ACD/LogSw GALAS

Overview

This module predicts intrinsic solubility (LogS₀, mmol/ml) of a compound in water at 25°C using a set of >6,800 compounds.

Features

• Calculates a Reliability Index for every prediction
• Performs a similarity search and displays top 5 most similar structures from the training sets of the model

Interface

1. Quantitative estimate of compound solubility in pure water
2. Indication of the prediction reliability along with the Reliability Index value
3. "Configure" and "Train" buttons provide the means to select the training library for use in calculations and to add new data to that library. The name of the currently selected library is indicated with italic font.
4. Estimated solubility in pure water in Sw (mg/ml) units
5. Up to 5 similar structures from the training set with experimental values

Note: Prediction reliability classification according to Reliability Index (RI) values:

• RI < 0.3 – Not Reliable,
• RI in range 0.3-0.5 – Borderline Reliability,
• RI in range 0.5-0.75 – Moderate Reliability,
• RI >= 0.75 – High Reliability

Technical information

Aqueous solubility module provides the quantitative estimate of the compound’s solubility (Log S_w, mmol/ml and S_w mg/ml) in pure water at 25°C using a fragmental GALAS (Global, Adjusted Locally According to Similarity) model. The latter methodology allows the module to provide a quantitative assessment of the quality of each prediction in the form of Reliability Index value.

Training set size: 4,764
Internal validation set size: 2,043
Main sources of experimental data:

• Reference books:
  • The Merck Index. An Encyclopedia of Chemicals, Drugs, and Biologicals, O'Neil, M.J., Smith, A., Heckelman, P.E., Budavari, S., Eds. 13th Edition, Merck & Co., Inc., Whitehouse Station, NJ, 2001
  • Therapeutic Drugs, Dolery, C., Ed. 2nd Edition, Churchill Livingstone, New York, NY, 1999
  • Clarke's Isolation and Identification of Drugs, Moffat, A.C., Jackson, J.V., Moss, M.S., Widdop, B., Eds. 2nd Edition, The Pharmaceutical Press, London, 1986
• Various articles from peer-reviewed scientific journals*

* - Articles reporting LogS_w models by other authors were the predominant type among analyzed literature, meaning that each publication contained larger collections of experimental data (usually in the order of tens or hundreds compounds) compiled from corresponding original experimental articles.

Internal Validation

Table 1. ACD/LogS_w (AB/LogS_w v2.0) model performance statistics for the various fractions of the internal validation set.

Subset	Coverage of the entire internal validation set (N=2,043)	R2	RMSE
RI > 0.3 N = 1,989	97.4%	0.85	0.81
RI > 0.5 N = 1,733	84.8%	0.87	0.75
RI > 0.75 N = 593	29.0%	0.94	0.59