One type of modeling involves the correlation of molecular descriptors with chromatographic retention times.
The final model is linear and has three molecular descriptors with the squared correlation coefficient of 0.9885 (R2 = 0.9885).
As described above, we have detailedly presented the ChemDes platform that covers 3679 molecular descriptors with diverse types and 59 types of molecular fingerprints.
For example, using different types of molecular descriptors with their detailed definitions would be very helpful to variable selection and model explanation when the users establish QSAR models.
Quantitative structure-retention relationship (QSRR) analysis was performed in order to identify molecular descriptors with the highest influence on k and ANN(k) model was selected as optimal.
We were able to show that free energies of binding can be reliably predicted by means of simple, readily available molecular descriptors with all three of the linear regression methods studied.
QSPR analysis was performed in order to identify molecular descriptors with the highest influence on %T and − logPapp and to create models which could be used for the design of novel HAA with improved gastrointestinal absorption.
In the present study a classification model was carried out to identify, through molecular descriptors with structural fragments and groups information, those acridinic derivatives with better inhibitory concentration on telomerase enzyme.
In the present investigation, we attempt cross-column prediction by combining in the same model usual LSER molecular descriptors with observed retentions of selected solutes within the calibration set, adopted to represent the stationary phase features.
Instead of the Leave-One-Out Attribute Selection worker a GA Attribute Selection worker may be used to determine a minimum molecular descriptor subset with maximum predictability.
