Abstract
Regression trees were built with an initial pool of 1085 molecular descriptors calculated by DRAGON software for 126 pyridinium bromides, to predict the melting point. A single tree was derived with 9 nodes distributed over 5 levels in less than 2 min showing very good correlation between the estimated and experimental values (R-2 = 0.933, RMS = 12.61 degreesC). A number n of new trees were grown sequentially, without the descriptors selected by previous trees, and combination of predictions from the n trees ( ensemble of trees) resulted in higher accuracy. A 3-fold cross-validation with the optimum number of trees (n = 4) yielded an R-2 value of 0.822. A counterpropagation neural network was trained with the variables selected by the first tree, and reasonable results were achieved (R-2 = 0.748). In a test set of 9 new pyridinium bromides, all the low melting point cases were successfully identified.
Original language | English |
---|---|
Pages (from-to) | 20-27 |
Number of pages | 8 |
Journal | Green Chemistry |
Volume | 7 |
Issue number | 1 |
DOIs | |
Publication status | Published - 1 Jan 2005 |
Keywords
- pyridinium derivative
- unclassified drug
- pyridinium bromide