3D QSAR Model: Validation
Category Paths
Follow one of these paths in the Orion user interface, to find the floe.
Models
Description
The 3D QSAR Model: Validation Floe is a tool for performing validation of a model against an external dataset.
The model validation floe requires two datasets: (1) a dataset of a model with stored receptors and reference molecules, if any, obtained from using the 3D QSAR Model: Builder Floe and (2) a dataset of test set molecules, along with their experimental potency.
Outputs from this floe contain a validation report and an output dataset with model predictions, along with 3D conformers.
Promoted Parameters
Title in user interface (promoted name)
Inputs
Ligand Database (in): Dataset with external molecules for validation.
Required
Type: data_source
Model (model): Dataset containing the model.
Required
Type: data_source
Potency Parameters
Input Potency field (in_potency_field): Field containing input potency data
Required
Type: field_parameter::float
Default: potency
Unit for Potency (potency_unit): Unit for input potency field (e.g. nanomolar or micromolar for IC50 and log for pIC50)
Type: string
Default: log
Choices: [‘micromolar’, ‘nanomolar’, ‘log’]
Minimum Potency (potency_min): Molecules with potency (log unit) at or below this value are not trustworthy and discarded.
Type: decimal
Default: 0.0
Maximum Potency (potency_max): Molecules with potency (log unit) at or above this value are not trustworthy and discarded.
Type: decimal
Default: 15.0
3D Conformer Parameters
Use Input 3D (use_input_3d): Whether to use 3D input structures. Flag will be ignored for molecules without 3D input structures.
Type: boolean
Default: True
Choices: [True, False]
Charge Method Parameters
Charge Type (method_type): Charge assignment method.
Type: string
Default: am1bcc
Choices: [‘am1bcc’, ‘mmff’, ‘current_charges’]