CoSy Zoom seminar

Register here

Abstract:

Dimensionality reduction is a widely employed technique in the field of genomics, with applications including visualisation of genetic variation, identification of population structure as well as ancestry estimation. In this talk I will discuss the use of convolutional autoencoders for performing nonlinear dimensionality reduction in a manner that exploits the sequential nature of genetic information. Using a highly diverse cohort of human samples, I will compare the performance of this methodology to the alternative techniques of PCA and t-SNE, and compare their abilities to capture local and global patterns of genetic variation.