A QSTR-based expert system to predict sweetness of molecules

This work describes a novel approach based on advanced molecular similarity to predict the sweetness of chemicals. The proposed Quantitative Structure-Taste Relationship (QSTR) model is an expert system developed keeping in mind the five principles defined by the Organization for Economic Co-operati...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Rojas Villa, Cristian Xavier, Todeschini, Roberto, Ballabio, Davide, Mauri, Andrea, Consonni, Viviana, Tripaldi, Piercosimo, Grisoni, Francesca
Formato: Articulo
Lenguaje:Inglés
Publicado: 2017
Materias:
Ciencias Exactas
Classification
Expert system
Molecular descriptors
QSAR
Sweetness
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/87648
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-87648
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Exactas
Classification
Expert system
Molecular descriptors
QSAR
Sweetness
spellingShingle Ciencias Exactas
Classification
Expert system
Molecular descriptors
QSAR
Sweetness
Rojas Villa, Cristian Xavier
Todeschini, Roberto
Ballabio, Davide
Mauri, Andrea
Consonni, Viviana
Tripaldi, Piercosimo
Grisoni, Francesca
A QSTR-based expert system to predict sweetness of molecules
topic_facet Ciencias Exactas
Classification
Expert system
Molecular descriptors
QSAR
Sweetness
description This work describes a novel approach based on advanced molecular similarity to predict the sweetness of chemicals. The proposed Quantitative Structure-Taste Relationship (QSTR) model is an expert system developed keeping in mind the five principles defined by the Organization for Economic Co-operation and Development (OECD) for the validation of (Q)SARs. The 649 sweet and non-sweet molecules were described by both conformation-independent extended-connectivity fingerprints (ECFPs) and molecular descriptors. In particular, the molecular similarity in the ECFPs space showed a clear association with molecular taste and it was exploited for model development. Molecules laying in the subspaces where the taste assignation was more difficult were modeled trough a consensus between linear and local approaches (Partial Least Squares-Discriminant Analysis and N-nearest-neighbor classifier). The expert system, which was thoroughly validated through a Monte Carlo procedure and an external set, gave satisfactory results in comparison with the state-of-the-art models. Moreover, the QSTR model can be leveraged into a greater understanding of the relationship between molecular structure and sweetness, and into the design of novel sweeteners.
format Articulo
Articulo
author Rojas Villa, Cristian Xavier
Todeschini, Roberto
Ballabio, Davide
Mauri, Andrea
Consonni, Viviana
Tripaldi, Piercosimo
Grisoni, Francesca
author_facet Rojas Villa, Cristian Xavier
Todeschini, Roberto
Ballabio, Davide
Mauri, Andrea
Consonni, Viviana
Tripaldi, Piercosimo
Grisoni, Francesca
author_sort Rojas Villa, Cristian Xavier
title A QSTR-based expert system to predict sweetness of molecules
title_short A QSTR-based expert system to predict sweetness of molecules
title_full A QSTR-based expert system to predict sweetness of molecules
title_fullStr A QSTR-based expert system to predict sweetness of molecules
title_full_unstemmed A QSTR-based expert system to predict sweetness of molecules
title_sort qstr-based expert system to predict sweetness of molecules
publishDate 2017
url http://sedici.unlp.edu.ar/handle/10915/87648
work_keys_str_mv AT rojasvillacristianxavier aqstrbasedexpertsystemtopredictsweetnessofmolecules
AT todeschiniroberto aqstrbasedexpertsystemtopredictsweetnessofmolecules
AT ballabiodavide aqstrbasedexpertsystemtopredictsweetnessofmolecules
AT mauriandrea aqstrbasedexpertsystemtopredictsweetnessofmolecules
AT consonniviviana aqstrbasedexpertsystemtopredictsweetnessofmolecules
AT tripaldipiercosimo aqstrbasedexpertsystemtopredictsweetnessofmolecules
AT grisonifrancesca aqstrbasedexpertsystemtopredictsweetnessofmolecules
AT rojasvillacristianxavier qstrbasedexpertsystemtopredictsweetnessofmolecules
AT todeschiniroberto qstrbasedexpertsystemtopredictsweetnessofmolecules
AT ballabiodavide qstrbasedexpertsystemtopredictsweetnessofmolecules
AT mauriandrea qstrbasedexpertsystemtopredictsweetnessofmolecules
AT consonniviviana qstrbasedexpertsystemtopredictsweetnessofmolecules
AT tripaldipiercosimo qstrbasedexpertsystemtopredictsweetnessofmolecules
AT grisonifrancesca qstrbasedexpertsystemtopredictsweetnessofmolecules
bdutipo_str Repositorios
_version_ 1764820489252896770

Ejemplares similares