@article {230, title = {Common Reference Ontologies for Plant Biology (cROP): A Platform for Integrative Plant Genomics}, year = {2014}, month = {Jan. 11-15, 2014}, address = {San Diego, CA}, abstract = {Around the world, a small number of plant species serve as the primary source of food for the human population, yet these crops are vulnerable to multiple stressors, such as diseases, nutrient deficiencies and unfavorable environmental conditions. Traditional breeding methods for plant improvement may be combined with next-generation methods such as automated scoring of traits and phenotypes to develop improved varieties. Linking these analyses to the growing corpus of genomics data generated by high-throughput sequencing, transcriptomics, proteomics, phenomics and genome annotation projects requires common, interoperable, reference vocabularies (ontologies) for the description of the data. The {\textquoteleft}Common Reference Ontologies for Plant Biology{\textquoteright} (cROP) initiative is building the needed suite of reference ontologies, together with enhanced data storage and visualization technologies. The cROP will assume the further development of the existing Plant Ontology (PO), Plant Trait Ontology (TO), and Plant Environment Ontology (EO) and will develop the Plant Stress Ontology (PSO) for abiotic and biotic stresses. It will also include relevant aspects of ontologies such as Gene Ontology (GO), Cell Type (CL), Chemical Entities of Biological Interest (ChEBI), Protein Ontology (PRO) and the Phenotypic Qualities Ontology (PATO). It will include a centralized platform where reference ontologies for plants will be used to access cutting-edge data resources for plant traits, phenotypes, diseases, genomes and semantically-queried gene expression and genetic diversity data across a wide range of plant species. cROP will unify and streamline a fragmented semantic framework and will support allele discovery, advance the understanding of crop evolution, and facilitate crop development.}, url = {https://pag.confex.com/pag/xxii/webprogram/Paper9799.html}, author = {Cooper, Laurel}, editor = {Justin L. Elser and Preece, Justin and Arnaud, Elizabeth and Sinisa Todorovic and Eugene Zhang and Christopher Mungall and Smith, Barry and Dennis Wm. Stevenson and Jaiswal, Pankaj} } @article {232, title = {Plant Environmental Condition Ontology (EO)}, year = {2014}, month = {Feb. 21-23, 2014}, publisher = {Phenotype Research Coordination Network}, address = {Biosphere2, Tucson, AZ}, author = {Jaiswal, Pankaj}, editor = {Cooper, Laurel and Laura Moore} } @article {233, title = {The Plant Ontology and the Trait Ontology: Resources for Plant Genomics}, year = {2014}, month = {Mar 31 - Apr 4}, address = {Montpellier, France}, author = {Cooper, Laurel} } @article {235, title = {Development of a Unified Phenotype Dataset for Plants}, year = {2013}, month = {Jan. 11-16, 2013}, type = {Poster presentationPoster presentation}, address = {San Diego, CA}, abstract = {Plant phenotype datasets can be found in a range of formats including free text and species-specific or knowledge domain-specific controlled vocabularies. While this enables some limited comparison of phenotype data across a single species or within a knowledge domain such as crop breeding, queries or analyses that span a broader set of species are not possible in the absence of a common vocabulary for describing phenotypes. To enable cross-species and cross-domain phenotype comparisons and analyses in plants, we have launched an effort to convert existing phenotype datasets for 8 plant species, encompassing both model species and crops, into a common format using taxonomically broad ontologies representing plant anatomical parts and developmental stages (Plant Ontology), biological processes (Gene Ontology), chemicals (ChEBI), and phenotypic qualities (PATO). Our effort focuses on mutant and overexpression phenotypes associated with genes of known sequence in Arabidopsis, tomato, potato, pepper, maize, rice, soybean and Medicago. Shared use of ontologies, annotation standards, formats and best practices across these eight plant species ensures that the resulting dataset will produce valid results for cross-species querying and semantic similarity analyses. Additionally, the dataset will enable us to explore the relationship between sequence similarity and phenotypic similarity across a range of plant species.}, url = {https://pag.confex.com/pag/xxi/webprogram/Paper5616.html}, author = {Huala, Eva}, editor = {Steven B. Cannon and Cooper, Laurel and George Gkoutos and Lisa C Harper and Jaiswal, Pankaj and Carolyn J. Lawrence and Johnny Lloyd and David Meinke and Menda, Naama and Laura Moore and Mueller, Lukas and Nelson, Rex T and Walls, Ramona L} } @article {238, title = {Development of the Reference Plant Trait Ontology: A Unified Resource for Plant Phenomics}, year = {2013}, month = {Jan. 11-16, 2013}, type = {PosterPoster}, address = {San Diego, CA}, abstract = {One of the central principles of biology is the concept that an organism{\textquoteright}s genotype interacts with the environment to produce the observable characteristics, or phenotype. Understanding this interaction is a core goal of modern biology, and enables development of organisms with commercially useful characteristics through modern breeding programs. A number of crop- or clade-specific plant trait ontologies have been developed to describe plant traits important for agriculture in order to address major scientific challenges such as food security. Traditionally, phenotype information has been captured in a free text manner, which cannot be easily indexed and presents an obstacle to data sharing. Recent advances in next generation sequencing and phenotyping technologies have allowed researchers to access a growing mountain of data, resulting in an emerging gap between the genomics information and the quantitative information describing phenotypes and traits. One approach to overcome this obstacle is through the annotation of data using a common controlled vocabulary or {\textquotedblleft}ontology". We present our vision of a species-neutral Reference Plant Trait Ontology (Ref-TO) which would be the basis for linking the disparate knowledge domains and that will support data integration and data mining across species. The Ref-TO is one of the modules for the Common Reference Ontology for Plant Science (cROP) which is being developed.}, url = {https://pag.confex.com/pag/xxi/webprogram/Paper7640.html}, author = {Cooper, Laurel}, editor = {Laura Moore and Arnaud, Elizabeth and Nelson, Rex T and Menda, Naama and Shrestha, Rosemary and Grant, David and L. Matteis and Mungall, Christopher J and Bastow, Ruth and McLaren, Graham and Jaiswal, Pankaj} } @article {1612, title = {An overview of the BioCreative 2012 Workshop Track III: interactive text mining task}, journal = {Database}, volume = {2013}, year = {2013}, month = {2013}, abstract = {In many databases, biocuration primarily involves literature curation, which usually involves retrieving relevant articles, extracting information that will translate into annotations and identifying new incoming literature. As the volume of biological literature increases, the use of text mining to assist in biocuration becomes increasingly relevant. A number of groups have developed tools for text mining from a computer science/linguistics perspective, and there are many initiatives to curate some aspect of biology from the literature. Some biocuration efforts already make use of a text mining tool, but there have not been many broad-based systematic efforts to study which aspects of a text mining tool contribute to its usefulness for a curation task. Here, we report on an effort to bring together text mining tool developers and database biocurators to test the utility and usability of tools. Six text mining systems presenting diverse biocuration tasks participated in a formal evaluation, and appropriate biocurators were recruited for testing. The performance results from this evaluation indicate that some of the systems were able to improve efficiency of curation by speeding up the curation task significantly (\~{}1.7- to 2.5-fold) over manual curation. In addition, some of the systems were able to improve annotation accuracy when compared with the performance on the manually curated set. In terms of inter-annotator agreement, the factors that contributed to significant differences for some of the systems included the expertise of the biocurator on the given curation task, the inherent difficulty of the curation and attention to annotation guidelines. After the task, annotators were asked to complete a survey to help identify strengths and weaknesses of the various systems. The analysis of this survey highlights how important task completion is to the biocurators{\textquoteright} overall experience of a system, regardless of the system{\textquoteright}s high score on design, learnability and usability. In addition, strategies to refine the annotation guidelines and systems documentation, to adapt the tools to the needs and query types the end user might have and to evaluate performance in terms of efficiency, user interface, result export and traditional evaluation metrics have been analyzed during this task. This analysis will help to plan for a more intense study in BioCreative IV.}, url = {http://database.oxfordjournals.org/content/2013/bas056.abstract}, author = {Arighi, Cecilia N. and Carterette, Ben and Cohen, K. Bretonnel and Krallinger, Martin and Wilbur, W. John and Fey, Petra and Dodson, Robert and Cooper, Laurel and Van Slyke, Ceri E. and Dahdul, Wasila and Mabee, Paula and Li, Donghui and Harris, Bethany and Gillespie, Marc and Jimenez, Silvia and Roberts, Phoebe and Matthews, Lisa and Becker, Kevin and Drabkin, Harold and Bello, Susan and Licata, Luana and Chatr-aryamontri, Andrew and Schaeffer, Mary L and Park, Julie and Haendel, Melissa and Van Auken, Kimberly and Li, Yuling and Chan, Juancarlos and Muller, Hans-Michael and Cui, Hong and Balhoff, James P. and Chi-Yang Wu, Johnny and Lu, Zhiyong and Wei, Chih-Hsuan and Tudor, Catalina O. and Raja, Kalpana and Subramani, Suresh and Natarajan, Jeyakumar and Cejuela, Juan Miguel and Dubey, Pratibha and Wu, Cathy} } @article {234, title = {Plant Ontology, a controlled and structured plant vocabulary for all botanical disciplines}, year = {2013}, month = {July 27-31, 2013}, type = {Poster presentationPoster presentation}, address = {New Orleans, LA}, abstract = {Recently, plant genome sequencing has expanded to different species of plants. This has dramatically expanded our knowledge of gene expression in plant structures and development, as well as plant evolution. However, due to the vast phylogenetic diversity within the plant kingdom some inconsistencies with terminology have occurred. These conflicting plant vocabularies challenge advancement in the plant sciences; therefore, it is important to have a consistent plant structure vocabulary that encompasses all green plants. The Plant Ontology (PO) has been constructed as a well-structured vocabulary whether the terms are anatomical or developmental. The PO also annotates gene expression data to a wide diversity of plant parts and stages of development, for example, terms can be linked with relevant genes that are expressed during the development of a certain structure. Terms are arranged in a hierarchical structure in which taxon-specific annotations occur; this provides the opportunity for users to compare gene expression in homologous structures across clades. This serves as a critical aid for plant scientists who incorporate large data sets to engage questions on genomics, development, and comparative genetics across different plant groups. The Plant Ontology also provides other resources for plant biologists to use such as the Annotation of Image Segments with Ontologies program (AISO), allowing users to annotate plant structures with relevant terminology and genes from images from digital photography or scanned copies. For example digital images of fossil flowers can be segmented and annotated with Plant Ontology terms, to create an image database where structures can be easily identified and compared with other structures from different specimens in longitudinal and cross sections. The goal of the Plant Ontology is to cultivate a consistent vocabulary for plant biologists across all disciplines of botany.}, url = {http://www.2013.botanyconference.org/engine/search/index.php?func=detail\&aid=1337}, author = {Brian Atkinson}, editor = {Cooper, Laurel and Laura Moore and Preece, Justin and Nikhil TV Lingutla and Sinisa Todorovic and Walls, Ramona L and Ruth Stockey and Gar Rothwell and Smith, Barry and Gandolfo, Maria A and Dennis Wm. Stevenson and Jaiswal, Pankaj} } @article {211, title = {The Plant Ontology as a Tool for Comparative Plant Anatomy and Genomic Analyses}, journal = {Plant \& Cell Physiology}, volume = {54}, year = {2013}, month = {2013 Feb}, pages = {1-23}, chapter = {1}, abstract = {The Plant Ontology (PO; http://www.plantontology.org/) is a publicly available, collaborative effort to develop and maintain a controlled, structured vocabulary ({\textquoteright}ontology{\textquoteright}) of terms to describe plant anatomy, morphology and the stages of plant development. The goals of the PO are to link (annotate) gene expression and phenotype data to plant structures and stages of plant development, using the data model adopted by the Gene Ontology. From its original design covering only rice, maize and Arabidopsis, the scope of the PO has been expanded to include all green plants. The PO was the first multispecies anatomy ontology developed for the annotation of genes and phenotypes. Also, to our knowledge, it was one of the first biological ontologies that provides translations (via synonyms) in non-English languages such as Japanese and Spanish. As of Release $\#$18 (July 2012), there are about 2.2 million annotations linking PO terms to >110,000 unique data objects representing genes or gene models, proteins, RNAs, germplasm and quantitative trait loci (QTLs) from 22 plant species. In this paper, we focus on the plant anatomical entity branch of the PO, describing the organizing principles, resources available to users and examples of how the PO is integrated into other plant genomics databases and web portals. We also provide two examples of comparative analyses, demonstrating how the ontology structure and PO-annotated data can be used to discover the patterns of expression of the LEAFY (LFY) and terpene synthase (TPS) gene homologs.}, keywords = {Alkyl and Aryl Transferases, bioinformatics, comparative genomics, genome annotation, Molecular Sequence Annotation, Multigene Family, ontology, Phenotype, plant anatomy, Plant Proteins, Software, terpene synthase}, issn = {1471-9053}, doi = {10.1093/pcp/pcs163}, url = {http://pcp.oxfordjournals.org/content/54/2/e1}, author = {Cooper, Laurel and Walls, Ramona L and Elser, Justin and Gandolfo, Maria A and Stevenson, Dennis W and Smith, Barry and Preece, Justin and Athreya, Balaji and Mungall, Christopher J and Rensing, Stefan and Hiss, Manuel and Lang, Daniel and Reski, Ralf and Berardini, Tanya Z and Li, Donghui and Huala, Eva and Schaeffer, Mary and Menda, Naama and Arnaud, Elizabeth and Shrestha, Rosemary and Yamazaki, Yukiko and Jaiswal, Pankaj} } @article {231, title = {A Resource for a Common Reference Ontology for Plants}, year = {2013}, month = {Jan. 11-16, 2013}, address = {San Diego, CA}, abstract = {In the new age of comparative plant biology, we are looking at datasets from numerous inter and intra-specific comparative analysis experiments on transcriptome, proteomics, phenomics and genome annotation projects. These experiments may describe, for example, a set of genes from one or more plant species that are differentially expressed in response to some type of treatment. These genes may have associations to phenotypes and molecular functions, in addition to various gene and protein features. For a researcher looking at this data, the value comes from the analysis of this data. Unfortunately, the data is present in many locations in online data repositories and is also annotated using different vocabularies and keywords that often do not match descriptions between different resources. The problem can be solved in two ways: (1) keep the data in different locations, but annotate it with common reference vocabularies that can be queried in real time using common query words and/or (2) keep the data in a centralized location, and resolve the conflicting descriptions by adopting a single standard. Considering the limited resources and enormous amount of data distributed at many sites, an integrated approach of adopting common annotation standards and a set of reference ontologies is desired. We will present a vision of an international resource for a Common Reference Ontology for Plants (cROP), in order to develop common standards for annotating plant gene function, expression and phenotypes, in addition to describing the anatomy and responses such as diseases, reported in various experiments and resources.}, url = {https://pag.confex.com/pag/xxi/webprogram/Paper5587.html}, author = {Jaiswal, Pankaj}, editor = {Smith, Barry and R. Bastow and Paul J. Kersey and Arnaud, Elizabeth and Cooper, Laurel and Christopher Rawlings} } @article {236, title = {The Species-Specific Crop Ontology (Generation Challenge Programme): Application and Integration into the Reference Plant Trait Ontology to Enable Data Mining on Phenotypes}, year = {2013}, month = {Jan. 11-16, 2013}, type = {Ontology Workshop TalkOntology Workshop Talk}, address = {San Diego, CA}, abstract = {The Crop Ontology (CO) of the Generation Challenge Program (GCP) (http://cropontology.org/) currently contains eleven crop-specific ontologies and has been developed for the Integrated Breeding Platform (IBP) (https://www.integratedbreeding.net/) by several CGIAR centers. The CO provides validated trait names used by crop communities of practice (CoP) for harmonizing the annotation of phenotypic and genotypic data and thus supporting data accessibility and discovery through web queries. The trait information is completed by the description of the measurement methods and scales and images. The trait dictionaries used to produce the Integrated Breeding (IB) fieldbooks are synchronized with the CO terms for automatic annotation of the phenotypic data measured in the field. The CO acts as a trait name server for various sites and databases: the Genotyping Data Management System (GDMS); the cassava database at Cornell University (http://cassavadb.org); Agtrials, the Global Repository for Evaluation Trials of Climate Change, Agriculture and Food Security (CCAFS), a CGIAR Research Program (http://agtrials.org ); and the EU-Sol BreedDB website (https://www.eu-sol.wur.nl/). The vision will be presented of a species-neutral and overarching Reference Plant Trait Ontology to support data annotation, integration and data mining across species, which has resulted from the successful collaboration between the CO project, the Plant Ontology (PO; http://www.plantontology.org/), the Trait Ontology (TO;http://www.gramene.org/plant_ontology/) the USDA-ARS SoyBase Database (http://www.soybase.org/), the Solanaceae Genomic Network (http://solgenomics.net/), and GarNet (http://www.garnetcommunity.org.uk/).}, url = {https://pag.confex.com/pag/xxi/webprogram/Paper5002.html}, author = {Arnaud, Elizabeth}, editor = {Shrestha, Rosemary and Kulakow, Peter and Bakare, Moshood and Antonio Lopez-Montes and Ofodile, Sam and T., Praveen Reddy and Prasad, Peteti and Shah, Trushar and Hash, Charles Thomas and Weltzien-Rattunde, Eva and Sissoko, Ibrahima and Guerrero, Alberto Fabio and Simon, Reinhard and Borja-Borja, Nikki Frances and Ramil, Mauleon and L. Matteis and Skofic, Milko and Hazekamp, Tom and McLaren, Graham and Cooper, Laurel and Jaiswal, Pankaj and Menda, Naama and Nelson, Rex and Grant, David and Bastow, Ruth and Rami, Jean-Francois} } @article {1605, title = {Annotating the Maize B73 Gene Expression Atlas in the Plant Ontology- A Tool for Plant Genomics.}, year = {2012}, month = {March 2012}, address = {Portland, OR}, abstract = {The Plant Ontology (www.plantontology.org) is a structured vocabulary and database resource for all plant scientists that links plant anatomy, morphology, and development to the rapidly expanding field of plant genomics. The primary purpose of the PO is to facilitate cross-database querying and to foster consistent use of vocabularies in annotation. An essential feature of the PO is the set of freely accessible web links from terms to associated annotations, which are structure- or development-specific genes, proteins, and phenotypes sourced from numerous plant genomics datasets. In collaboration with MaizeGDB (www.maizegdb.org), we have recently added approximately 1.5 million new associations between maize (Zea mays) gene models and Plant Ontology terms. These associations are based on a large NimbleGen microarray data set profiling genome-wide transcription patterns in 60 tissues, representing 11 distinct organs over the life cycle of a maize plant of the inbred line B73 (Sekhon, et al, Plant Journal, 2011). The microarray data was associated with ~35,000 maize gene models developed from the recent sequencing of its genome and updated to the current assembly, B73 RefGen_v2, as a collaboration between MaizeGDB and PLEXdb (www.plexdb.org). PO association files in gaf 2.0 format (www.geneontology.org) were further enhanced by the inclusion of classical gene names, mapped by CoGe (www.genomevolution.org/CoGe/). The maize gene atlas associations were made public in the Plant Ontology Release $\#$16 in October 2011. They are available for download, and can be viewed in various browser modes, both at the PO and at MaizeGDB. The addition of the maize gene atlas annotations to the PO represents an example of how ontologies provide access to large genomics data sets. Currently, the PO includes over 2 million such annotations from 17 species associated with over 1,300 terms. Other recent additions include annotations to cotton (Gossypium) and the moss Physcomitrella patens, with plans for the future inclusion of grape (Vitis) and potato (Solanum). The PO is a valuable resource for both research and teaching that can be used as a guide to plant structures and growth and developmental landmarks in life cycles of plants across many taxa.}, url = {http://maizemeeting.maizegdb.org/mm2012/see_abstract.php?id=302}, author = {Jaiswal, Pankaj}, editor = {Cooper, Laurel and Schaeffer, Mary and Walls, Ramona L and Justin L. Elser and Preece, Justin and Smith, Barry and Mungall, Christopher J and Gandolfo, Maria A and Dennis Wm. Stevenson} } @article {219, title = {An extension of the Plant Ontology project supporting wood anatomy and development research}, journal = {IAWA Journal}, volume = {33}, year = {2012}, pages = {113-117}, chapter = {113}, abstract = {A wealth of information on plant anatomy and morphology is available in the current and historical literature, and molecular biologists are producing massive amounts of transcriptome and genome data that can be used to gain better insights into the development, evolution, ecology, and physiological function of plant anatomical attributes. Integrating anatomical and molecular data sets is of major importance to the field of wood science, but this is often hampered by the lack of a standardized, controlled vocabulary that allows for cross-referencing among disparate data types. One approach to overcome this obstacle is through the annotation of data using a common controlled vocabulary or "ontology" (Ashburner et al. 2000; Smith et al. 2007). An ontology is a way of representing knowledge in a given domain that includes a set of terms to describe the classes in that domain, as well as the relationships among terms. Each term can be associated with an array of data such as names, definitions, identification numbers, and genes involved. Ontologies are fundamental for unifying diverse terminologies and are increasingly used by scientists, philosophers, the military and online web search engines. In an ontology, terms are carefully defined, allowing a wide array of researchers to (1) use terms consistently in scientific publications or standardized handbooks on quality/trait evaluations, and (2) search for and integrate data linked to these terms in anatomical, genetic, genomic, and other types of biological databases. The Plant Ontology (PO, www.plantontology.org) is a structured vocabulary and database resource that links plant anatomy and development to gene expression and phenotypic datasets from all areas of plant biology.}, url = {http://www.researchgate.net/publication/232271560_An_extension_of_the_Plant_Ontology_project_supporting_wood_anatomy_and_development_research}, author = {Lens, F and Cooper, Laurel and Gandolfo, Maria A and Groover, P and Jaiswal, Pankaj and Lachenbruch, R and Spicer, R and Staton, D and Dennis Wm. Stevenson and Walls, Ramona L and Wegrzyn, J} } @article {212, title = {Ontologies as Integrative Tools for Plant Science}, journal = {American Journal of Botany}, volume = {99}, year = {2012}, month = {2012 Aug}, pages = {1263-75}, chapter = {1263}, abstract = {PREMISE OF THE STUDY: Bio-ontologies are essential tools for accessing and analyzing the rapidly growing pool of plant genomic and phenomic data. Ontologies provide structured vocabularies to support consistent aggregation of data and a semantic framework for automated analyses and reasoning. They are a key component of the semantic web. METHODS: This paper provides background on what bio-ontologies are, why they are relevant to botany, and the principles of ontology development. It includes an overview of ontologies and related resources that are relevant to plant science, with a detailed description of the Plant Ontology (PO). We discuss the challenges of building an ontology that covers all green plants (Viridiplantae). KEY RESULTS: Ontologies can advance plant science in four keys areas: (1) comparative genetics, genomics, phenomics, and development; (2) taxonomy and systematics; (3) semantic applications; and (4) education. CONCLUSIONS: Bio-ontologies offer a flexible framework for comparative plant biology, based on common botanical understanding. As genomic and phenomic data become available for more species, we anticipate that the annotation of data with ontology terms will become less centralized, while at the same time, the need for cross-species queries will become more common, causing more researchers in plant science to turn to ontologies.}, keywords = {Botany, Computational Biology, Data Interpretation, Statistical, Database Management Systems, Databases, Factual, Genome, Plant, Genomics, Molecular Sequence Annotation, Phenotype, Plants, Semantics, Terminology as Topic, Vocabulary, Controlled}, issn = {1537-2197}, doi = {10.3732/ajb.1200222}, author = {Walls, Ramona L and Athreya, Balaji and Cooper, Laurel and Elser, Justin and Gandolfo, Maria A and Jaiswal, Pankaj and Mungall, Christopher J and Preece, Justin and Rensing, Stefan and Smith, Barry and Stevenson, Dennis W} } @article {240, title = {The Plant Ontology: A Tool for Linking Plant Anatomy and Development to Genomics Across Plant Taxa}, year = {2012}, month = {Sept. 6-9, 2012}, type = {posterposter}, address = {Robinson College, Cambridge, UK}, abstract = {The Plant Ontology (PO: http://www.plantontology.org) is a structured vocabulary and database resource for all plant scientists that links plant anatomy, morphology and development to the rapidly expanding field of plant genomics. The primary purpose of the PO is to facilitate cross-database querying and to foster the consistent use of vocabularies in annotation of genomics data. The PO encompasses all plant species, ranging from angiosperms to gymnosperms, pteridophytes (ferns), lycophytes (lycopods) and bryophytes (liverworts, mosses and hornworts). Recent changes in the PO include the addition of new ontology terms and annotations to describe non-seed plants, such as Physcomitrella and woody plant species. An essential feature of the PO is the set of freely accessible web links from terms to associated annotations, which are structure- or development-specific genes, proteins and phenotypes sourced from numerous plant genomics datasets. Currently, the PO includes over 2 million such annotations associated with over 1,300 terms. Outreach activities include workshops, conference presentations and outreach booths. The combination of ontology terms and the annotation of diverse gene expression and phenotype data sets facilitates diverse analyses, including assessing the similarity between genes of inter- or intra-specific origin and the exploration of structural homologies among organs, tissues and cell types. The PO is a valuable resource for both research and teaching that can be used as a guide to plant structures and growth and developmental landmarks in life cycles of plants across many taxa.}, author = {Preece, Justin}, editor = {Cooper, Laurel and Walls, Ramona L and Justin L. Elser and Smith, Barry and Mungall, Christopher J and Rensing, Stefan and Gandolfo, Maria A and Dennis Wm. Stevenson and Jaiswal, Pankaj} } @article {241, title = {The Plant Ontology: A Tool for Linking Plant Anatomy and Development to Genomics Across Plant Taxa}, year = {2012}, month = {July 20-24, 2012}, type = {poster}, address = {Austin, Tx}, abstract = {The Plant Ontology (PO: http://www.plantontology.org) is a structured vocabulary and database resource for all plant scientists that links plant anatomy, morphology and development to the rapidly expanding field of plant genomics. The primary purpose of the PO is to facilitate cross-database querying and to foster the consistent use of vocabularies in annotation of genomics data. The PO encompasses all plant species, ranging from angiosperms to gymnosperms, pteridophytes (ferns), lycophytes (lycopods) and bryophytes (liverworts, mosses and hornworts). Recent changes in the PO include the addition of new ontology terms and annotations to describe non-seed plants, such as Physcomitrella and woody plant species. An essential feature of the PO is the set of freely accessible web links from terms to associated annotations, which are structure- or development-specific genes, proteins and phenotypes sourced from numerous plant genomics datasets. Currently, the PO includes over 2 million such annotations associated with over 1,300 terms. Outreach activities include workshops, conference presentations and outreach booths. The combination of ontology terms and the annotation of diverse gene expression and phenotype data sets facilitates diverse analyses, including assessing the similarity between genes of inter- or intra-specific origin and the exploration of structural homologies among organs, tissues and cell types. The PO is a valuable resource for both research and teaching that can be used as a guide to plant structures and growth and developmental landmarks in life cycles of plants across many taxa.}, author = {Cooper, Laurel}, editor = {Walls, Ramona L and Justin L. Elser and Preece, Justin and Smith, Barry and Mungall, Christopher J and Rensing, Stefan and Gandolfo, Maria A and Dennis Wm. Stevenson and Jaiswal, Pankaj} } @article {1613, title = {Text mining in the biocuration workflow: applications for literature curation at WormBase, dictyBase and TAIR}, journal = {Database}, volume = {2012}, year = {2012}, month = {2012}, abstract = {WormBase, dictyBase and The Arabidopsis Information Resource (TAIR) are model organism databases containing information about Caenorhabditis elegans and other nematodes, the social amoeba Dictyostelium discoideum and related Dictyostelids and the flowering plant Arabidopsis thaliana, respectively. Each database curates multiple data types from the primary research literature. In this article, we describe the curation workflow at WormBase, with particular emphasis on our use of text-mining tools (BioCreative 2012, Workshop Track II). We then describe the application of a specific component of that workflow, Textpresso for Cellular Component Curation (CCC), to Gene Ontology (GO) curation at dictyBase and TAIR (BioCreative 2012, Workshop Track III). We find that, with organism-specific modifications, Textpresso can be used by dictyBase and TAIR to annotate gene productions to GO{\textquoteright}s Cellular Component (CC) ontology.}, url = {http://database.oxfordjournals.org/content/2012/bas040.abstract}, author = {Van Auken, Kimberly and Fey, Petra and Berardini, Tanya Z and Dodson, Robert and Cooper, Laurel and Li, Donghui and Chan, Juancarlos and Li, Yuling and Basu, Siddhartha and Muller, Hans-Michael and Chisholm, Rex and Huala, Eva and Sternberg, Paul W.} } @conference {223, title = {Towards a Reference Plant Trait Ontology for Modeling Knowledge of Plant Traits and Phenotype}, booktitle = {International Conference on Knowledge Discovery and Information Retrieval (IC3K2012)}, year = {2012}, month = {10/2012}, address = {Barcelona, Spain}, author = {Arnaud, Elizabeth and Cooper, Laurel and Shrestha, Rosemary and Menda, Naama and Nelson, Rex T and L. Matteis and M. Skofic and R. Bastow and Jaiswal, Pankaj and Mueller, Lukas and McLaren, Graham} } @article {1601, title = {Using the Plant Ontology to improve the interoperability of genomic and phenomic data sets}, year = {2011}, month = {Nov. 30 - Dec 3}, address = {Cold Spring Harbor Laboratory, New York}, abstract = {The Plant Ontology (PO: http://plantontology.org) is a structured vocabulary (ontology) consisting of terms, attributes, and relations that describe anatomy, morphology, and development stages of green plants. In addition, the PO provides access to genes and phenotypes that have been associated with ontology terms via the annotation of samples from specific tissues and developmental stages. The PO is an essential, powerful tool for the annotation of diverse gene-expression and phenotype data sets that can be used to assess the similarity between genes of inter- or intra-specific origin and to explore structural homologies among organs, tissues and cell types. The PO facilitates computational reasoning, based on ontological relationships and biological context, allowing researchers to probe the complex relationships among data sets for gene expression, phenotypes, gene-gene interactions, and molecular functions (via the Gene Ontology). For example, the logical definitions and relationships in the PO can be used to deduce that {\textquoteleft}petal{\textquoteright} in dicots and {\textquoteleft}lemma{\textquoteright} in monocot grasses are both subtypes of {\textquoteleft}phyllome{\textquoteright} (leaf-like structures) and that both are associated with {\textquoteleft}flower{\textquoteright} ({\textquoteleft}petal{\textquoteright} is part_of {\textquoteleft}flower{\textquoteright} and {\textquoteleft}lemma{\textquoteright} is part_of {\textquoteleft}inflorescence{\textquoteright} which has_part {\textquoteleft}flower{\textquoteright}). Researchers can use the association data in the PO to compare the expression patterns of orthologous genes in these structures in maize and Arabidopsis, or to determine if similar phenotypes in the two structures are linked to orthologous genes. Currently, the PO includes over 2 million annotations from maize, Arabidopsis,strawberry, rice, solanaceous crops (such as tomato), and the moss Physcomitrella patens. These annotations are associated with over 1,400 ontology terms. Almost 400 new anatomical terms have been added to the PO recently, to enhance the framework for cross-species comparisons and accommodate work in future agricultural models such as Musa and Eucalyptus. Approximately 80 new terms were added specifically for non-vascular plants, with an emphasis on those needed to describe gene expression in P. patens. In this presentation, we will provide an overview of the Plant Ontology and its resources and present a pilot study comparing inter-specific gene expression profiles, based on the orthology of genes and ontological relations among plant structures.}, author = {Walls, Ramona L}, editor = {Cooper, Laurel and Gandolfo, Maria A and Dennis Wm. Stevenson and Smith, Barry and Justin L. Elser and Preece, Justin and Mungall, Christopher J and Jaiswal, Pankaj} } @article {1600, title = {Using the Plant Ontology to Link Anatomical Structures to Gene Annotations in Physcomitrella patens}, year = {2011}, month = {Sept 12, 2011}, address = {Black Forest, Germany}, abstract = {To fully explore the research possibilities created by the recent sequencing of the Physcomitrella patens genome, biological information must be linked to the genome sequence through the process of annotation. The use of ontologies ensures consistent annotations within and across species, enabling both gene prediction and cross-species comparisons of gene expression. While the Gene Ontology (GO) is an excellent tool for describing gene function and localization at the subcellular level, comprehensive annotation also requires ontology terms to describe plant anatomy and morphology, as well as growth and development stages. The Plant Ontology (PO) provides these terms through its two branches: the Plant Anatomy Ontology and the Plant Growth and Development Stage Ontology. The PO allows for uniform descriptions of the phenotypes and tissues used in gene expression studies. With the addition of over 80 new terms to describe bryophytes, the PO is well suited for the description of Physcomitrella anatomy and morphology. In this presentation, we will provide an overview of the Plant Ontology and its principles and review the new terms and changes that have been made to accommodate mosses. We will give a brief tutorial on how to access the PO and associated data, and conclude by showing examples of association files that other groups have contributed, in order to illustrate the utility of linking Physcomitrella genome data to PO terms.}, url = {http://plantco.de/MOSS2011/index.html}, author = {Walls, Ramona L}, editor = {Cooper, Laurel and Gandolfo, Maria A and Dennis Wm. Stevenson and Smith, Barry and Justin L. Elser and Preece, Justin and Mungall, Christopher J and Jaiswal, Pankaj} } @article {1597, title = {The Plant Ontology: A Database for Plant Genomics}, year = {2010}, month = {2010}, address = {Quebec, Montreal, Canada}, abstract = {As data is generated from the various plant genome and comparative genomics projects, the working vocabulary from group to group and species to species can be disparate. To enable researchers across species to draw conclusions from known or predicted experiments, we are developing controlled vocabularies (ontologies) to describe plant morphologies, anatomical structures, and growth and developmental stages. Since the inception of the Plant Ontology (PO) database in 2003, plant biologists have been able to annotate and describe tissue and/or growth stage specific expression of proteins, genes, and phenotypes that were observed in experiments by utilizing PO terms in the database. There are currently over 1,100 terms documented in the PO, with over 500,000 associations, of which over 85\% have been added within the last year. Currently, we are in the process of expanding the coverage of PO to non-angiosperm plants to include mosses (Physcomitrella), Lycopods (Selaginella), pteridophytes (ferns) and gymnosperms (conifers and cycads). We are also adding additional species-specific terms to accommodate annotations from Vitaceae (grape), Rosaceae (apple, cherry), Fabaceae (Medicago and soybean), Compositeae (sunflower), Solanaceae (potato, tomato), Poaceae (wheat, barley, oat, Sorghum and Brachypodium), Salicaceae (poplar) and Malvaceae (cotton). The development of the PO is coordinated with the development of the Gene Ontology (GO), and together these resources can be used to provide a comprehensive picture of the function, location and phenotypic effects of genes and gene products. The Plant Ontology project is funded by the National Science Foundation, USA and includes collaborations with groups from around the world.}, url = {http://abstracts.aspb.org/pb2010/public/P14/P14010.html}, author = {Cooper, Laurel} } @article {1552, title = {Plant Ontology: Databases And Applications}, year = {2010}, month = {2010}, address = {San Diego, CA}, abstract = {As data is generated from multiple plant genome projects and comparative genomics approaches, the vocabulary from group to group and species to species can be disparate. To enable researchers across species to draw conclusions from known or predicted experiments, we are developing controlled vocabularies (ontologies) to describe plant morphological, anatomical, and growth and developmental stages. Since the inception of the Plant Ontology (PO) database in 2003, plant biologists have been able to consistently use the PO terms in the database for annotation of tissue and/or growth stage specific expression of proteins, genes, and phenotypes that were observed in experiments. The PO terms documented number over 1,100, and there are over 500,000 associations, of which over 85\% have been added within the last year. The terms and associations can be used in tandem with information (such as their biochemical charcterization from their source database) to predict plant phenotypes, determine function of gene products, and possibly initiate new gene discovery with comparative genomics analysis. Future development by the Plant Ontology Consortium will be centered on adding additional species-specific terms to accommodate annotations from Rutaceae (citrus), Fabaceae (Medicago and soybean), Solanaceae (tomato), Triticeae (wheat, oat, and barley), and Populus (poplar).}, url = {http://www.intl-pag.org/18/abstracts/C01_PAGXVIII_924.html}, author = {Justin L. Elser}, editor = {Cooper, Laurel and Jaiswal, Pankaj} } @article {1596, title = {Plant Ontology: Databases And Applications}, year = {2010}, month = {Jan 9-13, 2010}, address = {San Diego, CA}, abstract = {As data is generated from multiple plant genome projects and comparative genomics approaches, the vocabulary from group to group and species to species can be disparate. To enable researchers across species to draw conclusions from known or predicted experiments, we are developing controlled vocabularies (ontologies) to describe plant morphological, anatomical, and growth and developmental stages. Since the inception of the Plant Ontology (PO) database in 2003, plant biologists have been able to consistently use the PO terms in the database for annotation of tissue and/or growth stage specific expression of proteins, genes, and phenotypes that were observed in experiments. The PO terms documented number over 1,100, and there are over 500,000 associations, of which over 85\% have been added within the last year. The terms and associations can be used in tandem with information (such as their biochemical characterization from their source database) to predict plant phenotypes, determine function of gene products, and possibly initiate new gene discovery with comparative genomics analysis. Future development by the Plant Ontology Consortium will be centered on adding additional species-specific terms to accommodate annotations from Rutaceae (citrus), Fabaceae (Medicago and soybean), Solanaceae (tomato), Triticeae (wheat, oat, and barley), and Populus (poplar).}, author = {Justin L. Elser}, editor = {Cooper, Laurel and Jaiswal, Pankaj} }