ADAPT topological descriptors

There are three general classes of descriptors topological, geometrical, and physicochemical. Topological descriptors are derived from the topological representation of the structure, the connection table. The geometrical descriptors are derived from the three dimensional model of the molecule. Physicochemical descriptors may be measured experimentally, calculated using a mathematical model, or represented by linearly correlated calculated descriptors. The descriptors that are currently available in ADAPT are as follows ... 

The %HIA, on a scale between 0 and 100%, for the same dataset was modeled by Deconinck et al. with multivariate adaptive regression splines (MARS) and a derived method two-step MARS (TMARS) [38]. Among other Dragon descriptors, the TMARS model included the Tig E-state topological parameter [25], and MARS included the maximal E-state negative variation. The average prediction error, which is 15.4% for MARS and 20.03% for TMARS, shows that the MARS model is more robust in modeling %H1A. 

Jurs and co-workers have used parameters generated by the ADAPT system [34], The descriptors fall into three categories topological, electronic, and geometric. 

One of the software systems available for pattern recognition studies is ADAPT (automated data analysis using pattern recognition techniques). The structure of each member of the data set is represented by molecular descriptors. These numerical indices, which encode information about the molecule, fall into four classes topological, geometrical, electronic and physicochemical. The data are analysed using pattern recognition techniques to develop a classifier which can discriminate between the classes of data. 

---