#!/usr/bin/env bash

work_root="../../../../data/processing_data/Simu/mouse"

simu_and_ass(){
    # simulate sequencing
    cd $1
    ./simu.R
    cd -
    # assembly with hisat2+stringtie
    sh asscmd $1
}
simu_and_ass ${work_root}/sim30
simu_and_ass ${work_root}/sim100
simu_and_ass ${work_root}/sim300
simu_and_ass ${work_root}/sim600
simu_and_ass ${work_root}/sim1200

cd ${work_root}
#gffcompare
#
for i in sim*/ass/merged_no_G.gtf;do gffcompare -r /home/yduan/work_file/lncRNAdb/methods_assement/data_for_prediction/random_5k_data/simu/human/input/template.gtf -R $i -o ${i%/*}/no_G;done
for i in sim*/ass/merged_with_G.gtf;do gffcompare -r /home/yduan/work_file/lncRNAdb/methods_assement/data_for_prediction/random_5k_data/simu/human/input/template.gtf -R $i -o ${i%/*}/with_G;done
#
##split tracking
for i in sim*; do ../tracking_split.py $i/ass/with_G.tracking $i/ass/with_G_split ;done
for i in sim*; do ../tracking_split.py $i/ass/no_G.tracking $i/ass/no_G_split ;done

##count transcript for each class code per depth
for i in sim*/ass/*_split_*;do wc -l $i;done | awk 'BEGIN{OFS="\t"}{tmp=$1;$1=$2;$2=tmp;print}' | cut -d"/" -f1,3 --output-delimiter=$'\t'| awk 'BEGIN{OFS="\t";print("Species\tDepth\tGtf_Guide\tClass_code\tcount")}{$5=$3;$4=gensub(/.+_split_(.+)/,"\\1","g",$2);$3=gensub(/(.+)_split_.+/,"\\1","g",$2);$2=gensub(/sim(.+)/,"\\1","g",$1);$1="human";print}' > trans_count.txt
cd -