Comparison of binary and 2D QSAR analyses using inhibitors of human carbonic anhydrase II as a test case

Binary and conventional 2D QSAR have been derived for a set of carbonic anh ydrase II (CA II) inhibitors. An overall predictive accuracy of 94% was obt ained by binary QSAR and of 84% by 2D QSAR model. For both models, preferre d molecular descriptor sets were identified, which were overlapping but not identical. Both binary and 2D QSAR captured important molecular features o f CA II inhibitors, notably the presence of a sulfonamido group, which is c ritical for binding, but also hydrophobicity. Promising results were obtain ed when the derived QSAR models were used to test a set of CA II inhibitors not included in the training set. In binary QSAR, previously unobserved bo undary effects were detected both in the analysis of known inhibitors and w hen screening a large combinatorial library for putative inhibitors. The co mplementary use of binary and conventional 2D QSAR is thought to increase t he accuracy of the lead discovery process by QSAR techniques.