Learning the therapeutic use of drugs from the three-dimensional spatial information of their molecular structure with convolutional neural networks
Abstract The development of new molecules is a multi-stage process and clinical trials to verify their efficacy cost billions of dollars each year. Machine learning is a tool that is rapidly advancing in image, voice, and text recognition, and working in silico would increase the ability to predict...
- Autores:
-
Martínez-Conde, Jorge Mario
Patiño-Vanegas, Alberto
- Tipo de recurso:
- Fecha de publicación:
- 2021
- Institución:
- Universidad Tecnológica de Bolívar
- Repositorio:
- Repositorio Institucional UTB
- Idioma:
- spa
- OAI Identifier:
- oai:repositorio.utb.edu.co:20.500.12585/12367
- Acceso en línea:
- https://hdl.handle.net/20.500.12585/12367
- Palabra clave:
- Chemoinformatics;
Drug Discovery;
Topographic Mapping
LEMB
- Rights
- openAccess
- License
- http://creativecommons.org/licenses/by-nc-nd/4.0/
| id |
UTB2_801e94b0cc636f4e96a06fced6f11c7e |
|---|---|
| oai_identifier_str |
oai:repositorio.utb.edu.co:20.500.12585/12367 |
| network_acronym_str |
UTB2 |
| network_name_str |
Repositorio Institucional UTB |
| repository_id_str |
|
| dc.title.spa.fl_str_mv |
Learning the therapeutic use of drugs from the three-dimensional spatial information of their molecular structure with convolutional neural networks |
| dc.title.alternative.spa.fl_str_mv |
[Aprendizaje del uso terapéutico de fármacos a partir de la información espacial tridimensional de su estructura molecular con redes neuronales convolucionales |
| title |
Learning the therapeutic use of drugs from the three-dimensional spatial information of their molecular structure with convolutional neural networks |
| spellingShingle |
Learning the therapeutic use of drugs from the three-dimensional spatial information of their molecular structure with convolutional neural networks Chemoinformatics; Drug Discovery; Topographic Mapping LEMB |
| title_short |
Learning the therapeutic use of drugs from the three-dimensional spatial information of their molecular structure with convolutional neural networks |
| title_full |
Learning the therapeutic use of drugs from the three-dimensional spatial information of their molecular structure with convolutional neural networks |
| title_fullStr |
Learning the therapeutic use of drugs from the three-dimensional spatial information of their molecular structure with convolutional neural networks |
| title_full_unstemmed |
Learning the therapeutic use of drugs from the three-dimensional spatial information of their molecular structure with convolutional neural networks |
| title_sort |
Learning the therapeutic use of drugs from the three-dimensional spatial information of their molecular structure with convolutional neural networks |
| dc.creator.fl_str_mv |
Martínez-Conde, Jorge Mario Patiño-Vanegas, Alberto |
| dc.contributor.author.none.fl_str_mv |
Martínez-Conde, Jorge Mario Patiño-Vanegas, Alberto |
| dc.subject.keywords.spa.fl_str_mv |
Chemoinformatics; Drug Discovery; Topographic Mapping |
| topic |
Chemoinformatics; Drug Discovery; Topographic Mapping LEMB |
| dc.subject.armarc.none.fl_str_mv |
LEMB |
| description |
Abstract The development of new molecules is a multi-stage process and clinical trials to verify their efficacy cost billions of dollars each year. Machine learning is a tool that is rapidly advancing in image, voice, and text recognition, and working in silico would increase the ability to predict and prioritize a drug's function. In this research we asked whether the function of therapeutic drugs can be predicted from the stereochemical configuration of the molecule. We use convolutional neural networks to predict the therapeutic use of drugs, trained with both two-dimensional and three-dimensional information of their chemical structure. The model trained with only six views of the 3D information of the molecular structure improved the accuracy by 10 over the model trained with the 2D information. © 2021, Universidad Nacional de Colombia. All rights reserved. |
| publishDate |
2021 |
| dc.date.issued.none.fl_str_mv |
2021 |
| dc.date.accessioned.none.fl_str_mv |
2023-07-21T20:46:13Z |
| dc.date.available.none.fl_str_mv |
2023-07-21T20:46:13Z |
| dc.date.submitted.none.fl_str_mv |
2023 |
| dc.type.coarversion.fl_str_mv |
http://purl.org/coar/version/c_b1a7d7d4d402bcce |
| dc.type.coar.fl_str_mv |
http://purl.org/coar/resource_type/c_2df8fbb1 |
| dc.type.driver.spa.fl_str_mv |
info:eu-repo/semantics/article |
| dc.type.hasversion.spa.fl_str_mv |
info:eu-repo/semantics/draft |
| dc.type.spa.spa.fl_str_mv |
http://purl.org/coar/resource_type/c_6501 |
| status_str |
draft |
| dc.identifier.citation.spa.fl_str_mv |
Martínez-Conde, J. M., & Patiño-Vanegas, A. (2021). Learning the therapeutic use of drugs from the three-dimensional spatial information of their molecular structure with convolutional neural networks. Dyna, 88(219), 247-255. |
| dc.identifier.uri.none.fl_str_mv |
https://hdl.handle.net/20.500.12585/12367 |
| dc.identifier.doi.none.fl_str_mv |
10.15446/dyna.v88n219.92778 |
| dc.identifier.instname.spa.fl_str_mv |
Universidad Tecnológica de Bolívar |
| dc.identifier.reponame.spa.fl_str_mv |
Repositorio Universidad Tecnológica de Bolívar |
| identifier_str_mv |
Martínez-Conde, J. M., & Patiño-Vanegas, A. (2021). Learning the therapeutic use of drugs from the three-dimensional spatial information of their molecular structure with convolutional neural networks. Dyna, 88(219), 247-255. 10.15446/dyna.v88n219.92778 Universidad Tecnológica de Bolívar Repositorio Universidad Tecnológica de Bolívar |
| url |
https://hdl.handle.net/20.500.12585/12367 |
| dc.language.iso.spa.fl_str_mv |
spa |
| language |
spa |
| dc.rights.coar.fl_str_mv |
http://purl.org/coar/access_right/c_abf2 |
| dc.rights.uri.*.fl_str_mv |
http://creativecommons.org/licenses/by-nc-nd/4.0/ |
| dc.rights.accessrights.spa.fl_str_mv |
info:eu-repo/semantics/openAccess |
| dc.rights.cc.*.fl_str_mv |
Attribution-NonCommercial-NoDerivatives 4.0 Internacional |
| rights_invalid_str_mv |
http://creativecommons.org/licenses/by-nc-nd/4.0/ Attribution-NonCommercial-NoDerivatives 4.0 Internacional http://purl.org/coar/access_right/c_abf2 |
| eu_rights_str_mv |
openAccess |
| dc.format.extent.none.fl_str_mv |
9 páginas |
| dc.format.mimetype.spa.fl_str_mv |
application/pdf |
| dc.publisher.place.spa.fl_str_mv |
Cartagena de Indias |
| dc.source.spa.fl_str_mv |
DYNA (Colombia) |
| institution |
Universidad Tecnológica de Bolívar |
| bitstream.url.fl_str_mv |
https://repositorio.utb.edu.co/bitstream/20.500.12585/12367/1/2346-2183-dyna-88-219-247.pdf https://repositorio.utb.edu.co/bitstream/20.500.12585/12367/2/license_rdf https://repositorio.utb.edu.co/bitstream/20.500.12585/12367/3/license.txt https://repositorio.utb.edu.co/bitstream/20.500.12585/12367/4/2346-2183-dyna-88-219-247.pdf.txt https://repositorio.utb.edu.co/bitstream/20.500.12585/12367/5/2346-2183-dyna-88-219-247.pdf.jpg |
| bitstream.checksum.fl_str_mv |
5f5bfafc1f687d468eef04eddc7d01f3 4460e5956bc1d1639be9ae6146a50347 e20ad307a1c5f3f25af9304a7a7c86b6 ce1f54b09432b382b6d30faf8959ee4e 90065a8d65d54bfb6c4657462bf27444 |
| bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 MD5 |
| repository.name.fl_str_mv |
Repositorio Institucional UTB |
| repository.mail.fl_str_mv |
repositorioutb@utb.edu.co |
| _version_ |
1814021610521231360 |
| spelling |
Martínez-Conde, Jorge Mariod44c0352-890f-4297-9c84-981612db7ebcPatiño-Vanegas, Albertoed3ee444-6afd-4230-9ab9-5b0212fa21e62023-07-21T20:46:13Z2023-07-21T20:46:13Z20212023Martínez-Conde, J. M., & Patiño-Vanegas, A. (2021). Learning the therapeutic use of drugs from the three-dimensional spatial information of their molecular structure with convolutional neural networks. Dyna, 88(219), 247-255.https://hdl.handle.net/20.500.12585/1236710.15446/dyna.v88n219.92778Universidad Tecnológica de BolívarRepositorio Universidad Tecnológica de BolívarAbstract The development of new molecules is a multi-stage process and clinical trials to verify their efficacy cost billions of dollars each year. Machine learning is a tool that is rapidly advancing in image, voice, and text recognition, and working in silico would increase the ability to predict and prioritize a drug's function. In this research we asked whether the function of therapeutic drugs can be predicted from the stereochemical configuration of the molecule. We use convolutional neural networks to predict the therapeutic use of drugs, trained with both two-dimensional and three-dimensional information of their chemical structure. The model trained with only six views of the 3D information of the molecular structure improved the accuracy by 10 over the model trained with the 2D information. © 2021, Universidad Nacional de Colombia. All rights reserved.9 páginasapplication/pdfspahttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessAttribution-NonCommercial-NoDerivatives 4.0 Internacionalhttp://purl.org/coar/access_right/c_abf2DYNA (Colombia)Learning the therapeutic use of drugs from the three-dimensional spatial information of their molecular structure with convolutional neural networks[Aprendizaje del uso terapéutico de fármacos a partir de la información espacial tridimensional de su estructura molecular con redes neuronales convolucionalesinfo:eu-repo/semantics/articleinfo:eu-repo/semantics/drafthttp://purl.org/coar/resource_type/c_6501http://purl.org/coar/version/c_b1a7d7d4d402bccehttp://purl.org/coar/resource_type/c_2df8fbb1Chemoinformatics;Drug Discovery;Topographic MappingLEMBCartagena de IndiasLipkus, A.H., Yuan, Q., Lucas, K.A., Funk, S.A., Bartelt III, W.F., Schenck, R.J., Trippe, A.J. Structural diversity of organic chemistry. A scaffold analysis of the CAS Registry (2008) Journal of Organic Chemistry, 73 (12), pp. 4443-4451. Cited 256 times. doi: 10.1021/jo8001276Ruddigkeit, L., Van Deursen, R., Blum, L.C., Reymond, J.-L. Enumeration of 166 billion organic small molecules in the chemical universe database GDB-17 (2012) Journal of Chemical Information and Modeling, 52 (11), pp. 2864-2875. Cited 707 times. http://pubs.acs.org/journal/jcisd8 doi: 10.1021/ci300415dLipinski, C.A., Lombardo, F., Dominy, B.W., Feeney, P.J. Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings (2001) Advanced Drug Delivery Reviews, 46 (1-3), pp. 3-26. Cited 8868 times. www.elsevier.com/locate/drugdeliv doi: 10.1016/S0169-409X(00)00129-0Hann, M.M. Molecular obesity, potency and other addictions in drug discovery (2011) MedChemComm, 2 (5), pp. 349-355. Cited 283 times. doi: 10.1039/c1md00017aBolten, B.M., DeGregorio, T. Trends in development cycles. Market indicators (2002) Nature Reviews Drug Discovery, 1 (5), pp. 335-336. Cited 58 times. doi: 10.1038/nrd805Dearden, J.C. In silico prediction of drug toxicity (2003) Journal of Computer-Aided Molecular Design, 17 (2-4), pp. 119-127. Cited 216 times. https://www.springer.com/journal/10822 doi: 10.1023/A:1025361621494Torres, J Python deep learning: introducción práctica con Keras y TensorFlow 2 (2020) . Cited 7 times. Marcombo; [online] https://books.google.com.co/books?id=5vpmzQEACAAJFerdousi, R., Safdari, R., Omidi, Y. Computational prediction of drug-drug interactions based on drugs functional similarities (2017) Journal of Biomedical Informatics, 70, pp. 54-64. Cited 96 times. http://www.elsevier.com/inca/publications/store/6/2/2/8/5/7/index.htt doi: 10.1016/j.jbi.2017.04.021Ellison, N. Goodman & Gilman’s The Pharmacological Basis of therapeutics (2002) Anesthesia & Analgesia, 94 (5), p. 1377. Cited 6 times. 10th Ed., [online]. P https://journals.lww.com/anesthesia-analgesia/Fulltext/2002/05000/Goodman___Gilman_s_The_Pharmacological_Basis_of.85.aspxAliper, A., Plis, S., Artemov, A., Ulloa, A., Mamoshina, P., Zhavoronkov, A. Deep learning applications for predicting pharmacological properties of drugs and drug repurposing using transcriptomic data (Open Access) (2016) Molecular Pharmaceutics, 13 (7), pp. 2524-2530. Cited 319 times. http://pubs.acs.org/journal/mpohbp doi: 10.1021/acs.molpharmaceut.6b00248Rogers, D., Hahn, M. Extended-connectivity fingerprints (2010) Journal of Chemical Information and Modeling, 50 (5), pp. 742-754. Cited 3388 times. http://pubs.acs.org/journal/jcisd8 doi: 10.1021/ci100050tMeyer, J.G., Liu, S., Miller, I.J., Coon, J.J., Gitter, A. Learning Drug Functions from Chemical Structures with Convolutional Neural Networks and Random Forests (2019) Journal of Chemical Information and Modeling. Cited 44 times. http://pubs.acs.org/journal/jcisd8 doi: 10.1021/acs.jcim.9b00236Lengauer, T., Rarey, M. Computational methods for biomolecular docking (1996) Current Opinion in Structural Biology, 6 (3), pp. 402-406. Cited 551 times. http://www.elsevier.com/locate/sbi doi: 10.1016/S0959-440X(96)80061-3Wei, B.Q., Weaver, L.H., Ferrari, A.M., Matthews, B.W., Shoichet, B.K. Testing a flexible-receptor docking algorithm in a model binding site (2004) Journal of Molecular Biology, 337 (5), pp. 1161-1182. Cited 185 times. https://www.journals.elsevier.com/journal-of-molecular-biology doi: 10.1016/j.jmb.2004.02.015Shoichet, B.K., Kuntz, I.D., Bodian, D.L. Molecular docking using shape descriptors (Open Access) (1992) Journal of Computational Chemistry, 13 (3), pp. 380-397. Cited 374 times. doi: 10.1002/jcc.540130311Jiménez, J., Škalič, M., Martínez-Rosell, G., De Fabritiis, G. KDEEP: Protein-Ligand Absolute Binding Affinity Prediction via 3D-Convolutional Neural Networks (2018) Journal of Chemical Information and Modeling, 58 (2), pp. 287-296. Cited 428 times. http://pubs.acs.org/journal/jcisd8 doi: 10.1021/acs.jcim.7b00650Lowe, H.J., Barnett, G.O. Understanding and using the medical subject headings (MeSH) vocabulary to perform literature searches (1994) JAMA, 271 (14), pp. 1103-1108. Cited 346 times. http://jama.jamanetwork.com/journal.aspx doi: 10.1001/jama.271.14.1103Meyer, J.G., Liu, S., Miller, I.J., Coon, J.J., Gitter, A. Learning Drug Functions from Chemical Structures with Convolutional Neural Networks and Random Forests (Open Access) (2019) Journal of Chemical Information and Modeling. Cited 44 times. http://pubs.acs.org/journal/jcisd8 doi: 10.1021/acs.jcim.9b00236Ragoza, M., Hochuli, J., Idrobo, E., Sunseri, J., Koes, D.R. Protein-Ligand Scoring with Convolutional Neural Networks (2017) Journal of Chemical Information and Modeling, 57 (4), pp. 942-957. Cited 429 times. http://pubs.acs.org/journal/jcisd8 doi: 10.1021/acs.jcim.6b00740Kim, S., Chen, J., Cheng, T., Gindulyte, A., He, J., He, S., Li, Q., (...), Bolton, E.E. PubChem in 2021: New data content and improved web interfaces (Open Access) (2021) Nucleic Acids Research, 49 (D1), pp. D1388-D1395. Cited 1480 times. https://academic.oup.com/nar/issue doi: 10.1093/nar/gkaa971Anderson, E., Veith, G.D., Weininger, D. (1987) SMILES, a Line Notation and Computerized Interpreter for Chemical Structures. Environmental research brief. Cited 78 times. and Environmental Research Laboratory (Duluth, Minn)., U.S. Environmental Protection Agency, Environmental Research Laboratory, Ed., [online]. 4P https://books.google.com.co/books?id=KSofvgAACAAJhttp://purl.org/coar/resource_type/c_6501ORIGINAL2346-2183-dyna-88-219-247.pdf2346-2183-dyna-88-219-247.pdfapplication/pdf2221708https://repositorio.utb.edu.co/bitstream/20.500.12585/12367/1/2346-2183-dyna-88-219-247.pdf5f5bfafc1f687d468eef04eddc7d01f3MD51CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8805https://repositorio.utb.edu.co/bitstream/20.500.12585/12367/2/license_rdf4460e5956bc1d1639be9ae6146a50347MD52LICENSElicense.txtlicense.txttext/plain; charset=utf-83182https://repositorio.utb.edu.co/bitstream/20.500.12585/12367/3/license.txte20ad307a1c5f3f25af9304a7a7c86b6MD53TEXT2346-2183-dyna-88-219-247.pdf.txt2346-2183-dyna-88-219-247.pdf.txtExtracted texttext/plain39581https://repositorio.utb.edu.co/bitstream/20.500.12585/12367/4/2346-2183-dyna-88-219-247.pdf.txtce1f54b09432b382b6d30faf8959ee4eMD54THUMBNAIL2346-2183-dyna-88-219-247.pdf.jpg2346-2183-dyna-88-219-247.pdf.jpgGenerated Thumbnailimage/jpeg8272https://repositorio.utb.edu.co/bitstream/20.500.12585/12367/5/2346-2183-dyna-88-219-247.pdf.jpg90065a8d65d54bfb6c4657462bf27444MD5520.500.12585/12367oai:repositorio.utb.edu.co:20.500.12585/123672023-07-22 00:17:35.732Repositorio Institucional UTBrepositorioutb@utb.edu.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 |