"Data Preparation Techniques using PCA,CA,MCA for Hybrid H_K-Means, CLARA, Hybrid K-Means-K_Mediods, Fuzzy methods to efficiently Cluster Bioinformatics Data"


Katikireddy Srinivas, Research Scholar & Dr. K V D Kiran, Professor of CSE
Department of CSE, K L E F, Vaddeswaram,Guntur Dt, AndhraPradesh.


Bio-Informatics is dealing with integration of Biotechnology, Biomedical, Biological concepts with Computer science and Information Technology. At this pandemic Covid-19 health emergency scenario, Machine learning is very much help full for Tele-health and tele medicine tools to face the pandemic challenges effectively. As a supporting module to Tele medicine I would like to device an automated drug choosing system for the patients suffering with routine illness conditions from the existing valid drug bank using AI and Machine learning. In this scenario I would like to use computer science knowledge based on the physio chemical properties and enzyme inhibition properties of drug dataset provided by standard drug bank repository ie www.drugbank.ca and www.malacards.org.Here I applied existing clustering techniques as a blend of k-means, k-medoids, hierarchical methods and Fuzzy k-means to determine an appropriate set of drugs from the given drugbank for different illness conditions of of thyroid patient].In this research work data preparation for drug evaluation is playing a crucial role , we used PCA,CA,MCA methods to make our Cluster system is efficient and effective. We have shown the analysis of blend of cluster methods successful for this cluster system using graphical presentation and derived best hybrid cluster methods as final outcome.