Flare Field Descriptors

Generates Cresset 3D field descriptors for a set of aligned ligands, which can be used to build machine-learning models. The molecules must be pre-aligned - you can use the ‘pyflare’ executable with the ‘align.py’ python script or the 'Flare™ Align' node to perform the alignment.

The Flare Field Descriptors node has 2 modes: the ‘training set’ and ‘prediction set’ modes. Setting which mode to use depends on whether a descriptor types/coordinates table is given or not. If not given, the node will work in training set mode: if given, the prediction set mode will activate instead.

In training set mode, the input (training set) ligands are used to derive a set of 'sample positions' around the molecules based on their field points, which can be used to probe any ligand for the selected field descriptor types (for example, electrostatics and volume) at those positions. The ‘training set’ mode only requires the (training set) ligands for input and calculates the chosen field descriptor types and coordinates. The descriptor values are added as extra columns to the input ligands/training set: the descriptor types and sample point coordinates will be written as a table to the descriptors output port.

The ‘prediction set’ mode requires the input (prediction set) ligands and a table of descriptor types and coordinates. The table can be taken from the descriptor types/coordinates table generated when working in training set mode. The descriptor values will be calculated at the sample point coordinates specified in the table, and will be added as extra columns to the input ligands/prediction set. No descriptor types/coordinates table is written to the output in this mode.

Please refer to the Flare manual for a detailed explanation of the science behind the calculation of Cresset 3D field descriptors.

This node wraps the 'pyflare' executable, which must be installed with a valid license for this node to work. If this is installed in the default location on Windows, then it should be found automatically. Otherwise, you must either set the 'Cresset Home' preference or the CRESSET_HOME environment variable to the base Cresset software install directory. You may also set the 'pyflare Path' preference or the CRESSET_PYFLARE_EXE environment variable to point directly at the executable itself.

For more information visit www.cresset-group.com or contact us at support@cresset-group.com.

Options

Basic

Ligands
The aligned set of ligands to be used for training or prediction.
Descriptors
Optional table containing types and coordinates of descriptors. If not given, this data will be generated.
Electrostatic
Calculate electrostatic fields.
Volume
Calculate volume indicator field (0 outside, -1 inside).
vdW
Calculate steric (van der Waals potential) fields.
Hydrophobic
Calculate hydrophobic (greasy steric bulk) fields.
Sample point minimum distance
Only used when working in training set mode. Set the minimum distance between two sample points, so that they are at least this number of Angstroms apart. If two points come closer together than this threshold then the smaller one will be removed. Values of 0.5 to 2.0 are recommended.

Input Ports

Icon
Aligned ligands to be used for training or prediction.
Icon
Optional table containing types and coordinates of descriptors. If not given, this data will be generated.

Output Ports

Icon
The input ligands with the tags for field descriptors.
Icon
Table containing types and coordinates of the descriptors. Generates if this information is not given in the input.

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.