CRISPR/CAS9 Target Prediction with Deep Learning

Creative Commons License

AKTAŞ Ö., Dogan E., Ensari T.

International Scientific Meeting on Electrical-Electronics and Biomedical Engineering and Computer Science (EBBT), İstanbul, Türkiye, 24 - 26 Nisan 2019 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası:
  • Doi Numarası: 10.1109/ebbt.2019.8741648
  • Basıldığı Şehir: İstanbul
  • Basıldığı Ülke: Türkiye
  • Anahtar Kelimeler: deep learning, convolutional neural networks, multi layer perceptron, CRISPR/CAS9, DATABASE
  • Dokuz Eylül Üniversitesi Adresli: Evet

Özet

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. In order 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 (Convolutional Neural Networks-CNN) and multilayer perceptron (Multi Layer Perceptron-MLP) algorithms are used. A performance comparison of the CRISPR/CAS9 system for both algorithms was performed.