Genome Dreaming

Abstract

We investigate and build the framework required to generate or “dream” of genomes that encode novel organisms. Importantly, we find that developing methods to validate the generated sequences is as important as building a good model to realize this task due to the lack of methods capable of interpreting and evaluating a generated sequence. We report on our results in building and optimizing a generative model (using Recurrent Neural Networks) and novel validation and visualization techniques that enable model evaluation and unsupervised discovery and comparison of gene properties to form a testable hypothesis for the

8 Figures and Tables

Cite this paper

@inproceedings{Maheshwari2016GenomeD, title={Genome Dreaming}, author={Akshay J. Maheshwari and Bohan Wu and Oguz H. Elibol}, year={2016} }