data_unstranded.bw is sparse and has a different range
ArnovanHilten opened this issue · 1 comments
ArnovanHilten commented
I loaded the predictions of the model into IGV viewer together with the BAM file and data_unstranded (shown below). For example for this peak:
The tracks show the following:
- BAM file [0-159]
- data_unstranded.bw [0-34]
- cmb chrombpnet_nobias predictions [0 - 3.07]
- bias model predictions [0 - 0.41]
- chrombpnet.h5 (cm) predictions [0-27]
Why is the data_unstranded so different from the original BAM profile? The estimated shift was +0/+0. I am also confused by the range and the shape differences between the tracks.
Did something go wrong during preprocessing? None of the predicted tracks is close to the original BAM input.
ArnovanHilten commented
Figured it out, you just keep the starting position of each read.