Supervised segmentation of phenotype descriptions for the human skeletal phenome using hybrid methods

Groza, Tudor, Hunter, Jane and Zankl, Andreas (2012) Supervised segmentation of phenotype descriptions for the human skeletal phenome using hybrid methods. BMC Bioinformatics, 13 265-1-265-19. doi:10.1186/1471-2105-13-265


Author Groza, Tudor
Hunter, Jane
Zankl, Andreas
Total Author Count Override 3
Title Supervised segmentation of phenotype descriptions for the human skeletal phenome using hybrid methods
Journal name BMC Bioinformatics   Check publisher's open access policy
ISSN 1471-2105
Publication date 2012-10-15
Sub-type Article (original research)
DOI 10.1186/1471-2105-13-265
Open Access Status DOI
Volume 13
Start page 265-1
End page 265-19
Total pages 19
Place of publication London, United Kingdom
Publisher BioMed Central
Collection year 2013
Language eng
Formatted abstract
Background:
Over the course of the last few years there has been a significant amount of research performed on ontology-based formalization of phenotype descriptions. In order to fully capture the intrinsic value and knowledge expressed within them, we need to take advantage of their inner structure, which implicitly combines qualities and anatomical entities. The first step in this process is the segmentation of the phenotype descriptions into their atomic elements.

Results:
We present a two-phase hybrid segmentation method that combines a series individual classifiers using different aggregation schemes (set operations and simple majority voting). The approach is tested on a corpus comprised of skeletal phenotype descriptions emerged from the Human Phenotype Ontology. Experimental results show that the best hybrid method achieves an F-Score of 97.05% in the first phase and F-Scores of 97.16% / 94.50% in the second phase.

Conclusions:
The performance of the initial segmentation of anatomical entities and qualities (phase I) is not affected by the presence / absence of external resources, such as domain dictionaries. From a generic perspective, hybrid methods may not always improve the segmentation accuracy as they are heavily dependent on the goal and data characteristics.
Q-Index Code C1
Q-Index Status Confirmed Code
Institutional Status UQ
Additional Notes Published: 15 October 2012.Article number265

 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 3 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 3 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Mon, 15 Oct 2012, 13:53:09 EST by Dr Tudor Groza on behalf of School of Information Technol and Elec Engineering