Sesquiterpene Lactones-Based Classification of the Family Asteraceae Using Neural Networks and k-Nearest Neighbors

Abstract

In a recent publication we described the application of an unsupervised learning method using self-organizing maps to the separation of three tribes and seven subtribes of the plant family Asteraceae based on a set of sesquiterpene lactones (STLs) isolated from individual species. In the present work, two different structure representations--atom counts (2D) and radial distribution function (RDF) (3D)--and two supervised classification methods--counterpropagation neural networks and k-nearest neighbors (k-NN)--were used to predict the tribe in which a given STL occurs. The data set was extended from 144 to 921 STLs, and the Asteraceae tribes were augmented from three to seven. The k-NN classifier with k = 1 showed the best performance, while the RDF code outperformed the atom counts. The quality of the obtained model was assessed with two test sets, which exemplified two possible applications: (1) finding a plant source for a desired compound and (2) based on a plant species chemical profile (STLs): (a) study the relationship between the current taxonomic classification and plant's chemistry and (b) assign a species to a tribe by majority vote. In addition, the problem of defining the applicability domain of the models was assessed by means of two different approaches-principal component analysis combined with Hotelling T2 statistic and an a posteriori probability-based rule.

Sesquiterpene Lactones with Anti-Hepatitis C Virus Activity Using Molecular Descriptors

“…(1). Molecular structures of SLs (1-8), exo-methylene lactones (9,10) and parthenolide analogues (11)(12)(13)(14)(15)(16)(17)(18)(19) analyzed for the anti-HCV activity.…”

“…The most used ANNs architecture for pattern recognition and classification is the Self-organizing maps (SOM). SOM is a powerful visualization tool able to reduce dimensions of projections and displays similarities among objects, which has already been successfully used in several applications in chemical database [15][16][17][18][19].…”

Chemotaxonomy of three genera of the annonaceae family using self-organizing maps and 13C NMR data of diterpenes

“…[22][23][24][25][26][27][28] Chemotaxonomic studies have been applied at several levels using different classes of secondary metabolites: superorders of angiosperms; 20,24,25 families such as Asteraceae, 29 Meliaceae, 27 Apocynaceae, 28 Lamiaceae; 30 tribes of Asteraceae. 23,[31][32][33][34][35] ANNs (Artificial Neural Networks) are a method or, more precisely, a set of methods, used extensively since the 1990s. Since ANNs are not restricted to linear correlations and can also take into account non-linear data correlations, they can be efficiently applied for modeling, prediction and classification.…”

“…36 Another very useful application is in the prediction and classification of spectra such as infrared, 39 mass, 40 and nuclear magnetic resonance [41][42][43] , including some QSAR studies. 44 In natural products chemistry, there are a few studies available showing applications of ANNs, such as the classification of Asteraceae tribes, 31,32,35 and the prediction of skeletal types. 45,46 13 C NMR (Nuclear Magnetic Resonance) data yield rich information about the molecular structure and are sufficiently sensitive to detect small differences in the molecule.…”

Self-organizing maps and VolSurf approach to predict aldose reductase inhibition by flavonoid compounds

“…A SOM can map multivariate data onto a two dimensional grid, grouping similar patterns near each other and it was successfully used in several applications using chemistry database, such as classification of photochemical reactions (Zhang & Aires-de-Souza, 2005), chemotaxonomy of the Asteraceae family (Da Costa et al, 2005;Hristozov et al, 2007), for a series of 103 sesquiterpene lactones which showed anti-inflammatory activity (Wagner et al, 2006), in drug design (Gasteiger et al, 2003), in the prediction of the cytotoxic potency of 55 SLs (Fernandes et al, 2008), in the comparison of dataset compounds (Bernard, 1998), in the classification of metabolites (Gupta & Airesde-Sousa, 2007) and in the prediction of the diterpene skeletons (Emerenciano et al, 2006) classification of plants at lower hierarchical levels (Correia et al, 2008).…”