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 SMOreg algorithm (with Pearson Universal Kernel (PUK)) as classifier in Weka 3.9.4 with 10-fold cross-validation. The 3 QuBiLS-MIDAS descriptors are namely:

AM_B_AB_nCi_2_M3_SS2_n_T_LGL[5-6]_c-s_MID
MN_B_AB_nCi_2_M11_SS7_T_LGP[1]_e-p_MID
IB_K_B_AB_nCi_2_M3_NS1_T_LGL[1-2]_m-h_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 = 0.7287, MAE = 0.0793, RMSE = 0.1539, RAE = 52.9587 %, and RRSE = 69.1266 %.

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