Machine learning and giant genomic datasets
A team from Columbia University and Princeton University have developed an algorithm to accurately analyse genetic ancestry across ‘tera’ sized datasets – a potentially significant development in the development of personalised healthcare. Since the completion of the Human Genome Project, and the savings in both time and money that next generation sequencing enables, genetic datasets have grown exponentially whilst analysis has fought to keep pace. Now, a team of researchers have developed a machine learning algorithm they call TeraStructure, capable of analysing very large data sets. Machine learning is a computer analysis method which allows an artificial intelligence to literally teach itself, using statistical principles and the growing capability of computers to process data. Tech giants such as Google, Microsoft and Apple all have their own programs, but promising applications…
Link to Full Article: Machine learning and giant genomic datasets
Sharing
