DUSR (Distributed Ultrafast Shape Recognition): a Hadoop Based Tool to Identify Similar Shaped Ligand Molecules

Abstract

Abstract: Background: Identifying potential drug candidates through Ligand-based virtual screening is often associated with processing of huge amount of data and hence is a computational intensive task. Ultrafast Shape Recognition (USR) algorithm has been reported as a faster alternative for molecular shape comparison which maps the chemical structure of query ligand into its shape moment vector to find novel chemical scaffolds in chemical compound libraries. The USR algorithm however was devoid of the ability to discriminate ligand molecules according to their pharmacokinetic features. Methods: To overcome this discrepancy, a modification in the existing USR algorithm called DUSR (Distributed Ultrafast Shape Recognition) was carried out where chemical compounds were screened on the basis of their drug-likeliness properties prior to the molecular shape comparison followed by shape complementarity momentum measure. The DUSR due to its Hadoop implementation acts as a faster approach than the existing standalone tools, utilizing the MapReduce algorithm supporting the high throughput screening of million conformers in a much reduced time span. We further demonstrated the utility of DUSR on dataset of 2 million ligand molecules by running shape comparison based searching job on standalone and multisystem Hadoop platforms. Results: The result suggested that DUSR completed its job in 1h 15 m 41s, 0 h 23 m 41s and 0h13m 22s sec for 2038924 molecules on Hadoop standalone mode, 3-nodes cluster & 5-nodes cluster of distributed commodity hardware respectively. Key words: DUSR (Distributed Ultrafast Shape Recognition), High throughput Screening, Hadoop, MapReduce, Virtual Screening.