Automatic concept recognition using the human phenotype ontology reference and test suite corpora

Affiliations

¹ School of ITEE, The University of Queensland, St. Lucia, QLD 4072, Australia, Garvan Institute of Medical Research, Darlinghurst, Sydney, NSW 2010, Australia, Institute for Medical Genetics and Human Genetics, Charité-Universitätsmedizin Berlin, 13353 Berlin, Germany, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge, UK, National Institute of Informatics, Hitotsubashi, Tokyo, Japan, Mouse Informatics Group, Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton CB10 1SA, UK, LASIGE, Departamento de Informática, Faculdade de Ciências, Universidade de Lisboa, 1749-016 Lisboa, Portugal, Genetic Services of Western Australia, King Edward Memorial Hospital, WA 6008, Australia, School of Paediatrics and Child Health, University of Western Australia, WA 6008, Australia, Institute for Immunology and Infectious Diseases, Murdoch University, WA 6150, Australia, Office of Population Health, Public Health and Clinical Services Division, Western Australian Department of Health, WA 6004, Australia, Academic Department of Medical Genetics, Sydney Children's Hospitals Network (Westmead), NSW 2145, Australia, Discipline of Genetic Medicine, Sydney Medical School, The University of Sydney, NSW 2006, Australia, Max Planck Institute for Molecular Genetics, 14195 Berlin, Germany, Institute for Bioinformatics, Department of Mathematics and Computer Science, Freie Universität Berlin, 14195 Berlin, Germany and Berlin Brandenburg Center for Regenerative Therapies, 13353 Berlin, Germany School of ITEE, The University of Queensland, St. Lucia, QLD 4072, Australia, Garvan Institute of Medical Research, Darlinghurst, Sydney, NSW 2010, Australia, Institute for Medical Genetics and Human Genetics, Charité-Universitätsmedizin Berlin, 13353 Berlin, Germany, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge, UK, National Institute of Informatics, Hitotsubashi, Tokyo, Japan, Mouse Informa
² School of ITEE, The University of Queensland, St. Lucia, QLD 4072, Australia, Garvan Institute of Medical Research, Darlinghurst, Sydney, NSW 2010, Australia, Institute for Medical Genetics and Human Genetics, Charité-Universitätsmedizin Berlin, 13353 Berlin, Germany, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge, UK, National Institute of Informatics, Hitotsubashi, Tokyo, Japan, Mouse Informatics Group, Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton CB10 1SA, UK, LASIGE, Departamento de Informática, Faculdade de Ciências, Universidade de Lisboa, 1749-016 Lisboa, Portugal, Genetic Services of Western Australia, King Edward Memorial Hospital, WA 6008, Australia, School of Paediatrics and Child Health, University of Western Australia, WA 6008, Australia, Institute for Immunology and Infectious Diseases, Murdoch University, WA 6150, Australia, Office of Population Health, Public Health and Clinical Services Division, Western Australian Department of Health, WA 6004, Australia, Academic Department of Medical Genetics, Sydney Children's Hospitals Network (Westmead), NSW 2145, Australia, Discipline of Genetic Medicine, Sydney Medical School, The University of Sydney, NSW 2006, Australia, Max Planck Institute for Molecular Genetics, 14195 Berlin, Germany, Institute for Bioinformatics, Department of Mathematics and Computer Science, Freie Universität Berlin, 14195 Berlin, Germany and Berlin Brandenburg Center for Regenerative Therapies, 13353 Berlin, Germany.

PMID: 25725061
PMCID: PMC4343077
DOI: 10.1093/database/bav005

Automatic concept recognition using the human phenotype ontology reference and test suite corpora

Tudor Groza et al. Database (Oxford). 2015.

. 2015 Feb 27:2015:bav005.

doi: 10.1093/database/bav005. Print 2015.

Affiliations

¹ School of ITEE, The University of Queensland, St. Lucia, QLD 4072, Australia, Garvan Institute of Medical Research, Darlinghurst, Sydney, NSW 2010, Australia, Institute for Medical Genetics and Human Genetics, Charité-Universitätsmedizin Berlin, 13353 Berlin, Germany, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge, UK, National Institute of Informatics, Hitotsubashi, Tokyo, Japan, Mouse Informatics Group, Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton CB10 1SA, UK, LASIGE, Departamento de Informática, Faculdade de Ciências, Universidade de Lisboa, 1749-016 Lisboa, Portugal, Genetic Services of Western Australia, King Edward Memorial Hospital, WA 6008, Australia, School of Paediatrics and Child Health, University of Western Australia, WA 6008, Australia, Institute for Immunology and Infectious Diseases, Murdoch University, WA 6150, Australia, Office of Population Health, Public Health and Clinical Services Division, Western Australian Department of Health, WA 6004, Australia, Academic Department of Medical Genetics, Sydney Children's Hospitals Network (Westmead), NSW 2145, Australia, Discipline of Genetic Medicine, Sydney Medical School, The University of Sydney, NSW 2006, Australia, Max Planck Institute for Molecular Genetics, 14195 Berlin, Germany, Institute for Bioinformatics, Department of Mathematics and Computer Science, Freie Universität Berlin, 14195 Berlin, Germany and Berlin Brandenburg Center for Regenerative Therapies, 13353 Berlin, Germany School of ITEE, The University of Queensland, St. Lucia, QLD 4072, Australia, Garvan Institute of Medical Research, Darlinghurst, Sydney, NSW 2010, Australia, Institute for Medical Genetics and Human Genetics, Charité-Universitätsmedizin Berlin, 13353 Berlin, Germany, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge, UK, National Institute of Informatics, Hitotsubashi, Tokyo, Japan, Mouse Informa
² School of ITEE, The University of Queensland, St. Lucia, QLD 4072, Australia, Garvan Institute of Medical Research, Darlinghurst, Sydney, NSW 2010, Australia, Institute for Medical Genetics and Human Genetics, Charité-Universitätsmedizin Berlin, 13353 Berlin, Germany, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge, UK, National Institute of Informatics, Hitotsubashi, Tokyo, Japan, Mouse Informatics Group, Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton CB10 1SA, UK, LASIGE, Departamento de Informática, Faculdade de Ciências, Universidade de Lisboa, 1749-016 Lisboa, Portugal, Genetic Services of Western Australia, King Edward Memorial Hospital, WA 6008, Australia, School of Paediatrics and Child Health, University of Western Australia, WA 6008, Australia, Institute for Immunology and Infectious Diseases, Murdoch University, WA 6150, Australia, Office of Population Health, Public Health and Clinical Services Division, Western Australian Department of Health, WA 6004, Australia, Academic Department of Medical Genetics, Sydney Children's Hospitals Network (Westmead), NSW 2145, Australia, Discipline of Genetic Medicine, Sydney Medical School, The University of Sydney, NSW 2006, Australia, Max Planck Institute for Molecular Genetics, 14195 Berlin, Germany, Institute for Bioinformatics, Department of Mathematics and Computer Science, Freie Universität Berlin, 14195 Berlin, Germany and Berlin Brandenburg Center for Regenerative Therapies, 13353 Berlin, Germany.

PMID: 25725061
PMCID: PMC4343077
DOI: 10.1093/database/bav005

Abstract

Concept recognition tools rely on the availability of textual corpora to assess their performance and enable the identification of areas for improvement. Typically, corpora are developed for specific purposes, such as gene name recognition. Gene and protein name identification are longstanding goals of biomedical text mining, and therefore a number of different corpora exist. However, phenotypes only recently became an entity of interest for specialized concept recognition systems, and hardly any annotated text is available for performance testing and training. Here, we present a unique corpus, capturing text spans from 228 abstracts manually annotated with Human Phenotype Ontology (HPO) concepts and harmonized by three curators, which can be used as a reference standard for free text annotation of human phenotypes. Furthermore, we developed a test suite for standardized concept recognition error analysis, incorporating 32 different types of test cases corresponding to 2164 HPO concepts. Finally, three established phenotype concept recognizers (NCBO Annotator, OBO Annotator and Bio-LarK CR) were comprehensively evaluated, and results are reported against both the text corpus and the test suites. The gold standard and test suites corpora are available from http://bio-lark.org/hpo_res.html. Database URL: http://bio-lark.org/hpo_res.html.

PubMed Disclaimer

Figures

**Figure 1.**
Distribution of HPO test cases according to their types mapped to the top-level HPO categories. The larger the symbol, the more test case entries the corresponding mapping has. For example, the largest number of test case entries of Length-1 is present in Abnormality of the integument. In addition to providing an overview on the test suite content, this figure also depicts a birds-eye view over the variation in terms of characteristics of the concept lexical representations in the different top-level HPO categories. We can observe, e.g. that only a very few top-level categories contain concept labels with a length greater than 10. Similarly, metaphoric constructs seem to be present only in skeletal abnormalities, which also dominate together with the abnormalities of the integument and of the metabolism the range of labels containing punctuation.

**Figure 2.**
Distribution of HPO annotations according to the top-level HPO categories. Two distributions are shown: an overall distribution that accounts for duplicate concept annotations (i.e. every instance of an annotation is counted), and a unique distribution that shows the counts of the unique concept annotations (i.e. every concept is counted a single time, indifferently of how many annotations exist in the corpus).

**Figure 3.**
F-Score results achieved by the three systems on the HPO gold standard, distributed according to the HPO top-level category.

**Figure 4.**
F-Score results achieved by the three systems on the HPO test suites, distributed according to the type of the test case.

See this image and copyright information in PMC

References

1. Robinson P.N., Köhler S., Bauer S., et al. (2008) The Human Phenotype Ontology: a tool for annotating and analyzing human hereditary disease. Am. J. Hum. Genet., 83, 610–615. - PMC - PubMed
1. Köhler S., Doelken S.C., Mungall C.J., et al. . (2014) The Human Phenotype Ontology project: linking molecular biology and disease through phenotype data. Nucleic Acids Res., 42, D966–D974. - PMC - PubMed
1. Washington N.L., Haendel M.A., Mungall C.J., et al. (2009). Linking human diseases to animal models using ontology-based phenotype annotation. PLoS Biol., 7, e1000247. - PMC - PubMed
1. Köhler S., Doelken S.C., Ruef B.J., et al. . (2014) Construction and accessibility of a cross-species phenotype ontology along with gene annotations for biomedical research. F1000Research, 2, 30, [v2; ref status: indexed, http://f1000r.es/2td]. - PMC - PubMed
1. Chen C.K., Mungall C.J., Gkoutos G.V., et al. (2012) MouseFinder: candidate disease genes from mouse phenotype data. Hum. Mutat., 33, 858–866. - PMC - PubMed

Publication types

Actions
Actions

MeSH terms

Actions
Actions
Actions
Actions
Actions

Grants and funding

LinkOut - more resources

Full Text Sources
Other Literature Sources
- scite Smart Citations

Save citation to file

Email citation

Add to Collections

Add to My Bibliography

Your saved search

Create a file for external citation management software

Your RSS Feed

Automatic concept recognition using the human phenotype ontology reference and test suite corpora

Affiliations

Automatic concept recognition using the human phenotype ontology reference and test suite corpora

Authors

Affiliations

Abstract

Figures

References

Publication types

MeSH terms

Grants and funding

LinkOut - more resources

Full Text Sources

Other Literature Sources