Description:
Regression model with 2 QuBiLS-MIDAS descriptors used for the prediction of the Percentage of Repellency, PR, (%) to trigger Aedes aegypti (Yellow Fever Mosquito) spatial repellency at the time of 180 min.

The training was performed with the Stacking algorithm as default in Weka 3.9.4 with 10-fold cross-validation by using Linear Regression algorithm as meta classifier and as classifiers: Random Forest, SMOreg (with Pearson Universal Kernel (PUK)), and IBk (with K-nearest neighbors = 10 and True cross-validation). The 2 QuBiLS-MIDAS descriptors are namely:

IB_K_Q_AB_nCi_2_M1_SS2_o_T_LGL[1-2]_r_MID
MN_B_AB_nCi_2_M11_SS7_T_LGP[1]_e-p_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 = 0.9056, MAE = 3.8905, RMSE = 5.7667, RAE = 31.6109 %, and RRSE = 38.9025 %.

Classification Breakpoint:
The breakpoint is 90 %. Values greater than or equal to the breakpoint will elicit a repellent response in Blatella germanica and Periplaneta americana cockroaches. 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