Entering edit mode
3.4 years ago
sujasubramanian
▴
70
I am trying to build a computational model to predict TF binding site based on Chip seq data (.narrowPeak), the data contains an intensity value corresponding to each binding region. Can i use this value as a feature to predict the region, any suggestions.
i am taking start, end and chromosome no from .narrow file. And i use Microarray gene expression values also for my study. Gene expression and TFs (binding site) details, if i am using intensity of TF binding region as one of the feature how can i treat those intensity measures? column 7 indicates intensity 2.74497 4.36821 10.33905
chr21 9825324 9827741 . 1000 . 2.74497 164.24833 159.38104 1798
chr20 26188685 26190663 . 1000 . 4.36821 127.28879 122.72253 1420
chr1 12508603 12509563 . 1000 . 10.33905 106.66706 102.27689 470
chr6 68598519 68599658 . 1000 . 16.07275 103.14953 98.8843 657