Ai Feedback
Exact(9)
In order to evaluate the predictive performance of models predicting log Vss, the Vss-target dataset was randomly divided into two sets.
However, here we used data for rat Kt:p, rather than human Kt:p, when building models predicting log Kt:p.
We built models predicting log Vss, rather than Vss, because Vss has a very skewed distribution, with relatively few compounds having very high Vss values.
Then, the predicted log Kt:p values from these models together with molecular descriptors are used as descriptors to build models predicting log Vss.
The best model built for each tissue was then used to predict that tissue's log Kt:p value for all compounds in the Vss-target dataset, where those predicted log Kt:p values are used as descriptors (in addition to a large number of molecular descriptors) to build and validate models predicting log Vss.
In the first phase we build QSPkR models for predicting log Kt:p values for different tissues based on molecular descriptors; whilst in the second phase we used the predicted log Kt:p values as descriptors, in addition to molecular descriptors, to build QSPkR models predicting log Vss.
Similar(51)
Finally, the best model predicting log Kt:p for each tissue is chosen as the model produced by the method with the lowest MAE.
Hence, once the best model predicting log Kt:p has been selected for each tissue based on the results shown in Table 1, the decision about which of those models will be used as descriptors should be made by directly taking into account the predictive performance of each predicted log Kt:p descriptor in log Vss models.
Results of multiple regression model predicting log-transformed serum concentration of BDEs with housing characteristics.
Regression models were adjusted for the ICNARC model predicted log-odds of hospital mortality to further account for any residual differences in acute severity of illness at admission.
Regression models were adjusted for the ICNARC model predicted log-odds of hospital mortality, in order to account for residual differences within the matched pairs [ 10].
Related(19)
models predicting depression
models predicting disc
models including log
models using log
models predicting fAPAR
models predicting impulsivity
models predicting class
models predicting wood
models predicting viscosity
models predicting probability
models predicting pKa
models predicting growth
models predicting shell
models predicting particle
models predicting metastasis
models predicting burrow
models predicting program
models predicting progression
models predicting mortality
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