Initially, all molecules were translated into a series of descriptors to encode various aspects of chemical structures including both 2-D and 3-D structure information.
As such, every IL is described by a series of molecular descriptors.
Further incorporation of a series of sound descriptors not only did not provide better performance, but raised the computational cost.
This method was used to select the best parameters for classifying the chemicals by their carcinogenic potency (P-carcinogens and NP- non-carcinogens) among the different molecular descriptors series.
Within CAESAR, the data mining approach has been improved using a highly verified set of compounds (all chemical structures have been double-checked, and experimental data verified in case of some unusual finding, compared to similar compounds), and adopting a wide series of chemical descriptors.
In the first group, which mainly comprises quantitative structure-activity relationships (QSAR) models, statistical methods are applied to identify quantitative patterns between the structure of a chemical compound (represented as a series of molecular descriptors) and a specific biological property [5].
We have studied a series of structural descriptors intended for describing protein shapes (the radius of gyration, the radius of cross-section, and the coefficient of compactness) and their possible connection with folding behavior, either rates of folding or the emergence of folding intermediates, and compared them with classical descriptors, protein chain length and contact order.
This approach was preferred to Fourier analysis or harmonic regression because it allows for missing data (common in our data set) and decomposes spectra into a series of temporal descriptors that can be used as independent variables in a number of statistical methods, such as multiple regression [29].
The edited images were converted to 8-bit grayscale, and then binarized using the default IsoData algorithm (Ridler and Calvard, 1978), adjusting the maximum threshold value manually to distinguish the charcoal particles, and with the minimum threshold value set at 0. A series of shape descriptors were generated for all the resulting particle images.
To evaluate our proposed descriptor, a series of simulated experiments using synthetic datasets is conducted via shape matching tests.
