Text Mining Resources

Anatomy resources


Effects involving anatomical entities such as tissues and organs are key to understanding the connections between molecular-level events and organism-level effects such as disease.

For example, to analyse a statement like "NO synhase may induce an anti-tumour effect by affecting blood vessel growth" it is necessary to recognize not only the molecular entity (NO synhase) and the affected pathological entity (tumour), but also the anatomical entity (blood vessel) as well as the statements of their relationships.

The tools and lexical resources presented on this page make use of the wealth of anatomy domain ontologies available in the OBO Foundry collection of Open Biological and Biomedical Ontologies to facilitate anatomical entity mention detection and classification.

The following resources are provided:

  • Approximate string-matching ontology lookup tool
  • Selection of OBO foundry ontologies relevant to physical anatomical entity mention recognition
  • Set of 5000 common noun phrases from PubMed annotated to identify anatomical entity mentions
  • Lexical items relevant to anatomical entities together with their upper-level ontological categories in the various OBO anatomy resources
  • Multi-Level Event Extraction (MLEE) corpus and tools for entity mention detection and event extraction across levels of biological organization from the molecular to the organ system level
  • AnEM corpus, a domain- and species-independent resource manually annotated for anatomical entity mentions using a fine-grained classification system
  • BioNLP ST'13 Cancer Genetics task resources, containing, among other annotations, anatomical entity mention annotation for 350 abstracts that are not part of AnEM or MLEE.


Anatomical entities are central to much of biomedical discourse and must be considered in any attempt to fully analyse biomedical scientific text. However, while a wealth of tools and resources have been introduced in domain natural language processing efforts for the recognition of molecular level entity (gene, protein, chemical) and organism name mentions in text, there has been little study of the recognition of mentions of anatomical entities such as tissues and organs.

To address this issue and to facilitate more detailed and comprehensive analysis of biomedical scientific text, the work presented here aims to establish a fine-grained, species-independent anatomical entity mention detection task.

This effort builds on the rich resources available in the OBO Foundry as well as recent efforts toward the consolidation of various species-specific OBO anatomy resources.

The details of the effort are presented in the manuscript Anatomical Entity Recognition with Open Biomedical Ontologies.



Creative Commons License
The tools and resources created as part of this effort by the National Centre for Text Mining (NaCTeM) are licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License. Please see also the general NaCTeM terms and conditions of usage.

If you use the resources and tools, please attribute them by citing the paper below.

For the licences of OBO Foundry ontologies, please refer to