OECD TG 405, known as the Draize test, describes how data is obtained for scoring criteria for acute eye irritation/corrosion (OECD, 2012a ). The Draize test involves application of a chemical of interest to white albino rabbit eyes in vivo. Damage is scored for cornea, iris, conjunctivae and chemosis. Each ocular endpoint has subjective scoring rules described in Table 1 . GHS hazards describe how Draize endpoint scores can be mapped to 4 categories of irritation: Type 1, Type 2A, Type 2B and non-irritating. Type 1 and Type 2 irritants are differentiated by reversibility with Type 1 irritants causing serious or irreversible eye damage that persists for 21 days post-exposure. Type 2 irritants are reversible before 21 days. Type 2A and Type 2B irritants are differentiated by the severity of irritation with Type 2A irritants more severe than Type 2B and further subcategorized if effects are fully reversible within 7 days of substance application. Eye irritation categories are defined from endpoint features. The classification strategy for H318 (Draize Type 1), H319 (Draize Type 2A) and H320 (Draize Type 2B) is generated in Figure 4 from classifications given by the Infectious Disease Research Institute (IDRI)5 and defined by the UN GHS. OECD guideline data is interpreted according to the following rules (OECD, 2012a ): Type 2A versus 2B can be determined by 7 day reversibility of effects. Severity of cornea and iris effects with 21-day reversibility differentiate Type 1 and 2A.
For each substance we derived from all the Draize studies an average value for each Draize endpoint (iris, cornea, etc.) and a maximum value for each endpoint. The ECHA Draize studies report Draize endpoint values, thus allowing for the sum and maximum values to be found for these endpoints.
In addition, we derived one “reversibility” feature matching the study and endpoint with the longest reversibility time. For example, for a chemical with a chemosis endpoint that shows a reversibility period greater than 21 days we apply the value “irreversible” to the “reversibility” feature. Finally, the classification and labeling hazard value reported in the given substance’s ECHA dossier was used to define a Draize GHS category corresponding to the category of Draize response (Type 1, 2A, 2B). The features for this model are described below:
For each substance we derived from all the Draize studies an average value for each Draize endpoint (iris, cornea, etc.) and a maximum value for each endpoint. The ECHA Draize studies report Draize endpoint values, thus allowing for the sum and maximum values to be found for these endpoints.
In addition, we derived one “reversibility” feature matching the study and endpoint with the longest reversibility time. For example, for a chemical with a chemosis endpoint that shows a reversibility period greater than 21 days we apply the value “irreversible” to the “reversibility” feature. Finally, the classification and labeling hazard value reported in the given substance’s ECHA dossier was used to define a Draize GHS category corresponding to the category of Draize response (Type 1, 2A, 2B). The features for this model are described below:
Chemosis mean: chemosis mean scores
Chemosis max: max of chemosis scores for substance
Iris mean: mean iris scores
Iris max: max iris scores
Cornea mean: mean of cornea scores
Cornea max: max of cornea scores
Conjunctivae mean: mean of conjunctivae scores
Conjunctivae max: max of conjunctivae scores
Reversibility: longest endpoint reversal period
Draize GHS Category: H318 = Type 1, H319 = Type 2A, H320 = Type 2B
