Chemaxon's Solubility Predictor¶
This documentation gives a short introduction to Chemaxon's Solubility Predictor.
Table of Contents¶
Availability¶
The Solubility Predictor is currently available in the following Chemaxon products.
MarvinSketch¶
The Solubility Predictor is integrated into Marvin Sketch as a plugin, making prediction fast and easy. The plugin can be found under the Calculations > Solubility > Aqueous Solubility menu item.
The plugin window appears once an input molecule appears on the canvas of MarvinSketch. Prediction error is shown
if the plugin is run on an empty canvas.
Menu system¶
The menu system of plugin has File, Options and Help menu items.
File menu¶
The File menu has the following items.
Export to PDF: exports the prediction results into a PDF report file.- Exit: closes the plugin window.
Options menu¶
The Options menu has the following items.
- Measurement Unit: sets the measurement unit of the prediction. The unit can be logS(default), mol/l or mg/ml.
- Restore default settings: restores the default settings of the prediction.
Help menu¶
The Help menu opens the help guide of the predictor.
Result panels¶
The result panels display the pH-solubility plot and the following prediction results:
-
Solubility information: displays the intrinsic solubility value, the solubility at pH 7.4 and a qualitative solubility category. The categories are:
- low: if the intrinsic solubility is < 0.01 mg/ml.
- moderate: if the intrinsic solubility is between 0.01 mg/ml and 0.06 mg/ml.
- high: if the intrinsic solubility is > 0.06 mg/ml.
- pH-Solubility table: displays the predicted pH-solubility values in a table format.

Fig. 1 The result window of the Solubility Predictor in MarvinSketch
cxcalc¶
The Solubility Predictor is integrated into the cxcalc command line tool. The command syntax is
where the calculation options are the following:
logs options:
-h --help this help message
-U --unit measurement unit [mg/ml | mol/l | logS] (default:
logS)
-i --intrinsic intrinsic solubility (default: false)
-c --category solubility category (default: false)
-H --pH solubility at this pH (default: not set)
-l --lower (default: 0)
-u --upper (default: 14)
-s --step (default: 1)
Here are some examples on how to use the Solubility Predictor via cxcalc:
- Calculating intrinsic solubility and solubility at pH 7.4:
- Calculating solubility values between pH 7.0 and 13.0 in mol/l unit:
- Predicting qualitative solubility category:
Chemical Terms¶
The Solubility Predictor is also integrated into Chemaxon's Chemical Terms language. The solubility can be calculated by the logS() function that has two parameters:
- The unit parameter, which could be logS, mg/ml, mol/l or category. In case category is used, qualitative solubility is calculated. If no unit parameter is set, logS is used.
- The pH parameter (e.g. '7.4') that sets the pH for the calculation. If no pH parameter is set, intrinsic solubility is calculated.
The following examples show how the logS function can be used with the evaluator command line tool:
- Calculating intrinsic solubility for acetic acid in logS unit:
- Calculating solubility at pH 7.0 in mol/l unit:
- Determining qualitative solubility category at pH 7.4:
KNIME¶
Solubility prediction is also available as a node in the KNIME workflow management system. All the calculation options are also available in KNIME. The pictures below show the General and the Advanced Options panels of the node:
Fig. 2 General options of the Solubility KNIME node
Fig. 3 Advanced options of the Solubility KNIME node
KNIME example¶
The following simple KNIME workflow is an example of how to predict solubility in KNIME:
Fig. 4 A KNIME workflow for predicting solubility in KNIME
The workflow starts with an importer node that provides input for the solubility node. The solubility node is set to calculate the intrinsic solubility in mol/l unit and the solubility category. The output is directed to a MarvinView node that is used to view the results.
The picture above shows the state of the nodes before the running of the workflow.
The first few lines of the output viewed in the MarvinView node:
Fig. 4 First few lines of the output of the workflow
Solubility API¶
The Solubility Plugin API with usage examples can be reached here.
Performance reports¶
We tested the accuracy of the Solubility Predictor on the full and a filtered subset (multi-component, charged molecules and structures containing rare elements were eliminated) of the HongPing Zhao’s solubility dataset. See the reference within the report.
Background materials¶
If you are curious about the details of Chemaxon's solubility model, you can find them here.
If you want to know more about how the model handle salts, you can read about that here.
References¶
-
Hou, T. J.; Xia, K.; Zhang, W.; Xu, X. J. ADME Evaluation in Drug Discovery. 4. Prediction of Aqueous Solubility Based on Atom Contribuition Approach. J. Chem. Inf. Comput. Sci. 2004 , 44, 266-275
-
Shoghi, E.; Fuguet, E.; Bosch, E.; Rafols, C. Solubility-pH profiles of some acidic, basic and amphoteric drugs European Journal of Pharmaceutical Sciences 2013 , 48, 291-300



