No Cover Image

Journal article 68 views 22 downloads

SLGNN: synthetic lethality prediction in human cancers based on factor-aware knowledge graph neural network

Yan Zhu, Yuhuan Zhou, Yang Liu Orcid Logo, Xuan Wang, Junyi Li Orcid Logo

Bioinformatics, Volume: 39, Issue: 2

Swansea University Author: Yang Liu Orcid Logo

  • 67389.VoR.pdf

    PDF | Version of Record

    Copyright: The Authors 2023. This is an Open Access article distributed under the terms of the Creative Commons Attribution License.

    Download (1.9MB)

Abstract

MotivationSynthetic lethality (SL) is a form of genetic interaction that can selectively kill cancer cells without damaging normal cells. Exploiting this mechanism is gaining popularity in the field of targeted cancer therapy and anticancer drug development. Due to the limitations of identifying SL...

Full description

Published in: Bioinformatics
ISSN: 1367-4811
Published: Oxford University Press (OUP) 2023
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa67389
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: MotivationSynthetic lethality (SL) is a form of genetic interaction that can selectively kill cancer cells without damaging normal cells. Exploiting this mechanism is gaining popularity in the field of targeted cancer therapy and anticancer drug development. Due to the limitations of identifying SL interactions from laboratory experiments, an increasing number of research groups are devising computational prediction methods to guide the discovery of potential SL pairs. Although existing methods have attempted to capture the underlying mechanisms of SL interactions, methods that have a deeper understanding of and attempt to explain SL mechanisms still need to be developed.ResultsIn this work, we propose a novel SL prediction method, SLGNN. This method is based on the following assumption: SL interactions are caused by different molecular events or biological processes, which we define as SL-related factors that lead to SL interactions. SLGNN, apart from identifying SL interaction pairs, also models the preferences of genes for different SL-related factors, making the results more interpretable for biologists and clinicians. SLGNN consists of three steps: first, we model the combinations of relationships in the gene-related knowledge graph as the SL-related factors. Next, we derive initial embeddings of genes through an explicit message aggregation process of the knowledge graph. Finally, we derive the final gene embeddings through an SL graph, constructed using known SL gene pairs, utilizing factor-based message aggregation. At this stage, a supervised end-to-end training model is used for SL interaction prediction. Based on experimental results, the proposed SLGNN model outperforms all current state-of-the-art SL prediction methods and provides better interpretability.
College: Faculty of Science and Engineering
Funders: This work was supported by the grants from the National Key R&D Program of China [2021YFA0910700]; Shenzhen Science and Technology University Stable Support Program [GXWD20201230155427003-20200821222112001]; Shenzhen Science and Technology Program [JCYJ20200109113201726]; Guangdong Basic and Applied Basic Research Foundation [2021A1515012461, 2021A1515220115]; and Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies [2022B1212010005].
Issue: 2