ACD/LogS0 GALAS: Difference between revisions

From ACD Percepta
Jump to navigation Jump to search
No edit summary
Line 33: Line 33:


<div class="mw-collapsible-content">
<div class="mw-collapsible-content">
Aqueous solubility module provides the quantitative estimate of the compound’s solubility (Log S<sub>w</sub>, mmol/ml and S<sub>w</sub> mg/ml) in pure water at 25°C using a fragmental GALAS (<b>G</b>lobal, <b>A</b>djusted <b>L</b>ocally <b>A</b>ccording to <b>S</b>imilarity) 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.
Aqueous solubility module provides the quantitative estimate of the compound’s solubility in water at 25°C (in terms of intrinsic solubility Log S<sub>0</sub>, mmol/ml) using a fragmental GALAS (<b>G</b>lobal, <b>A</b>djusted <b>L</b>ocally <b>A</b>ccording to <b>S</b>imilarity) 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<br>
'''Training set size:''' 4,764<br>
Line 45: Line 45:


<span style="font-size:8pt">
<span style="font-size:8pt">
<nowiki>*</nowiki> - Articles reporting LogS<sub>w</sub> 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.
<nowiki>*</nowiki> - Articles reporting the models of solubility in pure water (LogS<sub>w</sub>) 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. Original LogS<sub>w</sub> data had been converted to LogS<sub>0</sub> prior to modeling.
</span>
</span>
<br>
<br>
Line 51: Line 51:
<br>
<br>
{| cellpadding="2" cellspacing="0" style="border-top:2px solid black; border-bottom:2px solid black"
{| cellpadding="2" cellspacing="0" style="border-top:2px solid black; border-bottom:2px solid black"
|+ <b>Table 1.</b> ACD/LogS<sub>w</sub> (AB/LogS<sub>w</sub> v2.0) model performance statistics for the various fractions of the internal validation set.
|+ <b>Table 1.</b> ACD/LogS<sub>0</sub> model performance statistics for various fractions of the internal validation set.
|-
|-
! style="border-bottom:1px solid black; background:#EAEAEA" width="150" | Subset  
! style="border-bottom:1px solid black; background:#EAEAEA" width="150" | Subset  
Line 58: Line 58:
! style="border-bottom:1px solid black; background:#EAEAEA" width="100" | <i>RMSE</i>
! style="border-bottom:1px solid black; background:#EAEAEA" width="100" | <i>RMSE</i>
|-
|-
| align="center" height="60" | <i>RI</i> > 0.3 <br> N = 1,989
| align="center" height="60" | <i>RI</i> > 0.3 <br> N = 1,990


| align="center" |
| align="center" |
Line 65: Line 65:
|}
|}


| align="center" | 0.85 || align="center" | 0.81
| align="center" | 0.83 || align="center" | 0.84
|-
|-
| align="center" height="60" | <i>RI</i> > 0.5 <br> N = 1,733
| align="center" height="60" | <i>RI</i> > 0.5 <br> N = 1,663


| align="center" |
| align="center" |
{| cellpadding="0" cellspacing="0" style="width:80%; height:40px"
{| cellpadding="0" cellspacing="0" style="width:80%; height:40px"
| style="color:white; background:#B9CDE5" align="right" width="84.8%" | <b>84.8%&nbsp;</b> || style="background:#EDF2F9" width="15.2%" | &nbsp;
| style="color:white; background:#B9CDE5" align="right" width="81.4%" | <b>81.4%&nbsp;</b> || style="background:#EDF2F9" width="18.6%" | &nbsp;
|}
|}


| align="center" | 0.87 || align="center" | 0.75
| align="center" | 0.87 || align="center" | 0.77
|-
|-
| align="center" height="60" | <i>RI</i> > 0.75 <br> N = 593
| align="center" height="60" | <i>RI</i> > 0.75 <br> N = 567


| align="center" |
| align="center" |
{| cellpadding="0" cellspacing="0" style="width:80%; height:40px"
{| cellpadding="0" cellspacing="0" style="width:80%; height:40px"
| style="color:white; background:#B9CDE5" align="right" width="29.0%" | <b>29.0%&nbsp;</b> || style="background:#EDF2F9" width="71.0%" | &nbsp;
| style="color:white; background:#B9CDE5" align="right" width="27.7%" | <b>27.7%&nbsp;</b> || style="background:#EDF2F9" width="72.3%" | &nbsp;
|}
|}


| align="center" | 0.94 || align="center" | 0.59
| align="center" | 0.93 || align="center" | 0.64
|}
|}


</div>
</div>
</div>
</div>

Revision as of 09:35, 22 January 2013

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


Logs0.png


  1. Quantitative estimate of the compound's intrinsic solubility in 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. 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 in water at 25°C (in terms of intrinsic solubility Log S0, mmol/ml) 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 the models of solubility in pure water (LogSw) 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. Original LogSw data had been converted to LogS0 prior to modeling.

Internal Validation


Table 1. ACD/LogS0 model performance statistics for various fractions of the internal validation set.
Subset Coverage of the entire
internal validation set (N=2,043)
R2 RMSE
RI > 0.3
N = 1,990
97.4%   
0.83 0.84
RI > 0.5
N = 1,663
81.4%   
0.87 0.77
RI > 0.75
N = 567
27.7%   
0.93 0.64