Automatic design of decision-tree induction algorithms tailored to flexible-receptor docking data
Autor(a) principal: | |
---|---|
Data de Publicação: | 2012 |
Outros Autores: | , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da FURG (RI FURG) |
Texto Completo: | http://repositorio.furg.br/handle/1/4925 |
Resumo: | Background: This paper addresses the prediction of the free energy of binding of a drug candidate with enzyme InhA associated with Mycobacterium tuberculosis. This problem is found within rational drug design, where interactions between drug candidates and target proteins are verified through molecular docking simulations. In this application, it is important not only to correctly predict the free energy of binding, but also to provide a comprehensible model that could be validated by a domain specialist. Decision-tree induction algorithms have been successfully used in drug-design related applications, specially considering that decision trees are simple to understand, interpret, and validate. There are several decision-tree induction algorithms available for general-use, but each one has a bias that makes it more suitable for a particular data distribution. In this article, we propose and investigate the automatic design of decision-tree induction algorithms tailored to particular drug-enzyme binding data sets. We investigate the performance of our new method for evaluating binding conformations of different drug candidates to InhA, and we analyze our findings with respect to decision tree accuracy, comprehensibility, and biological relevance. Results: The empirical analysis indicates that our method is capable of automatically generating decision-tree induction algorithms that significantly outperform the traditional C4.5 algorithm with respect to both accuracy and comprehensibility. In addition, we provide the biological interpretation of the rules generated by our approach, reinforcing the importance of comprehensible predictive models in this particular bioinformatics application. Conclusions: We conclude that automatically designing a decision-tree algorithm tailored to molecular docking data is a promising alternative for the prediction of the free energy from the binding of a drug candidate with a flexible-receptor |
id |
FURG_3e8621018488bf627fc5ebdcf750f22b |
---|---|
oai_identifier_str |
oai:repositorio.furg.br:1/4925 |
network_acronym_str |
FURG |
network_name_str |
Repositório Institucional da FURG (RI FURG) |
repository_id_str |
|
spelling |
Barros, Rodrigo CoelhoWinck, Ana TrindadeMachado, Karina dos SantosBasgalupp, Márcio PortoCarvalho, Andre Carlos Ponce de Leon Ferreira deRuiz, Duncan Dubugras AlcobaSouza, Osmar Norberto de2015-05-28T20:46:40Z2015-05-28T20:46:40Z2012BARROS, Rodrigo Coelho et al. Automatic design of decision-tree induction algorithms tailored to flexible-receptor docking data. BMC Bioinformatics, v. 13, p. 1-14, 2012. Disponível em: <http://www.biomedcentral.com/1471-2105/13/310>. Acesso em: 15 maio 2015.1471-2105http://repositorio.furg.br/handle/1/492510.1186/1471-2105-13-310Background: This paper addresses the prediction of the free energy of binding of a drug candidate with enzyme InhA associated with Mycobacterium tuberculosis. This problem is found within rational drug design, where interactions between drug candidates and target proteins are verified through molecular docking simulations. In this application, it is important not only to correctly predict the free energy of binding, but also to provide a comprehensible model that could be validated by a domain specialist. Decision-tree induction algorithms have been successfully used in drug-design related applications, specially considering that decision trees are simple to understand, interpret, and validate. There are several decision-tree induction algorithms available for general-use, but each one has a bias that makes it more suitable for a particular data distribution. In this article, we propose and investigate the automatic design of decision-tree induction algorithms tailored to particular drug-enzyme binding data sets. We investigate the performance of our new method for evaluating binding conformations of different drug candidates to InhA, and we analyze our findings with respect to decision tree accuracy, comprehensibility, and biological relevance. Results: The empirical analysis indicates that our method is capable of automatically generating decision-tree induction algorithms that significantly outperform the traditional C4.5 algorithm with respect to both accuracy and comprehensibility. In addition, we provide the biological interpretation of the rules generated by our approach, reinforcing the importance of comprehensible predictive models in this particular bioinformatics application. Conclusions: We conclude that automatically designing a decision-tree algorithm tailored to molecular docking data is a promising alternative for the prediction of the free energy from the binding of a drug candidate with a flexible-receptorengAutomatic design of decision-tree induction algorithms tailored to flexible-receptor docking datainfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleinfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da FURG (RI FURG)instname:Universidade Federal do Rio Grande (FURG)instacron:FURGORIGINALAutomatic design of decision-tree induction.pdfAutomatic design of decision-tree induction.pdfapplication/pdf1220284https://repositorio.furg.br/bitstream/1/4925/1/Automatic%20design%20of%20decision-tree%20induction.pdf2a547881e0a58facad1ce378adf590d5MD51open accessLICENSElicense.txtlicense.txttext/plain; charset=utf-81748https://repositorio.furg.br/bitstream/1/4925/2/license.txt8a4605be74aa9ea9d79846c1fba20a33MD52open access1/49252015-05-28 17:46:40.557open accessoai:repositorio.furg.br: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Repositório InstitucionalPUBhttps://repositorio.furg.br/oai/request || http://200.19.254.174/oai/requestopendoar:2015-05-28T20:46:40Repositório Institucional da FURG (RI FURG) - Universidade Federal do Rio Grande (FURG)false |
dc.title.pt_BR.fl_str_mv |
Automatic design of decision-tree induction algorithms tailored to flexible-receptor docking data |
title |
Automatic design of decision-tree induction algorithms tailored to flexible-receptor docking data |
spellingShingle |
Automatic design of decision-tree induction algorithms tailored to flexible-receptor docking data Barros, Rodrigo Coelho |
title_short |
Automatic design of decision-tree induction algorithms tailored to flexible-receptor docking data |
title_full |
Automatic design of decision-tree induction algorithms tailored to flexible-receptor docking data |
title_fullStr |
Automatic design of decision-tree induction algorithms tailored to flexible-receptor docking data |
title_full_unstemmed |
Automatic design of decision-tree induction algorithms tailored to flexible-receptor docking data |
title_sort |
Automatic design of decision-tree induction algorithms tailored to flexible-receptor docking data |
author |
Barros, Rodrigo Coelho |
author_facet |
Barros, Rodrigo Coelho Winck, Ana Trindade Machado, Karina dos Santos Basgalupp, Márcio Porto Carvalho, Andre Carlos Ponce de Leon Ferreira de Ruiz, Duncan Dubugras Alcoba Souza, Osmar Norberto de |
author_role |
author |
author2 |
Winck, Ana Trindade Machado, Karina dos Santos Basgalupp, Márcio Porto Carvalho, Andre Carlos Ponce de Leon Ferreira de Ruiz, Duncan Dubugras Alcoba Souza, Osmar Norberto de |
author2_role |
author author author author author author |
dc.contributor.author.fl_str_mv |
Barros, Rodrigo Coelho Winck, Ana Trindade Machado, Karina dos Santos Basgalupp, Márcio Porto Carvalho, Andre Carlos Ponce de Leon Ferreira de Ruiz, Duncan Dubugras Alcoba Souza, Osmar Norberto de |
description |
Background: This paper addresses the prediction of the free energy of binding of a drug candidate with enzyme InhA associated with Mycobacterium tuberculosis. This problem is found within rational drug design, where interactions between drug candidates and target proteins are verified through molecular docking simulations. In this application, it is important not only to correctly predict the free energy of binding, but also to provide a comprehensible model that could be validated by a domain specialist. Decision-tree induction algorithms have been successfully used in drug-design related applications, specially considering that decision trees are simple to understand, interpret, and validate. There are several decision-tree induction algorithms available for general-use, but each one has a bias that makes it more suitable for a particular data distribution. In this article, we propose and investigate the automatic design of decision-tree induction algorithms tailored to particular drug-enzyme binding data sets. We investigate the performance of our new method for evaluating binding conformations of different drug candidates to InhA, and we analyze our findings with respect to decision tree accuracy, comprehensibility, and biological relevance. Results: The empirical analysis indicates that our method is capable of automatically generating decision-tree induction algorithms that significantly outperform the traditional C4.5 algorithm with respect to both accuracy and comprehensibility. In addition, we provide the biological interpretation of the rules generated by our approach, reinforcing the importance of comprehensible predictive models in this particular bioinformatics application. Conclusions: We conclude that automatically designing a decision-tree algorithm tailored to molecular docking data is a promising alternative for the prediction of the free energy from the binding of a drug candidate with a flexible-receptor |
publishDate |
2012 |
dc.date.issued.fl_str_mv |
2012 |
dc.date.accessioned.fl_str_mv |
2015-05-28T20:46:40Z |
dc.date.available.fl_str_mv |
2015-05-28T20:46:40Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.citation.fl_str_mv |
BARROS, Rodrigo Coelho et al. Automatic design of decision-tree induction algorithms tailored to flexible-receptor docking data. BMC Bioinformatics, v. 13, p. 1-14, 2012. Disponível em: <http://www.biomedcentral.com/1471-2105/13/310>. Acesso em: 15 maio 2015. |
dc.identifier.uri.fl_str_mv |
http://repositorio.furg.br/handle/1/4925 |
dc.identifier.issn.none.fl_str_mv |
1471-2105 |
dc.identifier.doi.pt_BR.fl_str_mv |
10.1186/1471-2105-13-310 |
identifier_str_mv |
BARROS, Rodrigo Coelho et al. Automatic design of decision-tree induction algorithms tailored to flexible-receptor docking data. BMC Bioinformatics, v. 13, p. 1-14, 2012. Disponível em: <http://www.biomedcentral.com/1471-2105/13/310>. Acesso em: 15 maio 2015. 1471-2105 10.1186/1471-2105-13-310 |
url |
http://repositorio.furg.br/handle/1/4925 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da FURG (RI FURG) instname:Universidade Federal do Rio Grande (FURG) instacron:FURG |
instname_str |
Universidade Federal do Rio Grande (FURG) |
instacron_str |
FURG |
institution |
FURG |
reponame_str |
Repositório Institucional da FURG (RI FURG) |
collection |
Repositório Institucional da FURG (RI FURG) |
bitstream.url.fl_str_mv |
https://repositorio.furg.br/bitstream/1/4925/1/Automatic%20design%20of%20decision-tree%20induction.pdf https://repositorio.furg.br/bitstream/1/4925/2/license.txt |
bitstream.checksum.fl_str_mv |
2a547881e0a58facad1ce378adf590d5 8a4605be74aa9ea9d79846c1fba20a33 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da FURG (RI FURG) - Universidade Federal do Rio Grande (FURG) |
repository.mail.fl_str_mv |
|
_version_ |
1798313578283925504 |