Gusar – create QSAR/QSPR models on the basis of the appropriate training sets

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.

ECOTOXICITY PREDICTION

Quantitative prediction of ecotoxicity for chemical compounds by GUSAR software. The QSAR models were developed for the following endpoints: 96-hour fathead minnow 50% lethal concentration, 48-hour daphnia magna 50% lethal concentration, Tetrahymena pyriformis 50% growth inhibition concentration and Bioconcentration Factor.

DRAW STRUCTURE

Activity Name	N train	N test	N models	R2	Q2	R2 test	RMSE test	Coverage, %
Fathead Minnow LC50 Log10(mmol/L)	462	115	173	0.83	0.79	0.83	0.68	100
Bioaccumulation factor Log10(BCF)	478	120	196	0.83	0.80	0.85	0.56	100
Tetrahymena pyriformis IGC50 Log10(mol/L)	874	219	196	0.91	0.88	0.87	0.39	100
Daphnia magna LC50 -Log10(mol/L)	269	68	117	0.82	0.78	0.65	0.99	100

CHARACTERISTICS OF QSAR MODELS FOR ECOTOXICITY 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.