GUSAR software was developed to create QSAR/QSPR models on the basis of the appropriate training sets represented as SDfile contained data about chemical structures and endpoint in quantitative terms.
ACUTE RAT TOXICITY PREDICTION
In silico prediction of LD50 values for rats with four types of administration (oral, intravenous, intraperitoneal, subcutaneous, inhalation) by GUSAR software. The training sets were created on the basis of data from SYMYX MDL Toxicity Database. They include the information about ~10000 chemical structures with data on acute rat’s toxicity represented on the LD50 values (log10 (mmol/kg)).

Copyright © Way2Drug.com, 2011 - 2016 | Privacy Policy
DRAW STRUCTURE
Administration
N train
N test
N models
R2
Q2
R2 test
RMSE test
Coverage, %
Oral
6280
2692
40
0.61
0.57
0.59
0.57
97.5
Intraperitoneal
2480
1065
68
0.66
0.56
0.57
0.57
96.1
Intravenous
920
394
50
0.73
0.66
0.63
0.62
99.2
Subcutaneous
759
325
7
0.69
0.59
0.50
0.69
92.0
CHARACTERISTICS OF QSAR MODELS FOR RAT LD50 VALUES PREDICTIONS
N train - number of compounds in the training set;
N test - number of compounds in the test set;
R2 - average R2 of the models calculated for the appropriate training set;
Q2 - average Q2 of the models calculated for the appropriate training set;
Coverage - % compounds from the test set in Applicability Domain.

Lagunin A., Zakharov A., Filimonov D., Poroikov V. QSAR Modelling of Rat Acute Toxicity on the Basis of PASS Prediction. Mol. Informatics, 2011, 30(2-3), 241–250. (HTML, PDF)