Description:
Regression model with 3 QuBiLS-MIDAS descriptors the Contact Repellency in Aedes aegypti (Yellow Fever Mosquito). It is predicted the avoidance frequency, that is, an average of mosquito contact repellency over 3h
time period.
The training was performed with the Vote meta classifier in Weka 3.9.4 with 10-fold cross-validation, by using the “average” combination rule of these base learners: IBk (with K-nearest neighbors = 10 and True
cross-validation), M5P, and Random Forest algorithms. The 3 QuBiLS-MIDAS descriptors are namely:
GV[1]_S_Q_AB_nCi_2_M13_NS1_o_C_KA_r_MID
MN_Q_AB_nCi_2_M3_SS2_T_KA_e_MID
GOWAWA[0.8;1;AO2-OWA;1.0;1;ES2-OWA;0.9]_B_AB_nCi_2_M14_NS1_A_KA_psa-v_MID
Training set:
14 compounds extracted from 10.1021/jf900964e
Performance:
For a 10-fold cross-validation, the statistical parameters (performance without applicability domain) are R = 0.8123, MAE = 0.0784, RMSE = 0.1531, RAE = 52.3524 %, and RRSE = 68.7511 %.
Classification Breakpoint:
The breakpoint is 0.90. Values greater than or equal to the breakpoint will elicit a repellent response in Aedes aegypti mosquitoes. Lower values represent certain actions occurring, however, these are not enough to activate a repellent reaction.
Reference:
Paluch, G.; Grodnitzky, J.; Bartholomay, L.; Coats, J. Quantitative Structure-Activity Relationship of Botanical Sesquiterpenes: Spatial and Contact Repellency to the Yellow Fever Mosquito, Aedes Aegypti. J. Agric. Food Chem. 2009, 57 (16), 7618–7625. DOI: 10.1021/jf900964e