Makine öğrenmesiyle CRISPR/Cas9 sistemi için mikroRNA hedef tahmini

Since the existence of humankind, many solutions have been investigated for the way of genetic and subsequent diseases. In the late 1900s, a groundbreaking technology, CRISPR was discovered in bacteria. After the exploration of this technique, it is supposed that incurable diseases can be healed by this invention. The CRISPR/CAS9 system is a powerful tool for regulating damaged genome sequences. Nucleases that are damaged in their sequence are called miRNAs (micro RNAs). The miRNAs targeted by multiple promoter sgRNA (single guide RNA) are cut or regulated from RNA by the CRISPR/CAS9 method. The sgRNAs targeted to the wrong miRNAs may cause unwanted genome distortions. To minimize these genome distortions, sgRNA target estimation was performed for CRISPR/CAS9 with deep learning in this study. In this article, Convolutional Neural Networks (CNN), Multi-Layer Perceptron (MLP) and Bidirectional Long Short-Term (BLSTM) algorithms are used. Performance comparison of the CRISPR/CAS9 system for three algorithms was performed.