differences in biological pathway resources}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Integratingcontentfrommultiplebiologicalpathwayresourcesisnecessarytofullyexploitpathwayknowledgefortheofbiologyandmedicine.Dif-ferencesincontent,representation,coverage,andmoreoccurbetweendatabases,andarechallengestoresourcemerging.Weintroduceatypologyofrepresentationaldifferencesbetweenpathwayresourcesandgiveexam-plesusingseveraldatabases:BioCyc,KEGG,PANTHERpathways,andReactome.WealsodetectandquantifyannotationmismatchesbetweenHumanCycandReactome.Thetypologyofmismatchescanbeusedtoguideentityandrelationshipalignmentbetweenthesedatabases,helpingusidentifyandunderstandinourknowledge,andallowingtheresearchcommunitytoderivegreaterfromtheexistingpathwaydata.

}, url = {http://ceur-ws.org/Vol-1747/IT401_ICBO2016.pdf}, author = {Lucy Wang and John Gennari and Neil Abernethy} } @conference {IT206, title = {IT206: The UNEP Ontologies and the OBO Foundry}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

n/a

}, url = {http://ceur-ws.org/Vol-1747/IT206_ICBO2016.pdf}, author = {Barry Smith and Mark Jensen} } @conference {IT205, title = {IT205: Data-driven Agricultural Research for Development: A Need for Data Harmonization Via Semantics}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Addressing global challenges to agricultural productivity and profitability increasingly requires access to data from a variety of disciplines, and the ability to easily combine and analyze related data sets. Innovation in agricultural research for development must therefore be mediated by reliable and consistently annotated information resources across disciplinary domains. Leveraging semantics ensures this consistency and ease of reuse, and the global CGIAR Consortium that includes 15 agricultural research for development Centers is attempting to harness this promise through efforts such as its Open Access, Open Data Initiative. CGIAR{\texttrademark}s Crop Ontology project plays a key role in this, and will soon be enhanced by an Agronomy Ontology (AgrO). AgrO is being built to represent traits identified by agronomists and the simulation model variables of the International Consortium for Agricultural Systems Applications (ICASA). Further, it will coordinate its semantics with existing ontologies such as the Environment Ontology (ENVO), Unit Ontology (UO), and Phenotype And Trait Ontology (PATO). Once stable, it is anticipated to address one of the domains temporarily represented in the Sustainable Development Goals Interface Ontology (SDGIO), pertaining to multiple SDGs such as the elimination of hunger and poverty. AgrO will complement existing crop, livestock, and fish ontologies to enable harmonized approaches to data collection, facilitating data sharing and reuse. Further, AgrO will power an Agronomy Management System and fieldbook, similar to the Crop Ontology-based Integrated Breeding Platform (IBP) and fieldbook. There is substantial interest from agronomists and modelers in such a fieldbook to standardize agronomic data collection, and the ontology itself as a means of facilitating hitherto missing linkages with breeding and other data, and enabling wider sharing and reuse of agronomic research data.

}, url = {http://ceur-ws.org/Vol-1747/IT205_ICBO2016.pdf}, author = {Medha Devare and C{\'e}line Aubert and Marie-Ang{\'e}lique Laporte and L{\'e}o Valette and Elizabeth Arnaud and Pier Luigi Buttigieg} } @conference {IT204, title = {IT204: A sustainable approach to knowledge representation in the domain of sustainability: bridging SKOS and OWL}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {n/a}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {Chris Mungall and Mark Jensen and Marie-Ang{\'e}lique Laporte and Pier Buttigieg} } @conference {IT203, title = {IT203: Defining and sustaining populations and communities}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

The UN Sustainable Development Goals (SDGs) cover subjects such as ending poverty, achieving gender equality, ensuring access to water, energy, and food, and protecting ecosystems. Every SDG includes wording that refers directly or indirectly to a population or community or organisms, humans or otherwise. Therefore, the Population and Community Ontology (PCO) plays a crucial role in defining the language of the SDGs and their targets and indicators. This talk will describe the PCO and its applicability to sustainability studies.

}, url = {http://ceur-ws.org/Vol-1747/IT203_ICBO2016.pdf}, author = {Ramona Walls} } @conference {IT202, title = {IT202: Sustainable Development Goals Interface Ontology}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

n/a

}, url = {http://ceur-ws.org/Vol-1747/IT202_ICBO2016.pdf}, author = {Mark Jensen} } @conference {IT201, title = {IT201: Environmental semantics for sustainable development in an interconnected biosphere}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Development unavoidably impacts the ecosystems constituting often producing complex outcomes across a range of spatial and temporal scales. The interconnectivity of global ecosystems and their varied responses to disturbance necessitate great caution when using or encountering terms such as sustainable and sustainability. The Environment Ontology (ENVO; www.environmentontology.org) is coordinating with the Sustainable Development Goals Interface Ontology (SDGIO) to improve semantic representation of environments in the context of global development. In this talk, we will present progress towards this goal, emphasising the potential of ecosystem semantics in bridging and seeding new domain ontologies.

}, url = {http://ceur-ws.org/Vol-1747/IT201_ICBO2016.pdf}, author = {Pier Luigi Buttigieg and Mark Jensen and Ramona Walls and Christopher Mungall} } @conference {373, title = {IP34: Plant Reactome: A Resource for Comparative Plant Pathway Analysis}, booktitle = {ICBO and BioCreative 2016}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, address = {Corvallis, OR}, abstract = {

The Plant Reactome database (http://plantreactome.gramene.org/) hosts metabolic, genetic and signaling pathways for several model and crop plant species. The Reactome data model organizes gene products, small molecules and macromolecular interactions into reactions and pathways in the context of their subcellular location to build a systemslevel framework of a plant cell. The Plant Reactome features Oryza sativa (rice) as a reference species, built by importing the RiceCyc metabolic network and curating new metabolic, signaling and genetic pathways. The Plant Reactome database now contains 241 rice reference pathways and orthology-based pathway projections for 58 plant species. Plant Reactome allows users to i) compare pathways across various plant species; ii) query and visualize curated baseline and differential expression data available in the EMBL-EBI{\textquoteright}s Expression Atlas in the context of pathways in the Plant Reactome; and iii) analyze genome-scale expression data and conduct pathway enrichment analysis to enable researchers to identify pathways affected by the stresses or treatments studied in their data sets. Plant Reactome links out to numerous external reference resources, including the gene pages of Gramene, Phytozome, SoyBase, Legume Information System, PeanutBase, Uniprot, as well as ChEBI for small molecules, PubMed for literature supported evidences, and GO for molecular function and biological processes. Users can access/download our data in various formats from our website and via APIs. The presentation will discuss tools for pathway enrichment analysis and homologue pathway comparison, development of the Plant Reactome portal, curation of reference rice pathways, and phylogeny-based analyses of projected pathway annotations. The project is supported by the Gramene database award (NSF IOS-1127112)and the Human Reactome award (NIH: P41 HG003751, ENFIN LSHG-CT-2005-518254, Ontario Research Fund, and EBI Industry Programme).

}, author = {Sushma Naithani and Justin Preece and Parul Gupta and Peter D{\textquoteright}Eustachio and Justin Elser and Antonio Mundao and Joel Weiser and Sheldon McKay and Lincoln Stein and Doreen Ware and Pankaj Jaiswal} } @conference {365, title = {IP33: The Dynamic Impact Approach as a web-based platform for analysis of time-course or multiple treatments omics datasets.}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, address = {Corvallis, Oregon, USA}, abstract = {

Life is dynamic. Therefore, a true understanding of processes responsible for maintaining life requires a dynamic approach. Time-course experiments using omics approaches allow to capture such dynamism; however, dataset from time-course experiments, especially if considering multiple treatments, are challenging to analyze statistically. Even more challenging is to unravel the meaning of the changes observed and capture the underline significant biological changes. Bioinformatic tools for the analysis of time-course experiments are scant and many use the enrichment analysis approach. This approach has an inherent incapacity of analyzing time-course and/or multiple-treatment experiments without reducing the dataset to clusters, such as genes with a common patterns (i.e., co-regulated). In order to overcome the limitation of enrichment analysis tools a Dynamic Impact Approach (DIA) tool was developed. DIA uses the statistical significance (i.e., P-value) and the expression ratio of each comparison to calculate an Impact and a Direction of the Impact values for each biological term (i.e., Gene Ontology, pathway) in each condition. The Impact captures the overall effect of the condition studied on the biological term, while the Direction of the Impact captures the dynamism of the effect (i.e., overall activated or inhibited). The reliability of DIA to provide biological insights compared to enrichment approach tools has been demonstrated in several large transcriptomics studies. DIA can analyze any database available; however, it is now capable to analyze KEGG pathways, Gene Ontology terms, and up-stream regulators. Among the major advantage of DIA compared to enrichment approach tools, is the simplicity in providing highly graphical outputs easy to interpret and to integrate. A beta-version of a DIA web-based tool was recently launch and it is available at http://104.236.163.18:3838/dia/.

}, keywords = {co-regulation, Dynamic Impact Approach, gene ontology, ontology, pathways}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {Massimo Bionaz and Austin Nguyen} } @conference {IP32, title = {IP32: Enhancing SciENcv through semantic research profile integration with the VIVO-ISF ontology}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

n/a

}, url = {http://ceur-ws.org/Vol-1747/IP32_ICBO2016.pdf}, author = {Marijane White and Matthew Brush and Shahim Essaid and Robin Champieux and Adrienne Zell and Melissa Haendel and Colin Grove and Syeda Momina Tabish and David Eichmann} } @conference {IP31, title = {IP31: Planteome Gene Annotation Enrichment Analysis}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Annotation enrichment analysis of a gene list helps biologists to identify the potential biological functions associated with it. With the extensions of plant ontology categories, the discovery of significant ontology terms associated with a gene list becomes more and more informative. We introduce a tool to help biologists to find out these terms based on the expanding ontology database of the Planteome project. In addition, we propose some new visualization schemes to help users construct a meaningful interpretation of the results guided by the ontology tree.

}, url = {http://ceur-ws.org/Vol-1747/IP31_ICBO2016.pdf}, author = {Botong Qu and Jaden Diefenbaugh and Eugene Zhang and Justin Elser and Pankaj Jaiswal and Seth Carbon and Christopher Mungall} } @conference {IP30, title = {IP30: Supporting database annotations and beyond with the Evidence \& Conclusion Ontology (ECO)}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

The Evidence \& Conclusion Ontology (ECO) is a community standard for summarizing evidence in scientific research in a controlled, structured way. Annotations at the world{\textquoteright}s most frequented biological databases (e.g. model organisms, UniProt, Gene Ontology) are supported using ECO terms. ECO describes evidence derived from experimental and computational methods, author statements curated from the literature, inferences drawn by curators, and other types of evidence. Here, we describe recent ECO developments and collaborations, most notably: (i) a new ECO website containing user documentation, up-to-date news, and visualization tools; (ii) improvements to the ontology structure; (iii) implementing logic via an ongoing collaboration with the Ontology for Biomedical Investigations (OBI); (iv) addition of numerous experimental evidence types; and (v) addition of new evidence classes describing computationally derived evidence. Due to its utility, popularity, and simplicity, ECO is now expanding into realms beyond the protein annotation community, for example the biodiversity and phenotype communities. As ECO continues to grow as a resource, we are seeking new users and new use cases, with the hope that ECO will continue to be a broadly used and easy-to-implement community standard for representing evidence in diverse biological applications. Feel free to visit two ECO-sponsored workshops at ICBO 2016 to learn more: 1. {\`O}An introduction to the Evidence and Conclusion Ontology and representing evidence in scientific research{\'O} and 2. {\`O}OBI-ECO Interactions \& Evidence{\'O}.

}, url = {http://ceur-ws.org/Vol-1747/IP30_ICBO2016.pdf}, author = {Marcus Chibucos and Suvarna Nadendla and James Munro and Elvira Mitraka and Dustin Olley and Nicole Vasilevsky and Matthew Brush and Michelle Giglio} } @conference {IP29, title = {IP29: Global Agricultural Concept Scheme: A Hub for Agricultural Vocabularies}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Thesauri are used to tag semi-structured documents, texts, while more complex semantic structures are used to describe (annotate) scientific data. We are creating a Global Agricultural Concept Scheme (GACS) by mapping AGROVOC, CABT and NALT {\DH} three major thesauri in the area of food and agriculture, with a beta release in May 2016. We see GACS as a hub linking user-oriented thesauri with semantically more precise domain ontologies linking, in turn, to datasets about food and agriculture, in order to make that data more interoperable and reusable

}, url = {http://ceur-ws.org/Vol-1747/IP29_ICBO2016.pdf}, author = {Caterina Caracciolo and Tom Baker and Elizabeth Arnaud} } @conference {IP28, title = {IP28: uc_FIDO: unambiguous characterization of food interactions with drugs ontology}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

uc_FIDO is an ontology that unambiguously characterizes food interactions with drugs in the human body. This ontology is part of a group of food ontologies describing food and the human experience at the International Center for Food Ontology Operability, Data and Semantics (IC-FOODS) at UC Davis. The first of its kind, uc_FIDO characterizes relations between food, medicine, and human health. uc_FIDO brings together several existing ontologies related to anatomy, metabolic pathways, biological processes, drug ingredients and food structures. Through these ontologies, uc_FIDO annotates relationships between food and drug bioactives, human physiological conditions, and biological reaction pathways. Relationships that link together fully characterize various food interactions with drugs and their effects. The current dearth of ontologies for characterizing foods limits advancement of informatics solutions for improving health. As ontologies of foods are developed, it becomes necessary to describe ingredients, bioactive molecules, potential toxins, and other molecules in food interacting with drugs and the human body.

}, url = {http://ceur-ws.org/Vol-1747/IP28_ICBO2016.pdf}, author = {Constantine Spyrou and Matthew Lange} } @conference {IP27, title = {IP27: Dealing with elements of medical encounters: an approach based on ontological realism}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Electronic health records (EHRs) serve as repositories of documented data collected in a health care encounter. An EHR records information about who receives, who provides the health care and about the place where the encounter happens. We also observe additional elements relating to social relations in which the healthcare consumer is involved. To provide a consensus representation of common data and to enhance interoperability between different EHR repositories we have created a solution grounded in formal ontology. Here, we present how an ontology for the obstetric and neonatal domain deals with these general elements documented in health care encounters. Our goal is to promote the interoperability of information among EHRs created in different specialties. To develop our ontology, we used two main approaches: one based on ontological realism, the other based on the principles of the OBO Foundry, including reuse of reference ontologies.

}, url = {http://ceur-ws.org/Vol-1747/IP27_ICBO2016.pdf}, author = {Fernanda Farinelli and Mauricio Almeida and Peter Elkin and Barry Smith} } @conference {IP26, title = {IP26: Performance Evaluation Clinical Task Ontology(PECTO)}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

n/a

}, url = {http://ceur-ws.org/Vol-1747/IP26_ICBO2016.pdf}, author = {Jose F Florez-Arango and Santiago Pati{\~n}o-Giraldo and Jack W Smith and Sriram Iyengar} } @conference {IP25, title = {IP25: The Zebrafish Experimental Conditions Ontology Systemizing Experimental Descriptions in ZFIN}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

The Zebrafish Experimental Conditions Ontology (ZECO) defines the major experimental conditions used in research studies that employ the zebrafish, Danio rerio. We are systematically building the ontology to encompass both standard control conditions and experimental conditions and it is designed to allow better data curation and more precise information retrieval.

}, url = {http://ceur-ws.org/Vol-1747/IP25_ICBO2016.pdf}, author = {Yvonne Bradford and Ceri Van Slyke and Sabrina Toro and Sridhar Ramachandran} } @conference {IP24, title = {IP24: An OBI ontology Datum Proof Sheet}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

There are numerous past and current examples of ontology-driven projects that provide auto-generated user interfaces for managing entities and relations, each presenting its own varied and complex data model. Our Datum Proof Sheet application aims to simplify the application development landscape by building community consensus about the way basic categorical, textual and numeric datum fields should be described within the OBOFoundry community of ontologies. The proof sheet shows selected datums (grouped under the context of an OBI {\`O}data representational model{\'O} item) as form inputs on an HTML page, enabling an application ontology{\~O}s contents to be presented to end users (ranging in our case from epidemiologists to software developers) for review without necessarily having a working application to showcase them in. The basic relations and cases necessary for presenting datums in a user interface are mostly satisfied by OBI{\~O}s design, but we introduce a few extra elements to bring more clarity to datum specifications, and to provide user interface term labels and definitions that may differ from those that ontologists prefer in the {\`O}backend{\'O}.

}, url = {http://ceur-ws.org/Vol-1747/IP24_ICBO2016.pdf}, author = {Damion Dooley and Emma Griffiths and Fiona Brinkman and William Hsiao} } @conference {IP23, title = {IP23: Towards an Ontology of Schizophrenia}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

The paper presents an Ontology of Schizophrenia (OS) that is designed to provide a formal representation of schizophrenia-related entities crucial to the treatment and study of schizophrenia. OS is developed in accordance with the OBO (Open Biomedical Ontology) Foundry principles and constructed in compliance with Basic Formal Ontology (BFO) as its upper-level ontology. It uses mid-level and domain ontologies built in conformity with BFO such as the Ontology for General Medical Science (OGMS) and the Mental Functioning Ontology (MFO). OS is developed using Prot{\'e}g{\'e} 4.3 and is implemented in OWL2. Having imported BFO2.0 OWL and the development version of OGMS, OS adds approximately 30 schizophrenia-related terms and attempts to provide both formal and textual definitions for each. The terms in OS are in addition annotated with ontology metadata such as labels, textual definitions, definition sources, term editors and editor notes.

}, url = {http://ceur-ws.org/Vol-1747/IP23_ICBO2016.pdf}, author = {Fumiaki Toyoshima} } @conference {IP22, title = {IP22: SourceData: Making Data discoverable}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

n/a

}, url = {http://ceur-ws.org/Vol-1747/BT101_ICBO2016.pdf}, author = {Nancy George and Sara El-Gebali and Thomas Lemberger} } @conference {IP21, title = {IP21: FoodON: A Global Farm-to-Fork Food Ontology}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Several resources and standards for indexing food descriptors currently exist, but their content and interrelations are not semantically and logically coherent. Simultaneously, the need to represent knowledge about food is central to many fields including biomedicine and sustainable development. FoodON is a new ontology built to interoperate with the OBO Library and to represent entities which bear a . It encompasses materials in natural ecosystems and food webs as well as human-centric categorization and handling of food. The latter will be the initial focus of the ontology, and we aim to develop semantics for food safety, food security, the agricultural and animal husbandry practices linked to food production, culinary, nutritional and chemical ingredients and processes. The scope of FoodON is ambitious and will require input from multiple domains. FoodON will import or map to material in existing ontologies and standards and will create content to cover gaps in the representation of food-related products and processes. As a robust food ontology can only be created by consensus and wide adoption, we are currently forming an international consortium to build partnerships, solicit domain expertise, and gather use cases to guide the ontologys development. The products of this work are being applied to research and clinical datasets such as those associated with the Canadian Healthy Infant Longitudinal Development (CHILD) study which examines the causal factors of asthma and allergy development in children, and the Integrated Rapid Infectious Disease Analysis (IRIDA) platform for genomic epidemiology and foodborne outbreak investigation.

}, url = {http://ceur-ws.org/Vol-1747/IP21_ICBO2016.pdf}, author = {Emma Griffiths and Damion Dooley and Pier Luigi Buttigieg and Robert Hoehndorf and Fiona Brinkman and William Hsiao} } @conference {IP20, title = {IP20: Growth of the Zebrafish Anatomy Ontology: Expanded to support adult morphology and dynamic changes in the early embryo}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

The Zebrafish Anatomy Ontology (ZFA) is an application ontology used by ZFIN to support curation of expression and phenotype. The research community also uses the ontology to support annotation of high throughput studies. As the research focus of the zebrafish community evolves it drives changes in the ZFA. Here we provide an update on the changes made to support research carried out in adult fish and describe the changes in modeling of the neural crest in the ontology in order to bring the structure of the ontology into closer accordance with the morphological changes that occur during development.

}, url = {http://ceur-ws.org/Vol-1747/IP20_ICBO2016.pdf}, author = {Ceri Van Slyke and Yvonne Bradford and Christian Pich} } @conference {IP19, title = {IP19: Opportunities and challenges presented by Wikidata in the context of biocuration}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Wikidata is a world readable and writable knowledge base maintained by the Wikimedia Foundation. It offers the opportunity to collaboratively construct a fully open access knowledge graph spanning biology, medicine, and all other domains of knowledge. To meet this potential, social and technical challenges must be overcome most of which are familiar to the biocuration community. These include community ontology building, high precision information extraction, provenance, and license management. By working together with Wikidata now, we can help shape it into a trustworthy, unencumbered central node in the Semantic Web of biomedical data.

}, url = {http://ceur-ws.org/Vol-1747/BT105_ICBO2016.pdf}, author = {Benjamin Good and Timothy Putman and Andrew Su and Andra Waagmeester and Sebastian Burgstaller-Muehlbacher and Elvira Mitraka} } @conference {IP18, title = {IP18: The ImmPort Antibody Ontology}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

n/a

}, url = {http://ceur-ws.org/Vol-1747/IP18_ICBO2016.pdf}, author = {William Duncan and Travis Allen and Jonathan Bona and Olivia Helfer and Barry Smith and Alan Ruttenberg and Alexander D. Diehl} } @conference {IP17, title = {IP17: Comparison of ontology mapping techniques to map plant trait ontologies}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Crop specific ontologies for phenotype annotations in breeding have proliferated over the last 10 years. Across-crop data interoperability involves linking those ontologies together. For this purpose, the Planteome project is mapping the Crop Ontology traits (www.cropontology.org) to the reference ontology for plant traits, Trait Ontology (TO). Manual mapping is time-consuming and not sustainable in the long-run as ontologies keep on evolving and multiplicating. We are thus working on developing reliable automated mapping techniques to assist curators in performing semantic integration. Our study shows the benefit of the ontology matching technique based on formal definitions and shared ontology design patterns, compared to standard automatic ontology matching algorithm, such as AML (AgreementMakerLight).

}, url = {http://ceur-ws.org/Vol-1747/IP17_ICBO2016.pdf}, author = {Marie-Ang{\'e}lique Laporte and L{\'e}o Valette and Laurel Cooper and Chris Mungall and Austin Meier and Pankaj Jaiswal and Elizabeth Arnaud} } @conference {IP16, title = {IP16: Definition Coverage in the OBO Foundry Ontologies: The Big Picture}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

n/a

}, url = {http://ceur-ws.org/Vol-1747/IP16_ICBO2016.pdf}, author = {Daniel Schlegel and Selja Sepp{\"a}l{\"a} and Peter Elkin} } @conference {IP15, title = {IP15: uc_Milk: An ontology for scientifically-based unambiguous characterization of mammalian milk, their composition and the biological processes giving rise to their creation}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Recent efforts in biological ontology go to great lengths to unambiguously categorize biological entities and phenomena of the natural world, as well as their relationships with each other. This paper illustrates the importance of unambiguously characterizing mammalian milk because milk is a complex mixture of many chemical components and thus represents a key role in infant nourishment and development. In addition to the build of a computable knowledge base around mammalian milk, ontological modeling of this aspect of biology and chemistry enable increased understanding of mammalian milk composition and the biological structures and biochemical processes giving rise to their creation. Utilizing unambiguous vocabularies to compare human milk with other mammalian milks relative to the biological and behavioral survival challenges facing varied mammalian organisms and the phenotypic qualities each milk confers, is a fundamental goal of this project.

}, url = {http://ceur-ws.org/Vol-1747/IP15_ICBO2016.pdf}, author = {Emeline Colet and Matthew Lange} } @conference {IP14, title = {IP14: Towards designing an ontology encompassing the environment-agriculture-food-diet-health knowledge spectrum for food system sustainability and resilience.}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Feeding 9 billion people is not solely a matter of food, health, nutrition, and the environment. Promoting human health by increasing the sustainability and resilience of food systems requires integrating information from a broad range of disciplines from human nutrition/health systems and agricultural/natural systems to social, financial, physical and political systems. Ontologies serve to specify common terminologies for critical concepts and relationships within these systems, however very few ontologies have been developed with this interdisciplinary focus. Biological ontologies, whether focused on human physiology, soil quality, or nutritional value are only part of the story when it comes to determining linkages throughout the food system that help determine human health and well-being. We seek to build an ontology of food and food systems that encompasses the relevant sustainability issues in their entirety. We have already built an ontology of sustainable sourcing of agricultural raw materials issues and indicators, but aim to expand our ontology to include attributes of resilience, and other issues along the environment-agriculture-food-diet-health knowledge spectrum. Additionally, we aim to create this ontology with the intention of quick usability for the food system decision-maker.

}, url = {http://ceur-ws.org/Vol-1747/IP14_ICBO2016.pdf}, author = {Ruthie Musker and Matthew Lange and Allan Hollander and Patrick Huber and Nathaniel Springer and Courtney Riggle and James Quinn and Thomas Tomich} } @conference {IP13, title = {IP13: uc_Eating: Ontology for unambiguous characterization of eating and food habits}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

The uc_Eating ontology is a standardized unambiguous characterization system for modeling human food habits and eating processes. The uc_Eating ontology along with the physiological, environmental, behavioral, and food ontologies it maps to, provide an infrastructure for annotating the relationships between food, food consumption, eating behaviors, and environments creating a foundation for computable knowledge bases around food and beverage consumption scenarios, their observation, interrogation, and manipulation at biological, behavioral, and environmental levels.

}, url = {http://ceur-ws.org/Vol-1747/IP13_ICBO2016.pdf}, author = {Kimiya Taji and Matthew Lange} } @conference {IP12, title = {IP12: NAPRALERT, from an historical information silo to a linked resource able to address the new challenges in Natural Products Chemistry and Pharmacognosy.}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

NAPRALERT (https://www.napralert.org) is a database on natural products, including data on ethnobotany, chemistry, pharmacology, toxicology, and clinical trials from literature dating back to the 19th century. Established in 1975 by Norman R. Farnsworth, it became a web accessible resource in 2005 but soon became stagnant while literature grew exponentially. After a complete rewrite of the platform, the focus is now on connecting this resource to the rest of the existing databases and expanding its usability. The creation of a Pharmacognosy/Natural Product ontology will foster better understanding of this domain, its linking potential with other resources and the ability to automatize literature annotation and entry efficiently.

}, url = {http://ceur-ws.org/Vol-1747/IP12_ICBO2016.pdf}, author = {Jonathan Bisson and James McAlpine and James Graham and Guido Pauli} } @conference {IP11, title = {IP11: Uc_Sense: An Ontology for Scientifically-based Unambiguous Characterization of Sensory Experiences}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Recent efforts in biological ontology go to great lengths to unambiguously categorize biological entities and phenomena of the natural world, as well as their relationships with each other. This paper illustrates the importance of unambiguously characterizing the perception of entities relative to biological apparati required for specific modes of sensing, physiological conduction of sensed experiences, along with subjective interpretation and communication of sensed experiences. In addition to building a computable knowledge base around existing sensory science, ontological modelling of this aspect of biology will enable an increased understanding about alternate perceptions of identical stimuli. Leveraging this understanding to modulate desired behavior toward increased health and happiness outcomes is a fundamental goal of this project.

}, url = {http://ceur-ws.org/Vol-1747/IP11_ICBO2016.pdf}, author = {Aaron Baer and Matthew Lange} } @conference {IP10, title = {IP10: Analysis of SNOMED {\textquoteleft}bleeding{\textquoteright} concepts \& terms}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

We present an analysis of SNOMED CT {\^O}bleeding{\~O} concepts {\DH} those concepts with descriptions that include {\^O}hematoma{\~O}, {\^O}hemorrhage{\~O}, or {\^O}bleeding{\~O}; or that are descended from {\^O}Bleeding (finding){\~O} in the Is-a hierarchy; or that have Hematomas or Hemorrhages as their associated morphology {\DH} to assess how consistently they are used in the ontology.

}, url = {http://ceur-ws.org/Vol-1747/IP10_ICBO2016.pdf}, author = {Jonathan Bona and Selja Sepp{\"a}l{\"a} and Werner Ceusters} } @conference {IP09, title = {IP09: How to Summarize Big Knowledge Subjects}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

One manifestation of the {\textquotedblleft}Big Knowledge{\textquoteright}{\textquoteright} challenge is providing automated tools for summarization of ontology content to facilitate user comprehension. An aggregation approach for the automatic identification and display of major subjects covered by an ontology{\textquoteright}s content is presented. The results show that our methodology is viable in capturing the {\textquotedblleft}big picture{\textquotedblright} of ontology content.

}, url = {http://ceur-ws.org/Vol-1747/IP09_ICBO2016.pdf}, author = {Ling Zheng and Yehoshua Perl and James Geller and Gai Elhanan} } @conference {IP08, title = {IP08: Gold-Standard Ontology-Based Annotation of Concepts in Biomedical Text in the CRAFT Corpus: Updates and Extensions}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Ontologies are increasingly used for semantic integration across disparate curated biomedical resources, while gold-standard annotated corpora are needed for accurate training and evaluation of text-mining tools. Bringing together the respective power of these, we created the Colorado Richly Annotated Full-Text (CRAFT) Corpus, a collection of full-length, open-access biomedical journal articles that have been manually annotated both syntactically and semantically with select Open Biomedical Ontologies (OBOs), the first release of which includes \ 100,000 annotations of concepts mentioned in the text of 67 articles and mapped to the classes of eight prominent OBOs. Here we present our continuing work on the corpus, including updated versions of these annotations with newer versions of the ontologies, new annotations made with two additional OBOs, annotations made with newly created extension classes defined in terms of existing classes of the ontologies, and new annotations of roots of prefixed and suffixed words.

}, url = {http://ceur-ws.org/Vol-1747/IP08_ICBO2016.pdf}, author = {Michael Bada and Nicole Vasilevsky and Melissa Haendel and Lawrence Hunter} } @conference {IP07, title = {IP07: The Cell Line Ontology integration and analysis of the knowledge of LINCS cell lines}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Cell lines are crucial to study molecular signatures and pathways, and are widely used in the NIH Common Fund LINCS project. The Cell Line Ontology (CLO) is a community-based ontology representing and classifying cell lines from different resources. To better serve the LINCS research community, from the LINCS Data Portal and ChEMBL, we identified 1,097 LINCS cell lines, among which 717 cell lines were associated with 121 cancer types, and 352 cell line terms did not exist in CLO. To harmonize LINCS cell line representation and CLO, CLO design patterns were slightly updated to add new information of the LINCS cell lines including different database cross-reference IDs. A new shortcut relation was generated to directly link a cell line to the disease of the patient from whom the cell line was originated. After new LINCS cell lines and related information were added to CLO, a CLO subset/view (LINCS-CLOview) of LINCS cell lines was generated and analyzed to identify scientific insights into these LINCS cell lines. This study provides a first time use case on how CLO can be updated and applied to support cell line research from a specific research community or project initiative.

}, url = {http://ceur-ws.org/Vol-1747/IP07_ICBO2016.pdf}, author = {Edison Ong and Jiangan Xie and Zhaohui Ni and Qingping Liu and Yu Lin and Vasileios Stathias and Caty Chung and Stephan Schurer and Yongqun He} } @conference {IP06, title = {IP06: Building a molecular glyco-phenotype ontology to decipher undiagnosed diseases}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Hundreds of rare diseases are due to mutation on genes related to glycans synthesis, degradation or recognition. These glycan-related defects are well described in the literature but largely absent in ontologies and databases of chemical entities and phenotypes, limiting the application of computational methods and ontology-driven tools for characterization and discovery of glycan related diseases. We are curating articles and textbooks in glycobiology related to genetic diseases to inform the content and the structure of an ontology of Molecular Glyco-Phenotypes (MGPO). MGPO will be applied toward use cases including disease diagnosis and disease gene candidate prioritization, using semantic similarity and pattern matching at the glycan level with glycomics data from patient of the Undiagnosed Diseases Network.

}, url = {http://ceur-ws.org/Vol-1747/IP06_ICBO2016.pdf}, author = {Jean-Philippe Gourdine and Thomas Metz and David Koeller and Matthew Brush and Melissa Haendel} } @conference {IP05, title = {IP05: An Ontological Representation for the Transtheoretical Theory}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Ontologies are widely used in computer science and medicine. Ontologies may be useful in health promotion and disease prevention for intervention development. Interventionists usually use theory to guide intervention design and evaluation, but there is no standard vocabulary for health behavior theory. A formal mechanism for converting theory to a computer-based representation may provide a tool that can assist in the development of computer-based interventions. This paper demonstrates how ontology can be used to represent a health behavior theory using the Transtheoretical Model (TTM) of behavior change as an example.

}, url = {http://ceur-ws.org/Vol-1747/IP05_ICBO2016.pdf}, author = {Hua Min and Robert H. Friedman and Julie Wright} } @conference {IP04, title = {IP04: EGO: a biomedical ontology for integrative epigenome representation and analysis}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Epigenomics is crucial to understand biological mechanisms beyond genome DNA. To better represent epigenomic knowledge and support data integration, we developed a prototype Epigenome Ontology (EGO). EGO top level hierarchy and design pattern are provided with a use case illustration. EGO is proposed to be used for statistically analyzing enriched epigenomic features based on given sequence data input using statistical methods.

}, url = {http://ceur-ws.org/Vol-1747/IP04_ICBO2016.pdf}, author = {Yongqun He and Zhaohui Qin and Jie Zheng} } @conference {IP03, title = {IP03: Multi-species Ontologies of the Craniofacial Musculoskeletal System}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

We created the Ontology of Craniofacial Development and Malformation (OCDM) [1] to provide a unifying framework for organizing and integrating craniofacial data ranging from genes to clinical phenotypes from multi-species. Within this framework we focused on spatio-structural representation of anatomical entities related to craniofacial development and malformation, such as craniosynostosis and midface hypoplasia. Animal models are used to support human studies and so we built multi-species ontologies that would allow for cross-species correlation of anatomical information. For this purpose we first developed and enhanced the craniofacial component of the human musculoskeletal system in the Foundational Model of Anatomy Ontology (FMA)[2], and then imported this component, which we call the Craniofacial Human Ontology (CHO), into the OCDM. The CHO was then used as a template to create the anatomy for the mouse, the Craniofacial Mouse Ontology (CMO) as well as for the zebrafish, the Craniofacial Zebrafish Ontology (CZO).

}, url = {http://ceur-ws.org/Vol-1747/IP03_ICBO2016.pdf}, author = {JL Mejino and James Brinkley and Timothy Cox and Landon Detwiler} } @conference {IP02, title = {IP02: Adding evidence type representation to DIDEO}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

In this poster we present novel development and extension of the Drug-drug Interaction and Drug-drug Interaction Evidence Ontology (DIDEO). We demonstrate how reasoning over this extension of DIDEO can a) automatically create a multi-level hierarchy of evidence types from descriptions of the underlying scientific observations and b) automatically subsume individual evidence items under the correct evidence type. Thus DIDEO will enable evidence items added manually by curators to be automatically categorized into a drug-drug interaction framework with precision and minimal effort from curators. As with all previous DIDEO development this extension is consistent with OBO Foundry principles.

}, url = {http://ceur-ws.org/Vol-1747/IP02_ICBO2016.pdf}, author = {Mathias Brochhausen and Philip E. Empey and Jodi Schneider and William R. Hogan and Richard D. Boyce} } @conference {D105, title = {D205: Easy Extraction of Terms and Definitions with OWL2TL}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

"Facilitating good communication between semantic web specialists and domain experts is necessary to efficient ontology development. This development may be hindered by the fact that domain experts tend to be unfamiliar with tools used to create and edit OWL files. This is true in particular when changes to definitions need to be reviewed as often as multiple times a day. We developed ""OWL to Term List"" (OWL2TL) with the goal of allowing domain experts to view the terms and definitions of an OWL file organized in a list that is updated each time the OWL file is updated. The tool is available online and currently generates a list of terms, along with additional annotation properties that are chosen by the user, in a format that allows easy copying into a spreadsheet."

}, url = {http://ceur-ws.org/Vol-1747/D205_ICBO2016.pdf}, author = {John Judkins and Joseph Utecht and Mathias Brochhausen} } @conference {D204, title = {D203: Humane OWL: RDF and OWL for Humans}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Humane OWL (HOWL) is a syntax for RDF and OWL designed for manual editing. By allowing human-readable labels to be used in place of IRIs, and providing convenient syntax for OWL annotations and expressions, HOWL files can be used like source code with tools such as GitHub, then translated into any other RDF or OWL format for use with other tools.

}, url = {http://ceur-ws.org/Vol-1747/D203_ICBO2016.pdf}, author = {James A. Overton} } @conference {D203, title = {D202: Reusing the NCBO BioPortal technology for agronomy to build AgroPortal}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Many vocabularies and ontologies are produced to represent and annotate agronomic data. By reusing the NCBO BioPortal technology, we have already designed and implemented an advanced prototype ontology repository for the agronomy domain. We plan to turn that prototype into a real service to the community. The AgroPortal project aims at reusing the scientific outcomes and experience of the biomedical domain in the context of plant, agronomic, food, environment (perhaps animal) sciences. We offer an ontology portal which features ontology hosting, search, versioning, visualization, comment, recommendation, enables semantic annotation, as well as storing and exploiting ontology alignments. All of these within a fully semantic web compliant infrastructure. The AgroPortal specifically pays attention to respect the requirements of the agronomic community in terms of ontology formats (e.g., SKOS, trait dictionaries) or supported features. In this paper, we present our prototype as well as preliminary outputs of four driving agronomic use cases. With the experience acquired in the biomedical domain and building atop of an already existing technology, we think that AgroPortal offers a robust and stable reference repository that will become highly valuable for the agronomic domain.

}, url = {http://ceur-ws.org/Vol-1747/D202_ICBO2016.pdf}, author = {Clement Jonquet and Anne Toulet and Elizabeth Arnaud and Sophie Aubin and ED Yeumo and Vincent Emonet and John Graybeal and Mark A. Musen and Cyril Pommier and Pierre Larmande} } @conference {D202, title = {D201: Ontobull and BFOConvert: Web-based programs to support automatic ontology conversion}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

When a widely reused ontology appears in a new version which is not compatible with older versions, the ontologies reusing it need to be updated accordingly. Ontobull (http://ontobull.hegroup.org) has been developed to automatically update ontologies with new term IRI(s) and associated metadata to take account of such version changes. To use the Ontobull web interface a user is required to (i) upload one or more ontology OWL source files; (ii) input an ontology term IRI mapping; and (where needed) (iii) provide update settings for ontology headers and XML namespace IDs. Using this information, the backend Ontobull Java program automatically updates the OWL ontology files with desired term IRIs and ontology metadata. The Ontobull subprogram BFOConvert supports the conversion of an ontology that imports a previous version of BFO. A use case is pro- vided to demonstrate the features of Ontobull and BFOConvert.

}, url = {http://ceur-ws.org/Vol-1747/D201_ICBO2016.pdf}, author = {Edison Ong and Zuoshuang Xiang and Jie Zheng and Barry Smith and Yongqun He} } @conference {D101-BP04, title = {D106-BP04: Enhancing Information Accessibility of Publications with Text Mining and Ontology}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

We present an ongoing effort on utilizing text mining methods and existing biological ontologies to help readers to access the information contained in the scientific articles. Our approach includes using multiple strategies for biological entity detection and using association analysis on extracted analysis. The entity extraction processes utilizes regular expression rules, ontologies, and keyword dictionary to get a comprehensive list of biological entities. In addition to extract list of entities, we also apply natural language processing and association analysis techniques to generate inferences among entities and comparing to known relations documented in the existing ontologies.

}, url = {http://ceur-ws.org/Vol-1747/D106-BP04_ICBO2016.pdf}, author = {Weijia Xu and Amit Gupta and Pankaj Jaiswal and Crispin Taylor and Patti Lockhart} } @conference {D205, title = {D104: Updates to the AberOWL ontology repository}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

A large number of ontologies have been developed in the biological and biomedical domains, which are mostly expressed in the Web Ontology Language (OWL). These ontologies form a logical foundation for our knowledge in these domains, and they are in widespread use to annotate biomedical and biological datasets. The use of the semantics provided by ontologies requires the use of automated reasoning {\textendash} inferring new knowledge by evaluating the asserted axioms. AberOWL is an ontology repository which utilises an OWL 2 EL reasoner to provide semantic access to classified ontologies. Since our original presentation of the AberOWL framework, we have developed several additional tools and features which enrich its ability to integrate and explore data, make use of the semantic and inferred content of ontologies. Here we present an overview of AberOWL and the enhancements and new features which have been developed since its conception. AberOWL is freely available at http://aber-owl.net.

}, url = {http://ceur-ws.org/Vol-1747/D104_ICBO2016.pdf}, author = {M{\'A} Rodr{\'\i}guez-Garc{\'\i}a and Luke Slater and Imane Boudellioua and Paul Schofield and Georgios Gkoutos and Robert Hoehndorf} } @conference {D103-W14-04, title = {D103-W12-05-IP36: The Phenoscape Knowledgebase: tools and APIs for computing across phenotypes from evolutionary diversity and model organisms}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

The Phenoscape Knowledgebase (KB) is an ontologydriven database that combines existing phenotype annotations from model organism databases with new phenotype annotations from the evolutionary literature. Phenoscape curators have created phenotype annotations for more than 5,000 species and higher taxa, by defining computable phenotype concepts for more than 20,000 character states from over 160 published phylogenetic studies. These phenotype concepts are in the form of Entity{\textendash}Quality (EQ) [1] compositions which incorporate terms from the Uberon anatomy ontology, the Biospatial Ontology (BSPO), and the Phenotype and Trait Ontology (PATO). Taxonomic concepts are drawn from the Vertebrate Taxonomy Ontology (VTO). This knowledge of comparative biodiversity is linked to potentially relevant developmental genetic mechanisms by importing associations of genes to phenotypic effects and gene expression locations from zebrafish (ZFIN [2]), mouse (MGI [3]), Xenopus (Xenbase [4]), and human (Human Phenotype Ontology project [5]). Thus far, the Phenoscape KB has been used to identify candidate genes for evolutionary phenotypes [6], to match profiles of ancestral evolutionary variation with gene phenotype profiles [7], and to combine data across many evolutionary studies by inferring indirectly asserted values within synthetic supermatrices [8]. Here we describe the software architecture of the Phenoscape KB, including data ingestion, integration of OWL reasoning, web service interface, and application features (Fig. 1).

}, url = {http://ceur-ws.org/Vol-1747/D103-W14-04_ICBO2016.pdf}, author = {James Balhoff} } @conference {D102, title = {D102: SPARQL2OWL: towards bridging the semantic gap between RDF and OWL}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Several large databases in biology are now making their information available through the Resource Description Framework (RDF). RDF can be used for large datasets and provides a graph-based semantics. The Web Ontology Language (OWL), another Semantic Web standard, provides a more formal, model- theoretic semantics. While some approaches combine RDF and OWL, for example for querying, knowledge in RDF and OWL is often expressed differently. Here, we propose a method to generate OWL ontologies from SPARQL queries using n-ary relational patterns. Combined with background knowledge from ontologies, the generated OWL ontologies can be used for expressive queries and quality control of RDF data. We implement our method in a a prototype tool available at https://github.com/ bio- ontology- research- group/SPARQL2OWL.

}, url = {http://ceur-ws.org/Vol-1747/D102_ICBO2016.pdf}, author = {Mona Alsharani and Hussein Almashouq and Robert Hoehndorf} } @conference {D201, title = {D101: Plant Image Segmentation and Annotation with Ontologies in BisQue}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

n/a

}, url = {http://ceur-ws.org/Vol-1747/D101_ICBO2016.pdf}, author = {Justin Preece and Justin Elser and Pankaj Jaiswal and Kris Kvilekval and Dmitry Fedorov and B.S. Manjunath and Ryan Kitchen and Xu Xu and Dmitrios Trigkakis and Sinisa Todorovic and Seth Carbon} } @conference {BT304, title = {BT304: BioCconvert: A Conversion Tool Between BioC and PubAnnotation}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

BioC is a simple XML data format for text, annotations, and relations. PubAnnotation is a repository of text annotations focused on the life science literature. A conversion tool between BioC XML and the JSON import / export format of PubAnnotation has been developed, BioCconvert. As a demonstration, the Ab3P gold standard abbreviation annotations are being made available through PubAnnotation.

}, url = {http://ceur-ws.org/Vol-1747/BT304_ICBO2016.pdf}, author = {Donald C. Comeau and Rezarta Islamaj Do{\u g}an and Sun Kim and Chih-Hsuan Wei and W. John Wilbur and Zhiyong Lu} } @conference {BT303, title = {BT303: PubAnnotation: a public shared platform for scientific literature annotation.}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

"In the last decade, the technology for biomedical literature annotation made a significant progress in terms of accuracy and speed. Now, some annotation systems claim that they have reached a production level. However, there still remain critical issues which we believe hinder further progress of the community. Among them, a relatively well known issue is "interoperability" of annotation resources. We also recognize that the community is missing a general solution for "storage infrastructure". The talk will present the PubAnnotation project which aims at addressing these two issues. In the end, a new model for "sustainable shared tasks", which is implemented on PubAnnotation, will be introduced as well."

}, url = {http://ceur-ws.org/Vol-1747/BT303_ICBO2016.pdf}, author = {Jin-Dong Kim} } @conference {BT302, title = {BT302: Annotations for biomedical research and healthcare {\textendash} Bridging the gap}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

"Characterizing protein products from various model organisms with Gene Ontology terms, indexing the biomedical literature with MeSH descriptors, and coding clinical data with ICD10-CM all constitute examples of annotation tasks, i.e., the extraction ands summarization of knowledge related to a biological entity, article or patient, in reference to some controlled vocabulary or ontology. However, the annotations made in biomedical research and healthcare environments tend to rely on different terminologies and ontologies, making it difficult to reconcile these annotations for translational research purposes. We will discuss how terminology integration systems, such as the Unified Medical Language System (UMLS) and BioPortal, can help bridge the gap between annotations made by biomedical researchers and physicians, and argue that more efforts are needed to foster interoperability between the resources developed by these two communities."

}, url = {http://ceur-ws.org/Vol-1747/BT302_ICBO2016.pdf}, author = {Olivier Bodenreider} } @conference {BT301, title = {BT301: NLP for the Institute: Developing and Deploying an NLP Capability to Accelerate Cancer Research}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

"It has been well documented that a great deal of data useful for medical research is present in clinical narrative text. There is perhaps less discussion about how often what was structured data at its origin has become inaccessible except in free text form. This problem is further compounded in tertiary care institutions, like the OHSU Knight Cancer Institute, where the entire history of a referred patient{\textquoteright}s condition may only be present in the electronic health record (EHR) as free text. At the same time, future medical advances, such as in cancer research, will require much more complete patient data than has been previously available. Such advances include the discovery of new cures, expanding early detection, and realizing the promise of precision medicine. Phenotype description and outcome characterization are two areas in particular where text sources could greatly supplement our current data. The OHSU Knight Cancer Institute has begun a program to create a natural language processing (NLP) capability to extract, store, and link data from free text sources at the patient level, and make this data available to researchers in a continuous, reusable, efficient and timely manner through services delivery from the Translational Research Hub (TRH). This talk will present the challenges, progress, and future goals of our program to build NLP capabilities that can help us use free text from the EHR to first support the transformation of cancer research with the hopes of positively impacting clinical care in the future."

}, url = {http://ceur-ws.org/Vol-1747/BT301_ICBO2016.pdf}, author = {Aaron Cohen} } @conference {BT205, title = {BT205: Text Mining for Drug Development: Gathering Insights to Support Decision Making}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Drug discovery in Pharma R\&D is an information driven process requiring many disparate bits of data from many different sources, both structured and unstructured. Text mining is the key methodology used to extract entities and relationships from unstructured text in the quest for the knowledge needed to bring a safe and effective drug to market and beyond. Much of the insight needed in early drug research to identify drug target to disease relationships and progress a potential drug target, comes from published literature and internal reports. Later stage drug development requires many additional sources of information including case reports, clinical trials, competitive intelligence and other diverse sources. In this publication, I will present 4 different use cases on how text mining is used to drive decision making in drug discovery and development and also how it can be used to identify patient insights from sources such as social media.

}, url = {http://ceur-ws.org/Vol-1747/BT205_ICBO2016.pdf}, author = {Sherri Matis-Mitchell} } @conference {BT204, title = {BT204: CancerMine: Knowledge base construction for personalised cancer treatment}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Knowledge of the relevant genomic aberrations that drive a particular cancer type is necessary to accelerate efficient interpretation of genomic data and enable large-scale endeavors in precision medicine. Currently, this field is limited by the lack of focused and scalable literature curation tools that can reliably capture the required information. Here we present a knowledge-base of genes that have been described in the literature as drivers, oncogenes or tumour suppressors with respect to a specific type of cancer. We have annotated a large body of literature which reports oncogenic aberrations using a custom designed annotation tool. We then applied VERSE, an in-house relation extraction tool, to catalogue driver mutations and illustrate the ability to build a useful resource for clinical interpretation of genomic data for personalized treatment approaches.

}, url = {http://ceur-ws.org/Vol-1747/BT204_ICBO2016.pdf}, author = {Jake Lever and Martin Jones and Steven Jm Jones} } @conference {BT203, title = {BT203: MutD {\textendash} A PubMed Scale Resource for Protein Mutation-Disease Relations through Bio-Medical Literature Mining}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

A large amount of information about the role of gene variants and mutations in diseases is available in curated databases such as OMIM, ClinVar, and UniprotKB. However, much of this information remains {\textquoteleft}locked{\textquoteright} in the unstructured form in the scientific publications. Since manual curation involves significant human effort and time there is always a lag in the information between the curated databases and the literature. The recent findings published in the literature takes significant time to find its way into the curated knowledgebase. Text mining approaches can accelerate the process of assembling this knowledge from the published literature. However, developing a text-mining system with semantic understanding capability in the biomedical domain is very challenging. In an earlier work, we described MutD, a literature mining system that extracts relationship between protein point mutation and diseases from bio-medical abstracts. In this abstract, we present access to a PubMed scale resource through a web interface that allows users to retrieve protein point mutation-disease relations extracted through biomedical literature mining.

}, url = {http://ceur-ws.org/Vol-1747/BT203_ICBO2016.pdf}, author = {RK Elayavilli and Majid Rastegar-Mojarad and Hongfang Liu} } @conference {BT202, title = {BT202: Social Media Mining for Pharmacovigilance}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

N/A

}, url = {http://icbo.cgrb.oregonstate.edu/}, author = {Graciela Gonzalez} } @conference {BT201, title = {BT201: Text mining to enable routine personalized cancer therapy}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Genomic profiling information is frequently available to oncologists, enabling targeted cancer therapy. Because clinically relevant genomic information is rapidly emerging in narrative data sources such as biomedical literature and clinical trials documents, there is a need for text mining technologies to support targeted therapies. In this talk, we will present two projects about developing text-mining tools to enable personalized cancer therapy, including 1) to identify molecular effects of drugs in biomedical literature, and 2) to create a knowledge base of cancer treatment trials with annotations about genetic alterations. We believe such tools would be valuable for physicians and patients who are seeking information about personalized cancer therapy, thus facilitating their decision making.

}, url = {http://ceur-ws.org/Vol-1747/BT201_ICBO2016.pdf}, author = {Hua Xu} } @conference {BT104, title = {BT105: Opportunities and challenges presented by Wikidata in the context of biocuration}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Wikidata is a world readable and writable knowledge base maintained by the Wikimedia Foundation. It offers the opportunity to collaboratively construct a fully open access knowledge graph spanning biology, medicine, and all other domains of knowledge. To meet this potential, social and technical challenges must be overcome most of which are familiar to the biocuration community. These include community ontology building, high precision information extraction, provenance, and license management. By working together with Wikidata now, we can help shape it into a trustworthy, unencumbered central node in the Semantic Web of biomedical data.

}, url = {http://ceur-ws.org/Vol-1747/BT105_ICBO2016.pdf}, author = {Benjamin Good and Sebastian Burgstaller-Muehlbacher and Elvira Mitraka and Timothy Putman and Andrew Su and Andra Waagmeester} } @conference {BT103, title = {BT104: Crowdsourcing Protein Family Database Curation}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

We propose a novel method for crowdsourcing a protein family database. We discuss how we intend to identify novel groupings of proteins from user sequence similarity search, and how text mining will be applied to assist in annotation of these novel groupings, and more broadly as an enrichment of protein sequence similarity search results.

}, url = {http://ceur-ws.org/Vol-1747/BT104_ICBO2016.pdf}, author = {Matt Jeffryes and Maria Liakata and Alex Bateman} } @conference {BT102, title = {BT103: Collaborative Workspaces for Pathway Curation}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

We present a web based visual biocuration workspace, focusing on curating detailed mechanistic pathways. It was designed as a flexible platform where multiple humans, NLP and AI agents can collaborate in real-time on a common model using an event driven API. We will use this platform for exploring disruptive technologies that can scale up biocuration such as NLP, human-computer collaboration, crowd-sourcing, alternative publishing and gamification. As a first step, we are designing a pilot to include an author-curation step into the scientific publishing, where the authors of an article create formal pathway fragments representing their discovery- heavily assisted by computer agents. We envision that this {\textquotedblleft}micro-curation{\textquotedblright} use-case will create an excellent opportunity to integrate multiple NLP approaches and semi-automated curation.

}, url = {http://ceur-ws.org/Vol-1747/BT103_ICBO2016.pdf}, author = {Funda Durupinar-Babur and MC Siper and Ugur Dogrusoz and Istemi Bahceci and Ozgun Babur and Emek Demir} } @conference {BT101, title = {BT102: Cycles of Scientific Investigation in Discourse - Machine Reading Methods for the Primary Research Contributions of a Paper}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

We describe a novel approach to machine reading of the primary scientific literature. We treat a description of an experiment as a discourse, viewing a scientific corpus not merely into a collection of documents, but also an extended conversation formed by the collective set of experiments, their introductions and interpretations. This paper introduces this approach as a methodology called {\textquoteleft}Cycles of Scientific Investigation in Discourse{\textquoteright} (CoSID). In CoSID, we capture the central conceptual structure of a paper as a series of nested reasoning loops, composed of passages in results sections, which describe individual research findings. We ground our work with a number of worked examples based on data from the MINTACT and Pathway Logic databases, and illustrate the idea in the context of machine-enable biocuration.

}, url = {http://ceur-ws.org/Vol-1747/BT102_ICBO2016.pdf}, author = {Gully A. Burns and Anita de Waard and Pradeep Dasigi and Eduard H. Hovy} } @conference {342, title = {BT101: SourceData: Making Data discoverable}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

In molecular and cell biology, most of the data presented in published papers are not available in formats that allow for direct analysis and systematic mining. The goal of the SourceData project (http://sourcedata.embo.org) is to make published data easier to find, to connect papers containing related information and to promote the reuse and novel analysis of published data. The main concept underlying the project is that the structure of a dataset provides information about the design of the study in question and can be exploited in powerful data-oriented search strategies. SourceData has therefore developed tools to generate machine-readable descriptive metadata from figures in published manuscripts. Experimentally tested hypotheses are represented as directed relationships between standardized biological entities. Once processed, a comprehensive {\textquoteleft}scientific knowledge graph{\textquoteright} can be generated from this data (see demo video1 at https://vimeo.com/sourcedata/kg), making the body of data efficiently searchable. Importantly, this graph is objectively grounded in published data and not on the potentially subjective interpretation of the results.\ 

}, url = {http://ceur-ws.org/Vol-1747/BT101_ICBO2016.pdf}, author = {Nancy George and Sara El-Gebali and Thomas Lemberger} } @conference {BP03, title = {BP03: Label Embedding Approach for Transfer Learning}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Automatically tagging textual mentions with the concepts, types and entities that they represent are important tasks for which supervised learning has been found to be very effective. In this paper, we consider the problem of exploiting multiple sources of training data with variant ontologies. We present a new transfer learning approach based on embedding multiple label sets in a shared space, and using it to augment the training data.

}, url = {http://ceur-ws.org/Vol-1747/BP03_ICBO2016.pdf}, author = {Rasha Obeidat and Xiaoli Fern and Prasad Tadepalli} } @conference {BP02, title = {BP02: Disease Named Entity Recognition Using NCBI Corpus}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Named Entity Recognition (NER) in biomedical literature is a very active research area. NER is a crucial component of biomedical text mining because it allows for information retrieval, reasoning and knowledge discovery. Much research has been carried out in this area using semantic type categories, such as fiDNAfl, fiRNAfl, fiproteinsfl and figenesfl. However, disease NER has not received its needed attention yet, specifically human disease NER. Traditional machine learning approaches lack the precision for disease NER, due to their dependence on token level features, sentence level features and the integration of features, such as orthographic, contextual and linguistic features. In this paper a method for disease NER is proposed which utilizes sentence and token level features based on Conditional Random Fields using the NCBI disease corpus. Our system utilizes rich features including orthographic, contextual, affixes, bigrams, part of speech and stem based features. Using these feature sets our approach has achieved a maximum F-score of 94\% for the training set by applying 10 fold cross validation for semantic labeling of the NCBI disease corpus. For testing and development corpus the model has achieved an F-score of 88\% and 85\% respectively.

}, url = {http://ceur-ws.org/Vol-1747/BP02_ICBO2016.pdf}, author = {Thomas Hahn and Hidayat Ur Rahman and Richard Segall} } @conference {BP01, title = {BP01: Ignet: A centrality and INO-based web system for analyzing and visualizing literature-mined networks}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Ignet (Integrative Gene Network) is a web-based system for dynamical- ly updating and analyzing gene interaction networks mined using all Pub- Med abstracts. Four centrality metrics, namely degree, eigenvector, be- tweenness, and closeness are used to determine the importance of genes in the networks. Different gene interaction types between genes are classified using the Interaction Network Ontology (INO) that classifies interaction types in an ontological hierarchy along with individual keywords listed for each interaction type. An interactive user interface is designed to explore the interaction network as well as the centrality and ontology based net- work analysis. Availability: http://ignet.hegroup.org.

}, url = {http://ceur-ws.org/Vol-1747/BP01_ICBO2016.pdf}, author = {Arzucan Ozgur and Junguk Hur and Zuoshuang Xiang and Edison Ong and Dragomir Radev and Yongqun He} } @conference {BIT106, title = {BIT106: Use of text mining for Experimental Factor Ontology coverage expansion in the scope of target validation}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Understanding the molecular biology and development of disease plays a key role in drug development. Integrating evidence from different experimental approaches with data available from public resources (such as gene expression level changes and reaction pathways affected by pathogenic mutations) can be a powerful approach for evaluating different aspects of target-disease associations. The application of ontologies is of fundamental importance to effective integration. The Target Validation Platform is a user-friendly interface that integrates such evidences from various resources with the aim of assisting scientists to identify and prioritise drug targets. Currently, the EFO is used as the reference ontology for diseases in the platform, importing terms from existing disease ontologies such as the Human Phenotype Ontology as required. In order to generalize the use of EFO from key target-diseases for wider use, we need to compare the target associated disease coverage in EFO with the scope of other available disease terminology resources. In this study, we address this issue by using text mining and present our initial results.

}, url = {http://ceur-ws.org/Vol-1747/BIT106_ICBO2016.pdf}, author = {Senay Kafkas and Ian Dunham and Helen Parkinson and Johanna Mcentyre} } @conference {BIT105, title = {BIT105: A Web Application for Extracting Key Domain Information for Scientific Publications using Ontology}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

We present demos of an ongoing project, domain informational vocabulary extraction (DIVE), which aims to enrich digital publications through entity and key informational words detection and by adding additional annotations. The system implements multiple strategies for biological entity detection, including using regular expression rules, ontologies, and a keyword dictionary. These extracted entities are then stored in a database and made accessible through an interactive web application for curation and evaluation by authors. Through the web interface, the user can make additional annotations and corrections to the current results. The updates can then be used to improve the entity detection in subsequent processed articles. Although the system is being developed in the context of annotating journal articles, it can be also be beneficial to domain curators and researchers at large.

}, url = {http://ceur-ws.org/Vol-1747/BIT105_ICBO2016.pdf}, author = {Weijia Xu and Amit Gupta and Pankaj Jaiswal and Crispin Taylor and Patti Lockhart} } @conference {BIT104, title = {BIT104: Cardiovascular Health and Physical Activity: A Model for Health Promotion and Decision Support Ontologies}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Current cardiovascular disease decision support systems (DSS) rely primarily on ontologies that characterize and quantify disease, recommending appropriate pharmacotherapy (PT) and/or surgical interventions (SI). PubMed and Google Scholar searches reveal no specific ontologies or literature related to DSS for recommending physical activity (PA) and diet interventions (DI) for cardiovascular health and fitness (CVHF) improvement. This dearth of CVHF-PA/DI structured knowledge repositories has resulted in a scarcity of user-friendly tools for scientifically validated information retrieval about CVHF improvement. Advancement of health science depends on timely development and implementation of health (rather than disease) ontologies. We developed a time-efficient workflow for constructing/maintaining structured knowledge repositories capable of providing informational underpinnings for CVHF- PA/DI ontologies and DSS that support health promotion, including precise, personalized exercise prescription. This workflow creates conceptual lattices about effects of varied PA on CVHF. These conceptual maps lay the foundation for accelerated creation of health-focused ontologies, which ultimately equip DSS with CVHF knowledge related PA and DI.

}, url = {http://ceur-ws.org/Vol-1747/BIT104_ICBO2016.pdf}, author = {Vimala Ponna and Aaron Baer and Matthew Lange} } @conference {BIT103, title = {BIT103: Scalable Text Mining Assisted Curation of PTM Proteoforms in the Protein Ontology}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

The Protein Ontology (PRO) defines protein classes and their interrelationships from the family to the protein form (proteoform) level within and across species. One of the unique contributions of PRO is its representation of post-translationally modified (PTM) proteoforms. However, progress in adding PTM proteoform classes to PRO has been relatively slow due to the extensive manual curation effort required. Here we report an automated pipeline for creation of PTM proteoform classes that leverages two phosphorylation-focused text mining tools (RLIMS-P, which detects mentions of kinases, substrates, and phosphorylation sites, and eFIP, which detects phosphorylation-dependent protein-protein interactions (PPIs)) and our integrated PTM database, iPTMnet. By applying this pipeline, we obtained a set of \ 820 substrate-site pairs that are suitable for automated PRO term generation with literature-based evidence attribution. Inclusion of these terms in PRO will increase PRO coverage of species-specific PTM proteoforms by 50\%. Many of these new proteoforms also have associated kinase and/or PPI information. Finally, we show a phosphorylation network for the human and mouse peptidyl-prolyl cis-trans isomerase (PIN1/Pin1) derived from our dataset that demonstrates the biological complexity of the information we have extracted. Our approach addresses scalability in PRO curation and will be further expanded to advance PRO representation of phosphorylated proteoforms.

}, url = {http://ceur-ws.org/Vol-1747/BIT103_ICBO2016.pdf}, author = {Karen Ross and Darren Natale and Cecilia Arighi and Sheng-Chih Chen and Hongzhan Huang and Gang Li and Jia Ren and Michael Wang and K Vijay-Shanker and Cathy Wu} } @conference {BIT102, title = {BIT102: One tagger, many uses: Illustrating the power of ontologies in dictionary-based named entity recognition}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

Automatic annotation of text is an important complement to manual annotation, because the latter is highly labour intensive. We have developed a fast dictionary-based named entity recognition (NER) system and addressed a wide variety of biomedical problems by applied it to text from many different sources. We have used this tagger both in real-time tools to support curation efforts and in pipelines for populating databases through bulk processing of entire Medline, the open-access subset of PubMed Central, NIH grant abstracts, FDA drug labels, electronic health records, and the Encyclopedia of Life. Despite the simplicity of the approach, it typically achieves 80{\DH}90\% precision and 70{\DH}80\% recall. Many of the underlying dictionaries were built from open biomedical ontologies, which further facilitate integration of the text-mining results with evidence from other sources.

}, url = {http://ceur-ws.org/Vol-1747/BIT102_ICBO2016.pdf}, author = {Jensen, LJ} } @conference {BIT101, title = {BIT101-D204: Large-scale Semantic Indexing with Biomedical Ontologies}, booktitle = {International Conference on Biomedical Ontology and BioCreative (ICBO BioCreative 2016)}, series = {Proceedings of the Joint International Conference on Biological Ontology and BioCreative (2016)}, year = {2016}, month = {11/30/16}, publisher = {CEUR-ws.org Volume 1747}, organization = {CEUR-ws.org Volume 1747}, abstract = {

We introduce PubTator, a web-based application that enables large-scale semantic indexing and automatic concept recognition in biomedical ontologies. Not only was PubTator formally evaluated and top-rated in BioCreative, it also has been widely adopted and used by the scientific community from around the world, supporting both research projects and real-world applications in biocuration, crowdsourcing and translational bioinformatics.

}, url = {http://ceur-ws.org/Vol-1747/BIT101-D204_ICBO2016.pdf}, author = {Chih-Hsuan Wei and Robert Leaman and Zhiyong Lu} }