Synthetic Generation of Genomic Datasets using Synthetic Data Vault
Many wonder what the mysterious world of coding can allow you to do. The first things that come to mind are software UI (User Interface) or UX (User Experience), maybe game development, and many other things out there. But there is one field that may seem to be hidden from the world. All are found in some virtual underground dungeon. No, I am not taking you to the dark web. I am talking about data analysis and machine learning. Python is the best programming language that allows you to manipulate Excel datasets. From containing personal information of customers to numbers of statistics of a store and their items. We can use those kinds of datasets and use one to program it to run through an algorithm to give us simply a score. In this, we will be dealing with DNA genomic datatsets and we will put it through an algorithm that creates synthetic genomic data. The score will specifically focus on the broadness to unuiqueness of the type of genomic data in the original dataset and the new dataset.
SFTE 499, Senior Capstone
Ernest Bonat
Richardson 100
10 – 10:30 AM