Neuro-symbolic representation learning on biological knowledge graphs

<h3>Motivation</h3><p dir="ltr">Biological data and knowledge bases increasingly rely on Semantic Web technologies and the use of knowledge graphs for data integration, retrieval and federated queries. In the past years, feature learning methods that are applicable to gra...

Full description

Saved in:
Bibliographic Details
Main Author: Mona Alshahrani (3576653) (author)
Other Authors: Mohammad Asif Khan (9220790) (author), Omar Maddouri (19725331) (author), Akira R Kinjo (19725334) (author), Núria Queralt-Rosinach (3846793) (author), Robert Hoehndorf (38206) (author)
Published: 2017
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513557009268736
author Mona Alshahrani (3576653)
author2 Mohammad Asif Khan (9220790)
Omar Maddouri (19725331)
Akira R Kinjo (19725334)
Núria Queralt-Rosinach (3846793)
Robert Hoehndorf (38206)
author2_role author
author
author
author
author
author_facet Mona Alshahrani (3576653)
Mohammad Asif Khan (9220790)
Omar Maddouri (19725331)
Akira R Kinjo (19725334)
Núria Queralt-Rosinach (3846793)
Robert Hoehndorf (38206)
author_role author
dc.creator.none.fl_str_mv Mona Alshahrani (3576653)
Mohammad Asif Khan (9220790)
Omar Maddouri (19725331)
Akira R Kinjo (19725334)
Núria Queralt-Rosinach (3846793)
Robert Hoehndorf (38206)
dc.date.none.fl_str_mv 2017-04-25T03:00:00Z
dc.identifier.none.fl_str_mv 10.1093/bioinformatics/btx275
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Neuro-symbolic_representation_learning_on_biological_knowledge_graphs/27087976
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biological sciences
Bioinformatics and computational biology
Knowledge graphs
Data integration
Feature learning methods
Symbolic methods
Knowledge representation
Neural networks
Node embeddings
dc.title.none.fl_str_mv Neuro-symbolic representation learning on biological knowledge graphs
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <h3>Motivation</h3><p dir="ltr">Biological data and knowledge bases increasingly rely on Semantic Web technologies and the use of knowledge graphs for data integration, retrieval and federated queries. In the past years, feature learning methods that are applicable to graph-structured data are becoming available, but have not yet widely been applied and evaluated on structured biological knowledge. Results: We develop a novel method for feature learning on biological knowledge graphs. Our method combines symbolic methods, in particular knowledge representation using symbolic logic and automated reasoning, with neural networks to generate embeddings of nodes that encode for related information within knowledge graphs. Through the use of symbolic logic, these embeddings contain both explicit and implicit information. We apply these embeddings to the prediction of edges in the knowledge graph representing problems of function prediction, finding candidate genes of diseases, protein-protein interactions, or drug target relations, and demonstrate performance that matches and sometimes outperforms traditional approaches based on manually crafted features. Our method can be applied to any biological knowledge graph, and will thereby open up the increasing amount of Semantic Web based knowledge bases in biology to use in machine learning and data analytics.</p><h3>Availability and implementation</h3><p dir="ltr">https://github.com/bio-ontology-research-group/walking-rdf-and-owl</p><h3>Supplementary information</h3><p dir="ltr">Supplementary data are available at Bioinformatics online.</p><h2>Other Information</h2><p dir="ltr">Published in: Bioinformatics<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1093/bioinformatics/btx275" target="_blank">https://dx.doi.org/10.1093/bioinformatics/btx275</a></p>
eu_rights_str_mv openAccess
id Manara2_d9ffc9141dae446e7b56c1734994af72
identifier_str_mv 10.1093/bioinformatics/btx275
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/27087976
publishDate 2017
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Neuro-symbolic representation learning on biological knowledge graphsMona Alshahrani (3576653)Mohammad Asif Khan (9220790)Omar Maddouri (19725331)Akira R Kinjo (19725334)Núria Queralt-Rosinach (3846793)Robert Hoehndorf (38206)Biological sciencesBioinformatics and computational biologyKnowledge graphsData integrationFeature learning methodsSymbolic methodsKnowledge representationNeural networksNode embeddings<h3>Motivation</h3><p dir="ltr">Biological data and knowledge bases increasingly rely on Semantic Web technologies and the use of knowledge graphs for data integration, retrieval and federated queries. In the past years, feature learning methods that are applicable to graph-structured data are becoming available, but have not yet widely been applied and evaluated on structured biological knowledge. Results: We develop a novel method for feature learning on biological knowledge graphs. Our method combines symbolic methods, in particular knowledge representation using symbolic logic and automated reasoning, with neural networks to generate embeddings of nodes that encode for related information within knowledge graphs. Through the use of symbolic logic, these embeddings contain both explicit and implicit information. We apply these embeddings to the prediction of edges in the knowledge graph representing problems of function prediction, finding candidate genes of diseases, protein-protein interactions, or drug target relations, and demonstrate performance that matches and sometimes outperforms traditional approaches based on manually crafted features. Our method can be applied to any biological knowledge graph, and will thereby open up the increasing amount of Semantic Web based knowledge bases in biology to use in machine learning and data analytics.</p><h3>Availability and implementation</h3><p dir="ltr">https://github.com/bio-ontology-research-group/walking-rdf-and-owl</p><h3>Supplementary information</h3><p dir="ltr">Supplementary data are available at Bioinformatics online.</p><h2>Other Information</h2><p dir="ltr">Published in: Bioinformatics<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1093/bioinformatics/btx275" target="_blank">https://dx.doi.org/10.1093/bioinformatics/btx275</a></p>2017-04-25T03:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1093/bioinformatics/btx275https://figshare.com/articles/journal_contribution/Neuro-symbolic_representation_learning_on_biological_knowledge_graphs/27087976CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/270879762017-04-25T03:00:00Z
spellingShingle Neuro-symbolic representation learning on biological knowledge graphs
Mona Alshahrani (3576653)
Biological sciences
Bioinformatics and computational biology
Knowledge graphs
Data integration
Feature learning methods
Symbolic methods
Knowledge representation
Neural networks
Node embeddings
status_str publishedVersion
title Neuro-symbolic representation learning on biological knowledge graphs
title_full Neuro-symbolic representation learning on biological knowledge graphs
title_fullStr Neuro-symbolic representation learning on biological knowledge graphs
title_full_unstemmed Neuro-symbolic representation learning on biological knowledge graphs
title_short Neuro-symbolic representation learning on biological knowledge graphs
title_sort Neuro-symbolic representation learning on biological knowledge graphs
topic Biological sciences
Bioinformatics and computational biology
Knowledge graphs
Data integration
Feature learning methods
Symbolic methods
Knowledge representation
Neural networks
Node embeddings