Biological applications of knowledge graph embedding models

J 2021

Biological applications of knowledge graph embedding models

MOHAMED, Sameh K, Ayah NOUNU a Vít NOVÁČEK

Základní údaje

Originální název

Biological applications of knowledge graph embedding models

Název česky

Biological applications of knowledge graph embedding models

Autoři

MOHAMED, Sameh K, Ayah NOUNU a Vít NOVÁČEK (203 Česká republika, garant, domácí)

Vydání

Briefings in Bioinformatics, Oxford (UK), Oxford University Press, 2021, 1467-5463

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Velká Británie a Severní Irsko

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL

Impakt faktor

Impact factor: 13.994

Organizační jednotka

Fakulta informatiky

DOI

http://dx.doi.org/10.1093/bib/bbaa012

UT WoS

000642298000084

Klíčová slova anglicky

biomedical knowledge graphs; knowledge graph embeddings; tensor factorization; link prediction; drug target interactions; polypharmacy side effects

Štítky

Artificial Intelligence, data integration, knowledge extraction, knowledge graphs, knowledge integration, relational machine learning

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 8. 11. 2024 15:54, doc. Mgr. Bc. Vít Nováček, PhD

Anotace

V originále

Complex biological systems are traditionally modelled as graphs of interconnected biological entities. These graphs, i.e. biological knowledge graphs, are then processed using graph exploratory approaches to perform different types of analytical and predictive tasks. Despite the high predictive accuracy of these approaches, they have limited scalability due to their dependency on time-consuming path exploratory procedures. In recent years, owing to the rapid advances of computational technologies, new approaches for modelling graphs and mining them with high accuracy and scalability have emerged. These approaches, i.e. knowledge graph embedding (KGE) models, operate by learning low-rank vector representations of graph nodes and edges that preserve the graph’s inherent structure. These approaches were used to analyse knowledge graphs from different domains where they showed superior performance and accuracy compared to previous graph exploratory approaches. In this work, we study this class of models in the context of biological knowledge graphs and their different applications. We then show how KGE models can be a natural fit for representing complex biological knowledge modelled as graphs. We also discuss their predictive and analytical capabilities in different biology applications. In this regard, we present two example case studies that demonstrate the capabilities of KGE models: prediction of drug–target interactions and polypharmacy side effects. Finally, we analyse different practical considerations for KGEs, and we discuss possible opportunities and challenges related to adopting them for modelling biological systems.

Citovat

MOHAMED, Sameh K, Ayah NOUNU a Vít NOVÁČEK. Biological applications of knowledge graph embedding models. Briefings in Bioinformatics. Oxford (UK): Oxford University Press, 2021, roč. 22, č. 2, s. 1679-1693. ISSN 1467-5463. Dostupné z: https://dx.doi.org/10.1093/bib/bbaa012.

@article{2326179,
   author = {Mohamed, Sameh K and Nounu, Ayah and Nováček, Vít},
   article_location = {Oxford (UK)},
   article_number = {2},
   doi = {http://dx.doi.org/10.1093/bib/bbaa012},
   keywords = {biomedical knowledge graphs; knowledge graph embeddings; tensor factorization; link prediction; drug target interactions; polypharmacy side effects},
   language = {eng},
   issn = {1467-5463},
   journal = {Briefings in Bioinformatics},
   title = {Biological applications of knowledge graph embedding models},
   url = {https://academic.oup.com/bib/article/22/2/1679/5739186},
   volume = {22},
   year = {2021}
}

TY  - JOUR
ID  - 2326179
AU  - Mohamed, Sameh K - Nounu, Ayah - Nováček, Vít
PY  - 2021
TI  - Biological applications of knowledge graph embedding models
JF  - Briefings in Bioinformatics
VL  - 22
IS  - 2
SP  - 1679-1693
EP  - 1679-1693
PB  - Oxford University Press
SN  - 14675463
KW  - biomedical knowledge graphs
KW  - knowledge graph embeddings
KW  - tensor factorization
KW  - link prediction
KW  - drug target interactions
KW  - polypharmacy side effects
UR  - https://academic.oup.com/bib/article/22/2/1679/5739186
N2  - Complex biological systems are traditionally modelled as graphs of interconnected biological entities. These graphs, i.e. biological knowledge graphs, are then processed using graph exploratory approaches to perform different types of analytical and predictive tasks. Despite the high predictive accuracy of these approaches, they have limited scalability due to their dependency on time-consuming path exploratory procedures. In recent years, owing to the rapid advances of computational technologies, new approaches for modelling graphs and mining them with high accuracy and scalability have emerged. These approaches, i.e. knowledge graph embedding (KGE) models, operate by learning low-rank vector representations of graph nodes and edges that preserve the graph’s inherent structure. These approaches were used to analyse knowledge graphs from different domains where they showed superior performance and accuracy compared to previous graph exploratory approaches. In this work, we study this class of models in the context of biological knowledge graphs and their different applications. We then show how KGE models can be a natural fit for representing complex biological knowledge modelled as graphs. We also discuss their predictive and analytical capabilities in different biology applications. In this regard, we present two example case studies that demonstrate the capabilities of KGE models: prediction of drug–target interactions and polypharmacy side effects. Finally, we analyse different practical considerations for KGEs, and we discuss possible opportunities and challenges related to adopting them for modelling biological systems.
ER  -

MOHAMED, Sameh K, Ayah NOUNU a Vít NOVÁČEK. Biological applications of knowledge graph embedding models. \textit{Briefings in Bioinformatics}. Oxford (UK): Oxford University Press, 2021, roč.~22, č.~2, s.~1679-1693. ISSN~1467-5463. Dostupné z: https://dx.doi.org/10.1093/bib/bbaa012.

Podrobný výpis o publikaci