Complex graph neural networks for medication interaction verification

Gustavo Westarb; Stefano Frizzo Stefenon; Aurélio Faustino Hoppe; Andreza Sartori; Anne Carolina Rodrigues Klaar; Valderi Reis Quietinho Leithardt

doi:10.3233/JIFS-223656

Complex graph neural networks for medication interaction verification

Gustavo Westarb, Stefano Frizzo Stefenon, Aurélio Faustino Hoppe, Andreza Sartori, Anne Carolina Rodrigues Klaar, Valderi Reis Quietinho Leithardt

COPELABS - Centro de Investigação em Computação Centrada nas Pessoas e Cognição

Resultado de pesquisa › revisão de pares

7 Citações (Scopus)

Resumo

This paper presents the development and application of graph neural networks to verify drug interactions, consisting of drug-protein networks. For this, the DrugBank databases were used, creating four complex networks of interactions: target proteins, transport proteins, carrier proteins, and enzymes. The Louvain and Girvan-Newman community detection algorithms were used to establish communities and validate the interactions between them. Positive results were obtained when checking the interactions of two sets of drugs for disease treatments: diabetes and anxiety; diabetes and antibiotics. There were found 371 interactions by the Girvan-Newman algorithm and 58 interactions via Louvain.

Idioma original	Inglês
Páginas (de-até)	10383-10395
Número de páginas	13
Revista	Journal of Intelligent and Fuzzy Systems
Volume	44
Número de emissão	6
DOIs	https://doi.org/10.3233/JIFS-223656
Estado da publicação	Publicadas - 1 jun. 2023

Nota bibliográfica

Publisher Copyright:
© 2023-The authors. Published by IOS Press.

Financiamento

Financiadoras/-es	Número do financiador
VALORIZA-Research Center for Endogenous Resource Valorization	UIDB/04111/2020, UIDB/05064/2020
Fundação para a Ciência e a Tecnologia

ODS da ONU

Este resultado contribui para o(s) seguinte(s) Objetivo(s) de Desenvolvimento Sustentável

Acesso ao documento

10.3233/JIFS-223656

Outros arquivos e links

Link to publication in Scopus

Citar isto

@article{031a5b2311e244bab4d0dafc612473cd,

title = "Complex graph neural networks for medication interaction verification",

abstract = "This paper presents the development and application of graph neural networks to verify drug interactions, consisting of drug-protein networks. For this, the DrugBank databases were used, creating four complex networks of interactions: target proteins, transport proteins, carrier proteins, and enzymes. The Louvain and Girvan-Newman community detection algorithms were used to establish communities and validate the interactions between them. Positive results were obtained when checking the interactions of two sets of drugs for disease treatments: diabetes and anxiety; diabetes and antibiotics. There were found 371 interactions by the Girvan-Newman algorithm and 58 interactions via Louvain.",

keywords = "Drug interaction, communities detection, graph neural network",

author = "Gustavo Westarb and Stefenon, {Stefano Frizzo} and Hoppe, {Aur{\'e}lio Faustino} and Andreza Sartori and Klaar, {Anne Carolina Rodrigues} and Leithardt, {Valderi Reis Quietinho}",

note = "Publisher Copyright: {\textcopyright} 2023-The authors. Published by IOS Press.",

year = "2023",

month = jun,

day = "1",

doi = "10.3233/JIFS-223656",

language = "English",

volume = "44",

pages = "10383--10395",

journal = "Journal of Intelligent and Fuzzy Systems",

issn = "1064-1246",

publisher = "Sage Publications",

number = "6",

}

TY - JOUR

T1 - Complex graph neural networks for medication interaction verification

AU - Westarb, Gustavo

AU - Stefenon, Stefano Frizzo

AU - Hoppe, Aurélio Faustino

AU - Sartori, Andreza

AU - Klaar, Anne Carolina Rodrigues

AU - Leithardt, Valderi Reis Quietinho

PY - 2023/6/1

Y1 - 2023/6/1

N2 - This paper presents the development and application of graph neural networks to verify drug interactions, consisting of drug-protein networks. For this, the DrugBank databases were used, creating four complex networks of interactions: target proteins, transport proteins, carrier proteins, and enzymes. The Louvain and Girvan-Newman community detection algorithms were used to establish communities and validate the interactions between them. Positive results were obtained when checking the interactions of two sets of drugs for disease treatments: diabetes and anxiety; diabetes and antibiotics. There were found 371 interactions by the Girvan-Newman algorithm and 58 interactions via Louvain.

AB - This paper presents the development and application of graph neural networks to verify drug interactions, consisting of drug-protein networks. For this, the DrugBank databases were used, creating four complex networks of interactions: target proteins, transport proteins, carrier proteins, and enzymes. The Louvain and Girvan-Newman community detection algorithms were used to establish communities and validate the interactions between them. Positive results were obtained when checking the interactions of two sets of drugs for disease treatments: diabetes and anxiety; diabetes and antibiotics. There were found 371 interactions by the Girvan-Newman algorithm and 58 interactions via Louvain.

KW - Drug interaction

KW - communities detection

KW - graph neural network

UR - http://www.scopus.com/inward/record.url?scp=85165017606&partnerID=8YFLogxK

U2 - 10.3233/JIFS-223656

DO - 10.3233/JIFS-223656

M3 - Article

AN - SCOPUS:85165017606

SN - 1064-1246

VL - 44

SP - 10383

EP - 10395

JO - Journal of Intelligent and Fuzzy Systems

JF - Journal of Intelligent and Fuzzy Systems

IS - 6

ER -

Complex graph neural networks for medication interaction verification

Resumo

Nota bibliográfica

Financiamento

ODS da ONU

Acesso ao documento

Outros arquivos e links

Impressão digital

Citar isto