Publication

QSAR modeling of antitubercular activity of diverse organic compounds

View document

Bibliographic Details
Summary:Tuberculosis (TB) is a worldwide infectious disease that has shown over time extremely high mortality levels. The urgent need to develop new antitubercular drugs is due to the increasing rate of appearance of multi-drug resistant strains to the commonly used drugs, and the longer durations of therapy and recovery, particularly in immuno-compromised patients. The major goal of the present study is the exploration of data from different families of compounds through the use of a variety of machine learning techniques so that robust QSAR-based models can be developed to further guide in the quest for new potent anti-TB compounds. Eight QSAR models were built using various types of descriptors (from ADRIANA.Code and Dragon software) with two publicly available structurally diverse data sets, including recent data deposited in PubChem. QSAR methodologies used Random Forests and Associative Neural Networks. Predictions for the external evaluation sets obtained accuracies in the range of 0.76-0.88 (for active/inactive classifications) and Q(2)=0.66-0.89 for regressions. Models developed in this study can be used to estimate the anti-TB activity of drug candidates at early stages of drug development (C) 2011 Elsevier B.V. All rights reserved.
Main Authors:Kovalishyn, Vasyl
Other Authors:Aires-de-Sousa, Joao; Ventura, Cristina; Elvas Leitao, Ruben; Martins, Filomena
Subject:QSAR Neural Networks Random Forests Antitubercular Drug Design Neural-Network Antimycobacterial Activity Benzimidazole Derivatives Variable Selection In-Vitro Mycobacterium-Tuberculosis Isoniazid Derivatives Agents Inhibitor Design
Year:2011
Country:Portugal
Document type:article
Access type:open access
Associated institution:Instituto Politécnico de Lisboa
Language:English
Origin:Repositório Científico do Instituto Politécnico de Lisboa
_version_ 1863852877356728320
author Kovalishyn, Vasyl
author2 Aires-de-Sousa, Joao
Ventura, Cristina
Elvas Leitao, Ruben
Martins, Filomena
author2_role author
author
author
author
author_facet Kovalishyn, Vasyl
Aires-de-Sousa, Joao
Ventura, Cristina
Elvas Leitao, Ruben
Martins, Filomena
author_role author
contributor_name_str_mv RCIPL
country_str PT
creators_json_str [{\"Person.name\":\"Kovalishyn, Vasyl\",\"Person.identifier.orcid\":\"0000-0002-9352-7332\"},{\"Person.name\":\"Aires-de-Sousa, Joao\",\"Person.identifier.orcid\":\"0000-0002-5887-2966\"},{\"Person.name\":\"Ventura, Cristina\"},{\"Person.name\":\"Elvas Leitao, Ruben\",\"Person.identifier.orcid\":\"0000-0002-2196-412X\"},{\"Person.name\":\"Martins, Filomena\"}]
datacite.contributors.contributor.contributorName.fl_str_mv RCIPL
datacite.creators.creator.creatorName.fl_str_mv Kovalishyn, Vasyl
Aires-de-Sousa, Joao
Ventura, Cristina
Elvas Leitao, Ruben
Martins, Filomena
datacite.date.Accepted.fl_str_mv 2011-05-01T00:00:00Z
datacite.date.available.fl_str_mv 2013-02-16T17:50:57Z
datacite.date.embargoed.fl_str_mv 2013-02-16T17:50:57Z
datacite.rights.fl_str_mv http://purl.org/coar/access_right/c_abf2
datacite.subjects.subject.fl_str_mv QSAR
Neural Networks
Random Forests
Antitubercular
Drug Design
Neural-Network
Antimycobacterial Activity
Benzimidazole Derivatives
Variable Selection
In-Vitro
Mycobacterium-Tuberculosis
Isoniazid Derivatives
Agents
Inhibitor
Design
datacite.titles.title.fl_str_mv QSAR modeling of antitubercular activity of diverse organic compounds
dc.contributor.none.fl_str_mv RCIPL
dc.creator.none.fl_str_mv Kovalishyn, Vasyl
Aires-de-Sousa, Joao
Ventura, Cristina
Elvas Leitao, Ruben
Martins, Filomena
dc.date.Accepted.fl_str_mv 2011-05-01T00:00:00Z
dc.date.available.fl_str_mv 2013-02-16T17:50:57Z
dc.date.embargoed.fl_str_mv 2013-02-16T17:50:57Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv http://hdl.handle.net/10400.21/2232
dc.language.none.fl_str_mv eng
dc.publisher.none.fl_str_mv Elsevier Science BV
dc.rights.none.fl_str_mv http://purl.org/coar/access_right/c_abf2
dc.subject.none.fl_str_mv QSAR
Neural Networks
Random Forests
Antitubercular
Drug Design
Neural-Network
Antimycobacterial Activity
Benzimidazole Derivatives
Variable Selection
In-Vitro
Mycobacterium-Tuberculosis
Isoniazid Derivatives
Agents
Inhibitor
Design
dc.title.fl_str_mv QSAR modeling of antitubercular activity of diverse organic compounds
dc.type.none.fl_str_mv http://purl.org/coar/resource_type/c_6501
description Tuberculosis (TB) is a worldwide infectious disease that has shown over time extremely high mortality levels. The urgent need to develop new antitubercular drugs is due to the increasing rate of appearance of multi-drug resistant strains to the commonly used drugs, and the longer durations of therapy and recovery, particularly in immuno-compromised patients. The major goal of the present study is the exploration of data from different families of compounds through the use of a variety of machine learning techniques so that robust QSAR-based models can be developed to further guide in the quest for new potent anti-TB compounds. Eight QSAR models were built using various types of descriptors (from ADRIANA.Code and Dragon software) with two publicly available structurally diverse data sets, including recent data deposited in PubChem. QSAR methodologies used Random Forests and Associative Neural Networks. Predictions for the external evaluation sets obtained accuracies in the range of 0.76-0.88 (for active/inactive classifications) and Q(2)=0.66-0.89 for regressions. Models developed in this study can be used to estimate the anti-TB activity of drug candidates at early stages of drug development (C) 2011 Elsevier B.V. All rights reserved.
dirty 0
eu_rights_str_mv openAccess
format article
fulltext.url.fl_str_mv https://repositorio.ipl.pt/bitstreams/7d3cbfec-b442-45b8-9857-0116662bb0ec/download
id ripl_90c809967fc07ab83e21ad8b364ff35c
identifier.url.fl_str_mv http://hdl.handle.net/10400.21/2232
instacron_str ipl
institution Instituto Politécnico de Lisboa
instname_str Instituto Politécnico de Lisboa
language eng
network_acronym_str ripl
network_name_str Repositório Científico do Instituto Politécnico de Lisboa
oai_identifier_str oai:repositorio.ipl.pt:10400.21/2232
organization_str_mv urn:organizationAcronym:ipl
person_str_mv Kovalishyn, Vasyl
Kovalishyn, Vasyl
http://orcid.org/0000-0002-9352-7332
0000-0002-9352-7332
Aires-de-Sousa, Joao
Aires-de-Sousa, Joao
https://www.ciencia-id.pt/171B-1434-6FC1
171B-1434-6FC1
http://orcid.org/0000-0002-5887-2966
0000-0002-5887-2966
Ventura, Cristina
Elvas Leitao, Ruben
Elvas Leitao, Ruben
https://www.ciencia-id.pt/F41B-8A26-88D4
F41B-8A26-88D4
http://orcid.org/0000-0002-2196-412X
0000-0002-2196-412X
Martins, Filomena
publishDate 2011
publisher.none.fl_str_mv Elsevier Science BV
reponame_str Repositório Científico do Instituto Politécnico de Lisboa
repository_id_str urn:repositoryAcronym:ripl
service_str_mv urn:repositoryAcronym:ripl
spelling engElsevier Science BVporTuberculosis (TB) is a worldwide infectious disease that has shown over time extremely high mortality levels. The urgent need to develop new antitubercular drugs is due to the increasing rate of appearance of multi-drug resistant strains to the commonly used drugs, and the longer durations of therapy and recovery, particularly in immuno-compromised patients. The major goal of the present study is the exploration of data from different families of compounds through the use of a variety of machine learning techniques so that robust QSAR-based models can be developed to further guide in the quest for new potent anti-TB compounds. Eight QSAR models were built using various types of descriptors (from ADRIANA.Code and Dragon software) with two publicly available structurally diverse data sets, including recent data deposited in PubChem. QSAR methodologies used Random Forests and Associative Neural Networks. Predictions for the external evaluation sets obtained accuracies in the range of 0.76-0.88 (for active/inactive classifications) and Q(2)=0.66-0.89 for regressions. Models developed in this study can be used to estimate the anti-TB activity of drug candidates at early stages of drug development (C) 2011 Elsevier B.V. All rights reserved.application/pdfporQSAR modeling of antitubercular activity of diverse organic compoundsPersonalKovalishyn, VasylDSpacehttp://dspace.org/items/9df4c185-2270-47af-8813-c18428b5498dDSpacehttp://dspace.org/items/9df4c185-2270-47af-8813-c18428b5498dKovalishynVasylORCIDhttp://orcid.org0000-0002-9352-7332Researcher IDhttps://www.researcherid.comI-6823-2018Scopus Author IDhttps://www.scopus.com56160092400PersonalAires-de-Sousa, JoaoDSpacehttp://dspace.org/items/6662c1f3-0ccf-4f2c-9b34-81229d7b09dbDSpacehttp://dspace.org/items/6662c1f3-0ccf-4f2c-9b34-81229d7b09dbAires-de-SousaJoaoCiência IDhttps://www.ciencia-id.pt171B-1434-6FC1ORCIDhttp://orcid.org0000-0002-5887-2966Researcher IDhttps://www.researcherid.comC-7826-2013Scopus Author IDhttps://www.scopus.com6603089025Ventura, CristinaPersonalElvas Leitao, RubenDSpacehttp://dspace.org/items/440b7129-d4d9-4225-a936-ca694c0984b6DSpacehttp://dspace.org/items/440b7129-d4d9-4225-a936-ca694c0984b6Elvas LeitaoRubenCiência IDhttps://www.ciencia-id.ptF41B-8A26-88D4ORCIDhttp://orcid.org0000-0002-2196-412XResearcher IDhttps://www.researcherid.comD-2452-2009Scopus Author IDhttps://www.scopus.com55667178200Martins, FilomenaHostingInstitutionOrganizationalRCIPLe-mailmailto:rcaap@sp.ipl.ptrcaap@sp.ipl.ptISSNIsPartOf0169-74392013-02-16T17:50:57Z2011-052011-05-01T00:00:00ZHandlehttp://hdl.handle.net/10400.21/2232http://purl.org/coar/access_right/c_abf2open accessQSARNeural NetworksRandom ForestsAntitubercularDrug DesignNeural-NetworkAntimycobacterial ActivityBenzimidazole DerivativesVariable SelectionIn-VitroMycobacterium-TuberculosisIsoniazid DerivativesAgentsInhibitorDesign280502 bytesliteraturehttp://purl.org/coar/resource_type/c_6501journal articlehttp://purl.org/coar/access_right/c_abf2application/pdffulltexthttps://repositorio.ipl.pt/bitstreams/7d3cbfec-b442-45b8-9857-0116662bb0ec/downloadChemometrics and Intelligent Laboratory Systems10716974Amsterdam
spellingShingle QSAR modeling of antitubercular activity of diverse organic compounds
Kovalishyn, Vasyl
QSAR
Neural Networks
Random Forests
Antitubercular
Drug Design
Neural-Network
Antimycobacterial Activity
Benzimidazole Derivatives
Variable Selection
In-Vitro
Mycobacterium-Tuberculosis
Isoniazid Derivatives
Agents
Inhibitor
Design
subject.fl_str_mv QSAR
Neural Networks
Random Forests
Antitubercular
Drug Design
Neural-Network
Antimycobacterial Activity
Benzimidazole Derivatives
Variable Selection
In-Vitro
Mycobacterium-Tuberculosis
Isoniazid Derivatives
Agents
Inhibitor
Design
title QSAR modeling of antitubercular activity of diverse organic compounds
title_full QSAR modeling of antitubercular activity of diverse organic compounds
title_fullStr QSAR modeling of antitubercular activity of diverse organic compounds
title_full_unstemmed QSAR modeling of antitubercular activity of diverse organic compounds
title_short QSAR modeling of antitubercular activity of diverse organic compounds
title_sort QSAR modeling of antitubercular activity of diverse organic compounds
topic QSAR
Neural Networks
Random Forests
Antitubercular
Drug Design
Neural-Network
Antimycobacterial Activity
Benzimidazole Derivatives
Variable Selection
In-Vitro
Mycobacterium-Tuberculosis
Isoniazid Derivatives
Agents
Inhibitor
Design
topic_facet QSAR
Neural Networks
Random Forests
Antitubercular
Drug Design
Neural-Network
Antimycobacterial Activity
Benzimidazole Derivatives
Variable Selection
In-Vitro
Mycobacterium-Tuberculosis
Isoniazid Derivatives
Agents
Inhibitor
Design
url http://hdl.handle.net/10400.21/2232
visible 1