sortBed -i dpse-all-r3.04.gtf.gz > dpse_cdf.gtf

mergeBed -i dpse_cdf.gtf > dpse_merge.bed

awk -F '\t' 'BEGIN {OFS="\t"} {print $1, $5-$4+1}' dpse_merge.gtf > dpse_cds_length

awk '{a[$1] += $2} END{for (i in a) print i, a[i]}' dpse_cds_length | grep -v Unknown > dpse_sum_cds

# 2          20482223
# 3          14003747
# 4_group1    3712503
# 4_group2     804985
# 4_group3    8481325
# 4_group4    3843350
# 4_group5    1698578
# XL_group1a  5695660
# XL_group1e  7792946
# XL_group3a  1645471
# XL_group3b   275590
# XR_group3a   952761
# XR_group5    455163
# XR_group6   8384003
# XR_group8   6753117

awk '/^X/ {sum += $2} END {print sum}' dpse_sum_cds
awk '!/^X/ {sum += $2} END {print sum}' dpse_sum_cds
