I was trying to run codes from this paper
"A machine-learning approach for accurate detection of copy-number variants from exome sequencing"
I need to get data from GATK GC content and CANOES and combined them, but I got a different value from each one, GATK gave me gc.txt with 197921 line and CANOES gave 195841 lines so it couldn't be combined. why this happened and how could I get the same values?
P.S. I didn't write anything, all I do was running their code, also I mailed them and waiting for their answers. my reference gen is hg19.
the code is here.