Computers in chemistryComputers in chemistry V 0380 Diagnosing Breast Cancer Based on Support Vector Machines. -(LIU, H. X.; ZHANG*, R. S.; LUAN, F.; YAO, X. J.; LIU, M. C.; HU, Z. D.; FAN, B. T.; J. Chem. Inf. Comput. Sci. 43 (2003) 3, 900-907; Dep. Chem., Lanzhou Univ., Lanzhou 730000, Gansu, Peop. Rep. China; Eng.) -Lindner 34-223

A silicon (Si)-deficient top soil was used in a pot experiment to investigate the effect of Si application on the shoot and root morphology of alfalfa (Medicago sativa L.). Silicon was applied to the alfalfa plants at 6 different rates (0, 0.025, 0.05, 0.10, 0.20, 0.30 g/kg), and each treatment was replicated 6 times. This study indicated that the Si content of roots and shoots increased significantly (P<0.05) with increasing Si concentration in the soil, and that the Si content of roots was greater than that of shoots. Plants treated with Si had increased leaf area, height, forage yield and shoots per plant during the reproductive period in comparison with controls. The application of Si also increased root volume, the number of secondary roots and root biomass. The effects of Si application were greater on roots than on shoots. The ratio of shoot to root dry weight was below 1.62 when Si was applied to plants and 1.91 without Si application. Overall, overcoming available Si deficiency resulted in a significant increase in shoot and root growth.

Computers in chemistryComputers in chemistry V 0380 QSAR Study of Ethyl 2-[(3-Methyl-2,5-dioxo(3-pyrrolinyl))amino]-4-(trifluoromethyl)pyrimidine-5-carboxylate: An Inhibitor of AP-1 and NF-κB Mediated Gene Expression Based on Support VectorMachines. -(LIU, H. X.; ZHANG*, R. S.; YAO, X. J.; LIU, M. C.; HU, Z. D.; FAN, B. T.; J. Chem. Inf.

No abstract

The support vector machine (SVM), as a novel type of learning machine, for the first time, was used to develop a Quantitative Structure-Property Relationship (QSPR) model of the heat capacity of a diverse set of 182 compounds based on the molecular descriptors calculated from the structure alone. Multiple linear regression (MLR) and radial basis function networks (RBFNNs) were also utilized to construct quantitative linear and nonlinear models to compare with the results obtained by SVM. The root-mean-square (rms) errors in heat capacity predictions for the whole data set given by MLR, RBFNNs, and SVM were 4.648, 4.337, and 2.931 heat capacity units, respectively. The prediction results are in good agreement with the experimental value of heat capacity; also, the results reveal the superiority of the SVM over MLR and RBFNNs models.