The resulting models had prediction accuracies for training, test (containing 275 compounds together), and external validation (109 compounds) sets as high as 89%, 71%, and 74%, respectively.
For instance, Fig. 7 shows the spectra index, with spectra organized by compound, with a JSmol [33] view of the structure, a link to the compound page, and external links to more data about the compound.
The Ames dataset comprised a training set of 4358 compounds, and two external sets of 1089 and 1090 compounds.
After merging compounds from the two sets it was observed that Random Forest was better in classifying compounds and for external test sets gave more accurate results than for the other two set (Tables 3 and 4).
Figure 1 Advanced Dataset Graphs built for the "aquatic toxicity datasets, including the training set TR (red – 644 compounds), and two external sets TS, involving 339 (black) and 110 (blue) compounds respectively.
Likewise, modeling of the mouse data set (211 modeling compounds and 24 external validation compounds) was unsuccessful (data not shown).
The 635 compounds that form the complete dataset used for this work were split into training (370 compounds), first validation (93) and external sets (used as the second validation set of 172 compounds) of the CAESAR model.
The validated models (including non-stochastic and stochastic indices) classify correctly more than 90% of compounds in both training and external prediction data sets.
All these metabolites are required to support an effective symbiotic nitrogen fixation [ 8], and their spatial location is indicated by [c] and [e] for cytoplasm and external compound.
Finally, we compared it with the device based on compound 2. The OLEDs device with compound 3 exhibited maximum current and external quantum efficiencies of 62.8 cd/A and 18.0%, respectively, with a small efficiency roll-off at high current densities.
