Your English writing platform
Discover LudwigExact(23)
Mean applicability score was 4.9 (range: 2 8).
For each screening data set, the rankings are further filtered using one of the three applicability score formulations.
This dependence alone would be no drawback, but the training data set also affects the possible values of the applicability score.
Table 7 Ranges of the applicability score for the different combinations of ADE formulation, kernel and experiment ADE Kernel Target Training Set Screening Set Min Max Avg.
This result might be caused by the removal of some ligands, due to their low applicability score, which actually had been predicted correctly.
An applicability score evaluated metrics based on cost of data collection, probable spatial extent of applicability, technical complexity, and indicator responsiveness.
Similar(37)
In the innermost domain presented in Table 6, consisting of the 100 compounds with the highest applicability scores, very few ligands are contained.
The suitability of the applicability domain estimation is evaluated by comparing the model performance on the subsets of the screening data sets obtained by different thresholds for the applicability scores.
A closer inspection reveals that the virtual screening performance of the model is considerably improved if half of the molecules, those with the lowest applicability scores, are omitted from the screening.
Two of the three AD formulations (Kernel Density Estimation and weighted KDE) can be applied without imposing any computing time overhead because the respective applicability scores can be calculated simultaneously with the prediction using the same iteration.
Unfortunately, the applicability scores computed by the different formulations cannot be directly compared on different experiments, and thus it is not possible to present robust default thresholds to decide whether a compound should be regarded as part of the models domain or not.
Write better and faster with AI suggestions while staying true to your unique style.
Since I tried Ludwig back in 2017, I have been constantly using it in both editing and translation. Ever since, I suggest it to my translators at ProSciEditing.

Justyna Jupowicz-Kozak
CEO of Professional Science Editing for Scientists @ prosciediting.com