Using neural networks based on epigenomic maps for predicting the transcriptional regulation measured by CRISPR/Cas9

Abstract

[EN] Because of the great impact that the genomic editing with CRISPR/CAS9 has had in the recent years, and the great advances that it brings to biotechnology a great need of information has arisen. However researches struggle to find a definate pattern with these experiments making a very long process of trial and error to find an optimal solution for a particular experiment. With this project we intend to optimize the genomic edition with the newest advance CRISPR/Cas9, to find the optimal insertion site we design a mathematical model based on neural networks. During this process we had to deal with huge amount of information from the genome so we had to develop a way to filter and handle it efficiently. For this project we are going to focus in Arabidopsis Thaliana which is a very common plant in genomic edition and has many resources available online.