@conference {ICBO_2018_10, title = {ICBO_2018_10: Standardization of the Histopathology Cancer Report: An Ontological Approach}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

In recent years, the complexity of cancer pathology reporting has increased significantly. The pathology report covers not only general information such as the presence or absence of cancer, but includes a collection of specific parameters such as tumor size, grade, margin, lymphatic or vascular involvement as well as molecular testing e.g. proteomics and genomics (Figure 1). Soon, biomarkers and immune profiling will play an increasingly more important role in determining the eligibility for particular therapies, along with genetic predisposition and social risk factors. The increased use of digital pathology, which allows streamlined sharing of images, has highlighted the importance of clear communication of the information displayed in the pathology report. In the past years, significant effort has been devoted to redefining the way that histopathology report information is recorded. The College of American Pathologists (CAP) (http://www.cap.org/), a leading organization of board-certified pathologists, introduced synoptic cancer reports, a structured checklist to standardize clinical documentation. Despite continuous improvement and generation of electronic reports, formal representation [1] is still lacking. This lack of standardization limits the ability to integrate pathology information with other genomic and proteomic data and often results in loss of information.

}, keywords = {Cancer, Histopathology Cancer, Histopathology report, Ontology, pathology, Pathology standard, Tumor}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_10.pdf}, author = {Anna Maria Masci and Shannon McCall and Alessandro Racioppi and Helena Judge Ellis and Jihad S. Obeid and Barry Smith and Christian Stoeckert and Jie Zheng} } @conference {ICBO_2018_11, title = {ICBO_2018_11: Planteome \& BisQue: Automating Image Annotation with Ontologies using Deep-Learning Networks}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

The field of computer vision has recently experienced tremendous progress due to advances in deep learning. This development holds particular promise in applications for plant research, due to a significant increase in the scale of image data harvesting and a strong field-driven interest in the automated processing of observable phenotypes and visible traits within agronomically important species. Parallel developments have occurred in semantic computing; for example, new ontologies have been initiated to capture plant traits and disease indicators. When combined with existing segmentation capabilities, it is possible to conceptualize software applications that give researchers the ability to analyze large quantities of plant phenotype image data, and to auto-annotate that data with meaningful, computable semantic terminology. We have previously reported on a software application that integrates segmentation and ontologies, but lacked the ability to manage very high-resolution images, and also lacked a database platform to allow for high-volume storage requirements. We have also previously reported our migration of the AISO user-guided segmentation feature to a BisQue (Bio-Image Semantic Query User Environment) module to take advantage of its increased power, ability to scale, secure data management environment, and collaborative software ecosystem. Neither AISO nor our initial BisQue implementation possessed a machine-learning component for interpreting (parts of) images. Plant researchers could benefit greatly from a trained classification model that predicts image annotations with a high degree of accuracy. We have therefore implemented two deep-learning prototypes: a coarse classification module for plant object identification (i.e. flower, fruit) and a fine-grained classification module that focuses on plant traits (e.g. reticulate vs. parallel venation, tip shape). Both classification models return results mapped to ontology terms as a form of annotation enrichment. This current version of the Planteome Deep Segmenter module combines image classification with optional guided segmentation and ontology annotation. We have most recently run the module on local Planteome BisQue client services, and are currently working with CyVerse to install a hosted version on their BisQue client service.

}, keywords = {annotation, convolutional neural networks, deep learning, image analysis, machine learning, Ontology, segmentation}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_11.pdf}, author = {Dimitrios Trigkakis and Justin Preece and Austin Meier and Justin Elser and Kris Kvilekval and Dmitry Fedorov and B.S. Manjunath and Pankaj Jaiswal and Sinisa Todorovic} } @conference {ICBO_2018_12, title = {ICBO_2018_12: Transforming and Unifying Research with Biomedical Ontologies: The Penn TURBO project}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

The Penn TURBO (Transforming and Unifying Research with Biomedical Ontologies) project aims to accelerate finding and connecting key information from clinical records for research through semantic associations to the processes that generated the clinical data. Major challenges to using clinical data for research are integrating data from different sources which may contain multiple references to the same entity (e.g., person, health care encounter) and incomplete or conflicting information (e.g., gender, BMI). There is also the need to track the provenance of information used when making decisions on what is the actual phenotype of a person. We take a realism-based ontology approach to address these problems through transformation and instantiation of clinical data with an OBO-Foundry based application ontology in a semantic graph database. We have developed an application stack and used it on an 11,237 whole exome sequencing patient cohort capturing key demographics, diagnosis codes, and prescribed medications. The anticipated payoff is to be able to make use of inferencing provided by the semantics to classify and search for instances of people and specimens with desired characteristics.

}, keywords = {clinical data, diagnosis codes, OBO Foundry, prescriptions, realism-based ontology, referent tracking}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_12.pdf}, author = {Christian Stoeckert and David Birtwell and Hayden Freedman and Mark Miller and Heather Williams} } @conference {ICBO_2018_13, title = {ICBO_2018_13: The Identity and Mereology of Pathological Dispositions}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

Diseases, risks of pathological processes and predispositions have been formalized as dispositions. The relations between those pathological dispositions, however, remain unclear. We apply here a recently developed theory of mereology and identity among dispositions to analyze such relations. In particular, we show how a framework for the identity of disposition leads to a disease being not only a disposition to a disease course, but also to each pathological process; how it avoids risk multiplicativism; and how a predisposition can be identified with a risk whose estimated probability is higher than for the risk of a reference class. We discuss how this makes predisposition always relative to a reference class, to a time-frame and to sources of risk estimates; and we clarify the nature of risk factors.

}, keywords = {disease, disposition, identity, mereology, predisposition, risk, risk factor}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_13.pdf}, author = {Adrien Barton and Olivier Grenier and Jean-Francois Ethier} } @conference {ICBO_2018_14, title = {ICBO_2018_14: Does the Foundational Model of Anatomy ontology provide a knowledgebase for learning and assessment in anatomy education?}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {Throughout the development of the Foundational Model of Anatomy (FMA) ontology, one of the use cases has been anatomy education. In this work, we examine which types of knowledge taught to anatomy students can be supported by the FMA knowledge base. We first categorize types of anatomical knowledge, then express these patterns in the form {\textquotedblleft}Given ____, state ____{\textquotedblright}. Each of the 33 patterns was evaluated for whether this type of knowledge is compatible with the modeling and scope of the FMA.}, keywords = {anatomy, knowledge representation, medical education, nursing education, Ontology}, url = {http://icbo2018.cgrb.oregonstate.edu/}, author = {Melissa Clarkson and Mark Whipple} } @conference {ICBO_2018_15, title = {ICBO_2018_15: Quality Assurance of Ontology Content Reuse}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

Building ontologies is difficult and time-consuming. As such, content reuse has been promoted as an important guiding principle in ontology development. Reusing content from other ontologies can reduce the overall effort involved in new ontology construction and provide better alignment with existing knowledge modeling. However, reuse is not a panacea, and it comes with its own attendant difficulties. In this paper, we investigate some common quality assurance issues associated with reuse, such as duplicated content and versioning problems. Some heuristic-based approaches are proposed for analyzing ontologies for these kinds of quality assurance issues. An analysis is carried out on a sample of the large collection of BioPortal-hosted ontologies, many of which employ reuse. The findings indicate that curators and authors, particularly those new to the reuse process, should be on the alert when developing an ontology with reused content to avoid introducing problems into their own ontologies.

}, keywords = {BioPortal, modeling, Ontology, ontology quality assurance, ontology reuse}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_15.pdf }, author = {Michael Halper and Christopher Ochs and Yehoshua Perl and Sivaram Arabandi and Mark Musen} } @conference {ICBO_2018_16, title = {ICBO_2018_16: A falsification approach to create and check ontology definitions}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

Here we propose a workflow to derive ontological definitions using a falsification approach to eliminate properties that are not necessary or sufficient. First we present the interpretation of necessity and sufficiency. Then, we present the way to disprove either of these. Last, we derive the workflow that includes finding counter examples for candidate ontological definitions. We apply this approach to a Sequence Ontology definition as a matter of example.

}, keywords = {falsification, necessary and sufficient conditions, ontology definition}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_16.pdf }, author = {Citlalli Mej{\'\i}a and Julio Collado-Vides} } @conference {ICBO_2018_18, title = {ICBO_2018_18: Taking a Dive: Experiments in Deep Learning for Automatic Ontology-based Annotation of Scientific Literature}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

Text mining approaches for automated ontology-based curation of biological and biomedical literature have largely focused on syntactic and lexical analysis along with machine learning. Recent advances in deep learning have shown increased accuracy for textual data annotation. However, the application of deep learning for ontology-based curation is a relatively new area and prior work has focused on a limited set of models. Here, we introduce a new deep learning model/architecture based on combining multiple Gated Recurrent Units (GRU) with a character+word based input. We use data from five ontologies in the CRAFT corpus as a Gold Standard to evaluate our model{\textquoteright}s performance. We also compare our model to seven models from prior work. We use four metrics - Precision, Recall, F1 score, and a semantic similarity metric (Jaccard similarity) to compare our model{\textquoteright}s output to the Gold Standard. Our model resulted in 84\% Precision, 84\% Recall, 83\% F1, and 84\% Jaccard similarity. Results show that our GRU-based model outperforms prior models across all five ontologies. We also observed that character+word inputs result in a higher performance across models as compared to word only inputs. These findings indicate that deep learning algorithms are a promising avenue to be explored for automated ontology-based curation of data. This study also serves as a formal comparison and guideline for building and selecting deep learning models and architectures for ontology-based curation.

}, keywords = {automated curation, deep learning, named entity recognition, natural language processing, Ontology}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_18.pdf }, author = {Prashanti Manda and Lucas Beasley and Somya Mohanty} } @conference {ICBO_2018_19, title = {ICBO_2018_19: Current Development in the Evidence and Conclusion Ontology (ECO)}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

The Evidence \& Conclusion Ontology (ECO) has been developed to provide standardized descriptions for types of evidence within the biological domain. Best practices in biocuration require that when a biological assertion is made (e.g. linking a Gene Ontology term for a molecular function to a protein), the type of evidence supporting it is captured. In recent development efforts, we have been working with other ontology groups to ensure that ECO classes exist for the types of curation they support. These include the Ontology for Microbial Phenotypes and the Gene Ontology. In addition, we continue to support user-level class requests through our GitHub issue tracker. To facilitate the addition and maintenance of new classes, we utilize ROBOT (a command line tool for working with Open Biomedical Ontologies) as part of our standard workflow. ROBOT templates allow us to define classes in a spreadsheet and convert them to Web Ontology Language (OWL) axioms, which can then be merged into ECO. ROBOT is also part of our automated release process. Additionally, we are engaged in ongoing work to map ECO classes to Ontology for Biomedical Investigation classes using logical definitions. ECO is currently in use by dozens of groups engaged in biological curation and the number of ECO users continues to grow. The ontology, in OWL and Open Biomedical Ontology (OBO) formats, and associated resources can be accessed through our GitHub site (https://github.com/evidenceontology/evidenceontology) as well as the ECO web page (http://evidenceontology.org/).

}, keywords = {biocuration, evidence, gene annotation, ontology development, ontology mapping}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_19.pdf }, author = {Rebecca Tauber and James B. Munro and Suvarna Nadendla and Binika Chunara and Marcus C. Chibucos and Michelle Giglio} } @conference {ICBO_2018_2, title = {ICBO_2018_2: Adapting Disease Vocabularies for Curation at the Rat Genome Database}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

The Rat Genome Database (RGD) has been annotating genes, QTLs, and strains to disease terms for over 15 years. During that time the controlled vocabulary used for disease curation has changed a few times. The changes were necessitated because no single vocabulary or ontology was freely accessible and complete enough to cover all of the disease states described in the biomedical literature. The first disease vocabulary used at RGD was the {\textquotedblleft}C{\textquotedblright} branch of the National Library of Medicine{\textquoteright}s Medical Subject Headings (MeSH). By 2011 RGD had switched disease curation to the use of MEDIC (MErged DIsease voCabulary), which is a combination of MeSH and OMIM (Online Mendelian Inheritance in Man) constructed by curators at the Comparative Toxicogenomics Database (CTD). MEDIC was an improvement over MeSH, because of the added coverage of OMIM terms, but it was not long before RGD curators saw the need for more disease terms. So within a couple of years, RGD began to add terms to MEDIC under the guise of the RGD Disease Ontology (RDO). Since RGD assigned a unique ID to every MEDIC term imported from CTD, it was easy to add specially coded IDs to indicate those additional terms from a separate, supplemental file. Meanwhile, the human disease ontology (DO) had slowly been developing and expanding. As early as 2010, members of RGD were contributing to the development of DO. Based on the promise of improvements, it was determined that the Alliance of Genome Resources could use the DO as a unifying disease vocabulary across model organism databases. Despite the improvements in DO, RGD still had more than 1000 custom terms and 3800 MEDIC terms with annotations to deal with if RGD would convert to the use of DO. If RGD mapped those non-DO disease terms to DO, much granularity of meaning would be lost. To avoid the loss of granularity it was decided to extend the DO after import of the merged, already axiomized DO file. So after mapping DO completely to the RGD version of MEDIC, a broader, deeper disease vocabulary has been achieved.

}, keywords = {curation, disease vocabularies, online resource, Rat Genome Database}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_2.pdf }, author = {Stan Laulederkind and G. Thomas Hayman and Shur-Jen Wang and Elizabeth Bolton and Jennifer R. Smith and Marek Tutaj and Jeff de Pons and Mary Shimoyama and Melinda Dwinell} } @conference {ICBO_2018_20, title = {ICBO_2018_20: KNowledge Acquisition and Representation Methodology (KNARM)}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

Technological advancements in many fields have led to huge increases in data production, including data volume, diversity, and the speed at which new data is becoming available. In accordance with this, there is a lack of conformity in the ways data is interpreted. In-depth analyses making use of various data types and data sources, and extracting knowledge has become one of the many challenges with this big data. This is especially the case in life-sciences where simplification and flattening of diverse data types often leads to incorrect predictions. Effective applications of big data approaches in the life sciences require better, knowledge-based, semantic models that are suitable as a framework for big data integration, while avoiding overly extreme simplification, such as reducing various biological data types to the gene level. A major challenge in developing such semantic knowledge models, or ontologies, is the knowledge acquisition bottleneck. Automated methods are still very limited and significant human expertise is required. In this research, we describe a methodology to systematize this knowledge acquisition and representation challenge, termed KNowledge Acquisition and Representation Methodology (KNARM). We also examplify how KNARM was applied on three ontologies: BioAssay Ontology (BAO), LINCS FramEwork Ontology (LIFE) ,and Drug Target Ontology (DTO) built for three different projects: BioAssay Ontology, Library of Integrated Network-Based Cellular Signatures (LINCS), and Illuminating the Druggable Genome (IDG), and how the methodology help the ontologies work together in complex queries.

}, keywords = {big data, ontology building methodology, semi-automated ontology building}, author = {Hande K{\"u}{\c c}{\"u}k-Mcginty and Stephan Schurer and Ubbo Visser} } @conference {ICBO_2018_21, title = {ICBO_2018_21: From PO to GO and back}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {Our recent goal for the Plant Ontology (PO) is to have it integrated with then Gene Ontology (GO). The simplest aspect of this is to link morphological and anatomical images of structures in for PO terms with GO terms. This, also, would include images of in situs. By using a process of reciprocal illumination, we will be able to clarify and/or redefine PO terms, in particular. An example of this is the integument in the seed plants. Gymnosperms have one integument; whereas, Angiosperms (flowering plants) have two integuments, i.e., an inner integument surrounded by an outer integument. The question that arises is which of the two integuments in the Angiosperms is the equivalent of the single integument in then Gymnosperms? In Angiosperms, KANADI 1, 2 and 3 genes are expressed in the outer integument but not in the inner integument and in knock out mutants there is no outer integument. KANADI 1, 2 and 3 are found only in the Angiosperm outer integument. Thus, it appears that the inner integument of the Angiosperms is equivalent homologous) to the single integument of the Gymnosperms and the PO terms can be revised accordingly.}, keywords = {angiosperm, GO, gymnosperm, integument, Ontology, PO}, url = {http://icbo2018.cgrb.oregonstate.edu/}, author = {Dennis Stevenson and Cecilia Zumajo} } @conference {ICBO_2018_22, title = {ICBO_2018_22: Reconciling ontology definitions using the Ontology Pattern Reconciliation Workbench and the DOSDP framework}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

Many bio-ontologies use formal, logical definitions to automate multiple inheritance classification and drive cross-ontology inference. This requires the use of standardised design patterns: shared patterns of axiomatisation using common reference ontologies. Developing, managing and implementing a suitably consistent set of design patterns can be challenging. In many phenotype ontologies, for example, a large proportion of class terms have formal definitions following a general framework, known as entity/quality (EQ), with common relations and reference ontologies. Despite this, the formal definitions used are often too divergent to drive classification and cross-ontology inference. Here we present software tools for improving and managing formalisation using design patterns. The Ontology Pattern Reconciliation Workbench helps users prioritise patterns for reconciliation between two related ontologies based on the impact pattern reconciliation will have on cross-ontology mapping. An extension to the ontology starter kit provides a practical workflow for developing ontologies using formally specified design patterns.

}, keywords = {entity/quality definitions, logical definitions, ontology design patterns, pattern reconciliation, phenotype ontologies}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_22.pdf }, author = {Nicolas Matentzoglu and David Osumi-Sutherland} } @conference {ICBO_2018_23, title = {ICBO_2018_23: Prot{\'e}g{\'e} 5.5 {\textendash} Improvements for Editing Biomedical Ontologies}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

We present Prot{\'e}g{\'e} 5.5, a significant update to the Prot{\'e}g{\'e} Desktop software, which contains new features that are geared towards editing biomedical ontologies. This version of Prot{\'e}g{\'e} contains user-interface enhancements and optimizations that should make the browsing and editing of OBO-library-style biomedical ontologies easier, faster and more efficient when compared to previous versions of Prot{\'e}g{\'e}.

}, keywords = {Biomedical Ontology Editing, OWL, Prot{\'e}g{\'e}}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_23.pdf }, author = {Matthew Horridge and Rafael S Gon{\c c}alves and Csongor I Nyulas and Tania Tudorache and Mark Musen} } @conference {ICBO_2018_24, title = {ICBO_2018_24: eXtensible ontology development (XOD) using web-based Ontoanimal tools}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

The eXtensible ontology development (XOD) strategy proposes four principles to support interoperable and robust ontology development. These principles include ontology term reuse, semantic alignment, design pattern usage, and community extensibility. In this software demo, we show how Ontoanimal tools (e.g., Ontofox, Ontodog, Ontorat, and Ontokiwi) can be used to support the implementation of these XOD principles. The development of the Cell Line Ontology (CLO) is used for the demonstration.

}, keywords = {Cell Line Ontology, CLO, eXtensible ontology development, Ontodog, Ontofox, Ontokiwi, Ontorat, XOD}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_24.pdf }, author = {Edison Ong and Yongqun He and Jie Zheng} } @conference {ICBO_2018_25, title = {ICBO_2018_25: OOPS: The Ontology of Plant Stress, A semi-automated standardization methodology}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

Plant stress traits are an important breeding target for all crop species. Massive amounts of research dollars are spent combating plant diseases and nutrient deficiencies. Often this data is used to achieve a single goal, and then left in a repository to never be used again. As a scientific community, we should be striving to make all publicly funded data reusable, and interoperable. This goal is achievable only through careful annotation using universal data and metadata standards. One such standard is through the use of a standardized vocabulary, or ontology. This paper focuses on producing a semi-automated method to define, and label plant stresses using a combination of web scraping, and ontology design patterns. Standardizing the definitions, and linking plant stress with established hierarchies leverages previous work of developed knowledge bases such as taxonomic classifications and other ontologies.

}, keywords = {automation, data standards, nutrient deficiency, Ontology, plant pathology, Planteome, web scraping}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_25.pdf }, author = {Austin Meier and Marie-Ang{\'e}lique Laporte and Justin Elser and Laurel Cooper and Justin Preece and Pankaj Jaiswal and Jorrit Poelen} } @conference {ICBO_2018_26, title = {ICBO_2018_26: Multi-species Malformation Ontologies}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

In the Ontology of Craniofacial Development and Malformation (OCDM) [1] we created malformation ontologies for the human (Craniofacial Human Malformation Ontology [CHMO]), the mouse (Craniofacial Mouse Malformation Ontology [CMMO]) and the zebrafish (Craniofacial Zebrafish Malfomration Ontology [CZMO]) to comprehensively represent in all three species the different pathological entities involved in cranial dysmorphologies, and in particular, the phenotypic and genotypic abnormalities associated with craniofacial microsomias and their correlation to normal and canonical anatomical entities and their corresponding embryological development.

}, keywords = {craniofacial, malformation, Ontology}, author = {Jose Leonardo Mejino and Landon Detwiler and Timothy Cox and Michael Cunningham and James Brinkley} } @conference {ICBO_2018_27, title = {ICBO_2018_27: Semantic Interoperability: Challenges and Opportunities in Cell Type Knowledge Representation}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

The Human Cell Atlas (HCA) and the California Institute for Regenerative Medicine{\textquoteright}s Center of Excellence in Stem Cell Genomics (CESCG) are identifying novel cell types at a rapid pace using single cell RNA sequencing (scRNAseq). To maximize the scientific return on these discoveries, it will be critical that the data derived from these studies is translated into biological knowledge that is findable, accessible, interoperable and reproducible (FAIR). To achieve this objective, we are developing a provisional cell type ontology (pCL) where the data being gathered from experimental work is represented in a standard semantic format that can be exchanged, retrieved, and inferred over using standard approaches and tools.

}, keywords = {cell type, CL Ontology, GABAergic, glutamatergic, HCA, Interoperability, pCL, scRNAseq}, url = {http://icbo2018.cgrb.oregonstate.edu/}, author = {Richard Scheuermann and Brian Aevermann and Mohamed Keshk} } @conference {ICBO_2018_28, title = {ICBO_2018_28: KTAO: A kidney tissue atlas ontology to support community-based kidney knowledge base development and data integration}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

Human kidney has its complex structure and diverse interactions among its cells during homeostasis and in its diseased states. To systematically classify, represent, and integrate kidney gene activity, cell types, cell states, and interstitial components, we developed a Kidney Tissue Atlas Ontology (KTAO). KTAO reuses and aligns with existing ontologies such as the Cell Ontology, UBERON, and Human Phenotype Ontology. KTAO also generates new semantic axioms to logically link terms of entities in different domains. As a first study, KTAO represents over 200 known kidney gene markers and their profiles in different cell types in kidney patients. Such a representation supports kidney knowledge base generation, query, and data integration.

}, keywords = {AKI, atlas, CKD, disease, gene marker, Kidney, KTAO, Ontology}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_28.pdf }, author = {Yongqun He and Becky Steck and Edison Ong and Laura Mariani and Chrysta Lienczewski and Ulysses Balis and Matthias Kretzler and Jonathan Himmelfarb and John F. Bertram and Evren Azeloglu and Ravi Iyengar and Deborah Hoshizaki and Sean D. Mooney} } @conference {ICBO_2018_29, title = {ICBO_2018_29: Graph Summary of Ontology-based Annotations}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {It is desirable to learn about gene function in ever more detail and to communicate the information using the vocabularies of ontologies. However, rich annotations can exacerbate the challenge of intuitive comprehension of that complex knowledge by a human. We developed a graph-based tool called SObA (Summary of Ontology-based Annotations) to simplify and summarize complex annotations while allowing users to drill down into details easily by following the graph paths.In contrast to fixed-category summaries, such as ribbons or slims, for SObA, ontology graphs are trimmed dynamically, strictly dictated by available annotations. By following a set of simple rules, any node and path in the graph that is redundant or less informative is removed. Furthermore, visual cues to important nodes are provided by node color and size, which are determined by the type and amount of annotations. The SObA graph was implemented using the Cytoscape Javascript library, making it easy for users to traverse the graph at multiple levels of detail.SObA can be applied on any annotations that use DAG (directed acyclic graph) ontologies. We have implemented it on C. elegans phenotype annotations and on Gene Ontology annotations of many species. We are exploring the feasibility of applying SObA to summarize annotations of post-composed ontologies such as the mammalian phenotype ontology.}, keywords = {DAG, GO, Ontology, phenotype, summary graph}, url = {http://icbo2018.cgrb.oregonstate.edu/}, author = {Raymond Lee and Juancarlos Chan and Christian Grove and Paul Sternberg} } @conference {ICBO_2018_3, title = {ICBO_2018_3: Ontology based data architecture to promote data sharing in electrophysiology}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

Efforts to improve the preservation, searchability, and discoverability of research data are a priority. To facilitate these efforts in cell electrophysiology and biophysics we propose that ontologies be used to design and annotate data, as they provide a substantive metadata structure, with reasoned definitions arranged in a logical, hierarchal structure where the meaning of data are unambiguously assigned. We illustrate this by describing our cell electrophysiology data with an ontology. We then make this hierarchal structure with definitions the basis of the data architecture which is implemented upon transforming the data into the storage format: Hierarchical Data Format version 5 (HDF5).

}, keywords = {auditory, data management, HDF5, outer hair cell}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_3.pdf }, author = {Brenda Farrell and Jason Bengtson} } @conference {ICBO_2018_30, title = {ICBO_2018_30: An Expertise Ontology for Cooperative Extension}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

{The national Cooperative Extension System is a non-formal educational network with a mission of advancing agriculture, the environment, human health and well-being, and community economic development that is coordinated through and distributed across the state land-grant universities. At present there is no easy way to query knowledge assets across individual extension organizations with respect to expertise, accomplished projects, or successful interventions. In collaboration with the umbrella organization eXtension.org, we have developed a prototype ontology for describing expertise across the extension network. This ontology aims to provide a framework enabling linking experts, projects, organizations, competencies, digital resources, and other related assets. There are 14 major classes in this ontology: persons, roles, organizations, competencies, expertise types, subject domains, programs, networks, projects, activities, information resources, audiences, issues, and stakeholders. All these classes are anchored in the Basic Formal Ontology (Arp et al. 2015).Other ontologies used for these classes are FOAF, SKOS, the VIVO Ontology for Researcher Discovery (Mitchell 2018}),and the ASI Sustainable Sourcing Ontology (Hollander 2018). These classes fall into several categories. A couple of these classes such as information resources and subject domains tie into existing taxonomies, for instance subject domains being drawn from the National Institute of Food and Agriculture{\textquoteright}s Manual of Classification for Agricultural and Forestry Research, Education, and Extension (NIFA 2005). Other classes here are intended to support development of databases of instances, for instance directories of persons and organizations with information on subject domain expertise and competencies. Finally, several of these classes occupy structural positions in the ontology, for instance role serving as a class that links persons and organizations. A total of 197 classes are presentlydefined, including those enumerated from various taxonomies. Properties for this ontology have beendrawn from the Relations Ontology (Mungall 2018) and VIVO. At present 14 object properties havebeen incorporated in the ontology.Our development of this expertise ontology is part of a broader initiative to create a set of ontologies describing entities and interactions across the entirety of the food system, ranging from food production, impacts and linkages to the environment, to food consumption, nutrition, and human well-being.

}, keywords = {agriculture, Cooperative Extension, expertise, ontology development}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_30.pdf }, author = {Allan D. Hollander and Christine Geith and Matthew C. Lange} } @conference {ICBO_2018_31, title = {ICBO_2018_31: Test-driven Ontology Development in Prot{\'e}g{\'e}}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

Over the past decade, various quality assurance methodologies have emerged in the field of software engineering for preventing, detecting, and fixing faults and bugs in software. In particular, Test-driven Development (TDD) is now a popular quality assurance technique whereby extensive usage of test cases can be used to enforce the correctness of software artifacts. While testing has made its way into the field of ontology engineering, where some techniques for testing ontologies are now used in prominent biomedical ontology projects, Test-driven Development has yet to achieve significant uptake. In this paper we propose a Logic-Based Test-driven Ontology Development methodology, which takes cues from Test-Driven Development in the field of software engineering. Our hope is that this will encourage a "test-first" approach to ontology engineering and that it will form part of the arsenal available to ontology engineers in order to help them produce and maintain high quality ontologies. Test cases in our framework are represented by simple statements describing expected and/or unwanted logical consequences of an intended ontology. As with Test-driven Development in software engineering, our approach encourages small, frequent iterations in the testing and development life-cycle. We provide and present tool support for our approach in the form of OntoDebug {\textendash}- a plug-in for the ontology editor Prot{\'e}g{\'e}.

}, keywords = {ontology quality assurance, Prot{\'e}g{\'e} Plug-In, Test-Driven Ontology Development}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_31.pdf }, author = {Konstantin Schekotihin and Patrick Rodler and Wolfgang Schmid and Matthew Horridge and Tania Tudorache} } @conference {ICBO_2018_32, title = {ICBO_2018_32: Ontolobridge {\textendash} A Semi-Automated Ontology Update Request System for Better FAIR-ifying BioAssay Ontology, Drug Target Ontology, and LINCS Ontology}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {Ontologies are products that are becoming more relevant for data science as the need for standardized vocabulary and meta-data is increasing. However, if they want to stay relevant, ontologies have a constant need for evolving, especially in domains that involve dynamic data, like life-sciences data. Based on the need pointed out by domain experts for updating and/or requesting ontology terms while annotating BioAssay Protocols, we are developing a semi-automated technology that will allow users to request new terms and update existing ones easier. This need was pointed out by domain experts who are using CDD{\textquoteright}s new tool BioAssay Express (BAE). BAE allows users to annotate their bioassays in a semi-automated and standardized fashion using the highly-accessed ontologies (BioAssay Ontology (BAO), Gene Ontology (GO), Disease Ontology (DOID), and Drug Target Ontology (DTO) among others) in the background. Our goal in the Ontolobridge project is to help various users of BAE (researchers performing curation, dedicated curators, IT specialists, ontology owners, and librarians/repositories) request and update the existing vocabulary provided by BAO in a semi-automated way, with a user-friendly interface. Furthermore, APIs and tools including templates from CEDAR will be created in order to would allow users to request new ontology terms or changes to existing terms easily during the annotation process. In this way, we{\textquoteright}re aiming to increase the Findability, Interoperability, Accessibility, and Reproducibility (FAIR) of above mentioned ontologies and BioAssay Protocols better.}, keywords = {annotation, big data, BioAssay Express, BioAssay Ontology, CEDAR, FAIR, FAIR data, life sciences big data, ontology term request, semi-automated ontology updates}, url = {http://icbo2018.cgrb.oregonstate.edu/}, author = {Hande K{\"u}{\c c}{\"u}k-Mcginty and Alex Clark and John Graybeal and Daniel Cooper and John Turner and Michael Dorf and Mark Musen and Barry Bunin and Stephan Schurer} } @conference {ICBO_2018_35, title = {ICBO_2018_35: Can a Convolutional Neural Network Support Auditing of NCI Thesaurus Neoplasm Concepts?}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

We present a Machine Learning methodology using a Convolutional Neural Network to perform a specific case of an ontology Quality Assurance, namely discovery of missing IS-A relationships for Neoplasm concepts in the National Cancer Institute Thesaurus (NCIt). The training step checking all {\textquotedblleft}uncles{\textquotedblright} of a concept is computationally intensive. To shorten the time and to improve the accuracy, we define a restricted methodology to check only uncles that are similar to each current concept. The restricted technique yields higher classification recall (compared to the unrestricted one) when testing against known errors found by domain experts who manually reviewed Neoplasm concepts in a prior study. The results are encouraging and provide impetus for further improvements to our technique.

}, keywords = {Abstraction Network, CNN, deep learning, machine learning, National Cancer Institute Thesaurus, Neoplasm Hierarchy, quality assurance}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_35.pdf}, author = {Hao Liu and Ling Zheng and Yehoshua Perl and James Geller and Gai Elhanan} } @conference {ICBO_2018_36, title = {ICBO_2018_36: The New SNOMED CT International Medicinal Product Model}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

Objectives. To present the new SNOMED CT international medicinal product model. Methods. We present the main elements of the model, with focus on types of entities and their interrelations, definitional attributes for clinical drugs, and categories of groupers. Results. We present the status of implementation as of July 2018 and illustrate differences between the original and new models through an example. Conclusions. Benefits of the new medicinal product model include comprehensive representation of clinical drugs, logical definitions with necessary and sufficient conditions for all medicinal product entities, better high-level organization through distinct categories of groupers, and compliance with international standards.

}, keywords = {knowledge representation, Medicinal products, SNOMED CT}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_36.pdf}, author = {Olivier Bodenreider and Julie James} } @conference {ICBO_2018_37, title = {ICBO_2018_37: Ontology-Enhanced Representations of Non-image Data in The Cancer Image Archive}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

The Cancer Image Archive (TCIA) hosts over 11 million de-identified medical images related to cancer for research reuse. These are organized around DICOM-format radiological collections that are grouped by disease type, modality, or research focus. Many collections also include diverse non-image datasets in a variety of formats without a common approach to representing the entities that the data are about. This paper describes work to make these diverse non-image data more accessible and usable by transforming them into integrated semantic representations using Open Biomedical Ontologies, highlights obstacles encountered in the data, and presents detailed representations data found in select collections.

}, keywords = {Cancer, imaging, ontology development, semantics}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_37.pdf }, author = {Jonathan Bona and Tracy Nolan and Mathias Brochhausen} } @conference {ICBO_2018_38, title = {ICBO_2018_38: Expanding the Molecular Glycophenotype Ontology to include model organisms and acquired diseases}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

Glycans are an underappreciated class of molecules despite the fact that they are implicated in more than 100 known diseases. We have developed an ontology model that captures glycan abnormalities at the molecular level (glycophenotypes) called the molecular glycophenotype ontology (MGPO). Only 30\% of known glycosyltransferases have been implicated in human genetic disorders of glycosylation. Ortholog glycosyltransferases from model organism can cover relevant biological information on potential human diseases. Thus, extending MGPO to represent additional phenotypes and support annotation of model organism data will help cross-species comparison. Expansion of MGPO will also include annotation of glycophenotypes from acquired diseases.

}, keywords = {diseases, glycans, glycobiology, glycophenotypes, model organisms., Ontology}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_38.pdf }, author = {Jean-Philippe Gourdine and Nicole Vasilevsky and Lilly Winfree and Matthew Brush and Melissa Haendel} } @conference {ICBO_2018_39, title = {ICBO_2018_39: TOCSOC: A temporal ontology for comparing the survival outcomes of clinical trials in oncology}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

The outcome of clinical trials for cancer is typically summarized in terms of survival. However, different trials for the same disease may use different measures of survival, or use differing vocabulary to refer to the same outcome measure. This makes it harder to automate an objective comparison of treatments. We propose a temporal ontology of survival outcome measures that a) helps to standardize the vocabulary for reporting survival outcomes and b) makes it possible to automatically rank the relative efficacy of different treatments. The approach has been illustrated by examples from the oncology literature. The temporal ontology and the accompanying reasoner are freely available on Github (https://github.com/pdddinakar/TOCSOC)

}, keywords = {clinical trials, oncology, reasoning, survival outcome, temporal ontology}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_39.pdf }, author = {Deendayal Dinakarpandian and Bhavish Dinakar and Michaela Liedtke and Mark Musen} } @conference {ICBO_2018_4, title = {ICBO_2018_4: Comparison of Natural Language Processing Tools for Automatic Gene Ontology Annotation of Scientific Literature}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

Manual curation of scientific literature for ontology-based knowledge representation has proven infeasible and unscalable to the large and growing volume of scientific literature. Automated annotation solutions that leverage text mining and Natural Language Processing (NLP) have been developed to ameliorate the problem of literature curation. These NLP approaches use parsing, syntactical, and lexical analysis of text to recognize and annotate pieces of text with ontology concepts. Here, we conduct a comparison of four state of the art NLP tools at the task of recognizing Gene Ontology concepts from biomedical literature using the Colorado Richly Annotated Full-Text (CRAFT) corpus as a gold standard reference. We demonstrate the use of semantic similarity metrics to compare NLP tool annotations to the gold standard.

}, keywords = {curation, gene ontology, natural language processing, semantic similarity, text mining}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_4.pdf}, author = {Lucas Beasley and Prashanti Manda} } @conference {ICBO_2018_40, title = {ICBO_2018_40: Human Cell Atlas Ontology}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

The Human Cell Atlas (HCA) project aims to build comprehensive reference maps of Human cells that will further our understanding of biological processes and diagnosing and treating disease. We present the Human Cell Atlas Ontology (HCAO), an application ontology that builds and extends from existing ontology standards to provide terminology standards with well-defined semantics for describing experimental data coming into the HCA to ensure the data is interoperable and amenable to integrative analysis.

}, keywords = {application ontology, data interoperability, Human Cell Atlas}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_40.pdf }, author = {Danielle Welter and Simon Jupp and David Osumi-Sutherland} } @conference {ICBO_2018_41, title = {ICBO_2018_41: Formalizing the Representation of Immune Exposures for Human Immunology Studies}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

Human immunology studies typically examine how immune exposures associated with vaccinations, infectious, allergic or autoimmune diseases, or transplantations perturb the immune system with the goal to develop diagnostic tools and therapeutic interventions. While there are established approaches to formally represent the experimental data generated in such studies, which often comprises gene expression data, flow cytometry data, or serology data, the description of the immune exposures themselves is not well standardized. We here present a formal approach to represent immune exposures at a high level of granularity. We capture the exposure process (e.g. {\textquoteleft}vaccination{\textquoteright} or {\textquoteleft}occurrence of allergic disease{\textquoteright}), exposure material (e.g. {\textquoteleft}Tdap vaccine{\textquoteright} or {\textquoteleft}House dust mite{\textquoteright}), and the associated disease name and stage (e.g. {\textquoteleft}allergic rhinitis{\textquoteright} and {\textquoteleft}chronic{\textquoteright}). This representation scheme has been used successfully in the IEDB and an extended version has been adopted by HIPC to capture studies in ImmPort. We are reporting here on this scheme, our ongoing attempts to map the terms used to existing ontologies, and the challenges encountered.

}, keywords = {disease, Exposure, Immunology, Standardization}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_41.pdf }, author = {Randi Vita and Bjoern Peters and James Overton and Kei-Hoi Cheung and Steven Kleinstein} } @conference {ICBO_2018_42, title = {ICBO_2018_42: ELIXIR Interoperability: Standardisation of identifiers, schemas, and ontologies for scientific communities}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {ELIXIR (https://www.elixir-europe.org) unites Europe{\textquoteright}s leading life science organisations in managing the increasing volume of data being generated by publicly funded research. ELIXIR operates in a Hub-Node model with the Hub coordinating the activities undertaken by the Nodes via five technical platforms: Compute, Data, Interoperability, Tools, and Training to build a sustainable and foundational framework for Life Science informatics communities. This is done by establishing strategic guidelines underlying scientific operations across ELIXIR{\textquoteright}s twenty-one Node members (as of May 2018). The ELIXIR Interoperability Platform (EIP) has been established to deal with the challenge of delivering Findable, Accessible, Interoperable, and Reusable (FAIR) data across the different levels of complexity and variety of life science data types: across the datasets, data catalogues, data tools and services; across the multitude of biological disciplines and geographical or organisational boundaries. The EIP aims to make available the services and resources needed to make data FAIR. These strategies will be founded on FAIR Principles. Ontologies are a crucial component of the EIP strategy, with OBO Foundry Ontologies recognised as reference resource, and leveraged through resources such as Ontology Lookup Service, which provides additional user services for search and annotation. EIP is currently engaged in addressing specific community-derived use cases where incorporating ontological information is essential: rare disease, marine metagenomics, and plant informatics. These require reference ontologies such as Human Phenotype Ontology (HP), Disease Ontology (DO), Cell Ontology (CL), and UBERON.}, keywords = {Bioschemas, FAIR, identifiers, Interoperability, linked-data, Ontology}, url = {http://icbo2018.cgrb.oregonstate.edu/}, author = {Sirarat Sarntivijai and Nick Juty and Carole Goble and Helen Parkinson and Chris Evelo and Jerry Lanfear and Niklas Blomberg} } @conference {ICBO_2018_43, title = {ICBO_2018_43: Domain Informational Vocabulary Extraction Experiences with Publication Pipeline Integration and Ontology Curation}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

We will present updates on an ongoing project DIVE (Domain Informational Vocabulary Extraction), a system designed for extracting domain information from scientific publications. DIVE implements an ensemble of text mining methods for biological entity extraction from article text. DIVE also attempts use the co-occurrence patterns of these entities to establish probable relationships between them. DIVE also features an improved web interface for expert user curation of extracted information, thereby providing a means for a constantly growing and expert curated body of domain information for an article corpus. We also discuss our experiences from successful integration of DIVE with the publishing pipeline for two prominent Plant Biology Journals (The Plant Cell and Plant Physiology) from ASPB (American Society of Plant Biologists). The extracted results are embedded at the end of the final proof of the published article to enhance its accessibility and discoverability. Furthermore, DIVE tracks expert user curation actions on its web interface for future training and improvement of the entity detection algorithm.

}, keywords = {big data, Cyberinfrastructure, DIVE, machine learning, Ontology}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_43.pdf }, author = {Amit Gupta and Weijia Xu and Pankaj Jaiswal and Crispin Taylor and Jennifer Regala} } @conference {ICBO_2018_45, title = {ICBO_2018_45: Formal Ontological Framework for representation of Food Phenotype, Sensation, Perception Tractable Flavor}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

Among all sensory sciences, flavour remains a wicked problem. Sight, sound, and touch have all been digitized, and vast resources around their computation exist. While the biological basis for food consumption is primarily to nourish bodily functions, it fulfills a greater second function of sensory pleasure. Flavor, and the pleasure it engenders, is the primary driver of food choice. Moving toward a semantic web of food that enables personalization of food and flavor experiences requires an interoperable ontological model of flavor. This paper proposes a framework of several ontologies to model a comprehensive view of flavor, by partitioning it into three interoperable matrices of interacting variables: objective characteristics of food, subjective sensory experience, and interpretive communication of that experience. The objective matrix details the properties and behaviour of food molecules. The subjective matrix represents the multilayered and highly individualised consumption and sensory perception variables. The interpretative layer deals with the communication and language used to describe the food experience. Together these three matrices represent an initial ontological model for the flavor and sensory experience portion of the emerging semantic web of food.

}, keywords = {digital model, Flavour, Food Phenotype, formal ontologies, organoleptic, semantic web}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_45.pdf }, author = {Tarini Naravane and Matthew Lange} } @conference {ICBO_2018_46, title = {ICBO_2018_46: Standardizing Ontology Workflows Using ROBOT}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

Building and maintaining ontologies can be challenging due to the need to automate a number of common tasks, such as running quality control checks, automatic classification using reasoners, generating standard reports, extracting application-specific subsets, and managing ontology dependencies. These workflows are in some aspects analogous to workflows used in software engineering as part of the normal product lifecycle. However, in contrast to software development, there is a lack of easy to use tooling to support the execution of these workflows for ontology developers

}, keywords = {automation, import management, ontology development, ontology release, OWL, quality control, reasoning, workflows}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_46.pdf }, author = {Rebecca Tauber and James Balhoff and Eric Douglass and Chris Mungall and James A. Overton} } @conference {ICBO_2018_47, title = {ICBO_2018_47: On the statistical sensitivity of semantic similarity metrics}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

Measuring the semantic similarity between objects that have been annotated with ontological terms is fundamental to an increasing number of biomedical applications, and several different ontologically-aware semantic similarity metrics are in common use. In some of these applications, only weak semantic similarity is expected for biologically meaningful matches. In such cases, it is important to understand the limits of sensitivity for these metrics, beyond which biologically meaningful matches cannot be reliably distinguished from noise. Here, we present a statistical sensitivity comparison of five common semantic similarity metrics (Jaccard, Resnik, Lin, Jiang \& Conrath, and Hybrid Relative Specificity Similarity) representing three different kinds of metrics (Edge based, Node based, and Hybrid) and four different methods of aggregating individual annotation similarities to estimate similarity between two biological objects - All Pairs, Best Pairs, Best Pairs Symmetric, and Groupwise. We explore key parameter choices that can impact sensitivity. To evaluate sensitivity in a controlled fashion, we explore two different models for simulating data with varying levels of similarity and compare to the noise distribution using resampling. Source data are derived from the Phenoscape Knowledgebase of evolutionary phenotypes. Our results indicate that the choice of similarity metric, along with different parameter choices, can substantially affect sensitivity. Among the five metrics evaluated, we find that Resnik similarity shows the greatest sensitivity to weak semantic similarity. Among the ways to combine pairwise statistics, the Groupwise approach provides the greatest discrimination among values above the sensitivity threshold, while the Best Pairs statistic can be parametrically tuned to provide the highest sensitivity. Our findings serve as a guideline for an appropriate choice and parameterization of semantic similarity metrics, and point to the need for improved reporting of the statistical significance of semantic similarity matches in cases where weak similarity is of interest.

}, keywords = {annotation granularity, curation, Ontology, phenotype, semantic similarity}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_47.pdf }, author = {Prashanti Manda and Todd Vision} } @conference {ICBO_2018_48, title = {ICBO_2018_48: Evidence-based medicine,Knowledge Modeling Framework}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {Members within the Healthcare Collaborative Network are confronting major changes at work as well as the growing body of information, much of it invalid or irrelevant to clinical practice. Evidence-based medicine is used to analyze clinical data objectively in terms of quality from different studies. The knowledge modeling is important in knowledge management for understanding the source of knowledge, the inputs and outputs, the flow of knowledge and the dependents are necessary to model the knowledge.This article discusses a proposed evidence based medicine, knowledge modeling framework. The challenge is in representation, integration, analysis, interpretation of the available knowledge and data, management of heterogeneous data, the integration and transfer of enriched data, the effective use of knowledge-based decision systems, sharing of knowledge automatically from huge volumes of data. The above challenge arise the need for Evidence-based medicine Knowledge Modeling Framework, which should provide an answer for the question "How collection, sharing and re-uses of biomedical Big Data should be regulated?{\textquotedblright}.}, keywords = {Bioinformatics, Evidence-based medicine, Knowledge Modeling Framework}, url = {http://icbo2018.cgrb.oregonstate.edu/}, author = {Morcous Massoud} } @conference {ICBO_2018_5, title = {ICBO_2018_5: Semantic Integration of Heterogeneous Resources Based on Domain Ontology}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {Heterogeneity has become an important feature of information resources in the network environment. An integrated approach is needed to achieve the disclosure, association, and retrieval of multiple heterogeneous information resources. The traditional integration methods of information resource can solve the heterogeneous problems in terms of system level, syntax level, structure level, etc. The heterogeneity problems at semantic level will be solved under the support of domain ontology with enhanced semantic. This paper applies domain ontology to the semantic integration of heterogeneous information resources, designs a semantic integration model based on domain ontology, and focus on the problems that should be solved during the implementation of this model. This paper discusses the solutions for the problems and applies them to the process of semantic integration of open resources in the field of plant diversity. The application effect is verified to support the service scenes such as semantic retrieval and knowledge browsing in specific subject areas.}, keywords = {domain ontology, open resources, plant diversity, semantic heterogeneity, semantic integration}, url = {http://icbo2018.cgrb.oregonstate.edu/}, author = {Jinjing Guo and Huiling Ren and Jinxia Huang} } @conference {ICBO_2018_50, title = {ICBO_2018_50: A Natural Language Processing Pipeline to extract phenotypic data from formal taxonomic descriptions with a Focus on Flagellate Plants}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

Assembling large-scale phenotypic datasets for evolutionary and biodiversity studies of plants can be extremely difficult and time consuming. New semi-automated Natural Language Processing (NLP) pipelines can extract phenotypic data from taxonomic descriptions, and their performance can be enhanced by incorporating information from ontologies, like the Plant Ontology (PO) and the Plant Trait Ontology (TO). These ontologies are powerful tools for comparing phenotypes across taxa for large-scale evolutionary and ecological analyses, but they are largely focused on terms associated with flowering plants. We describe a bottom-up approach to identify terms from flagellate plants (including bryophytes, lycophytes, ferns, and gymnosperms) that can be added to existing plant ontologies. We first parsed a large corpus of electronic taxonomic descriptions using the Explorer of Taxon Concepts tool (http://taxonconceptexplorer.org/) and identified flagellate plant specific terms that were missing from the existing ontologies. We extracted new structure and trait terms, and we are currently incorporating the missing structure terms to the PO and modifying the definitions of existing terms to expand their coverage to flagellate plants. We will incorporate trait terms to the TO in the near future.

}, keywords = {flagellate plants, matrices, natural language processing, phenotypic traits, phylogeny, Plant Ontology, Plant Trait Ontology, taxonomic descriptions}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_50.pdf }, author = {Lorena Endara and Gordon Burleigh and Laurel Cooper and Pankaj Jaiswal and Marie-Ang{\'e}lique Laporte and Hong Cui} } @conference {ICBO_2018_51, title = {ICBO_2018_51: Manually Curated Database of Rice Proteins: a case of digitized experimental data via structured use of ontologies}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {The {\textquoteleft}Manually Curated Database of Rice Proteins{\textquoteright} (www.genomeindia.org/biocuration) is a data resource based on digitized experimental data on rice proteins. More than 15,000 published experimental datasets (consisting of over 90,000 data-points) from >550 published articles have been digitized in a manual curation exercise. The experimental datasets originate from over 150 different types of experimental techniques. Various combinations of ontologies have been used to represent different aspects of every data point of the experimental datasets. Thus, each data point could be imagined to be represented by an equation consisting of various ontology terms. Each ontology term represents a unique aspect of the data points. In original publication these data sets are represented as an image or a graph which cannot be searched computationally. As a consequence of this curation procedure data from numerous experimental techniques such as enzymatic assays, RT-PCR assays, localization analysis and trait analysis can be rapidly searched from a collection of hundred of curated research publications. The data can either be browsed from various perspectives (tissue, developmental stage, experimental technique, function, treatment etc.) or searched with the help of any ontology term or definition. All the experimental data can be browsed by either the gene name, plant developmental stage, plant tissue, environmental condition (treatment), trait (molecular or biochemical) or gene function. Figure 1. illustrates the interoperability and connectivity of the digitized experimental datasets. As an example one can start browsing with a list of {\textquoteleft}traits{\textquoteright}. Selection of any one trait will give the list of all the genes that have been associated with this trait in published literature. It also shows the actual experimental dataset and the experimental technique that was used for this association. Further selecting any one of these takes the user to the actual digitized data. Thus, the database provides a seamless access and search capability to experimental data that was earlier published as an image or graph and thus could not be searched (accessed) computationally. Continuous efforts are being done to add more and more published datasets to the database and to also extend the exercise to other crops as well.}, keywords = {Digitization, Experimental data, manual curation, rice}, url = {http://icbo2018.cgrb.oregonstate.edu/}, author = {Saurabh Raghuvanshi} } @conference {ICBO_2018_52, title = {ICBO_2018_52: The integrative use of anatomy ontology and protein-protein interaction networks to study evolutionary phenotypic transitions}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

Studying evolutionary phenotypic transitions, such as the fin to limb transition, is popular in evolutionary biology. The recent advances in next-generation technologies have accumulated large volumes of genomics and proteomics data, which can be used to analyze the genetic basis for evolutionary phenotypic transitions. Protein-protein interaction (PPI) networks can be used to predict candidate genes and identify gene modules related to evolutionary phenotypes; however, they suffer from low gene prediction accuracy. Therefore, an integrative framework was developed using PPI networks and anatomy ontology, which significantly improved the accuracy of network-based candidate gene predictions in zebrafish and mouse. This integrative framework will also be used to identify gene modules associated with the fin to limb transition and to study the changes in these modules which lead to the phenotypic change.

}, keywords = {anatomy ontology, data integration, gene prediction, network analysis, protein-protein interactions}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_52.pdf }, author = {Pasan Fernando and Erliang Zeng and Paula Mabee} } @conference {ICBO_2018_53, title = {ICBO_2018_53: Visualization of gene expression and expression as a phenotype with the XPO, XAO and DO using a combination of experimental data sources}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

Xenbase (www.xenbase.org) is a knowledge base for researchers and biomedical scientists that employ Xenopus (X. laevis and X. tropicalis) as a model organism in gaining a deeper understanding of developmental and disease processes. Through expert curation and automated data provisioning from various sources this MOD (model organism database) strives to integrate the Xenopus body of knowledge together with the visualization of biologically significant interactions. We present a vision for the usage of various ontologies that facilitate the visualization of gene expression from a combination of experimental data sources and the linking thereof back to human disease modeling. In keeping with the philosophy to foster greater insight through the use of visualization techniques that bring together data from different sources and show trends in the large body of experimental and curated data in Xenbase. The approach has been taken to represent key developmental stages and selected embryonic/adult tissue anatomy terms with a modified heat map rendering. This gives us the combined results from the in-situ gene expression summary as well as normalized TPM read counts (Sessions et al.) and UMI counts from the single cell experiment data (Peshkin et al.). Through the acquisition of RNA-seq and ChIP-seq Xenopus data from GEO and subsequent processing through a bioinformatics pipeline to obtain average TPM read counts and differential expression readings. This enables the subsequent construction and visualization of EaP (Expression as a Phenotype) in conjunction with the XPO (Xenopus Phenotype Ontology) and DO (Disease Ontoloty). This data manipulation has practical application in making the information accessible from gene pages and linking back to the source (eg:article/image). If you use Xenbase resources in your research please consider citing us, for example Nucleic Acids Res. 2018 46(D1):D861-D868.

}, keywords = {biocuration, gene expression, genomics, human disease modeling, model organism database, xenopus anatomy ontology, xenopus phenotype ontology}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_53.pdf }, author = {Troy Pells and Malcolm Fisher and Erik Segerdell and Joshua Fortriede and Kevin Burns and Stanley Chu and Praneet Chaturvedi and Christina James-Zorn and Vaneet Lotay and Mardi Nenni and V.G. Ponferrada and Dong Zhou Wang and Ying Wang and Kamran Karimi and Peter Vize and Aaron Zorn} } @conference {ICBO_2018_54, title = {ICBO_2018_54: Developing graphic libraries to accompany the Craniofacial Human Ontology}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

I describe the development of two graphic libraries to accompany parts of the Craniofacial Human Ontology. One library depicts phenotypes of cleft lip. The other represents development of the human head between 4 and 8 weeks of gestation.

}, keywords = {anatomy, graphics, Ontology, visual representation}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_54.pdf }, author = {Melissa Clarkson} } @conference {ICBO_2018_55, title = {ICBO_2018_55: Visualization: A Powerful Tool for Data Exploration and Storytelling}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {Advanced computing and imaging/sensing technologies enable scientists and researchers to study complex phenomena at unprecedented precision, resulting in an explosive growth of data. The size of the collected information about the Internet and mobile device users is expected to be even greater, a daunting challenge we must address in order to make sense and maximize utilization of all the available information. Visualization transforms large quantities of, often multiple-dimensional, data into graphical representations that exploit the high-bandwidth channel of the human visual system, leveraging the brain{\textquoteright}s remarkable ability to detect patterns and draw inferences. It has thus become an indispensable tool in many areas of study involving large, complex data. This talk presents and discusses several effective visualization designs made to support a variety of data driven tasks found in real-world applications from simulations for scientific discovery and design, to emergency management, cyber security, e-commerce and healthcare.}, keywords = {data exploration, scientific discovery, storytelling, Visualization}, url = {http://icbo2018.cgrb.oregonstate.edu/}, author = {Kwan-Liu Ma} } @conference {ICBO_2018_56, title = {ICBO_2018_56: Towards the Development of an Opioid Misuse Ontology}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

Opioid abuse is a major health crisis in the United States, and it is imperative that patients on an abuse trajectory be identified early. Ontologies, with their semantic representations, provide an advantageous framework for use in early identification of opioid misusers. This paper discusses the early-stage development of the Opioid Misuse Ontology (OMO). Existing ontologies from Ontobee and NCBO Bioportal were reviewed. Data representation for opioid use and misuse was modeled using ontologies with terms from existing resources where possible. Several terms were identified that need to be created. Future directions for OMO include development of new classes, creation of an OWL artifact, publication for public comment, and trialing with electronic medical record data to determine how well it identifies opioid misusers.

}, keywords = {misuse, Ontology, opioids}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_56.pdf }, author = {Corey Hayes and Jonathan Bona and Mathias Brochhausen} } @conference {ICBO_2018_57, title = {ICBO_2018_57: An Ontology For Formal Representation Of Medication Adherence-Related Knowledge: Case Study In Breast Cancer}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

Medication non-adherence is a major healthcare problem that negatively impacts the health and productivity of individuals and society as a whole. Reasons for medication non-adherence are multi-faced, with no clear-cut solution. Adherence to medication remains a difficult area to study, due to inconsistencies in representing medication-adherence behavior data that poses a challenge to humans and today{\textquoteright}s computer technology related to interpreting and synthesizing such complex information. Developing a consistent conceptual framework to medication adherence is needed to facilitate domain understanding, sharing, and communicating, as well as enabling researchers to formally compare the findings of studies in systematic reviews. The goal of this research is to create a common language that bridges human and computer technology by developing a controlled structured vocabulary of medication adherence behavior{\textemdash}{\textquotedblleft}Medication Adherence Behavior Ontology{\textquotedblright} (MAB-Ontology) using breast cancer as a case study to inform and evaluate the proposed ontology and demonstrating its application to real-world situation. The intention is for MAB-Ontology to be developed against the background of a philosophical analysis of terms, such as belief, and desire to be human, computer-understandable, and interoperable with other systems that support scientific research. The design process for MAB-ontology carried out using the METHONTOLOGY method incorporated with the Basic Formal Ontology (BFO) principles of best practice. This approach introduces a novel knowledge acquisition step that guides capturing medication-adherence-related data from different knowledge sources, including adherence assessment, adherence determinants, adherence theories, adherence taxonomies, and tacit knowledge source types. These sources were analyzed using a systematic approach that involved some questions applied to all source types to guide data extraction and inform domain conceptualization. A set of intermediate representations involving tables and graphs was used to allow for domain evaluation before implementation. The resulting ontology included 629 classes, 529 individuals, 51 object property, and 2 data property. The intermediate representation was formalized into OWL using Prot{\'e}g{\'e}. The MAB-ontology was evaluated through competency questions, use-case scenario, face validity and was found to satisfy the requirement specification. This study provides a unified method for developing a computerized-based adherence model that can be applied among various disease groups and different drug categories.

}, keywords = {adherence, adjuvant endocrine therapy, adjuvant hormonal therapy, aromatase inhibitors, Ontology, tamoxifen}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_57.pdf }, author = {Suhila Sawesi and Josette Jones and William Duncan} } @conference {ICBO_2018_58, title = {ICBO_2018_58: Computational Classification of Phenologs Across Biological Diversity}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

Phenotypic diversity analyses are the basis for research discoveries ranging from basic biology to applied research. Phenotypic analyses often benefit from the availability of large quantities of high-quality data in a standardized format. Image and spectral analyses have been shown to enable high-throughput, computational classification of a variety of phenotypes and traits. However, equivalent phenotypes expressed across individuals or groups that are not anatomically similar can pose a problem for such classification methods. In these cases, high-throughput, computational classification is still possible if the phenotypes are documented using standardized, language-based descriptions. Conversion of language-based phenotypes to computer-readable {\textquotedblleft}EQ{\textquotedblright} statements enables such large-scale analyses. EQ statements are composed of entities (e.g., leaf) and qualities (e.g., increased length) drawn from terms in ontologies. In this work, we present a method for automatically converting free-text descriptions of plant phenotypes to EQ statements using a machine learning approach. Random forest classifiers identify potential matches between phenotype descriptions and terms from a set of ontologies including GO (gene ontology), PO (plant ontology), and PATO (phenotype and trait ontology), among others. These candidate ontology terms are combined into candidate EQ statements, which are probabilistically evaluated with respect to a natural language parse of the phenotype description. Models and parameters in this method are trained using a dataset of plant phenotypes and curator-converted EQ statements from the Plant PhenomeNET project (Oellrich, Walls et al., 2015). Preliminary results comparing predicted and curated EQ statements are presented. Potential use across datasets to enable automated phenolog discovery are discussed.

}, keywords = {ontologies, phenologs, phenotypes, text mining}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_58.pdf }, author = {Ian Braun and Carolyn Lawrence-Dill} } @conference {ICBO_2018_59, title = {ICBO_2018_59: Coordinated Evolution of Ontologies of Informed Consent}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

Our project brings together a number of OBO Foundry ontologies related to the representation of informed consent, and expands and enriches them, so that they may provide a representation of informed consent across the informed consent (IC) life cycle. The IC lifecycle involves not only documentation of the consent when originally obtained, but actions that require clear communication of permissions from the initial acquisition of data and specimens through handoffs to, for example, secondary researchers, allowing them access to data or biospecimens referenced in the terms of the original consent. This poster details the progress we have made in representing the domain of consent, as well as the future applications that such work can make possible.

}, keywords = {informed consent, informed consent life cycle, ontology collaboration, reference ontology}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_59.pdf }, author = {J. Neil Otte and Cooper Stansbury and Jonathan Vajda and Frank Manion and Elizabeth Umberfield and Yongqun He and Marcelline Harris and Jihad Obeid and Mathias Brochhausen and William Duncan and Cui Tao} } @conference {ICBO_2018_6, title = {ICBO_2018_6: PHO: The Pharmacognosy Ontology}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {The discipline of pharmacognosy was named and defined in the early 19th century and consists primarily in the study of materia medica, or drugs. Its name, a derivation of the Greek pharmakon (medicine/drug) and ginosko (to know through experience) embraces a broad disciplinary range; current practice involves the investigation of natural products, the material produced by or derived from living organisms. It is a meta-discipline located at the frontiers of numerous sciences not limited to biology, chemistry, physics, and pharmacy. Pharmacognosy not only benefits from the technical and conceptual advances across these disciplines; it endows them with new study subjects and furnishes them with new tools and approaches. However, pharmacognosy has yet to articulate the diversity of its practices and procedures in a systematic, well-defined and logical manner, in suach a way as to participate in the lingua franca that ontologies can provide. Through the creation of a Pharmacognosy Ontology, we hope to contribute to this goal and consolidate the existing bridges between pharmacognosy and the many disciplines it is interacting with and thus contribute to a more profound understanding of the natural world.}, keywords = {meta-discipline ontology, natural product, pharmacognosy}, url = {http://icbo2018.cgrb.oregonstate.edu/}, author = {Jonathan Bisson and James Graham and Guido Pauli} } @conference {ICBO_2018_60, title = {ICBO_2018_60: Enhancing Semantic Analysis of Pathology Reports}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

Pathology reports play an essential role in cancer treatment and research. They contain vital findings about a patient{\textquoteright}s cancer, such as cell histology and molecular markers, that are used to diagnose the type of cancer, determine treatment options, and enhance our understanding of the nature of the disease. In this poster, we present our efforts to better search for meaningful data in pathology reports by enriching our search methods with semantic information.

}, keywords = {named entity recognition, natural language processing, Ontology, pathology report}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_60.pdf }, author = {William Duncan and Philip Whalen and Aditya Muralidharan and Jonathan Kiddy} } @conference {ICBO_2018_61, title = {ICBO_2018_61: Using the Oral Health and Disease Ontology to Study Dental Outcomes in National Dental PBRN Practices}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

The use of electronic dental records (EDR) has grown rapidly over the past decade, but the development of methods to use EDR data for research and quality improvement is still in its infancy. In this poster, we present our work in which use the Oral Health and Disease Ontology to integrate EDR data from 99 National Dental PBRN practices in order to study the longevity of posterior composite restorations and the rate of tooth loss following root canal treatments.

}, keywords = {dental procedure, dental research, Ontology, posterior composite restoration, root canal treatment}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_61.pdf }, author = {William Duncan and Thankam Thyvalikakath and Zasim Siddiqui and Michelle LaPradd and Chen Wen and Jim Zheng and Anna Roberts and Daniel Hood and Titus Schleyer and Aparna Manimangalam and Donald Rindal and Mark Jurkovich and Tracy Shea and David Bogacz and Terrence Yu and Jeffry Fellows and Valerie Gordan and Gregg Gilbert} } @conference {ICBO_2018_62, title = {ICBO_2018_62: Reasoning over anatomical homology in the Phenoscape KB}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

The Phenoscape project (www.phenoscape.org) has semantically annotated the features of species from the comparative literature, enabling links between candidate genes and novel species phenotypes for which they might be responsible. To enable discovery of homologous phenotypes and associated genes, we incorporated machine-reasoning with knowledge about homology into the Phenoscape Knowledgebase (KB). We show that with homology reasoning enabled, the results of database queries can be expanded to incorporate shared evolutionary history. We discuss the challenges in developing a logical model of homology assertions and implications for database queries, as well as theoretical entailment and practical performance tradeoffs between alternative models.

}, keywords = {anatomy ontology, evolution, homology, phenotypes, reasoning}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_62.pdf }, author = {Paula Mabee and James Balhoff and Wasila Dahdul and Hilmar Lapp and Christopher Mungall and Todd Vision} } @conference {ICBO_2018_63, title = {ICBO_2018_63: GO-MAP Implements CAFA Tools: Improved Automated Gene Function Annotation for Plants}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {Maize is both a crop species and a model for genetics and genomics research. As such, maize GO annotations produced by the community data projects Gramene and Phytozome are widely used to derive hypotheses for both crop improvement and basic science. Our maize-GAMER project assessed existing maize GO annotations and to implement and test the performance of some of the most commonly used GO prediction tools (i.e., Reciprocal Best Hits and domain presence) alongside three of the top performing tools submitted for evaluation in the CAFA1 (Critical Assessment of protein Function Annotation) competition. All datasets were compared based on F-score using an independent gold-standard dataset (2002 GO annotations for 1,619 genes) provided by MaizeGDB. In addition to producing and comparing these individual GO annotation sets, we also combined the datasets we generated to produce a maize-GAMER aggregate annotation set. Compared to Gramene and Phytozome, the maize-GAMER aggregate set annotates more genes in the maize genome and assigns more GO terms per gene. In addition, the maize-GAMER dataset{\textquoteright}s functional assignments are comparable to Gramene and Phytozome overall (based on F-score). These findings have been published, and the maize-GAMER GO annotations are available via CyVerse and MaizeGDB. Here we review the methods and describe GO-MAP, the pipeline used to generate these datasets. GO-MAP has been containerized to facilitate gene function annotation for other plant proteomes and will be released via CyVerse in the very near future.}, keywords = {assessment, CAFA, function, gene ontology}, url = {http://icbo2018.cgrb.oregonstate.edu/}, author = {Kokulapalan Wimalanathan and Carson Andorf and Iddo Friedberg and Carolyn Lawrence-Dill} } @conference {ICBO_2018_64, title = {ICBO_2018_64: Development and implementation of the Sickle Cell Disease Ontology}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {Sickle Cell Disease Ontology (SCDO), is a standardized and human and machine-readable resource that represents terminology about Sickle Cell Disease (SCD), for use by researchers, patients and clinicians. This is a collaborative effort to unambiguously describe all SCD concepts and unifying up-to-date knowledge in sickle cell disease.}, keywords = {Hemoglobinopathy, Ontology, Sickle Cell Disease, Translational research}, url = {http://icbo2018.cgrb.oregonstate.edu/}, author = {Gaston Mazandu and Sickle Cell Disease Ontology Working Group and Nicole Vasilevsky and Ambroise Wonkam and Nicola Mulder} } @conference {ICBO_2018_65, title = {ICBO_2018_65: An ontology-driven data capture and catalogue framework for the development of research and clinical databases in Sickle Cell Disease}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {We designed an ontology-based Research Electronic Data Capture (REDCap) database of integrated medical and environmental information for Sickle Cell Disease patients. This database integrates data elements in patient clinical records or case report forms (CRFs) across multiple sites and contributes to the unification and standardization of clinical data collection instruments for SCD patient and enhances clinical decision making process and patient care.}, keywords = {Ontology, REDCap, Sickle Cell Disease}, url = {http://icbo2018.cgrb.oregonstate.edu/}, author = {Khuthala Mnika and Sickle Cell Disease Ontology Working Group and Nicole Vasilevsky and Ambroise Wonkam and Nicola Mulder} } @conference {ICBO_2018_66, title = {ICBO_2018_66: Visualization of N-ary Relationships}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {Biologists are interested in conducting gene expression analysis to detect co-expression clusters that are regulated by the same set of genes. Due to the involvement of a high number of genes, it becomes difficult to visualize the gene networks to make meaningful insights. By utilizing N-ary data visualization technique, we find the cliques (a complete graph of N genes) among the gene sets and visualize them as a two-dimensional complex (Nodes, edges and polygonal faces) and devise an optimal layout. Consequently, the biologists can easily recognize the cliques in each cluster, the cardinality of the cliques, predominant interactions and the degree of heterogeneity of the data from the visualization.}, keywords = {cliques, data visualization, graph layout, N-ary relationship}, url = {http://icbo2018.cgrb.oregonstate.edu/}, author = {Botong Qu and Prashant Kumar and Eugene Zhang and Pankaj Jaiswal and Laurel Cooper and Justin Elser and Yue Zhang} } @conference {ICBO_2018_67, title = {ICBO_2018_67: Vocabularies, Ontologies, APIs, and Formats for Heterogeneous High Throughput Crop Phenotyping Data}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {The automation of sensors to measure crops is rapidly increasing in the size and complexity of the data that are available to scientists. The higher resolution, frequency, and diversity of information can enable new scientific discoveries and engineering approaches required to increase the efficiency and sustainability of our agricultural production systems. However, the size and complexity of these data makes it difficult to derive insights and actionable inference. These data often require contextual metadata including plant taxonomy, soil and weather, and agronomic and experimental conditions. While it is easy to agree on the principles of making data FAIR (findable, accessible, interoperable and reusable), it is a more substantial challenge to engineer such data in the absence of clear guidance. The landscape of standards, formats, vocabularies, and ontologies (hereafter, interfaces) that exist is difficult to navigate, and comprehensive specifications that cover the scope of crop phenotyping data are absent. Existing standards and conventions provide only a patchwork of coverage, making it difficult to standardize software and data interfaces. The TERRA Reference phenotyping platform (TERRA REF) is building a suite of open data and software to support advances in the use of crop sensing for breeding and precision agriculture. Although our data are large and diverse, we seek to make it FAIR, useful, and usable to the community of users who represent many science and engineering domains, including computer science, robotics, physics, and biology. This talk will describe our effort to identify, prioritize, and implement interfaces to these data, our efforts to build a community around shared data and software, and our focus on supporting existing software pipelines. It will conclude with a request for feedback on the role of ontologies can play in building a coherent interface to heterogeneous data.}, keywords = {APIs, Crop Plants, Environment, High Throughput Crop Phenotyping, High Throughput Phenotyping, Ontology, phenotype}, url = {http://icbo2018.cgrb.oregonstate.edu/}, author = {David LeBauer and Craig Willis} } @conference {ICBO_2018_68, title = {ICBO_2018_68: The Planteome Project- Reference Ontologies for Data Integration}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, 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.}, keywords = {anatomy, data annotation, development, Ontology, plants, traits}, url = {http://icbo2018.cgrb.oregonstate.edu/}, author = {Laurel Cooper and Pankaj Jaiswal} } @conference {ICBO_2018_69, title = {ICBO_2018_69: An (ontological) patient perspectiv}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {The Human Phenotype Ontology (HPO) has become the de facto standard representation of clinical {\textquotedblleft}deep phenotype{\textquotedblright} data for computational comparison of abnormalities and for use in genetic disease diagnostics. Using semantic similarity methods, the HPO is used to match non-exact sets of phenotypic features against known diseases, other patients, and model organisms. Algorithms based on HPO have been implemented into variant prioritization tools and are used by the 100,000 Genomes project, the NIH Undiagnosed Diseases Program/Network, and many other clinics, labs, tools, and databases. However, patient phenotypes can be laborious to capture adequately, and some phenotypes go unnoticed by the clinician (such as those only seen at home). Patients themselves are an eager and untapped source of information about symptoms and phenotypes, however, medical terminology is often perplexing to them, making it difficult to use resources like the HPO. Therefore, to support use of the HPO by patients directly, we have created a {\textquoteleft}layperson{\textquoteright} translation. Approximately 36\% of the HPO terms have at least one layperson synonym, 89\% of the diseases annotated to HPO have at least one HPO annotation with a layperson synonym, and 60\% of all disease annotations refer to HPO terms with lay translations. This coverage suggests that the layperson HPO would be useful in a diagnostic setting despite incomplete coverage. To evaluate the diagnostic utility of this lay translation, we created synthetic profiles ({\textquotedblleft}slim annotations{\textquotedblright}) for each annotated disease in the MONDO disease ontology and compared these slim annotations against the gold standard curated set. We also permuted these profiles by adding or removing annotations to determine how robust the lay annotation profiles might be in the face of missing or noisy data coming from patients. In order to evaluate the lay person profiles, we measured the semantic similarity between HPO gold standard annotations and the derived profiles (with and without noise added). 57\% of profiles scored 80\% similarity or higher, and 75\% of profiles scored 70\% similarity or higher. These results highlight the potential impact that the use of a patient-centered ontology view may have in clinical diagnostics for rare disease patients.}, keywords = {Medicine, Personalized medicine, phenotype, Translational science}, url = {http://icbo2018.cgrb.oregonstate.edu/}, author = {Melissa Haendel and Nicole Vasilevsky and Kayli Rageth and Sebastian Koehler and Peter Robinson and Julie McMurry and Kent Shefchek and Catherine Brownstein and Ingrid Holm and Chris Mungall} } @conference {ICBO_2018_7, title = {ICBO_2018_7: A Quality Assurance Methodology for ChEBI Ontology Focusing on Uncommonly Modeled Concepts}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

The Chemical Entities of Biological Interest (ChEBI) ontology is an important knowledge source of chemical entities in a biological context. ChEBI is large and complex, making it almost impossible to be error-free, given the scarce resources for quality assurance (QA). We present a methodology to locate concepts in ChEBI with a high probability of being erroneous. An Abstraction Network, which provides a compact summarization of an ontology, supports the methodology. By investigating a sample of ChEBI concepts, we show that uncommonly modeled concepts residing in small units of the Abstraction Network of ChEBI are statistically significantly more likely to have errors than other concepts. The finding may guide ChEBI ontology curators to focus their limited QA resources on such concepts to achieve a better QA yield. Furthermore, this study, combined with previous work, contributes to progress in showing that this methodology can be applied to a whole family of similar ontologies.

}, keywords = {ChEBI, chemical concept, chemical ontology, modeling error, quality assurance}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_7.pdf }, author = {Hao Liu and Ling Chen and Ling Zheng and Yehoshua Perl and James Geller} } @conference {ICBO_2018_70, title = {ICBO_2018_70: Improving Convergence Rates of Deep Learning for Very Small Image Training Sets}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {Typical visualization tasks in the domain of big image datasets include: image retrieval, clustering, and segmentation. Recently, there has been a tremendous progress in solving these tasks using deep convolutional neural networks (CNNs). CNNs typically require large training sets of manually annotated images for deep learning, which, however, is often impossible to provide in various applications, including image-based biological and medical research. This talk will address one way to address this critical issue {\textendash} a new CNN learning approach, based on second-order methods, aimed at improving: a) Convergence rates of existing gradient-based methods, and b) Robustness to the choice of learning hyper-parameters (e.g., learn- ing rate). Our approach simultaneously computes both gradients and second derivatives of the CNN{\textquoteright}s learning objective, and performs second-order back-propagation. In comparison with standard gradient-based deep learning, our evaluation demonstrates that we achieve faster convergences rates, and converge to better optima leading to better performance under a budgeted time for learning.}, keywords = {computer vision, deep learning, species classification}, url = {http://icbo2018.cgrb.oregonstate.edu/}, author = {Sinisa Todorovic} } @conference {ICBO_2018_71, title = {ICBO_2018_71: Comparative functional analysis in plants with Gramene}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {Gramene (http://www.gramene.org) is an integrated resource for comparative functional analysis in plants, and provides researchers with access to 53 genomes and pathways for 75 plant species. Gramene includes powerful phylogenetic approaches, such as protein-based gene trees with stable IDs and whole-genome DNA alignments, enabling comparison across plant species. Gramene also provides integrated search capabilities and interactive views to locate and visualize gene features, gene neighborhoods, phylogenetic trees, genetic variation, gene expression profiles, pathways, ontology associations, and curated and orthology-projected pathways. Gramene builds upon Ensembl and Reactome software, and is committed to open access and reproducible science based on FAIR principles. Gramene is supported by an NSF grant IOS-1127112, and from USDA-ARS (1907-21000-030-00D).}, keywords = {annotation, comparative analysis, functional genomics, ontology associations, pathways, plants}, url = {http://icbo2018.cgrb.oregonstate.edu/}, author = {Parul Gupta and Justin Preece and Pankaj Jaiswal and Marcela K. Tello-Ruiz and Sharon Wei and Sushma Naithani and Andrew Olson and Joshua Stein and Yinping Jiao and Bo Wang and Sunita Kumari and Young Koung Lee and Vivek Kumar} } @conference {ICBO_2018_72, title = {ICBO_2018_72: Ontology-based Comparative Transcriptomics: Novel Drought Stress-Induced Genes and Pathways in Rice}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {Rice is an important crop that feeds almost half the world population. As climate change models predict floods, drought and extreme temperatures in rice production areas, the need to better understand the genetic basis of adaptation and tolerance mechanisms to abiotic stresses is vital. To better understand tolerance mechanisms and responses under drought, we designed a time-series transcriptomic experiment with two different genotypes of Oryza sativa subspecies indica. These indica genotypes are grown in their center of diversity and are phenotyped as tolerant or susceptible to common abiotic stressors: submergence, saline, and/or drought. Using systems approach, our goal was to identify the stress tolerant candidate genes and genetic polymorphism to help accelerate the genetic gains in plant breeding efforts. We generated RNA-Seq transcriptome data for treated and untreated samples of the two indica genotypes, with three biological replicates, per time point in a drought-stress induced experiment. The sequence data generated was analyzed by calling polymorphisms, transcript isoforms, expression levels, assembling transcriptomes and identifying stress-induced pathways specific to each genetic background and tolerance level. The statistically significant results of these analyses were then annotated using various ontologies and by aligning against the quantitative trait loci and phenotypes annotated with trait ontology, SNP consequences annotated with sequence ontology, and gene ontologies, to identify function, process role and cellular localization of genes of interest. Collating these ontologies proved useful in identifying stress-induced genes overlapping the QTLs overlapping with drought phenotype and characterizing thousands of interesting genetic changes that may help us understand mechanism of drought response in rice.}, keywords = {Abiotic Stress, Bioinformatics, Biological Ontologies, Comparative Transcriptomics, Oryza sativa, Stress-Biology}, url = {http://icbo2018.cgrb.oregonstate.edu/}, author = {Noor Al-Bader and Pankaj Jaiswal} } @conference {ICBO_2018_73, title = {ICBO_2018_73: Taxa, metacoder, poppr and vcfR: Four packages for parsing, visualization, and manipulation of genetic, genomic and metagenomic data in R}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {Contemporary population genomic microbiome research are producing complex and large datasets that are difficult to manipulate and visualize. High throughput DNA sequencing projects typically result in files containing genetic variants in the Variant Call Format (VCF). These files are large and not strictly tabular, presenting an issue to investigators who wish to work with this data in the R environment. We created the package vcfR to facilitate exploration of VCF data in R. vcfR uses Rcpp to implement C++ functions, allowing R users to take advantage of the performance of compiled code without the user needing to know about the compiled code. This facilitates efficient use of VCF data in R. New users who are unfamiliar with VCF data can now explore the data to learn about their data. Quality control steps can be conducted. In addition, manipulations, such as subsetting samples or variants, can be performed. We provide conversion functions so analyses in the popular R genetics packages adegenet, poppr, ape and pegas. Analysis of population differentiation and copy number variation can be performed directly in vcfR. Our package vcfR facilitates efficient use, manipulation, and analysis of VCF data and integrates this data into the existing ecosystem of R genetic analysis and graphics packages. The taxa package provides a set of classes for the storage and manipulation of taxonomic data. Classes range from simple building blocks to project-level objects storing multiple user-defined datasets mapped to a taxonomy. It includes parsers that can read in taxonomic information in nearly any form. We have also developed the metacoder package for visualizing hierarchical data. Metacoder implements a novel visualization called heat trees that use the color and size of nodes and edges on a taxonomic tree to quantitatively depict up to 4 statistics. This allows for rapid exploration of data and information-dense, publication-quality graphics. This is an alternative to the stacked barcharts typically used in microbiome research. These complementary tools provide a new resource for analyzing hierarchical population genomic and microbiome data in R.}, keywords = {Bioinformatics, Metagenome, Microbiome, Population genetics, Population genomics, Taxonomy, Variant Call}, url = {http://icbo2018.cgrb.oregonstate.edu/}, author = {Niklaus Grunwald} } @conference {ICBO_2018_74, title = {ICBO_2018_74: The many faces of ontological data}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {To be added}, keywords = {Bioinformatics, data visualization, Ontology}, url = {http://icbo2018.cgrb.oregonstate.edu/}, author = {Melissa Haendel} } @conference {174, title = {ICBO_2018_75: ECOCORE: An ontology for core ecological concepts}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

The ontologies in the biological and biomedical domain represent entities from a broad spectrum of the life sciences such as molecules, diseases, phenotypes, and environments. However, until now, ontologies representing ecological concepts, such as trophic modes like autotrophy and insectivory, have been missing. In response to the needs of aggregators such as the Encyclopedia of Life and DataONE, we have developed an ontology of core ecological concepts, ECOCORE. The initial focus of development for ECOCORE is trophic dynamics. An example demonstrating this initial focus is the autotroph class, which is a subclass of organism. It is equivalent to organism and ({\textquoteleft}capable of{\textquoteright} some autotrophy). Autotrophy is a process. ECOCORE development calls on classes from many OBO ontologies, but involves specifically important collaborations with the Environment Ontology, the Behavior Ontology, and the Relations Ontology. ECOCORE development is open to community participation at the GitHub site https://github.com/EcologicalSemantics/ecocore. This presentation will describe ECOCORE and show some of its uses.

}, keywords = {biodiversity, ecology, evolutionary biology, Ontology, ontology development, trophic dynamics}, url = {http://icbo2018.cgrb.oregonstate.edu/}, author = {Anne Thessen and Pier Luigi Buttigieg and Ramona Walls and Jennifer Verdolin and Katja Schulz} } @conference {177, title = {ICBO_2018_76: Designing and Building the IC-FOODS Foundry: Community, Technology, and Standards for a Semantic Web of Food}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, year = {2008}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, address = {Corvallis, OR}, abstract = {

It is becoming increasingly clear that precise and sustainable cultivation methods informed by air, water, soil, plant, animal, and climate/weather sensors are capable of repairing landscapes, improving carbon sequestration, and reducing toxic runoff while also providing enough food to feed the planet. Simultaneously, compounding evidence demonstrates that appropriately guided food habits for individuals, informed by multi-omic interrogations of biomolecules together with lifestyle/activity data, hold potential for preventing disease and improving quality of life while also extending it. Food remains a key socio-cultural artifact representing status, religion, and clanship while also acting as a confluence for exchange of stories and sharing in delight. These stories and experiences are increasingly written, cataloged, annotated, and shared through modern social media channels. Increases in traditional and social media coverage about food has heightened consumer awareness while increasing consumer expectations for knowledge about how their food is grown, made, delivered and served. Food producers, processors, distributors and consumers all need computable languages underpinning data stores to make them findable, accessible, discoverable, and reusable (FAIR). IC-FOODS, the International Consortium for Food Ontology Operability Data and Semantics (IC-FOODS) was established with a primary mission: the design, assembly, and build of the Internet of Food (IoF). At the heart of the IoF is the Semantic Web of Food, whose language core is an emerging set of core ontologies that span the environment\<\>agriculture\<\>food processing\<\>food distribution\<\>diet\<\>food consumption/sensory experience\<\>health knowledge spectrum. Key to its mission is the establishment of working groups dedicated to aligning extant vocabularies with each other and with emerging scientific and gastronomic concepts. Sanding on the shoulders of the OBO (Open Biological Ontologies) Foundry, IC-FOODS is developing an integrated Foundry dedicated to ontologies related to Food and Food Systems. Whereas OBO is a natural home for biological ontologies about food--several ontologies related to food are only partially biological in their nature. These include ontologies of food processing and machinery, food industry, and economics/trade. This presentation outlines the strategies for implementing workgroups and technologies for building the IC-FOODS Foundry together with tightly coupled integration with the OBO Foundry.

}, keywords = {Farm to Fork, Food Ontology, semantic web}, author = {Matthew Lange} } @conference {181, title = {ICBO_2018_77: Big Data Visualization}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, year = {2008}, month = {08/06/2018}, publisher = {International Conference on Biomedical Ontology}, organization = {International Conference on Biomedical Ontology}, address = {Corvallis, OR}, abstract = {

Advanced computing and experimental technologies enable scientists to study complex phenomena at unprecedented precision, resulting in an explosive growth of data. The size of the collected information about the Internet and mobile device users is expected to be even greater, a daunting challenge we must address in order to make sense and maximize utilization of all the available information. Visualization transforms large quantities of, often multi-dimensional, data into graphical representations that exploit the high-bandwidth channel of the human visual system, leveraging the brain{\textquoteright}s remarkable ability to detect patterns and draw inferences. Visualization has thus become an indispensable tool in many areas of study involving large, complex data. In this talk, I will discuss designs and strategies for visualizing data generated by large-scale scientific simulations and network data derived from social media and cyber security applications.

}, keywords = {big data, data visulaization, Network Data, scientific discovery, Visual Analysis, Visualization}, author = {Kwan-Liu Ma} } @conference {ICBO_2018_8, title = {ICBO_2018_8: Using Equivalence Axioms from the Mammalian Phenotype Ontology to Facilitate Phenotype and Expression Comparisons}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

Comparisons of expression and phenotypes associated with a gene can enhance the understanding of gene function. These comparisons can be difficult to make due to differences in the ontologies used to annotate the data. Using equivalence axioms in the Mammalian Phenotype (MP) ontology and mappings between Uber-anatomy (UBERON) and EMAPA terms MGI has implemented gene expression + phenotype comparison matrices for genes in MGI. These matrices used the shared anatomical concepts between expression and phenotype ontologies to facilitate comparisons between annotations in these two domains.

}, keywords = {expression, mouse, phenotype}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_8.pdf }, author = {Susan Bello and Terry Hayamizu and Cynthia Smith and Martin Ringwald and The Mgi Software Group} } @conference {ICBO_2018_9, title = {ICBO_2018_9: A Prot{\'e}g{\'e} Plug-In for Test-Driven Ontology Development}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

Ontology development is a hard and often error-prone process, which requires ontology authors to correctly express their domain knowledge in a formal language. One way to ensure the quality of the resulting ontology is to use test cases, similarly to the best practices in software development. For ontology development, test cases can be specified as statements describing expected and/or unwanted logical consequences of an ontology. However, verifying the test cases and identifying the ontology parts that cause their violation is a complex task, which requires appropriate tool support. In this demo, we present OntoDebug {\textendash} a plug-in for the Prot{\'e}g{\'e} editor {\textendash} that supports test-driven ontology development. OntoDebug can automatically verify whether the ontology satisfies all defined test cases. If any test case is violated, the plug-in assists the user in debugging and repairing the ontology in an interactive way. The plug-in asks a series of questions about the ontology to pinpoint the faulty axioms. Once a fault is repaired, all answers that the author provided in the interactive debugging session may be converted into test cases, thus preserving the additional knowledge, which can be used in future testing of the ontology.

}, keywords = {Fault Detection in Ontologies, Fault Localization in Ontologies, Fault Repair in Ontologies, Ontology Debugging, Prot{\'e}g{\'e} Plug-In, Test-Driven Ontology Development, User Interaction}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_9.pdf }, author = {Konstantin Schekotihin and Patrick Rodler and Wolfgang Schmid and Matthew Horridge and Tania Tudorache} }