@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_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_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_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_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_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_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} }