BioKEEN: a library for learning and evaluating biological knowledge graph embeddings

Mehdi Ali; Charles Tapley Hoyt; Daniel Domingo-Fernández; Jens Lehmann; Hajira Jabeen

doi:10.1093/bioinformatics/btz117

BioKEEN: a library for learning and evaluating biological knowledge graph embeddings

Mehdi Ali, Charles Tapley Hoyt, Daniel Domingo-Fernández, Jens Lehmann, Hajira Jabeen

Research output: Contribution to journal › Article › peer-review

19 Scopus citations

Abstract

Knowledge graph embeddings (KGEs) have received significant attention in other domains due to their ability to predict links and create dense representations for graphs’ nodes and edges. However, the software ecosystem for their application to bioinformatics remains limited and inaccessible for users without expertise in programing and machine learning. Therefore, we developed BioKEEN (Biological KnowlEdge EmbeddiNgs) and PyKEEN (Python KnowlEdge EmbeddiNgs) to facilitate their easy use through an interactive command line interface. Finally, we present a case study in which we used a novel biological pathway mapping resource to predict links that represent pathway crosstalks and hierarchies.

Original language	English (US)
Pages (from-to)	3538-3540
Number of pages	3
Journal	Bioinformatics
Volume	35
Issue number	18
DOIs	https://doi.org/10.1093/bioinformatics/btz117
State	Published - Feb 15 2019
Externally published	Yes

Bibliographical note

KAUST Repository Item: Exported on 2021-03-12
Acknowledgements: We thank our partners from the Bio2Vec, MLwin and SimpleML projects for their assistance.

ASJC Scopus subject areas

Biochemistry
Computational Theory and Mathematics
Computational Mathematics
Molecular Biology
Statistics and Probability
Computer Science Applications

Access to Document

10.1093/bioinformatics/btz117

Cite this

@article{9a86b878842d4c6bbf7cdfcd5b2c554d,

title = "BioKEEN: a library for learning and evaluating biological knowledge graph embeddings",

abstract = "Knowledge graph embeddings (KGEs) have received significant attention in other domains due to their ability to predict links and create dense representations for graphs{\textquoteright} nodes and edges. However, the software ecosystem for their application to bioinformatics remains limited and inaccessible for users without expertise in programing and machine learning. Therefore, we developed BioKEEN (Biological KnowlEdge EmbeddiNgs) and PyKEEN (Python KnowlEdge EmbeddiNgs) to facilitate their easy use through an interactive command line interface. Finally, we present a case study in which we used a novel biological pathway mapping resource to predict links that represent pathway crosstalks and hierarchies.",

author = "Mehdi Ali and Hoyt, {Charles Tapley} and Daniel Domingo-Fern{\'a}ndez and Jens Lehmann and Hajira Jabeen",

note = "KAUST Repository Item: Exported on 2021-03-12 Acknowledgements: We thank our partners from the Bio2Vec, MLwin and SimpleML projects for their assistance.",

year = "2019",

month = feb,

day = "15",

doi = "10.1093/bioinformatics/btz117",

language = "English (US)",

volume = "35",

pages = "3538--3540",

journal = "Bioinformatics",

issn = "1367-4803",

publisher = "Oxford University Press",

number = "18",

}

TY - JOUR

T1 - BioKEEN: a library for learning and evaluating biological knowledge graph embeddings

AU - Ali, Mehdi

AU - Hoyt, Charles Tapley

AU - Domingo-Fernández, Daniel

AU - Lehmann, Jens

AU - Jabeen, Hajira

N1 - KAUST Repository Item: Exported on 2021-03-12 Acknowledgements: We thank our partners from the Bio2Vec, MLwin and SimpleML projects for their assistance.

PY - 2019/2/15

Y1 - 2019/2/15

N2 - Knowledge graph embeddings (KGEs) have received significant attention in other domains due to their ability to predict links and create dense representations for graphs’ nodes and edges. However, the software ecosystem for their application to bioinformatics remains limited and inaccessible for users without expertise in programing and machine learning. Therefore, we developed BioKEEN (Biological KnowlEdge EmbeddiNgs) and PyKEEN (Python KnowlEdge EmbeddiNgs) to facilitate their easy use through an interactive command line interface. Finally, we present a case study in which we used a novel biological pathway mapping resource to predict links that represent pathway crosstalks and hierarchies.

AB - Knowledge graph embeddings (KGEs) have received significant attention in other domains due to their ability to predict links and create dense representations for graphs’ nodes and edges. However, the software ecosystem for their application to bioinformatics remains limited and inaccessible for users without expertise in programing and machine learning. Therefore, we developed BioKEEN (Biological KnowlEdge EmbeddiNgs) and PyKEEN (Python KnowlEdge EmbeddiNgs) to facilitate their easy use through an interactive command line interface. Finally, we present a case study in which we used a novel biological pathway mapping resource to predict links that represent pathway crosstalks and hierarchies.

UR - http://hdl.handle.net/10754/668066

UR - https://academic.oup.com/bioinformatics/article/35/18/3538/5320556

UR - http://www.scopus.com/inward/record.url?scp=85072307229&partnerID=8YFLogxK

U2 - 10.1093/bioinformatics/btz117

DO - 10.1093/bioinformatics/btz117

M3 - Article

SN - 1367-4803

VL - 35

SP - 3538

EP - 3540

JO - Bioinformatics

JF - Bioinformatics

IS - 18

ER -

BioKEEN: a library for learning and evaluating biological knowledge graph embeddings

Abstract

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this