A new method for the study of molecule chemical information organized into three-way data structures (MOLMAP) was recently proposed in literature. Basically, MOLMAP molecular fingerprints are calculated by projecting bond properties of molecules into Kohonen networks and used to generate molecular descriptors for QSAR modeling. Since this technique has never been applied to other kinds of chemical multiway data, in this study classification models were carried out by means of MOLMAP approach on three-way analytical datasets of electronic nose and fluorescence data. For comparing purposes, other classification methods were applied to the same datasets: Discriminant Analysis on the PARAFAC scores and Partial Least Square-Discriminant Analysis (PLS-DA) on the unfolded data. Since the MOLMAP approach provided good results for the analyzed datasets, here, we propose the MOLMAP approach to be used as a general technique for the classification of multiway datasets. Actually, besides the good classification performances, other advantages came out: (a) the MOLMAP scores appeared as effective fingerprints for data characterization; (b) the role and importance of each portion of the multiway data can be analyzed in a comprehensive way; (c) it is possible to understand which variables have greater discriminant power and consequently apply data reduction. © 2007 Elsevier B.V. All rights reserved.

Ballabio, D., Consonni, V., & Todeschini, R. (2007). Classification of multiway analytical data based on MOLMAP approach. ANALYTICA CHIMICA ACTA, 605, 134-146 [10.1016/j.aca.2007.10.029].

Classification of multiway analytical data based on MOLMAP approach

BALLABIO, DAVIDE;CONSONNI, VIVIANA;TODESCHINI, ROBERTO
2007

Abstract

A new method for the study of molecule chemical information organized into three-way data structures (MOLMAP) was recently proposed in literature. Basically, MOLMAP molecular fingerprints are calculated by projecting bond properties of molecules into Kohonen networks and used to generate molecular descriptors for QSAR modeling. Since this technique has never been applied to other kinds of chemical multiway data, in this study classification models were carried out by means of MOLMAP approach on three-way analytical datasets of electronic nose and fluorescence data. For comparing purposes, other classification methods were applied to the same datasets: Discriminant Analysis on the PARAFAC scores and Partial Least Square-Discriminant Analysis (PLS-DA) on the unfolded data. Since the MOLMAP approach provided good results for the analyzed datasets, here, we propose the MOLMAP approach to be used as a general technique for the classification of multiway datasets. Actually, besides the good classification performances, other advantages came out: (a) the MOLMAP scores appeared as effective fingerprints for data characterization; (b) the role and importance of each portion of the multiway data can be analyzed in a comprehensive way; (c) it is possible to understand which variables have greater discriminant power and consequently apply data reduction. © 2007 Elsevier B.V. All rights reserved.
Articolo in rivista - Articolo scientifico
Scientifica
classification, chemometrics, Kohonen maps
English
134
146
Ballabio, D., Consonni, V., & Todeschini, R. (2007). Classification of multiway analytical data based on MOLMAP approach. ANALYTICA CHIMICA ACTA, 605, 134-146 [10.1016/j.aca.2007.10.029].
Ballabio, D; Consonni, V; Todeschini, R
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/10281/4539
Citazioni
  • Scopus 17
  • ???jsp.display-item.citation.isi??? 17
Social impact