Application of linear discriminant analysis in the virtual screening of antichagasic drugs through trypanothione reductase inhibition

摘要: We have performed virtual screening to identify new lead trypanothione reductase inhibitor (TRI) compounds, enzyme present in Tripanozoma cruzi, the agent responsible of Chagas disease. From a training set 58 linear discriminant analysis (LDA) was using 2D and 3D descriptors as discriminating variables order find out which function characterizes active TRI. The values statistical parameters F - Snedecor Wilk's λ for (DF) showed good significance, long rate success prediction both test set: 91.38% 88.63%, that order. Internal validation through Leave — Group Out methodology with results, assuring stability DF. Afterwards, DF applied 422,367 compounds. optimum range octanol water partition coefficient compound develop inhibition second filtering criteria. 739 structurally heterogeneous drugs library were selected promissory