Maintenance of Medical Records Database and Simulation of Gene Therapy using Big Data Concepts

In the current circumstance the best test that we confront is the accumulation and upkeep of physical data when contrasted with data put away in a virtual environment. As consistently passes, we have no restrictions for the data or data we get and this is an immediate aftereffect of the propelling advancement and the need to comprehend the necessity for extra. The proposed configuration uses focal thoughts of Big Data, that is, Data warehousing, Data mining and Machine learning. Cloud is utilized to make a dispersed database for multilateral access of medical records. Show and stacking of data is done by means of a web interface, which is utilized by the doctor's facilities. The data is sent and got by means of a REST API which goes about as an arbiter between the warehouse and the front end application. The warehouse (MongoDB), which is particularly offline, is the data warehousing unit which will go about as both the operational database and the analytical database. Cloud Era will go about as the stage for change and preparing of data into clusters for data mining and machine learning algorithms. The data sets are mined and exchanged to apache Spark for the last stage, i.e., Machine Learning for reproducing germ line and somatic gene therapy. The libraries to be utilized are Spark MLlib, Tensor Flow, Theano, Keras and Scikit Learn. The prepared data is mimicked utilizing MatPlotlib as GUI library. This stage is simply non-commercial and is implied for logical experimentation and instructive purposes.