Skip to main content
. Author manuscript; available in PMC: 2018 Dec 7.
Published in final edited form as: SAR QSAR Environ Res. 2017 Apr 20;28(4):297–310. doi: 10.1080/1062936X.2017.1311941

Table 5:

Results for sensitizing and non-sensitizing predictions for 141 chemicals as well as the LLNA potency class accuracy for all chemicals predicted in the original network, grouped by reaction domain. (Four chemicals are missing from this table, 2 had alerts for nucleophilic addition and the other 2 had alerts for SNAr.)

Alert Number of
Compounds
Sensitization
Accuracy
LLNA Potency
Class Accuracy
Over Prediction of
Class
Under
Prediction
of Class

Acylation 15 848780%  456033% 344720% 212713%
Michael Acceptor 21 100100100% 768666% 212914% 3010%
No Alert Found 64 858883% 687363% 10614% 222519%
Schiff Base Former 23 899683% 667461% 15922% 192613%
SN2 14 100100100% 576443% 283621% 15721%