ABDpred: Prediction of active antimicrobial compounds using supervised machine learning techniques.
Journal
The Indian journal of medical research
ISSN: 0971-5916
Titre abrégé: Indian J Med Res
Pays: India
ID NLM: 0374701
Informations de publication
Date de publication:
01 Jan 2024
01 Jan 2024
Historique:
received:
23
08
2022
medline:
6
3
2024
pubmed:
12
2
2024
entrez:
12
2
2024
Statut:
ppublish
Résumé
Discovery of new antibiotics is the need of the hour to treat infectious diseases. An ever-increasing repertoire of multidrug-resistant pathogens poses an imminent threat to human lives across the globe. However, the low success rate of the existing approaches and technologies for antibiotic discovery remains a major bottleneck. In silico methods like machine learning (ML) deem more promising to meet the above challenges compared with the conventional experimental approaches. The goal of this study was to create ML models that may be used to successfully predict new antimicrobial compounds. In this article, we employed eight different ML algorithms namely, extreme gradient boosting, random forest, gradient boosting classifier, deep neural network, support vector machine, multilayer perceptron, decision tree, and logistic regression. These models were trained using a dataset comprising 312 antibiotic drugs and a negative set of 936 non-antibiotic drugs in a five-fold cross validation approach. The top four ML classifiers (extreme gradient boosting, random forest, gradient boosting classifier and deep neural network) were able to achieve an accuracy of 80 per cent and above during the evaluation of testing and blind datasets. We aggregated the top performing four models through a soft-voting technique to develop an ensemble-based ML method and incorporated it into a freely accessible online prediction server named ABDpred ( http://clinicalmedicinessd.com.in/abdpred/ ).
Sections du résumé
BACKGROUND OBJECTIVES
UNASSIGNED
Discovery of new antibiotics is the need of the hour to treat infectious diseases. An ever-increasing repertoire of multidrug-resistant pathogens poses an imminent threat to human lives across the globe. However, the low success rate of the existing approaches and technologies for antibiotic discovery remains a major bottleneck. In silico methods like machine learning (ML) deem more promising to meet the above challenges compared with the conventional experimental approaches. The goal of this study was to create ML models that may be used to successfully predict new antimicrobial compounds.
METHODS
METHODS
In this article, we employed eight different ML algorithms namely, extreme gradient boosting, random forest, gradient boosting classifier, deep neural network, support vector machine, multilayer perceptron, decision tree, and logistic regression. These models were trained using a dataset comprising 312 antibiotic drugs and a negative set of 936 non-antibiotic drugs in a five-fold cross validation approach.
RESULTS
RESULTS
The top four ML classifiers (extreme gradient boosting, random forest, gradient boosting classifier and deep neural network) were able to achieve an accuracy of 80 per cent and above during the evaluation of testing and blind datasets.
INTERPRETATION CONCLUSIONS
UNASSIGNED
We aggregated the top performing four models through a soft-voting technique to develop an ensemble-based ML method and incorporated it into a freely accessible online prediction server named ABDpred ( http://clinicalmedicinessd.com.in/abdpred/ ).
Identifiants
pubmed: 38345040
doi: 10.4103/ijmr.ijmr_1832_22
pii: 02223309-202401000-00012
doi:
Substances chimiques
Anti-Infective Agents
0
Anti-Bacterial Agents
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
78-90Informations de copyright
Copyright © 2024 Copyright: © 2024 Indian Journal of Medical Research.
Références
J Chem Inf Comput Sci. 2003 Jan-Feb;43(1):228-36
pubmed: 12546557
Drug Discov Today. 2014 May;19(5):680-7
pubmed: 24451293
Nucleic Acids Res. 2011 Jul;39(Web Server issue):W486-91
pubmed: 21576229
Nat Rev Drug Discov. 2013 May;12(5):371-87
pubmed: 23629505
Nat Commun. 2021 Jun 24;12(1):3932
pubmed: 34168145
J Appl Microbiol. 2021 Jan;130(1):40-49
pubmed: 32619323
Adv Drug Deliv Rev. 2001 Mar 1;46(1-3):3-26
pubmed: 11259830
Curr Opin Microbiol. 2019 Oct;51:72-80
pubmed: 31733401
Front Med (Lausanne). 2019 May 24;6:105
pubmed: 31179281
Front Pharmacol. 2019 Aug 27;10:913
pubmed: 31507413
J Antibiot (Tokyo). 2017 Mar;70(3):308-312
pubmed: 27826144
Bioorg Med Chem Lett. 2015 Sep 15;25(18):4024-8
pubmed: 26243367
Front Microbiol. 2018 Nov 30;9:2928
pubmed: 30555448
J Med Chem. 2000 Mar 23;43(6):1143-8
pubmed: 10737746
Nucleic Acids Res. 2021 Jan 8;49(D1):D1388-D1395
pubmed: 33151290
Cell. 2020 Apr 2;181(1):29-45
pubmed: 32197064
Front Microbiol. 2020 Jan 28;10:3051
pubmed: 32063889
Expert Opin Drug Discov. 2020 Oct;15(10):1165-1180
pubmed: 32552005
Sci Rep. 2018 Jun 18;8(1):9267
pubmed: 29915354
Nucleic Acids Res. 2017 Jan 4;45(D1):D945-D954
pubmed: 27899562
Cell. 2020 Feb 20;180(4):688-702.e13
pubmed: 32084340
J Chem Inf Comput Sci. 1998 May-Jun;38(3):445-9
pubmed: 9611784
PLoS One. 2021 Jun 11;16(6):e0249338
pubmed: 34115750
Bioorg Med Chem Lett. 2016 Feb 1;26(3):1011-1015
pubmed: 26733473
Mol Med Rep. 2018 Jul;18(1):763-770
pubmed: 29845192
J Comput Chem. 2011 May;32(7):1466-74
pubmed: 21425294
J Comput Chem. 2009 Jun;30(8):1202-11
pubmed: 18988254
Lancet Infect Dis. 2020 Apr;20(4):e51-e60
pubmed: 32059790