Computational Study of Estrogen Receptor-Alpha Antagonist with Three-Dimensional Quantitative Structure-Activity Relationship, Support Vector Regression, and Linear Regression Methods

Table 3

The intercorrelations between the 11 selected features (descriptors) and the activity presented in pIC₅₀ for the studied compounds^a.

	𝑥1	𝑥2	𝑥3	𝑥4	𝑥5	𝑥6	𝑥7	𝑥8	𝑥9	𝑥10	𝑥11
pIC50	−0.32	0.2	−0.22	−0.25	−0.33	0.11	−0.02	0.19	0.24	−0.22	0.39
𝑥1	1
𝑥2	−0.08	1
𝑥3	0.33	−0.01	1
𝑥4	0.11	−0.11	−0.1	1
𝑥5	0.56	−0.12	0.34	0.43	1
𝑥6	0.11	0.18	0.29	−0.01	0.5	1
𝑥7	−0.28	0.26	0	−0.2	−0.13	0.43	1
𝑥8	−0.12	−0.21	0.05	0.04	0.26	0.63	0.05	1
𝑥9	−0.11	−0.03	−0.02	0.37	0.07	−0.02	0.06	−0.01	1
𝑥10	0.49	−0.04	0.52	0.29	0.93	0.68	−0.07	0.39	0.06	1
𝑥11	−0.43	0.2	−0.12	−0.35	−0.52	−0.25	0.09	−0.07	−0.06	−0.47	1

aDescriptors used are
𝑥₁: Complementary information content (CIC) (fast descriptors).
𝑥₂: Estate keys (sums): S_ssCH2 (fast descriptors).
𝑥₃: Estate keys (sums): S_aasC (fast descriptors).
𝑥₄: Estate keys (sums): S_dO (fast descriptors).
𝑥₅: Principal moment of inertia 𝑋 (spatial descriptors).
𝑥₆: Shadow area: 𝑍𝑋 plane (spatial descriptors).
𝑥₇: Shadow area fraction: 𝑌𝑍 plane (spatial descriptors).
𝑥₈: Shadow ratio (spatial descriptors).
𝑥₉: Dipole moment 𝑍 (spatial descriptors).
𝑥₁₀: SASA (jurs descriptors).
𝑥₁₁: RPCS (jurs descriptors).