Predicting missing annotations in Gene Ontology with Knowledge Graph Embeddings and True Path Rule

Özge Erten; Shervin Mehryar; Remzi Çelebi; Christopher Brewster

Predicting missing annotations in Gene Ontology with Knowledge Graph Embeddings and True Path Rule

Özge Erten^*, Shervin Mehryar, Remzi Çelebi, Christopher Brewster

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

25 Downloads (Pure)

Abstract

Gene Ontology (GO) and its Annotations (GOA) provide a controlled and evolving vocabulary for gene products and gene functions widely used in molecular biology. GO & GOA are updated and maintained both automatically from biological publications and manually by curators. These knowledge bases however are often incomplete for two reasons: 1) Research in biological domain itself is still ongoing; 2) The amount of experimental evidence might not be yet sufficient to validate annotations. In this paper, we address the gap in evidence between gene products and their annotations by making link predictions using Knowledge Graph Embedding (KGE) methods. Through the application of the True Path Rule (TPR) in the training stage of KGE, we were able to improve the performance of traditional KGE methods. We report two experimental scenarios with GO and GO Chicken Annotation datasets to show the contribution of embedding TPR to prediction accuracy.

Original language	English
Title of host publication	Semantic Web Applications and Tools for Health Care and Life Sciences 2023
Pages	82-86
Number of pages	5
Volume	3415
Publication status	Published - 1 Jan 2023
Event	14th International Conference on Semantic Web Applications and Tools for Health Care and Life Sciences - Basel, Switzerland Duration: 13 Feb 2023 → 16 Feb 2023 Conference number: 14

Publication series

Series	CEUR Workshop Proceedings
ISSN	1613-0073

Conference

Conference	14th International Conference on Semantic Web Applications and Tools for Health Care and Life Sciences
Abbreviated title	SWAT4HCLS 2023
Country/Territory	Switzerland
City	Basel
Period	13/02/23 → 16/02/23

Keywords

Knowledge graph embeddings
Link prediction
Predicting Gene Ontology Annotations
True path rule

Access to Document

Full TextFinal published version, 990 KBLicence: Taverne

https://ceur-ws.org/Vol-3415/paper-9.pdf

Cite this

@inproceedings{0b9b4b68b88040dcb8e4fa1af99b7337,

title = "Predicting missing annotations in Gene Ontology with Knowledge Graph Embeddings and True Path Rule",

abstract = "Gene Ontology (GO) and its Annotations (GOA) provide a controlled and evolving vocabulary for gene products and gene functions widely used in molecular biology. GO & GOA are updated and maintained both automatically from biological publications and manually by curators. These knowledge bases however are often incomplete for two reasons: 1) Research in biological domain itself is still ongoing; 2) The amount of experimental evidence might not be yet sufficient to validate annotations. In this paper, we address the gap in evidence between gene products and their annotations by making link predictions using Knowledge Graph Embedding (KGE) methods. Through the application of the True Path Rule (TPR) in the training stage of KGE, we were able to improve the performance of traditional KGE methods. We report two experimental scenarios with GO and GO Chicken Annotation datasets to show the contribution of embedding TPR to prediction accuracy.",

keywords = "Knowledge graph embeddings, Link prediction, Predicting Gene Ontology Annotations, True path rule",

author = "{\"O}zge Erten and Shervin Mehryar and Remzi {\c C}elebi and Christopher Brewster",

note = "Publisher Copyright: {\textcopyright} 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).; 14th International Conference on Semantic Web Applications and Tools for Health Care and Life Sciences, SWAT4HCLS 2023 ; Conference date: 13-02-2023 Through 16-02-2023",

year = "2023",

month = jan,

day = "1",

language = "English",

volume = "3415",

series = "CEUR Workshop Proceedings",

publisher = "Rheinisch-Westfaelische Technische Hochschule Aachen * Lehrstuhl Informatik V",

pages = "82--86",

booktitle = "Semantic Web Applications and Tools for Health Care and Life Sciences 2023",

}

Erten, Ö , Mehryar, S , Çelebi, R & Brewster, C 2023, Predicting missing annotations in Gene Ontology with Knowledge Graph Embeddings and True Path Rule. in Semantic Web Applications and Tools for Health Care and Life Sciences 2023. vol. 3415, CEUR Workshop Proceedings, pp. 82-86, 14th International Conference on Semantic Web Applications and Tools for Health Care and Life Sciences, Basel, Switzerland, 13/02/23. <https://ceur-ws.org/Vol-3415/paper-9.pdf>

Predicting missing annotations in Gene Ontology with Knowledge Graph Embeddings and True Path Rule. / Erten, Özge ; Mehryar, Shervin ; Çelebi, Remzi et al.
Semantic Web Applications and Tools for Health Care and Life Sciences 2023. Vol. 3415 2023. p. 82-86 (CEUR Workshop Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

TY - GEN

T1 - Predicting missing annotations in Gene Ontology with Knowledge Graph Embeddings and True Path Rule

AU - Erten, Özge

AU - Mehryar, Shervin

AU - Çelebi, Remzi

AU - Brewster, Christopher

N1 - Conference code: 14

PY - 2023/1/1

Y1 - 2023/1/1

N2 - Gene Ontology (GO) and its Annotations (GOA) provide a controlled and evolving vocabulary for gene products and gene functions widely used in molecular biology. GO & GOA are updated and maintained both automatically from biological publications and manually by curators. These knowledge bases however are often incomplete for two reasons: 1) Research in biological domain itself is still ongoing; 2) The amount of experimental evidence might not be yet sufficient to validate annotations. In this paper, we address the gap in evidence between gene products and their annotations by making link predictions using Knowledge Graph Embedding (KGE) methods. Through the application of the True Path Rule (TPR) in the training stage of KGE, we were able to improve the performance of traditional KGE methods. We report two experimental scenarios with GO and GO Chicken Annotation datasets to show the contribution of embedding TPR to prediction accuracy.

AB - Gene Ontology (GO) and its Annotations (GOA) provide a controlled and evolving vocabulary for gene products and gene functions widely used in molecular biology. GO & GOA are updated and maintained both automatically from biological publications and manually by curators. These knowledge bases however are often incomplete for two reasons: 1) Research in biological domain itself is still ongoing; 2) The amount of experimental evidence might not be yet sufficient to validate annotations. In this paper, we address the gap in evidence between gene products and their annotations by making link predictions using Knowledge Graph Embedding (KGE) methods. Through the application of the True Path Rule (TPR) in the training stage of KGE, we were able to improve the performance of traditional KGE methods. We report two experimental scenarios with GO and GO Chicken Annotation datasets to show the contribution of embedding TPR to prediction accuracy.

KW - Knowledge graph embeddings

KW - Link prediction

KW - Predicting Gene Ontology Annotations

KW - True path rule

M3 - Conference article in proceeding

VL - 3415

T3 - CEUR Workshop Proceedings

SP - 82

EP - 86

BT - Semantic Web Applications and Tools for Health Care and Life Sciences 2023

T2 - 14th International Conference on Semantic Web Applications and Tools for Health Care and Life Sciences

Y2 - 13 February 2023 through 16 February 2023

ER -