QSAR models for reproductive toxicity and endocrine disruption in regulatory use – a preliminary investigation†

†Presented at the 13^th International Workshop on QSARs in the Environmental Sciences (QSAR 2008), 8–12 June 2008, Syracuse, USA.

Figures & data

Table 1. Training set information for models for reproductive toxicity and endocrine disruption.

	Total (n)	Positive (n)	Negative (n)
Reproductive toxicity
Teratogenic risk	323	130	193
Rodent dominant lethal	191	78	113
Drosophila m. SLRL	377	190	187
Endocrine disruption
Estrogen α receptor binding	595	284	311
Estrogen reporter gene	481	195	286
Androgen receptor antagonism	523	242	281

Table 2. Cross-validation results for the QSAR models.

	Sensitivity (%)	Specificity (%)	Concordance (%)
Reproductive toxicity
Teratogenic risk	50.2	91.3	79.3
Rodent dominant lethal	41.3	95.2	75.9
Drosophila m. SLRL	73.9	88.1	81.6
Endocrine disruption
Estrogen α receptor binding	77.3	86.5	82.5
Estrogen reporter gene	46.4	94.9	80.9
Androgen receptor antagonism*	64.4	84.2	76.1
Note: The androgen receptor antagonism model was also validated by prospective external validation, where a validation set was chosen after the model had been constructed by randomly choosing test chemicals within the applicability domain. The chemicals were double blinded and tested in our laboratory. The external validation with 102 chemicals resulted in a sensitivity of 57%, a specificity of 98%, and a concordance of 92% of the model 14.

Table 3. Domains of the models within 57,014 EINECS substances.

	Domain (%)
Reproductive toxicity
Teratogenic risk	43
Rodent dominant lethal	48
Drosophila m. SLRL	56
Endocrine disruption
Estrogen α receptor binding	52
Estrogen reporter gene	61
Androgen receptor antagonism	56

Figure 1. Algorithm for reproductive toxicity screening.

Table 4. Prediction of 57,014 EINECS chemicals for reproductive toxicity.

QSAR models	Chemicals (n)	Chemicals within domain (n)	Positive chemicals (n)	Positive chemicals (%)
Teratogenic risk	57,014	24,516	2331	9.5
Rodent dominant lethal	57,014	27,366	1906	7.0
Drosophila m. SLRL	57,014	31,927	1668	5.2
Reproductive toxicity, total^a	57,014		5240	9.2
^aIf positive in at least one model.

Table 5. Prediction of 57,014 EINECS chemicals for teratogenic risk, genotoxic relation.

QSAR models	Unit	Positive chemicals
Teratogenic risk	n	2331
Teratogenic risk and rodent dominant lethal or Drosophila m. SLRL	n	349
Genotoxic relation	%	15

Table 6. Prediction of 57,014 EINECS chemicals for reproductive toxicity, endocrine disruption relation.

QSAR models	Positive chemicals (n)	Positive chemicals (%)
Reproductive toxicity	5240
Teratogenic risk or rodent dominant lethal or Drosophila m. SLRL
Reproductive toxicity and androgen receptor antagonism	278	5.3
Reproductive toxicity and estrogen reporter gene	172	3.3
Reproductive toxicity and estrogen α receptor binding	244	4.7

Figure 2. Chemical no. 1 predicted by the teratogenic risk model.

Figure 3. Chemical no. 2 predicted by the rodent dominant lethal model.

Vinggaard , AM , Niemelä , JR , Wedebye , EB and Jensen , GE . 2008 . Screening of 397 chemicals and development of a QSAR model for androgen receptor antagonism . Chem. Res. Toxicol. , 21 : 813 – 823 .

 PubMed Web of Science ®Google Scholar