Cargando…

A Novel Deep Neural Network Technique for Drug–Target Interaction

Drug discovery (DD) is a time-consuming and expensive process. Thus, the industry employs strategies such as drug repositioning and drug repurposing, which allows the application of already approved drugs to treat a different disease, as occurred in the first months of 2020, during the COVID-19 pand...

Descripción completa

Detalles Bibliográficos
Autores principales: de Souza, Jackson G., Fernandes, Marcelo A. C., de Melo Barbosa, Raquel
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8954728/
https://www.ncbi.nlm.nih.gov/pubmed/35336000
http://dx.doi.org/10.3390/pharmaceutics14030625
_version_ 1784676165121736704
author de Souza, Jackson G.
Fernandes, Marcelo A. C.
de Melo Barbosa, Raquel
author_facet de Souza, Jackson G.
Fernandes, Marcelo A. C.
de Melo Barbosa, Raquel
author_sort de Souza, Jackson G.
collection PubMed
description Drug discovery (DD) is a time-consuming and expensive process. Thus, the industry employs strategies such as drug repositioning and drug repurposing, which allows the application of already approved drugs to treat a different disease, as occurred in the first months of 2020, during the COVID-19 pandemic. The prediction of drug–target interactions is an essential part of the DD process because it can accelerate it and reduce the required costs. DTI prediction performed in silico have used approaches based on molecular docking simulations, including similarity-based and network- and graph-based ones. This paper presents MPS2IT-DTI, a DTI prediction model obtained from research conducted in the following steps: the definition of a new method for encoding molecule and protein sequences onto images; the definition of a deep-learning approach based on a convolutional neural network in order to create a new method for DTI prediction. Training results conducted with the Davis and KIBA datasets show that MPS2IT-DTI is viable compared to other state-of-the-art (SOTA) approaches in terms of performance and complexity of the neural network model. With the Davis dataset, we obtained 0.876 for the concordance index and 0.276 for the MSE; with the KIBA dataset, we obtained 0.836 and 0.226 for the concordance index and the MSE, respectively. Moreover, the MPS2IT-DTI model represents molecule and protein sequences as images, instead of treating them as an NLP task, and as such, does not employ an embedding layer, which is present in other models.
format Online
Article
Text
id pubmed-8954728
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-89547282022-03-26 A Novel Deep Neural Network Technique for Drug–Target Interaction de Souza, Jackson G. Fernandes, Marcelo A. C. de Melo Barbosa, Raquel Pharmaceutics Article Drug discovery (DD) is a time-consuming and expensive process. Thus, the industry employs strategies such as drug repositioning and drug repurposing, which allows the application of already approved drugs to treat a different disease, as occurred in the first months of 2020, during the COVID-19 pandemic. The prediction of drug–target interactions is an essential part of the DD process because it can accelerate it and reduce the required costs. DTI prediction performed in silico have used approaches based on molecular docking simulations, including similarity-based and network- and graph-based ones. This paper presents MPS2IT-DTI, a DTI prediction model obtained from research conducted in the following steps: the definition of a new method for encoding molecule and protein sequences onto images; the definition of a deep-learning approach based on a convolutional neural network in order to create a new method for DTI prediction. Training results conducted with the Davis and KIBA datasets show that MPS2IT-DTI is viable compared to other state-of-the-art (SOTA) approaches in terms of performance and complexity of the neural network model. With the Davis dataset, we obtained 0.876 for the concordance index and 0.276 for the MSE; with the KIBA dataset, we obtained 0.836 and 0.226 for the concordance index and the MSE, respectively. Moreover, the MPS2IT-DTI model represents molecule and protein sequences as images, instead of treating them as an NLP task, and as such, does not employ an embedding layer, which is present in other models. MDPI 2022-03-11 /pmc/articles/PMC8954728/ /pubmed/35336000 http://dx.doi.org/10.3390/pharmaceutics14030625 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
de Souza, Jackson G.
Fernandes, Marcelo A. C.
de Melo Barbosa, Raquel
A Novel Deep Neural Network Technique for Drug–Target Interaction
title A Novel Deep Neural Network Technique for Drug–Target Interaction
title_full A Novel Deep Neural Network Technique for Drug–Target Interaction
title_fullStr A Novel Deep Neural Network Technique for Drug–Target Interaction
title_full_unstemmed A Novel Deep Neural Network Technique for Drug–Target Interaction
title_short A Novel Deep Neural Network Technique for Drug–Target Interaction
title_sort novel deep neural network technique for drug–target interaction
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8954728/
https://www.ncbi.nlm.nih.gov/pubmed/35336000
http://dx.doi.org/10.3390/pharmaceutics14030625
work_keys_str_mv AT desouzajacksong anoveldeepneuralnetworktechniquefordrugtargetinteraction
AT fernandesmarceloac anoveldeepneuralnetworktechniquefordrugtargetinteraction
AT demelobarbosaraquel anoveldeepneuralnetworktechniquefordrugtargetinteraction
AT desouzajacksong noveldeepneuralnetworktechniquefordrugtargetinteraction
AT fernandesmarceloac noveldeepneuralnetworktechniquefordrugtargetinteraction
AT demelobarbosaraquel noveldeepneuralnetworktechniquefordrugtargetinteraction