Predictor can be applied for molecular property prediction when molecular properties can be expressed as the sum of atomic contributions. You have to create a training file which contains the structures and the experimental values of the property you would like to create a prediction for.
cxtrain
The command line program cxtrain
is available for logP, pKa and custom prediction training.
cxtrain prediction -t MP -i meltingpoint my_data_mp.sdfThe data tagged MP is
Molecular Property Prediction Trainer, (C) 1998-2011 ChemAxon Ltd. version 5.4.0 Trains molecular property predictions: pKa, logP, etc. Usage: cxtrain[options] [input file (training set)] Prediction: pka train pKa prediction logp train logP prediction prediction train custom prediction General options: cxtrain -h, --help this help message -i, --training-id sets the training ID -l, --list list available training ID's -g, --ignore-error continue with next molecule on error pKa options: -V, --validation validation results file path logP options: -t, --tag name of the SDFile tag that stores the experimental logP values -a, --add-built-in-training-set add built-in logP training set Custom prediction options: -t, --tag name of the SDFile tag that stores the experimental property values Examples: cxtrain pka -i mypka pKa_trainingset.sdf cxtrain logp -t LOGP -i mylogp -a logP_trainingset.sdf cxtrain logp --list cxtrain prediction -t PAMPA -i mypampa pampa_trainingset.sdf
MarvinSketch and MarvinWiew applet cannot access pKa correction library files and logP/predictor training parameter files stored on server. Applet allows only to use trainings stored on local computer.
The training of the Predictor plugin is simplest by using the graphical interface of Instant JChem where the logP and general property trainings are available. See the IJC documentation for details.