Evaluating the botanical coverage of PATO using an unsupervised learning algorithm

Alyssa Janning, Hong Cui

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations


In this paper, we explore issues in adopting PATO as a standard phenotypic quality ontology for the biological community. Using CharaParser's unsupervised learning algorithm and the Stanford Parser, we extract morphological descriptions from Flora of North America to be matched to terms in PATO. Using the resulting data, we examine PATO's coverage of botanically interesting terms in order to find gaps and to determine accuracy. To maintain PATO's neutrality, we recommend that term definitions be reevaluated and propose that complimentary ontologies be enhanced to close any outstanding gaps in terminology.

Original languageEnglish (US)
Title of host publicationProceedings of the 2012 iConference
Subtitle of host publicationCulture, Design, Society, iConference 2012
Number of pages2
StatePublished - 2012
Event2012 iConference: Culture, Design, Society, iConference 2012 - Toronto, ON, Canada
Duration: Feb 7 2012Feb 10 2012

Publication series

NameACM International Conference Proceeding Series


Other2012 iConference: Culture, Design, Society, iConference 2012
CityToronto, ON


  • Flora of North America
  • PATO
  • Stanford Parser
  • botany
  • ontologies
  • open biological ontologies
  • unsupervised learning

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications


Dive into the research topics of 'Evaluating the botanical coverage of PATO using an unsupervised learning algorithm'. Together they form a unique fingerprint.

Cite this