Data-driven modeling of the bicalutamide dissolution from powder systems

2020
journal article
article
dc.abstract.enLow solubility of active pharmaceutical compounds (APIs) remains an important challenge in dosage form development process. In the manuscript, empirical models were developed and analyzed in order to predict dissolution of bicalutamide (BCL) from solid dispersion with various carriers. BCL was chosen as an example of a poor watersoluble API. Two separate datasets were created: one from literature data and another based on in-house experimental data. Computational experiments were conducted using artificial intelligence tools based on machine learning (AI/ML) with a plethora of techniques including artificial neural networks, decision trees, rule-based systems, and evolutionary computations. The latter resulting in classical mathematical equations provided models characterized by the lowest prediction error. In-house data turned out to be more homogeneous, as well as formulations were more extensively characterized than literature-based data. Thus, in-house data resulted in better models than literature-based data set. Among the other covariates, the best model uses for prediction of BCL dissolution profile the transmittance from IR spectrum at 1260 cm−1 wavenumber. Ab initio modeling–based in silico simulations were conducted to reveal potential BCL–excipients interaction. All crucial variables were selected automatically by AI/ML tools and resulted in reasonably simple and yet predictive models suitable for application in Quality by Design (QbD) approaches. Presented data-driven model development using AI/ML could be useful in various problems in the field of pharmaceutical technology, resulting in both predictive and investigational tools revealing new knowledge.pl
dc.affiliationWydział Farmaceutyczny : Zakład Technologii Postaci Leku i Biofarmacjipl
dc.cm.date2020-12-02
dc.cm.id99436
dc.contributor.authorMendyk, Aleksander - 130937 pl
dc.contributor.authorPacławski, Adam - 148394 pl
dc.contributor.authorSzafraniec-Szczęsny, Joanna - 116206 pl
dc.contributor.authorAntosik-Rogóż, Agata - 199757 pl
dc.contributor.authorJamróz, Witold - 129799 pl
dc.contributor.authorPaluch, Marianpl
dc.contributor.authorJachowicz, Renata - 129780 pl
dc.date.accessioned2020-12-02T10:28:10Zpl
dc.date.available2020-12-02T10:28:10Zpl
dc.date.issued2020pl
dc.date.openaccess0
dc.description.accesstimew momencie opublikowania
dc.description.number3pl
dc.description.points100pl
dc.description.versionostateczna wersja wydawcy
dc.description.volume21pl
dc.identifier.articleid111pl
dc.identifier.doi10.1208/s12249-020-01660-wpl
dc.identifier.eissn1530-9932pl
dc.identifier.projectROD UJ / OPpl
dc.identifier.urihttps://ruj.uj.edu.pl/xmlui/handle/item/257589
dc.languageengpl
dc.language.containerengpl
dc.rightsUdzielam licencji. Uznanie autorstwa 4.0 Międzynarodowa*
dc.rights.licenceCC-BY
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/legalcode.pl*
dc.share.typeotwarte czasopismo
dc.subject.enartificial intelligencepl
dc.subject.endissolution modelingpl
dc.subject.enmultivariate modelingpl
dc.subject.enmulti-scale modelingpl
dc.subject.ensolubility enhancementpl
dc.subtypeArticlepl
dc.titleData-driven modeling of the bicalutamide dissolution from powder systemspl
dc.title.journalAAPS PharmSciTechpl
dc.typeJournalArticlepl
dspace.entity.typePublication
dc.abstract.enpl
Low solubility of active pharmaceutical compounds (APIs) remains an important challenge in dosage form development process. In the manuscript, empirical models were developed and analyzed in order to predict dissolution of bicalutamide (BCL) from solid dispersion with various carriers. BCL was chosen as an example of a poor watersoluble API. Two separate datasets were created: one from literature data and another based on in-house experimental data. Computational experiments were conducted using artificial intelligence tools based on machine learning (AI/ML) with a plethora of techniques including artificial neural networks, decision trees, rule-based systems, and evolutionary computations. The latter resulting in classical mathematical equations provided models characterized by the lowest prediction error. In-house data turned out to be more homogeneous, as well as formulations were more extensively characterized than literature-based data. Thus, in-house data resulted in better models than literature-based data set. Among the other covariates, the best model uses for prediction of BCL dissolution profile the transmittance from IR spectrum at 1260 cm−1 wavenumber. Ab initio modeling–based in silico simulations were conducted to reveal potential BCL–excipients interaction. All crucial variables were selected automatically by AI/ML tools and resulted in reasonably simple and yet predictive models suitable for application in Quality by Design (QbD) approaches. Presented data-driven model development using AI/ML could be useful in various problems in the field of pharmaceutical technology, resulting in both predictive and investigational tools revealing new knowledge.
dc.affiliationpl
Wydział Farmaceutyczny : Zakład Technologii Postaci Leku i Biofarmacji
dc.cm.date
2020-12-02
dc.cm.id
99436
dc.contributor.authorpl
Mendyk, Aleksander - 130937
dc.contributor.authorpl
Pacławski, Adam - 148394
dc.contributor.authorpl
Szafraniec-Szczęsny, Joanna - 116206
dc.contributor.authorpl
Antosik-Rogóż, Agata - 199757
dc.contributor.authorpl
Jamróz, Witold - 129799
dc.contributor.authorpl
Paluch, Marian
dc.contributor.authorpl
Jachowicz, Renata - 129780
dc.date.accessionedpl
2020-12-02T10:28:10Z
dc.date.availablepl
2020-12-02T10:28:10Z
dc.date.issuedpl
2020
dc.date.openaccess
0
dc.description.accesstime
w momencie opublikowania
dc.description.numberpl
3
dc.description.pointspl
100
dc.description.version
ostateczna wersja wydawcy
dc.description.volumepl
21
dc.identifier.articleidpl
111
dc.identifier.doipl
10.1208/s12249-020-01660-w
dc.identifier.eissnpl
1530-9932
dc.identifier.projectpl
ROD UJ / OP
dc.identifier.uri
https://ruj.uj.edu.pl/xmlui/handle/item/257589
dc.languagepl
eng
dc.language.containerpl
eng
dc.rights*
Udzielam licencji. Uznanie autorstwa 4.0 Międzynarodowa
dc.rights.licence
CC-BY
dc.rights.uri*
http://creativecommons.org/licenses/by/4.0/legalcode.pl
dc.share.type
otwarte czasopismo
dc.subject.enpl
artificial intelligence
dc.subject.enpl
dissolution modeling
dc.subject.enpl
multivariate modeling
dc.subject.enpl
multi-scale modeling
dc.subject.enpl
solubility enhancement
dc.subtypepl
Article
dc.titlepl
Data-driven modeling of the bicalutamide dissolution from powder systems
dc.title.journalpl
AAPS PharmSciTech
dc.typepl
JournalArticle
dspace.entity.type
Publication

* The migration of download and view statistics prior to the date of April 8, 2024 is in progress.

Views
6
Views per month
Views per city
Ashburn
2
Wroclaw
2
Dublin
1
Krakow
1
Downloads
mendyk_et-al_data-driven_modeling_of_the_bicalutamide_dissolution_2020.pdf
1