Fluorine pKa

For predicting are used a lot of generated molecule features using the most important and not correlated features from mordred (partial positive surface area, partial negative surface area, number of fluorine or carbon atoms etc.), rdkit (number of cycles, chiral centers etc) and custom calculation (dihedral angle, molecular weight and volume, dipole moment, sasa, functional group freedom etc). All this molecule features used for predicting pKa values using ML models.

Options

Execution time

How to execute feature generation.

Available options:

  • Fast/Inaccurate: Generates less conformers for feature generation. Results in faster prediction, but with less accurate results.
  • Slow/Accurate: Generates 3^(number of double bonds) conformers for feature generation. Results in slower prediction, but better accurate results.
  • Experimental - Fast/Accurate: Graph neural network with features that are generated very quickly is used for prediction. The results are even better than other modes.
SMILES column:

Select the column containing SMILES.

Input Ports

Icon

Table with SMILES in 'string' of 'SMI' format

Output Ports

Icon

Table with predicted pKa values

Popular Predecessors

  • No recommendations found

Popular Successors

  • No recommendations found

Views

This node has no views

Workflows

  • No workflows found

Links

Developers

You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.