Imagine if we could compute across phenotype data as easily as genomic data; this article calls for efforts to realize this vision and discusses the potential benefits.
},
doi = {10.1371/journal.pbio.1002033},
url = {http://dx.doi.org/10.1371\%2Fjournal.pbio.1002033},
author = {Deans, Andrew R. and Lewis, Suzanna E. and Huala, Eva and Anzaldo, Salvatore S. and Ashburner, Michael and Balhoff, James P. and Blackburn, David C. and Blake, Judith A. and Burleigh, J. Gordon and Chanet, Bruno and Cooper, Laurel D. and Courtot, M{\'e}lanie and Cs{\"o}sz, S{\'a}ndor and Cui, Hong and Dahdul, Wasila and Das, Sandip and Dececchi, T. Alexander and Dettai, Agnes and Diogo, Rui and Druzinsky, Robert E. and Dumontier, Michel and Franz, Nico M. and Friedrich, Frank and Gkoutos, George V. and Haendel, Melissa and Harmon, Luke J. and Hayamizu, Terry F. and He, Yongqun and Hines, Heather M. and Ibrahim, Nizar and Jackson, Laura M. and Jaiswal, Pankaj and James-Zorn, Christina and K{\"o}hler, Sebastian and Lecointre, Guillaume and Lapp, Hilmar and Carolyn J. Lawrence and Le Nov{\`e}re, Nicolas and Lundberg, John G. and Macklin, James and Mast, Austin R. and Midford, Peter E. and Mik{\'o}, Istv{\'a}n and Mungall, Christopher J and Oellrich, Anika and Osumi-Sutherland, David and Parkinson, Helen and Ram{\'\i}rez, Mart{\'\i}n J. and Richter, Stefan and Robinson, Peter N. and Ruttenberg, Alan and Schulz, Katja S. and Segerdell, Erik and Seltmann, Katja C. and Sharkey, Michael J. and Smith, Aaron D. and Smith, Barry and Specht, Chelsea D. and Squires, R. Burke and Thacker, Robert W. and Thessen, Anne and Fernandez-Triana, Jose and Vihinen, Mauno and Vize, Peter D. and Vogt, Lars and Wall, Christine E. and Walls, Ramona L and Westerfeld, Monte and Wharton, Robert A. and Wirkner, Christian S. and Woolley, James B. and Yoder, Matthew J. and Zorn, Aaron M. and Mabee, Paula}
}
@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 {237,
title = {AISO: Annotation of Image Segments using Ontologies},
year = {2013},
month = {Jan. 11-16, 2013},
type = {PosterPoster},
address = {San Diego, CA},
abstract = {We present AISO, an interactive image segmentation and ontology annotation tool. AISO is designed to give curators of biological specimens the ability to segment an image, such as those produced with digital photography or scanned from printed material, and annotate those segments with ontology terms. We developed this application in response to a need within the plant science community for a streamlined tool that enables the consistent and structured labeling of biological images. To this end, AISO brings together disparate image segmentation, semantic labeling, and data export features found in existing technologies and merges them into a user-friendly, science-focused software package. Given these capabilities, researchers within the biology community are empowered to construct meaningful image data sets drawn from publicly-available online image archives and publications. The interface is specifically designed to streamline the segmentation process in order to reduce the number of required manual corrections. AISO also directly integrates Plant Ontology terms via a lightweight web service, allowing users to select and apply appropriate plant terms to segmented images. The resulting image and ontology label data structure will enable consistent data extraction techniques, efficient database storage, and future semantic inference and active learning functionalities intended to reduce user effort and optimize the annotation process. AISO is a freely available, Java-based desktop application (http://jaiswallab.cgrb.oregonstate.edu/software).},
author = {Preece, Justin},
editor = {Lingutla, N and Todorovic, S and Jaiswal, P}
}
@mastersthesis {225,
title = {Annotation of image segments with ontologies (AISO)},
volume = {Master of Science (M.S.) in Computer Science},
year = {2013},
school = {Oregon State University},
type = {Master{\textquoteright}s},
address = {Corvallis},
abstract = {This M.S thesis presents an interactive software tool that I have developed in the course of the past two years. This interactive tool is called AISO. AISO is aimed at interactive image segmentation and annotation tool designed to allow users to segment an image {\textendash} such as those produced with digital photography or from scanned prints {\textendash} and then annotate those segments with ontology terms. Many photo-editing and illustration soft- ware packages enable the ad-hoc editing of an image, but any highlighting and labeling utility requires thorough knowledge of the softwares illustration capabilities (i.e. layering, boundary detection) and does not include the structured integration of scientific data. For example, any labels applied to hand-illustrated segments super-imposed onto an image would have to be individually constructed and associated with a particular portion of an image. AISO simplifies this functionality and requires only a few input gestures and clicks to identify and label segments. The resulting structured image and ontology data allows for consistent extraction techniques. Researchers are thus empowered to construct meaningful image data sets drawn from their laboratories, online image archives, and publications. For this thesis I evaluated AISO by soliciting feedback from a selected group of biological researchers. They provided overall positive feedback on user friendliness, consistency and predictability of AISO, speed of interaction of AISO. As the key contribution, this thesis provides the first open source software for plant biologists by integrating the state-of-the-art image segmentation algorithms with plant ontology webservice. Based on our preliminary user study, AISO has potential to significantly advance current practices in plant biology research.},
url = {http://hdl.handle.net/1957/42883},
author = {Nikhil TV Lingutla}
}
@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 {822,
title = {Annotating Gene Expression in