Description:
Regression model to predict inhibitors of acetylcholinesterase (ACHE). The model was built with the Multiple Linear Regression technique by using a total of 8 QuBiLS-MAS descriptors.

Training and testing datasets:
A total of 74 training compounds and 37 testing compounds were extracted from the Sutherland, et al., 10.1021/jm0497141

Internal performance:
For a 10-fold cross-validation repeated 100 times: Squared R = 0.7378, MAE = 0.5146, and RMSE = 0.6223.

External performance:
Squared R = 0.8114, MAE = 0.4555, and RMSE = 0.6006.

Regression equation:
pLC50 =

     -1.17   * RA_B_AB_nCi_2_MP2_C_LGP[2-8]_ec-dc4_MAS +
  -2210.7846 * TS[5]_GM_F_AB_nCi_2_MP6_H_X_LGP[5-6]_dc4_MAS +
      0.4237 * TS[7]_I50_F_AB_nCi_2_SS15_n_T_LGP[4-7]_alk_MAS +
      0.2281 * AC[6]_S_Q_AB_nCi_2_NS14_H_T_LGP[4]_ku_MAS +
     15.7997 * AC[3]_MX_B_BB_nCi_2_SS5_H_P_LGP[5-7]_est-dc4_MAS +
  -1572.5761 * MN_B_AB_nCi_2_MP8_n_T_LGP[5]_e-li_MAS +
      0.5096 * TS[1]_K_F_AB_nCi_2_MP2_C_LGP[2-8]_alk_MAS +
    -28.0899 * GV[6]_HM_Q_AB_nCi_2_MP12_n_A_LGP[3-6]_ec_MAS +
      7.9839