Role of compound orientation in CoMFA studies

Our work shows that different compound orientations have different results in Comparative Molecular Field Analysis (CoMFA). For three analyzed compound series, the squared correlation coefficients of cross-validation (q2) could vary as largely as 0.30 - 0.40 among all possible orientations. The reason for this comes from the routine adopted by CoMFA which uses discrete, regularly arrayed grids to represent the molecular field. Therefore, different orientations may map their molecular fields differently onto the grid and accordingly give different results from partial least square (PLS) analyses. We have developed a method, all-orientation searching, to seek for the orientation with the best CoMFA result. And, we suggest that all-orientation searching should be incorporated into the standard CoMFA procedure.