Prediction of Transcription Factor Binding Sites using Deep Learning |
Author(s): |
| Rudra Malali , Zeal College of Engineering and Research; Naman Jangid, Zeal College of Engineering and Research; Pranjali Deshmukh, Zeal College of Engineering and Research |
Keywords: |
| Transcription Factor Binding Sites (TFBSs), Convolutional Neural Network, Chromatin accessibility, Histone modification, TATA Box |
Abstract |
|
The transcription binding sites form the base for knowing the gene regulation and DNA annotation. The prediction of Transcription factor binding sites (TFBSs) is a vital step in genomic study and is carried out by using varied methods like Chip-Seq, Positive-Weight Matrix, Deep Poly and many more but according to studies, the Neural Networks have shown more accurate result. Thus, in our paper we are using a deep learning approach, taking DNA sequence, Chromatin Accessibility, Histone Modification and TATA box sites as inputs to our CNN model, to obtain more accurate TFBSs. During model training, we also used the complementary DNA sequence of the DNA strands in the dataset to achieve better results. |
Other Details |
|
Paper ID: IJSRDV8I40411 Published in: Volume : 8, Issue : 4 Publication Date: 01/07/2020 Page(s): 164-166 |
Article Preview |
|
|
|
|
