VALIDATION OF A SAR MODEL OF DATASET-1696 BY APPLICATION OF ARTIFICIAL INTELLIGENCE TECHNIQUES SUCH AS KNOCKING OUT OF THE FEATURE SELECTION.
Tuberculosis is a infectious disease caused by Mycobacterium tuberculosis (Mtb), affecting more than two billion people around the globe and is one of the major causes of death and mortalityin the developing world. Recent reports suggest that TB has been developing resistance to the widely used anti-tubercular drugs, resulting in the emergence and spread of multi drug-resistant (MDR) and extensively drug-resistant (XDR) strains throughout the world. But the research of molecules against such furious disease remains neglected among the research community. Hence OSDD is focusing such a neglected disease, I myself involving in such contribution and presenting my knowledge.
Artificial intelligence in Drug Designing include the generation of manual descriptor frame model structure on the basis of which a model is developed. On basis of which we can be able to predict the activity of new molecules. The machine learning methods to generate involves the use of all the descriptors for predicting a model. This work is an attempt of finding out the importance of each descriptor by knocking out. So and observing the effect of knocking out that descriptor on the model in this way. We can find out the important descriptors for predicting activity which may be useful in designing new compound.
Methodology begins with the experimented dataset search followed by generating models using machine learning method such as WEKA, followed by validating the model to be accurate and examining the essential molecular descriptors manually by eliminating one by one in order to expose the vital descriptors.