Deep Learning Algorithms Achieved Satisfactory Predictions When Trained on a Novel Collection of Anticoronavirus Molecules
Drug discovery and repurposing against COVID-19 is a highly relevant topic with huge efforts dedicated to delivering novel therapeutics targeting SARS-CoV-2. In this context, computer-aided drug discovery is of interest in orienting the early high throughput screenings and in optimizing the hit iden...
Guardado en:
Autores principales: | , , , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Frontiers Media S.A.
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/7bc2c5a443dc4da8b6177a50cec908ee |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:7bc2c5a443dc4da8b6177a50cec908ee |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:7bc2c5a443dc4da8b6177a50cec908ee2021-12-01T13:46:45ZDeep Learning Algorithms Achieved Satisfactory Predictions When Trained on a Novel Collection of Anticoronavirus Molecules1664-802110.3389/fgene.2021.744170https://doaj.org/article/7bc2c5a443dc4da8b6177a50cec908ee2021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fgene.2021.744170/fullhttps://doaj.org/toc/1664-8021Drug discovery and repurposing against COVID-19 is a highly relevant topic with huge efforts dedicated to delivering novel therapeutics targeting SARS-CoV-2. In this context, computer-aided drug discovery is of interest in orienting the early high throughput screenings and in optimizing the hit identification rate. We herein propose a pipeline for Ligand-Based Drug Discovery (LBDD) against SARS-CoV-2. Through an extensive search of the literature and multiple steps of filtering, we integrated information on 2,610 molecules having a validated effect against SARS-CoV and/or SARS-CoV-2. The chemical structures of these molecules were encoded through multiple systems to be readily useful as input to conventional machine learning (ML) algorithms or deep learning (DL) architectures. We assessed the performances of seven ML algorithms and four DL algorithms in achieving molecule classification into two classes: active and inactive. The Random Forests (RF), Graph Convolutional Network (GCN), and Directed Acyclic Graph (DAG) models achieved the best performances. These models were further optimized through hyperparameter tuning and achieved ROC-AUC scores through cross-validation of 85, 83, and 79% for RF, GCN, and DAG models, respectively. An external validation step on the FDA-approved drugs collection revealed a superior potential of DL algorithms to achieve drug repurposing against SARS-CoV-2 based on the dataset herein presented. Namely, GCN and DAG achieved more than 50% of the true positive rate assessed on the confirmed hits of a PubChem bioassay.Emna Harigua-SouiaiMohamed Mahmoud HeinhaneYosser Zina AbdelkrimOussama SouiaiInes Abdeljaoued-TejInes Abdeljaoued-TejIkram GuizaniFrontiers Media S.A.articledeep learningartificial neural networkSARS-CoV-2machine learninggraph convoluational networksdrug discovery and repurposingGeneticsQH426-470ENFrontiers in Genetics, Vol 12 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
deep learning artificial neural network SARS-CoV-2 machine learning graph convoluational networks drug discovery and repurposing Genetics QH426-470 |
spellingShingle |
deep learning artificial neural network SARS-CoV-2 machine learning graph convoluational networks drug discovery and repurposing Genetics QH426-470 Emna Harigua-Souiai Mohamed Mahmoud Heinhane Yosser Zina Abdelkrim Oussama Souiai Ines Abdeljaoued-Tej Ines Abdeljaoued-Tej Ikram Guizani Deep Learning Algorithms Achieved Satisfactory Predictions When Trained on a Novel Collection of Anticoronavirus Molecules |
description |
Drug discovery and repurposing against COVID-19 is a highly relevant topic with huge efforts dedicated to delivering novel therapeutics targeting SARS-CoV-2. In this context, computer-aided drug discovery is of interest in orienting the early high throughput screenings and in optimizing the hit identification rate. We herein propose a pipeline for Ligand-Based Drug Discovery (LBDD) against SARS-CoV-2. Through an extensive search of the literature and multiple steps of filtering, we integrated information on 2,610 molecules having a validated effect against SARS-CoV and/or SARS-CoV-2. The chemical structures of these molecules were encoded through multiple systems to be readily useful as input to conventional machine learning (ML) algorithms or deep learning (DL) architectures. We assessed the performances of seven ML algorithms and four DL algorithms in achieving molecule classification into two classes: active and inactive. The Random Forests (RF), Graph Convolutional Network (GCN), and Directed Acyclic Graph (DAG) models achieved the best performances. These models were further optimized through hyperparameter tuning and achieved ROC-AUC scores through cross-validation of 85, 83, and 79% for RF, GCN, and DAG models, respectively. An external validation step on the FDA-approved drugs collection revealed a superior potential of DL algorithms to achieve drug repurposing against SARS-CoV-2 based on the dataset herein presented. Namely, GCN and DAG achieved more than 50% of the true positive rate assessed on the confirmed hits of a PubChem bioassay. |
format |
article |
author |
Emna Harigua-Souiai Mohamed Mahmoud Heinhane Yosser Zina Abdelkrim Oussama Souiai Ines Abdeljaoued-Tej Ines Abdeljaoued-Tej Ikram Guizani |
author_facet |
Emna Harigua-Souiai Mohamed Mahmoud Heinhane Yosser Zina Abdelkrim Oussama Souiai Ines Abdeljaoued-Tej Ines Abdeljaoued-Tej Ikram Guizani |
author_sort |
Emna Harigua-Souiai |
title |
Deep Learning Algorithms Achieved Satisfactory Predictions When Trained on a Novel Collection of Anticoronavirus Molecules |
title_short |
Deep Learning Algorithms Achieved Satisfactory Predictions When Trained on a Novel Collection of Anticoronavirus Molecules |
title_full |
Deep Learning Algorithms Achieved Satisfactory Predictions When Trained on a Novel Collection of Anticoronavirus Molecules |
title_fullStr |
Deep Learning Algorithms Achieved Satisfactory Predictions When Trained on a Novel Collection of Anticoronavirus Molecules |
title_full_unstemmed |
Deep Learning Algorithms Achieved Satisfactory Predictions When Trained on a Novel Collection of Anticoronavirus Molecules |
title_sort |
deep learning algorithms achieved satisfactory predictions when trained on a novel collection of anticoronavirus molecules |
publisher |
Frontiers Media S.A. |
publishDate |
2021 |
url |
https://doaj.org/article/7bc2c5a443dc4da8b6177a50cec908ee |
work_keys_str_mv |
AT emnahariguasouiai deeplearningalgorithmsachievedsatisfactorypredictionswhentrainedonanovelcollectionofanticoronavirusmolecules AT mohamedmahmoudheinhane deeplearningalgorithmsachievedsatisfactorypredictionswhentrainedonanovelcollectionofanticoronavirusmolecules AT yosserzinaabdelkrim deeplearningalgorithmsachievedsatisfactorypredictionswhentrainedonanovelcollectionofanticoronavirusmolecules AT oussamasouiai deeplearningalgorithmsachievedsatisfactorypredictionswhentrainedonanovelcollectionofanticoronavirusmolecules AT inesabdeljaouedtej deeplearningalgorithmsachievedsatisfactorypredictionswhentrainedonanovelcollectionofanticoronavirusmolecules AT inesabdeljaouedtej deeplearningalgorithmsachievedsatisfactorypredictionswhentrainedonanovelcollectionofanticoronavirusmolecules AT ikramguizani deeplearningalgorithmsachievedsatisfactorypredictionswhentrainedonanovelcollectionofanticoronavirusmolecules |
_version_ |
1718405126218055680 |