Comparison of three holographic fingerprint descriptors and their binary counterparts

Molecular fingerprint representations were compared with respect to their ability to retrieve sets of ligands by retrospective similarity searching. Twelve different biological target classes were considered, and both "holographic" fingerprint vectors containing floating-point or integer values giving the frequency of occurrence of fragment types or atom pairs, and their "binary" representations were compared. The descriptors were substructure-based or grounded on topological and spatial pharmacophore type pairs. Enrichment factors between seven and 19 were obtained for the top-scoring two percent of the reference database, depending on the target class. Although the holographic fingerprints yielded higher enrichment factors on average, only for two target classes significant differences (> 20%) between holographic and binary fingerprint representations were observed. This result demonstrates that binary fingerprint representations can be applied to rapid similarity searching for most target classes without losing significant enrichment of actives in the virtual hit lists. A comparison of the individual molecules retrieved by holographic fingerprints and their binary representation revealed that significantly different sets of actives and "inactives" were found. The intersections of two virtual hit lists ranged from zero to approximately 90% for the set of known ligands. This result demonstrates that "binarization" of continuous molecular descriptors has a significant effect on the topology of chemical space and the resulting neighborhood behavior of chemical similarity searching.