Fingerprints atom pair

The second step comprises similarity searches from known ligands using 2-D descriptors like fingerprints, topological descriptors like atom-pair fingerprints. 

Atom pair Fingerprints count the shortest path of bonds between two atom types [62, 63], each bit corresponds to a specific pair separated by a predefined number of bonds. Recently, physico-chemical properties rather than atom typing were successfully implemented [64],... 

Fig. 1.2 Examples of molecule-dependent atom pair fingerprints (APF) descriptors depicted with respect to the drug Lipitor. Regions highlighted in light green and light blue correspond to substructures associated with two APFs the labels below each figure correspond to respective designations given in reference [46] for these APFs...

In addition to looking for data trends in physical property space using PCA and PLS, trends in chemical structure space can be delineated by viewing nonlinear maps (NLM) of two-dimensional structure descriptors such as Unity Fingerprints or topological atom pairs using tools such as Benchware DataMiner [42]. Two-dimensional NLM plots provide an overview of chemical structure space and biological activity/molecular properties are mapped in a 3rd and/or 4th dimension to look for trends in the dataset. 

Matter [45] has also validated a range of 2D and 3D structural descriptors for their ability to predict biological activity and for their ability to be able to sample structurally and biologically diverse datasets effectively. The descriptors examined included Unity 2D fingerprints [42], atom-pairs [47],... 

FIGURE 15.7 3D projections of PCA-based chemical spaces generated from a set of 2250 compounds obtained from nine datasets of 250 compounds each using four different molecular fingerprints (Atom pairs, MACCS keys, TGD, and piDAPH4) and the Tanimoto similarity function (see text for further details). For color details, please see color plate section. 

---