Aligning Biological Ontologies Using Artificial Neural Networks
Author Information
Author(s): Huang Jingshan, Dang Jiangbo, Huhns Michael N, Zheng W Jim
Primary Institution: Medical University of South Carolina
Hypothesis
Three weights for semantic aspects learned from a subset of concepts are representative of all concepts in the same ontology.
Conclusion
The experiment results verify that the proposed method significantly improves the automation of biological ontology alignment.
Supporting Evidence
- The method achieved a Precision of 0.9 and Recall of 0.85.
- Three weights for semantic aspects were learned and validated through experiments.
- Two real-world biological ontologies were used for testing the proposed method.
Takeaway
This study shows how we can use computers to help match different biological terms, making it easier for scientists to understand and share information.
Methodology
An artificial neural network approach was used to learn and adjust weights for semantic aspects in biological ontology alignment.
Potential Biases
Potential bias in the selection of training examples and the reliance on domain experts for validation.
Limitations
The study primarily focuses on finding equivalent concept pairs and does not address other mapping tasks.
Statistical Information
P-Value
0.9 and 0.85 for Precision and Recall respectively
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website