TY - JOUR
T1 - Feature Learning applied to the Estimation of Tensile Strength at Break in Polymeric Material Design
AU - Cravero, Fiorella
AU - Martínez, María Jimena
AU - Vazquez, Gustavo Esteban
AU - Díaz, Mónica Fátima
AU - Ponzoni, Ignacio
PY - 2016/11/27
Y1 - 2016/11/27
N2 - Several feature extraction approaches for QSPR modelling in Cheminformatics are discussed in this paper. In particular, this work is focused on the use of these strategies for predicting mechanical properties, which are relevant for the design of polymeric materials. The methodology analysed in this study employs a feature learning method that uses a quantification process of 2D structural characterization of materials with the autoencoder method. Alternative QSPR models inferred for tensile strength at break (a well-known mechanical property of polymers) are presented. These alternative models are contrasted to QSPR models obtained by feature selection technique by using accuracy measures and a visual analytic tool. The results show evidence about the benefits of combining feature learning approaches with feature selection methods for the design of QSPR models.
AB - Several feature extraction approaches for QSPR modelling in Cheminformatics are discussed in this paper. In particular, this work is focused on the use of these strategies for predicting mechanical properties, which are relevant for the design of polymeric materials. The methodology analysed in this study employs a feature learning method that uses a quantification process of 2D structural characterization of materials with the autoencoder method. Alternative QSPR models inferred for tensile strength at break (a well-known mechanical property of polymers) are presented. These alternative models are contrasted to QSPR models obtained by feature selection technique by using accuracy measures and a visual analytic tool. The results show evidence about the benefits of combining feature learning approaches with feature selection methods for the design of QSPR models.
UR - http://www.scopus.com/inward/record.url?scp=85020320225&partnerID=8YFLogxK
U2 - 10.2390/biecoll-jib-2016-286
DO - 10.2390/biecoll-jib-2016-286
M3 - Artículo
C2 - 28187416
AN - SCOPUS:85020320225
SN - 1613-4516
VL - 13
SP - 286
JO - Journal of integrative bioinformatics
JF - Journal of integrative bioinformatics
IS - 2
ER -