Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 1 de 1
Filtrar
Mais filtros











Intervalo de ano de publicação
1.
Rev. cuba. inform. méd ; 8(2)jul.-dic. 2016.
Artigo em Espanhol | LILACS, CUMED | ID: lil-787235

RESUMO

Los estudios QSAR definidos en la literatura están basados en enfoques uni-modales, dejando de analizar conjuntos de datos que contienen distintas informaciones químicas. En esta investigación se propone aplicar por primera vez y analizar el comportamiento del enfoque multi-modal en el desarrollo de estudios QSAR. Para este fin se utilizó una base de compuestos con actividad hepatotóxica, a partir de la cual se construyeron cuatro modalidades considerando distintos descriptores moleculares basados en diversas teorías y enfoques. Se desarrollaron varios modelos usando los enfoques uni-modales y multi-modales utilizando algoritmos de clasificación reportados en la literatura e implementados en el lenguaje R. Los parámetros de cada uno de los algoritmos se optimizaron con el procedimiento peatedgrid-searchcross-validation, mientras la validación de dichos modelos se realizó mediante validación cruzada de 10 pliegues con 10 repeticiones. Estadísticamente se comprobó que el enfoque multimodal mejora el desempeño de los modelos predictivos comparado con algunos de los modelos derivados de los conjuntos de datos con modalidades individuales(AU)


The QSAR studies defined in the literature are based on uni-modal approaches and do not consider datasets with different chemical information. Thus, this research has as objective to apply and analyze the behavior of multi-modal approaches when QSAR studies are carried out. To this end, a compound dataset with hepatotoxicity activity was employed and four modalities were built considering molecular descriptors based on different mathematical theories. Also, several predictive models were developed taking into account both uni-modal and multi-modal approaches by using classification algorithms reported in the literature and implemented in R language. The parameters of these algorithms with the procedure parameter tuning with repeated grid-search cross-validation were optimized, while the strategy 10-fold cross-validation with 10 repetitions was used to corroborate the predictive accuracy of the models. As result of this study it can be stated that the behavior of the models based on multi-modal approach present significant differences with to those models developed from uni-modal approaches(AU)


Assuntos
Humanos , Aplicações da Informática Médica , Software , Terapia Combinada/métodos
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA