Multi-domain semantic similarity in biomedical research
Abstract Background Given the increasing amount of biomedical resources that are being annotated with concepts from more than one ontology and covering multiple domains of knowledge, it is important to devise mechanisms to compare these resources that take into account the various domains of annotat...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2019-05-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12859-019-2810-9 |
| _version_ | 1818503254369107968 |
|---|---|
| author | João D. Ferreira Francisco M. Couto |
| author_facet | João D. Ferreira Francisco M. Couto |
| author_sort | João D. Ferreira |
| collection | DOAJ |
| description | Abstract Background Given the increasing amount of biomedical resources that are being annotated with concepts from more than one ontology and covering multiple domains of knowledge, it is important to devise mechanisms to compare these resources that take into account the various domains of annotation. For example, metabolic pathways are annotated with their enzymes and their metabolites, and thus similarity measures should compare them with respect to both of those domains simultaneously. Results In this paper, we propose two approaches to lift existing single-ontology semantic similarity measures into multi-domain measures. The aggregative approach compares domains independently and averages the various similarity values into a final score. The integrative approach integrates all the relevant ontologies into a single one, calculating similarity in the resulting multi-domain ontology using the single-ontology measure. Conclusions We evaluated the two approaches in a multidisciplinary epidemiology dataset by evaluating the capacity of the similarity measures to predict new annotations based on the existing ones. The results show a promising increase in performance of the multi-domain measures over the single-ontology ones in the vast majority of the cases. These results show that multi-domain measures outperform single-domain ones, and should be considered by the community as a starting point to study more efficient multi-domain semantic similarity measures. |
| first_indexed | 2024-12-10T21:21:37Z |
| format | Article |
| id | doaj.art-e4f5331a245040679b79e2d345959aab |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-12-10T21:21:37Z |
| publishDate | 2019-05-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-e4f5331a245040679b79e2d345959aab2022-12-22T01:33:06ZengBMCBMC Bioinformatics1471-21052019-05-0120S10233110.1186/s12859-019-2810-9Multi-domain semantic similarity in biomedical researchJoão D. Ferreira0Francisco M. Couto1LASIGE, Faculdade de Ciências, Universidade de LisboaLASIGE, Faculdade de Ciências, Universidade de LisboaAbstract Background Given the increasing amount of biomedical resources that are being annotated with concepts from more than one ontology and covering multiple domains of knowledge, it is important to devise mechanisms to compare these resources that take into account the various domains of annotation. For example, metabolic pathways are annotated with their enzymes and their metabolites, and thus similarity measures should compare them with respect to both of those domains simultaneously. Results In this paper, we propose two approaches to lift existing single-ontology semantic similarity measures into multi-domain measures. The aggregative approach compares domains independently and averages the various similarity values into a final score. The integrative approach integrates all the relevant ontologies into a single one, calculating similarity in the resulting multi-domain ontology using the single-ontology measure. Conclusions We evaluated the two approaches in a multidisciplinary epidemiology dataset by evaluating the capacity of the similarity measures to predict new annotations based on the existing ones. The results show a promising increase in performance of the multi-domain measures over the single-ontology ones in the vast majority of the cases. These results show that multi-domain measures outperform single-domain ones, and should be considered by the community as a starting point to study more efficient multi-domain semantic similarity measures.http://link.springer.com/article/10.1186/s12859-019-2810-9Semantic similarityEpidemiologyMultiple-domainPrediction |
| spellingShingle | João D. Ferreira Francisco M. Couto Multi-domain semantic similarity in biomedical research BMC Bioinformatics Semantic similarity Epidemiology Multiple-domain Prediction |
| title | Multi-domain semantic similarity in biomedical research |
| title_full | Multi-domain semantic similarity in biomedical research |
| title_fullStr | Multi-domain semantic similarity in biomedical research |
| title_full_unstemmed | Multi-domain semantic similarity in biomedical research |
| title_short | Multi-domain semantic similarity in biomedical research |
| title_sort | multi domain semantic similarity in biomedical research |
| topic | Semantic similarity Epidemiology Multiple-domain Prediction |
| url | http://link.springer.com/article/10.1186/s12859-019-2810-9 |
| work_keys_str_mv | AT joaodferreira multidomainsemanticsimilarityinbiomedicalresearch AT franciscomcouto multidomainsemanticsimilarityinbiomedicalresearch |