Designing Nanoparticle Release Systems for Drug-Vitamin Cancer Co-Therapy with Multiplicative Perturbation-Theory Machine Learning (PTML) Models

Nano-systems for cancer co-therapy including vitamins or vitamins derivatives have showed adequate results to continue with further researches to better understand them. However, the number of different combinations of drugs, vitamins, nanoparticle types, coating agents, synthesis conditions, system...

Descripción completa

Detalles Bibliográficos
Autores: Santana, Ricardo, Zuluaga, Robin, Gañán, Piedad, Arrasate Gil, Sonia, Onieva, Enrique, González Díaz, Humberto
Tipo de recurso: artículo
Fecha de publicación:2019
País:España
Institución:Universidad del País Vasco
Repositorio:Addi. Archivo Digital para la Docencia y la Investigación
OAI Identifier:oai:addi.ehu.eus:10810/72349
Acceso en línea:http://hdl.handle.net/10810/72349
Access Level:acceso abierto
Palabra clave:ChEMBL
Nanoparticle
PTML
Machine Learning
Big data
id ES_daabec59c5ebe9470bd70ea1668b032e
oai_identifier_str oai:addi.ehu.eus:10810/72349
network_acronym_str ES
network_name_str España
repository_id_str
spelling Designing Nanoparticle Release Systems for Drug-Vitamin Cancer Co-Therapy with Multiplicative Perturbation-Theory Machine Learning (PTML) ModelsSantana, RicardoZuluaga, RobinGañán, PiedadArrasate Gil, SoniaOnieva, EnriqueGonzález Díaz, HumbertoChEMBLNanoparticlePTMLMachine LearningBig dataNano-systems for cancer co-therapy including vitamins or vitamins derivatives have showed adequate results to continue with further researches to better understand them. However, the number of different combinations of drugs, vitamins, nanoparticle types, coating agents, synthesis conditions, system types (nanocapsules, micelles, etc.) to be tested is very large generating a high cost in experimentations. In this context, there are reports of large datasets of preclinical assays of compounds (like in ChEMBL database) and increasing but yet limited reports of experimental measurements of nano-systems per se. On the other hand, Machine Learning is gaining momentum in Nanotechnology and Pharmaceutical Sciences as a tool for rational design of new drugs and drug-release nano-systems. In this work, we propose to combine Perturbation Theory principles and Machine Learning to develop a PTML model for rational selection of the components of cancer co-therapy drug-vitamin release nano-systems (DVRNs). In so doing, we apply information fusion techniques with 2 data sets: (1) a large ChEMBL dataset of >36000 preclinical assays of vitamin derivatives and a new dataset of >1000 outcomes of DVRNs, collected herein from literature for the first time. The ChEMBL dataset used covers a considerable number of assay conditions (cjvit) each one with multiple levels. These conditions included >504 biological activity parameters (c0vit), >340 types of proteins (c1vit), >650 types of cells (c2vit), >120 assay organisms (c3vit), > 60 assay strain (c4vit). Regarding the DVRNs, there are 25 different types of nano-systems (njn), with up to 16 conditions (cjn) including also different levels such as: 8 2 biological activity parameters (c0n), 9 raw nanomaterials (c4n), 15 assay cells (c11n), etc. In a first stage, we used Moving Average operators to quantify the perturbations (deviations) in all input variables with respect to the conditions. After that, we used multiplicative PT operators to carry out data fusion, and dimensions reduction, and Linear Discriminant Analysis (LDA) to seek the PTML model. The best PTML model found showed values of Specificity, Sensitivity, and Accuracy in the range of 83-88% in training and external validation series for >130000 cases (DVRNs vs. ChEMBL data pairs) formed after data fusion. Until the best of our knowledge, this is the first general purpose model for the rational design of DVRNs for cancer co-therapy.R. S. C. thanks COLCIENCIAS for a scholarship for the doctorate studies; “Convocatoria para Doctorado Nacional 757” from 2017. This original research is part of the project “Investigación en Derecho Internacional y Nanotecnpología” registered in the Research Centre of Universidad Pontificia Bolivariana with register number 766B-06/17-37. Special gratitude is extended to CYTED NANOCELIA network. The authors acknowledge research grants from Ministry of Economy and Competitiveness, MINECO, Spain (FEDER CTQ2016-74881-P) and Basque government (IT1045-16). The authors also acknowledge the support of Ikerbasque, Basque Foundation for Science.RSC202520252019info:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10810/72349reponame:Addi. Archivo Digital para la Docencia y la Investigacióninstname:Universidad del País VascoIngléshttps://doi.org/10.1039/C9NR05070Ainfo:eu-repo/semantics/openAccess© 2019 The Royal Society of Chemistryoai:addi.ehu.eus:10810/723492026-06-18T09:23:17Z
dc.title.none.fl_str_mv Designing Nanoparticle Release Systems for Drug-Vitamin Cancer Co-Therapy with Multiplicative Perturbation-Theory Machine Learning (PTML) Models
title Designing Nanoparticle Release Systems for Drug-Vitamin Cancer Co-Therapy with Multiplicative Perturbation-Theory Machine Learning (PTML) Models
spellingShingle Designing Nanoparticle Release Systems for Drug-Vitamin Cancer Co-Therapy with Multiplicative Perturbation-Theory Machine Learning (PTML) Models
Santana, Ricardo
ChEMBL
Nanoparticle
PTML
Machine Learning
Big data
title_short Designing Nanoparticle Release Systems for Drug-Vitamin Cancer Co-Therapy with Multiplicative Perturbation-Theory Machine Learning (PTML) Models
title_full Designing Nanoparticle Release Systems for Drug-Vitamin Cancer Co-Therapy with Multiplicative Perturbation-Theory Machine Learning (PTML) Models
title_fullStr Designing Nanoparticle Release Systems for Drug-Vitamin Cancer Co-Therapy with Multiplicative Perturbation-Theory Machine Learning (PTML) Models
title_full_unstemmed Designing Nanoparticle Release Systems for Drug-Vitamin Cancer Co-Therapy with Multiplicative Perturbation-Theory Machine Learning (PTML) Models
title_sort Designing Nanoparticle Release Systems for Drug-Vitamin Cancer Co-Therapy with Multiplicative Perturbation-Theory Machine Learning (PTML) Models
dc.creator.none.fl_str_mv Santana, Ricardo
Zuluaga, Robin
Gañán, Piedad
Arrasate Gil, Sonia
Onieva, Enrique
González Díaz, Humberto
author Santana, Ricardo
author_facet Santana, Ricardo
Zuluaga, Robin
Gañán, Piedad
Arrasate Gil, Sonia
Onieva, Enrique
González Díaz, Humberto
author_role author
author2 Zuluaga, Robin
Gañán, Piedad
Arrasate Gil, Sonia
Onieva, Enrique
González Díaz, Humberto
author2_role author
author
author
author
author
dc.subject.none.fl_str_mv ChEMBL
Nanoparticle
PTML
Machine Learning
Big data
topic ChEMBL
Nanoparticle
PTML
Machine Learning
Big data
description Nano-systems for cancer co-therapy including vitamins or vitamins derivatives have showed adequate results to continue with further researches to better understand them. However, the number of different combinations of drugs, vitamins, nanoparticle types, coating agents, synthesis conditions, system types (nanocapsules, micelles, etc.) to be tested is very large generating a high cost in experimentations. In this context, there are reports of large datasets of preclinical assays of compounds (like in ChEMBL database) and increasing but yet limited reports of experimental measurements of nano-systems per se. On the other hand, Machine Learning is gaining momentum in Nanotechnology and Pharmaceutical Sciences as a tool for rational design of new drugs and drug-release nano-systems. In this work, we propose to combine Perturbation Theory principles and Machine Learning to develop a PTML model for rational selection of the components of cancer co-therapy drug-vitamin release nano-systems (DVRNs). In so doing, we apply information fusion techniques with 2 data sets: (1) a large ChEMBL dataset of >36000 preclinical assays of vitamin derivatives and a new dataset of >1000 outcomes of DVRNs, collected herein from literature for the first time. The ChEMBL dataset used covers a considerable number of assay conditions (cjvit) each one with multiple levels. These conditions included >504 biological activity parameters (c0vit), >340 types of proteins (c1vit), >650 types of cells (c2vit), >120 assay organisms (c3vit), > 60 assay strain (c4vit). Regarding the DVRNs, there are 25 different types of nano-systems (njn), with up to 16 conditions (cjn) including also different levels such as: 8 2 biological activity parameters (c0n), 9 raw nanomaterials (c4n), 15 assay cells (c11n), etc. In a first stage, we used Moving Average operators to quantify the perturbations (deviations) in all input variables with respect to the conditions. After that, we used multiplicative PT operators to carry out data fusion, and dimensions reduction, and Linear Discriminant Analysis (LDA) to seek the PTML model. The best PTML model found showed values of Specificity, Sensitivity, and Accuracy in the range of 83-88% in training and external validation series for >130000 cases (DVRNs vs. ChEMBL data pairs) formed after data fusion. Until the best of our knowledge, this is the first general purpose model for the rational design of DVRNs for cancer co-therapy.
publishDate 2019
dc.date.none.fl_str_mv 2019
2025
2025
dc.type.none.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv http://hdl.handle.net/10810/72349
url http://hdl.handle.net/10810/72349
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv https://doi.org/10.1039/C9NR05070A
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
© 2019 The Royal Society of Chemistry
eu_rights_str_mv openAccess
rights_invalid_str_mv © 2019 The Royal Society of Chemistry
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv RSC
publisher.none.fl_str_mv RSC
dc.source.none.fl_str_mv reponame:Addi. Archivo Digital para la Docencia y la Investigación
instname:Universidad del País Vasco
instname_str Universidad del País Vasco
reponame_str Addi. Archivo Digital para la Docencia y la Investigación
collection Addi. Archivo Digital para la Docencia y la Investigación
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869421601080999936
score 15.81155

Similares en LA Referencia