Predicting Gene-Disease Associations with Knowledge Graph Embeddings over Multiple Ontologies

Detalhes bibliográficos
Autor(a) principal: Nunes, Susana Catarina Plácido
Data de Publicação: 2021
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10451/52109
Resumo: Tese de mestrado, Bioinformática e Biologia Computacional, Universidade de Lisboa, Faculdade de Ciências, 2021
id RCAP_704f9eb25d221f27884be32d27d11c00
oai_identifier_str oai:repositorio.ul.pt:10451/52109
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Predicting Gene-Disease Associations with Knowledge Graph Embeddings over Multiple Ontologiesontologiassemelhança semânticagrafos de conhecimentorepresentações semânticasaprendizagem automáticaTeses de mestrado - 2021Departamento de InformáticaTese de mestrado, Bioinformática e Biologia Computacional, Universidade de Lisboa, Faculdade de Ciências, 2021There are still more than 1,400 Mendelian conditions whose molecular cause is un known. In addition, almost all medical conditions are somehow influenced by human genetic variation. This challenge also presents itself as an opportunity to understand the mechanisms of diseases, thus allowing the development of better mitigation strategies, finding diagnostic markers and therapeutic targets. Deciphering the link between genes and diseases is one of the most demanding tasks in biomedical research. Computational approaches for gene-disease associations prediction can greatly accelerate this process, and recent developments that explore the scientific knowledge described in ontologies have achieved good results. State-of-the-art approaches that take advantage of ontologies or knowledge graphs for these predictions are typically based on semantic similarity measures that only take into consideration hierarchical relations. New developments in the area of knowledge graphs embeddings support more powerful representations but are usually limited to a single ontology, which may be insufficient in multi-domain applications such as the prediction of gene-disease associations. This dissertation proposes a novel approach of gene-disease associations prediction by exploring both the Human Phenotype Ontology and the Gene Ontology, using knowledge graph embeddings to represent gene and disease features in a shared semantic space that covers both gene function and phenotypes. Our approach integrates different methods for building the shared semantic space, as well as multiple knowledge graph embeddings algorithms and machine learning methods. The prediction performance was evaluated on curated gene-disease associations from DisGeNET and compared to classical semantic similarity measures. Our experiments demonstrate the value of employing knowledge graph embeddings based on random walks and highlight the need for closer integration of different ontologies.Pesquita, Cátia, 1980-Repositório da Universidade de LisboaNunes, Susana Catarina Plácido2022-03-31T09:27:14Z202120212021-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10451/52109TID:202994287enginfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-11-08T16:57:11Zoai:repositorio.ul.pt:10451/52109Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T22:03:15.577329Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Predicting Gene-Disease Associations with Knowledge Graph Embeddings over Multiple Ontologies
title Predicting Gene-Disease Associations with Knowledge Graph Embeddings over Multiple Ontologies
spellingShingle Predicting Gene-Disease Associations with Knowledge Graph Embeddings over Multiple Ontologies
Nunes, Susana Catarina Plácido
ontologias
semelhança semântica
grafos de conhecimento
representações semânticas
aprendizagem automática
Teses de mestrado - 2021
Departamento de Informática
title_short Predicting Gene-Disease Associations with Knowledge Graph Embeddings over Multiple Ontologies
title_full Predicting Gene-Disease Associations with Knowledge Graph Embeddings over Multiple Ontologies
title_fullStr Predicting Gene-Disease Associations with Knowledge Graph Embeddings over Multiple Ontologies
title_full_unstemmed Predicting Gene-Disease Associations with Knowledge Graph Embeddings over Multiple Ontologies
title_sort Predicting Gene-Disease Associations with Knowledge Graph Embeddings over Multiple Ontologies
author Nunes, Susana Catarina Plácido
author_facet Nunes, Susana Catarina Plácido
author_role author
dc.contributor.none.fl_str_mv Pesquita, Cátia, 1980-
Repositório da Universidade de Lisboa
dc.contributor.author.fl_str_mv Nunes, Susana Catarina Plácido
dc.subject.por.fl_str_mv ontologias
semelhança semântica
grafos de conhecimento
representações semânticas
aprendizagem automática
Teses de mestrado - 2021
Departamento de Informática
topic ontologias
semelhança semântica
grafos de conhecimento
representações semânticas
aprendizagem automática
Teses de mestrado - 2021
Departamento de Informática
description Tese de mestrado, Bioinformática e Biologia Computacional, Universidade de Lisboa, Faculdade de Ciências, 2021
publishDate 2021
dc.date.none.fl_str_mv 2021
2021
2021-01-01T00:00:00Z
2022-03-31T09:27:14Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10451/52109
TID:202994287
url http://hdl.handle.net/10451/52109
identifier_str_mv TID:202994287
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799134583552212992