Integrating phenotype ontologies with PhenomeNET

2020

Preprint

Self Cite

Motivation: Over the past years, many computational methods have been developed to incorporate information about phenotypes for disease gene prioritization task. These methods generally compute the similarity between a patient's phenotypes and a database of gene-phenotype to find the most phenotypically similar match. The main limitation in these methods is their reliance on knowledge about phenotypes associated with particular genes, which is not complete in humans as well as in many model organisms such as the mouse and fish. Information about functions of gene products and anatomical site of gene expression is available for more genes and can also be related to phenotypes through ontologies and machine learning models. Results: We developed a novel graph-based machine learning method for biomedical ontologies which is able to exploit axioms in ontologies and other graph-structured data. Using our machine learning method, we embed genes based on their associated phenotypes, functions of the gene products, and anatomical location of gene expression. We then develop a machine learning model to predict gene-disease associations based on the associations between genes and multiple biomedical ontologies, and this model significantly improves over state of the art methods. Furthermore, we extend phenotype-based gene prioritization methods significantly to all genes which are associated with phenotypes, functions, or site of expression. Availability: Software and data are available at https://github. com/bio-ontology-research-group/DL2Vec.

Section: Phenotype-based Prioritization Of Candidate Genesmentioning

confidence: 99%

Predicting candidate genes from phenotypes, functions, and anatomical site of expression

Chen

Althagafi

2020

Preprint

Self Cite

“…While GO is not a phenotype ontology, it is used in the axioms that make up most phenotype ontologies (Gkoutos et al, 2017). We use the cross-species phenotype ontology PhenomeNET (Hoehndorf et al, 2011;Rodríguez-García et al, 2017), which relies on the GO for defining phenotypes, and replace the GO in PhenomeNET with GO-Plus.…”

Section: Gene-disease Association Prediction Using Go-plusmentioning

confidence: 99%

“…We downloaded the PhenomeNET ontology (Hoehndorf et al, 2011;Rodríguez-García et al, 2017) in OWL format from the AberOWL repository http://aber-owl.net (Hoehndorf et al, 2015a) on February 21, 2018. PhenomeNET is a cross-species phenotype ontology that combines phenotype ontologies, anatomy ontologies, GO, and several other ontologies in a formal manner (Hoehndorf et al, 2011).…”

Section: Phenomenet Ontologymentioning

confidence: 99%

Formal axioms in biomedical ontologies improve analysis and interpretation of associated data

Smaili

Gao

2019

Preprint

Self Cite

Motivation:There are now over 500 ontologies in the life sciences. Over the past years, significant resources have been invested into formalizing these biomedical ontologies. Formal axioms in ontologies have been developed and used to detect and ensure ontology consistency, find unsatisfiable classes, improve interoperability, guide ontology extension through the application of axiom-based design patterns, and encode domain background knowledge. At the same time, ontologies have extended their amount of human-readable information such as labels and definitions as well as other meta-data. As a consequence, biomedical ontologies now form large formalized domain knowledge bases and have a potential to improve ontology-based data analysis by providing background knowledge and relations between biological entities that are not otherwise connected. Results: We evaluate the contribution of formal axioms and ontology meta-data to the ontology-based prediction of protein-protein interactions and gene-disease associations. We find that the formal axioms that have been created for the Gene Ontology and several other ontologies significantly improve ontologybased prediction models through provision of domain-specific background knowledge. Furthermore, we find that the labels, synonyms and definitions in ontologies can also provide background knowledge that may be exploited for prediction. The axioms and meta-data of different ontologies contribute in varying degrees to improving data analysis. Our results have major implications on the further development of formal knowledge bases and ontologies in the life sciences, in particular as machine learning methods are more frequently being applied. Our findings clearly motivate the need for further development, and the systematic, application-driven evaluation and improvement, of formal axioms in ontologies. Availability: https://

“…We represent the phenotypes and functions through ontologies. To associate human and mouse phenotypes, we use the cross-species phenotype ontology PhenomeNET (Hoehndorf et al, 2011;Rodríguez-García et al, 2017), which combined the Human Phenotype Ontology (HP) (Köhler et al, 2018) and the Mammalian Phenotype Ontology (MP) (Smith et al, 2004). To incorporate knowledge of protein functions, we use the Gene Ontology (Ashburner et al, 2000;The Gene Ontology Consortium, 2017).…”

Section: Feature Generation and Representation Learning For Human Promentioning

confidence: 99%

“…To obtain formal representations of phenotypes and GO classes, we downloaded the cross-species PhenomeNET Ontology (Hoehndorf et al, 2011;Rodríguez-García et al, 2017) from the AberOWL ontology repository (Hoehndorf et al, 2015a) on September 13, 2018, and we downloaded the Gene Ontology (Ashburner et al, 2000;The Gene Ontology Consortium, 2017)…”

Section: Data Sourcesmentioning

confidence: 99%

Phenotypic, functional and taxonomic features predict host-pathogen interactions

Liu-Wei

Kafkas

2018

Preprint

Self Cite

Motivation: Identification of host-pathogen interactions (HPIs) can reveal mechanistic insights of infectious diseases for potential treatments and drug discoveries. Current computational methods for the prediction of HPIs often rely on our knowledge on the sequences and functions of pathogen proteins, which is limited for many species, especially for emerging pathogens. Matching the phenotypes elicited by pathogens with phenotypes associated with host proteins might improve the prediction of HPIs. Results: We developed an ontology-based machine learning method that predicts potential interaction protein partners for pathogens. Our method exploits information about disease mechanisms through features learned from phenotypic, functional and taxonomic knowledge about pathogens and human proteins. Additionally, by embedding the phenotypic information of the pathogens within a formal representation of pathogen taxonomy, we demonstrate that our model can accurately predict interaction partners for pathogens without known phenotypes, using a combination of their taxonomic relationships with other pathogens and information from ontologies as background knowledge. Our results show that the integration of phenotypic, functional and taxonomic knowledge not only improves the prediction of HPIs, but also enables us to investigate novel pathogens in emerging infectious diseases. Availability:https://github.com/bio-ontology-research-group/hpi-predict Contact: