APPLICATION OF DATA MODELLING IN BUILDING STRUCTURE-ACTIVITY CLASSIFIERS FROM Plasmodium falciparum BIOASSAY SCREENS

Abstract

Malaria is responsible for approximately 1 million deaths annually; thus, continued efforts to discover new antimalarials are required. The prevalence of resistance to known antimalarial drugs has resulted in the expansion of antimalarial drug discovery efforts. P. falciparum is the deadliest of the species of Plasmodium that infect humans, and it accounts for the majority of malaria infections and virtually all of the malariarelated mortality worldwide.So here we are trying to build trained Classifiers which enable virtual screening of compounds with specific activity towards P.falciparum. Due to rapid growth of various databases, business and health industry leaders have turned to computer applications that can increase the efficacy of treatment and services. Data Mining or Knowledge Discovery in Databases is a process of discovering meaningful new correlations, patterns, and trends by digging into large amounts of data stored in warehouses The purpose of bioinformatics data mining is to discover the relationships and patterns in large databases to provide useful information for biomedical analysis and diagnosis. Cheminformatics is paving a way for identification and development of novel drugs. In recent years, there has been an explosion in the availability of publicly accessible chemical information, including chemical structures of small molecules, structure-derived properties and associated biological activities in a variety of assays. These data sources present us with an opportunity to develop and apply computational tools to extract and understand the underlying structure-activity relationships. 1 Here, the various structure activity classifiers for the Plasmodium falciparum bioassay screens were made. The data is downloaded from PubChem Bioassay containing the compounds active and inactive for malaria. The molecular descriptors are calculated using Dragon software. The data is then preprocessed using the scripting language ‘R’. The script “Classification.Rnw” distributes the live malaria data in train data & test data (trainClass.Rdata and testClass.Rdata) on which we can further work. The script “Classification-method.Rnw” uses different methods and builds up the predictive models using the ‘caret’ package.