Predictive models for anti-tubercular molecules using machine learning on high-throughput biological screening datasets
Prostate cancer in men is the major cause of cancer mortality and is the active area for the researchers to discover new drugs for prostate cancer. 5alpha-reductase inhibitors have been proved to inhibit the growth and development of prostate cancer, hence identifying the potential of such compounds is necessary to invent new drugs. Quantitative structure activity relationship (QSAR) modeling is a well-known in silico drug designing approach that relates the chemical structure of compounds with their biological activities. In the present work 2D QSAR models are built using machine learning techniques such as linear regression, SMO, simple logistic, decision tree j48 and random forest, from the functions available in Weka 3.7 version. The present in silico QSAR study will help to identify new bioactivities for the drug discovery of prostate cancer and also narrow down the time required for drug discovery process.