A Machine Learning Approach to Genome Editing Techniques

Abstract

In the current era, the clustered regularly interspaced short palindromic repeats (CRISPR)/CRISPR-associated system (Cas) isdevelopedand used as the most adaptable instrument for genetic administration application. It is encompass of repetitive bases followed by short fragments of DNA. The manipulation of targeted genes and genomic regions that are balancing to a programmable single guide RNA (sgRNA),but the effectiveness of the sgRNA is not properly defined for the target site so unintended off-targets might be cleaved. Modernistic methods for sgRNA designs are based on predicting the off-targets for a sgRNA using basic sequence features. We present a summary and relative analysis of algorithms based on machine learning approaches which will be more impressive and predictable method for predicting susceptibility of a genomic site to be cleaved by a given sgRNA. We will show that the predictions are more accurate and then validate the occurrence of bulges.

 Keywords: CRISPR, CRISPR/Cas, sgRNA, DNA