#!/bin/bash
python3 -m src.bed_handler
python3 -m src.bed_handler.filter_bed \
--bed_file data/bed/gene.bed \
--filter_file data/gene_5-3_loop_tot.txt \
--col_name 'id' \
--outfile gene_with_5-3p_loop_tot.txt
python3 -m src.bed_handler.filter_bed \
--bed_file data/bed/gene.bed \
--filter_file data/gene_5-3_loop_ctrl.txt \
--col_name 'id' \
--outfile gene_with_5-3p_loop_ctrl.txt
python3 -m src.bed_handler.filter_bed \
--bed_file data/bed/gene.bed \
--filter_file data/gene_5-3_loop_siPPdown.txt \
--col_name 'id' \
--outfile gene_with_5-3p_loop_siPPdown.txt
python3 -m src.bed_handler.filter_bed \
--bed_file data/bed/gene.bed \
--filter_file data/gene_without_5-3_loop_siPPdown.txt \
--col_name 'id' \
--outfile gene_without_5-3p_loop_siPPdown.txt
python3 -m src.bed_handler.filter_bed \
--bed_file data/bed/gene.bed \
--filter_file data/gene_without_loops_siPPdown.txt \
--col_name 'id' \
--outfile gene_without_loops_siPPdown.txt
mkdir results/figures
array=(all_replicates rep1 rep2 rep3)
for myrep in ${array[*]}; do
python3 -m src.visu \
--design data/design_exp_${myrep}.txt \
--bw_folder data/bigwig/ \
--region_bed results/bed_file/filtered_gene.bed \
--region_name gene \
--output results/figures/ \
--border_name TSS TTS \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm 'None'
python3 -m src.visu \
--design data/design_exp_${myrep}.txt \
--bw_folder data/bigwig/ \
--region_bed results/bed_file/filtered_gene.bed \
--region_name gene \
--output results/figures/ \
--border_name TSS TTS \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm '0'
mv results/figures/metagene_gene_100bin_10000_nt-around-25-bin_b0_norm.pdf results/figures/metagene_gene_100bin_10000_nt-around-25-bin_b0_norm_${myrep}.pdf
mv results/figures/metagene_gene_100bin_10000_nt-around-25-bin.pdf results/figures/metagene_gene_100bin_10000_nt-around-25-bin_${myrep}.pdf
done
array=(all_replicates rep1 rep2 rep3)
for myrep in ${array[*]}; do
python3 -m src.visu \
--design data/design_exp_${myrep}.txt \
--bw_folder data/bigwig/ \
--region_bed results/bed_file/gene_with_5-3p_loop_siPPdown.txt \
--region_name gene \
--output results/figures/ \
--border_name TSS TTS \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm 'None'
python3 -m src.visu \
--design data/design_exp_${myrep}.txt \
--bw_folder data/bigwig/ \
--region_bed results/bed_file/gene_with_5-3p_loop_siPPdown.txt \
--region_name gene \
--output results/figures/ \
--border_name TSS TTS \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm '0'
mv results/figures/metagene_gene_100bin_10000_nt-around-25-bin_b0_norm.pdf results/figures/metagene_gene_100bin_10000_nt-around-25-bin_b0_norm_${myrep}_5-3-loop.pdf
mv results/figures/metagene_gene_100bin_10000_nt-around-25-bin.pdf results/figures/metagene_gene_100bin_10000_nt-around-25-bin_${myrep}_5-3-loop.pdf
done
for gene_bed in $(ls results/bed_file/CTCF*gene.bed); do
exon_bed=${gene_bed/gene/exon}
exon_name=(${exon_bed//\// })
full_name=${exon_name[-1]/.bed/}
full_name=${full_name/exon/gene-dup}
file_name=${exon_name[-1]/.bed/}
gene_bed=${gene_bed/.bed/-dup.bed}
python3 -m src.visu \
--design data/design_exp_all_replicates.txt \
--bw_folder data/bigwig/ \
--region_bed ${exon_bed} \
--region_name exon \
--output results/figures/ \
--border_name start_exon end_exon \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm 'None'
mv results/figures/metagene_exon_100bin_10000_nt-around-25-bin.pdf results/figures/${file_name}_metagene_exon_100bin_10000_nt-around-25-bin.pdf
python3 -m src.visu \
--design data/design_exp_all_replicates.txt \
--bw_folder data/bigwig/ \
--region_bed ${gene_bed} \
--region_name gene \
--output results/figures/ \
--border_name start_exon end_exon \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm '0'
rm results/figures/metagene_gene_100bin_10000_nt-around-25-bin_b0_norm.pdf
python3 -m src.visu \
--design data/design_exp_all_replicates.txt \
--bw_folder data/bigwig/ \
--region_bed ${exon_bed} \
--region_name exon \
--output results/figures/ \
--border_name start_exon end_exon \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm "results/figures/coef_table/tmp_cov_table_design_exp_all_replicates_${full_name}_100bin_10000_nt-around-25-bin_bin0_norm.txt"
mv results/figures/metagene_exon_100bin_10000_nt-around-25-bin_file_norm.pdf results/figures/${file_name}_metagene_exon_100bin_10000_nt-around-25-bin_file_norm.pdf
done
########################################################
# Condition siPP/siCTRL - exon ddx_down vs exon ddx_down_ctcf #
########################################################
# exon ddx_down_ctcf corresponds to exons down-regulated by ddx5/17 near a ctcf site and
# exon ddx_down corresponds to exons down-regulated by ddx5/17 far from ctcf sites
exps=(siCTRL siDDX)
for exp in ${exps[*]}; do
python3 -m src.visu \
--design data/design_exp_${exp}.txt \
--bw_folder data/bigwig/ \
--region_bed results/bed_file/CTCF_2000_both_ddx_down_with0_gene.bed results/bed_file/Far_CTCF_2000_both_ddx_down_with0_gene.bed \
--region_name ddx_down_ctcf ddx_down \
--output results/figures/ \
--border_name start_gene end_gene \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm "None"
mv results/figures/metagene_ddx_down_ctcf-ddx_down_100bin_10000_nt-around-25-bin.pdf results/figures/exp_${exp}_metagene_ddx_down_ctcf-ddx_down_100bin_10000_nt-around-25-bin_gene.pdf
python3 -m src.visu \
--design data/design_exp_${exp}.txt \
--bw_folder data/bigwig/ \
--region_bed results/bed_file/CTCF_2000_both_ddx_down_with0_gene.bed results/bed_file/Far_CTCF_2000_both_ddx_down_with0_gene.bed \
--region_name ddx_down_ctcf ddx_down \
--output results/figures/ \
--border_name start_gene end_gene \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm "0"
mv results/figures/metagene_ddx_down_ctcf-ddx_down_100bin_10000_nt-around-25-bin_b0_norm.pdf results/figures/exp_${exp}_metagene_ddx_down_ctcf-ddx_down_100bin_10000_nt-around-25-bin_b0_norm_gene.pdf
python3 -m src.visu \
--design data/design_exp_${exp}.txt \
--bw_folder data/bigwig/ \
--region_bed results/bed_file/CTCF_2000_both_ddx_down_with0_gene-dup.bed results/bed_file/Far_CTCF_2000_both_ddx_down_with0_gene-dup.bed \
--region_name ddx_down_ctcf ddx_down \
--output results/figures/ \
--border_name start_gene end_gene \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm "0"
rm results/figures/metagene_ddx_down_ctcf-ddx_down_100bin_10000_nt-around-25-bin_b0_norm.pdf
python3 -m src.visu \
--design data/design_exp_${exp}.txt \
--bw_folder data/bigwig/ \
--region_bed results/bed_file/CTCF_2000_both_ddx_down_with0_exon.bed results/bed_file/Far_CTCF_2000_both_ddx_down_with0_exon.bed \
--region_name ddx_down_ctcf ddx_down \
--output results/figures/ \
--border_name start_exon end_exon \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm "results/figures/coef_table/tmp_cov_table_design_exp_${exp}_CTCF_2000_both_ddx_down_with0_gene-dup-Far_CTCF_2000_both_ddx_down_with0_gene-dup_100bin_10000_nt-around-25-bin_bin0_norm.txt"
mv results/figures/metagene_ddx_down_ctcf-ddx_down_100bin_10000_nt-around-25-bin_file_norm.pdf results/figures/exp_${exp}_metagene_ddx_down_ctcf-ddx_down_100bin_10000_nt-around-25-bin_file_norm_exon.pdf
done
########################################################
# Condition siPP and siCTRL - ddx_down_5-3 #
########################################################
python3 -m src.visu \
--design data/design_exp_all_replicates.txt \
--bw_folder data/bigwig/ \
--region_bed results/bed_file/gene_with_5-3p_loop_siPPdown.txt \
--region_name ddx_down_5-3 \
--output results/figures/ \
--border_name start_gene end_gene \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm "0"
mv results/figures/metagene_ddx_down_5-3_100bin_10000_nt-around-25-bin_b0_norm.pdf results/figures/exp_all_metagene_ddx_down_5-3_100bin_10000_nt-around-25-bin_b0_norm_gene.pdf
########################################################
# Condition siPP - ddx_down_5-3 vs exon ddx_down #
########################################################
# gene ddx_down_5-3 corresponds to genes containing at least one exons down-regulated by ddx5/17 and having a 5'-3' loop and
# gene ddx_down corresponds to genes containing exons down-regulated by ddx but without a 5'-3' loop
python3 -m src.visu \
--design data/design_exp_siDDX.txt \
--bw_folder data/bigwig/ \
--region_bed results/bed_file/gene_with_5-3p_loop_siPPdown.txt results/bed_file/gene_without_loops_siPPdown.txt \
--region_name ddx_down_5-3 ddx_down \
--output results/figures/ \
--border_name start_gene end_gene \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm "0"
mv results/figures/metagene_ddx_down_5-3-ddx_down_100bin_10000_nt-around-25-bin_b0_norm.pdf results/figures/exp_siPP_metagene_ddx_down_5-3-ddx_down_100bin_10000_nt-around-25-bin_b0_norm_gene.pdf
python3 -m src.visu \
--design data/design_exp_siDDX.txt \
--bw_folder data/bigwig/ \
--region_bed results/bed_file/gene_with_5-3p_loop_siPPdown.txt results/bed_file/gene_without_loops_siPPdown.txt \
--region_name ddx_down_5-3 ddx_down \
--output results/figures/ \
--border_name start_gene end_gene \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm "None"
mv results/figures/metagene_ddx_down_5-3-ddx_down_100bin_10000_nt-around-25-bin.pdf results/figures/exp_siPP_metagene_ddx_down_5-3-ddx_down_100bin_10000_nt-around-25-bin_gene.pdf
rep=(1 2 3)
for i in ${rep[*]}; do
python3 -m src.visu \
--design data/design_exp_siDDX_rep${i}.txt \
--bw_folder data/bigwig/ \
--region_bed results/bed_file/gene_with_5-3p_loop_siPPdown.txt results/bed_file/gene_without_loops_siPPdown.txt \
--region_name ddx_down_5-3 ddx_down \
--output results/figures/ \
--border_name start_gene end_gene \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm "0"
mv results/figures/metagene_ddx_down_5-3-ddx_down_100bin_10000_nt-around-25-bin_b0_norm.pdf results/figures/exp_siPP_rep${i}_metagene_ddx_down_5-3-ddx_down_100bin_10000_nt-around-25-bin_b0_normgene.pdf
done
########################################################
# Condition siCTRL - ddx_down_5-3 vs exon ddx_down #
########################################################
# gene ddx_down_5-3 corresponds to genes containing at least one exons down-regulated by ddx5/17 and having a 5'-3' loop and
# gene ddx_down corresponds to genes containing exons down-regulated by ddx but without a 5'-3' loop
python3 -m src.visu \
--design data/design_exp_siCTRL.txt \
--bw_folder data/bigwig/ \
--region_bed results/bed_file/gene_with_5-3p_loop_siPPdown.txt results/bed_file/gene_without_loops_siPPdown.txt \
--region_name ddx_down_5-3 ddx_down \
--output results/figures/ \
--border_name start_gene end_gene \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm "0"
mv results/figures/metagene_ddx_down_5-3-ddx_down_100bin_10000_nt-around-25-bin_b0_norm.pdf results/figures/exp_siCTRL_metagene_ddx_down_5-3-ddx_down_100bin_10000_nt-around-25-bin_b0_norm_gene.pdf
python3 -m src.visu \
--design data/design_exp_siCTRL.txt \
--bw_folder data/bigwig/ \
--region_bed results/bed_file/gene_with_5-3p_loop_siPPdown.txt results/bed_file/gene_without_loops_siPPdown.txt \
--region_name ddx_down_5-3 ddx_down \
--output results/figures/ \
--border_name start_gene end_gene \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm "None"
mv results/figures/metagene_ddx_down_5-3-ddx_down_100bin_10000_nt-around-25-bin.pdf results/figures/exp_siCTRL_metagene_ddx_down_5-3-ddx_down_100bin_10000_nt-around-25-bin_gene.pdf
rep=(1 2 3)
for i in ${rep[*]}; do
python3 -m src.visu \
--design data/design_exp_siCTRL_rep${i}.txt \
--bw_folder data/bigwig/ \
--region_bed results/bed_file/gene_with_5-3p_loop_siPPdown.txt results/bed_file/gene_without_loops_siPPdown.txt \
--region_name ddx_down_5-3 ddx_down \
--output results/figures/ \
--border_name start_gene end_gene \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm "0"
mv results/figures/metagene_ddx_down_5-3-ddx_down_100bin_10000_nt-around-25-bin_b0_norm.pdf results/figures/exp_siCTRL_rep${i}_metagene_ddx_down_5-3-ddx_down_100bin_10000_nt-around-25-bin_b0_norm_gene.pdf
done
############################################################
# GC content exon ddx_down vs exon ddx_down_ctcf #
############################################################
python3 -m src.gc_content -B results/bed_file/Far_CTCF_2000_both_ddx_down_with0_exon.bed results/bed_file/CTCF_2000_both_ddx_down_with0_exon.bed -b ddx_down ddx_down_ctcf -g data/Homo_sapiens.GRCh37.dna.primary_assembly.fa -f "exons" -e 2000
############################################################################
# other Exon in genes containing an exon regulated by DDX
############################################################################
########################################################
# Condition siCTRL - exon ddx_down vs exon ddx_down_ctcf #
########################################################
python3 -m src.bed_handler.get_other_exon_in_same_gene -b results/bed_file/CTCF_2000_both_ddx_down_with0_exon.bed -d 2000 -o oexon_2000_CTCF_2000_both_ddx_down_with0_exon.bed
python3 -m src.bed_handler.get_other_exon_in_same_gene -b results/bed_file/Far_CTCF_2000_both_ddx_down_with0_exon.bed -d 2000 -o oexon_2000_Far_CTCF_2000_both_ddx_down_with0_exon.bed
exps=(siCTRL siDDX)
for exp in ${exps[*]}; do
python3 -m src.visu \
--design data/design_exp_${exp}.txt \
--bw_folder data/bigwig/ \
--region_bed results/bed_file/oexon_2000_CTCF_2000_both_ddx_down_with0_gene.bed results/bed_file/oexon_2000_Far_CTCF_2000_both_ddx_down_with0_gene.bed \
--region_name other_ddx_down_ctcf other_ddx_down \
--output results/figures/ \
--border_name start_gene end_gene \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm "None"
mv results/figures/metagene_other_ddx_down_ctcf-other_ddx_down_100bin_10000_nt-around-25-bin.pdf results/figures/exp_${exp}_metagene_other_ddx_down_ctcf-other_ddx_down_100bin_10000_nt-around-25-bin_gene.pdf
python3 -m src.visu \
--design data/design_exp_${exp}.txt \
--bw_folder data/bigwig/ \
--region_bed results/bed_file/oexon_2000_CTCF_2000_both_ddx_down_with0_gene.bed results/bed_file/oexon_2000_Far_CTCF_2000_both_ddx_down_with0_gene.bed \
--region_name other_ddx_down_ctcf other_ddx_down \
--output results/figures/ \
--border_name start_gene end_gene \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm "0"
mv results/figures/metagene_other_ddx_down_ctcf-other_ddx_down_100bin_10000_nt-around-25-bin_b0_norm.pdf results/figures/exp_${exp}_metagene_other_ddx_down_ctcf-other_ddx_down_100bin_10000_nt-around-25-bin_gene_b0_norm.pdf
python3 -m src.visu \
--design data/design_exp_${exp}.txt \
--bw_folder data/bigwig/ \
--region_bed results/bed_file/oexon_2000_CTCF_2000_both_ddx_down_with0_gene-dup.bed results/bed_file/oexon_2000_Far_CTCF_2000_both_ddx_down_with0_gene-dup.bed \
--region_name other_ddx_down_ctcf other_ddx_down \
--output results/figures/ \
--border_name start_gene end_gene \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm "0"
rm results/figures/metagene_other_ddx_down_ctcf-other_ddx_down_100bin_10000_nt-around-25-bin_b0_norm.pdf
python3 -m src.visu \
--design data/design_exp_${exp}.txt \
--bw_folder data/bigwig/ \
--region_bed results/bed_file/oexon_2000_CTCF_2000_both_ddx_down_with0_exon.bed results/bed_file/oexon_2000_Far_CTCF_2000_both_ddx_down_with0_exon.bed \
--region_name other_ddx_down_ctcf other_ddx_down \
--output results/figures/ \
--border_name start_exon end_exon \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm "results/figures/coef_table/tmp_cov_table_design_exp_${exp}_oexon_2000_CTCF_2000_both_ddx_down_with0_gene-gene-dup-oexon_2000_Far_CTCF_2000_both_ddx_down_with0_exon-gene-dup_100bin_10000_nt-around-25-bin_bin0_norm.txt"
mv results/figures/metagene_other_ddx_down_ctcf-other_ddx_down_100bin_10000_nt-around-25-bin_file_norm.pdf results/figures/exp_${exp}_metagene_other_ddx_down_ctcf-other_ddx_down_100bin_10000_nt-around-25-bin_file_norm_exon.pdf
done
###########################################################
# Figures siPP vs siCTRL pour ddx_down_ctcf,
# other_ddx_down_ctcf, ddx_down
###########################################################
list_names=(ddx_down_ctcf other_ddx_down_ctcf ddx_down)
bed_names=(CTCF_2000_both_ddx_down_with0_exon.bed oexon_2000_CTCF_2000_both_ddx_down_with0_exon.bed Far_CTCF_2000_both_ddx_down_with0_exon.bed)
for i in ${!list_names[*]}; do
cname=${list_names[i]}
bed=${bed_names[i]}
gbed=${bed/exon\.bed/gene-dup.bed}
nbed=${gbed/\.bed/}
python3 -m src.visu \
--design data/design_exp_all_replicates.txt \
--bw_folder data/bigwig/ \
--region_bed results/bed_file/${gbed} \
--region_name ${cname} \
--output results/figures/ \
--border_name TSS TTS \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm '0'
rm results/figures/metagene_${cname}_100bin_10000_nt-around-25-bin_b0_norm.pdf
python3 -m src.visu \
--design data/design_exp_all_replicates.txt \
--bw_folder data/bigwig/ \
--region_bed results/bed_file/${bed} \
--region_name ${cname} \
--output results/figures/ \
--border_name " " " " \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 30 \
-y 0.15 0.4 \
--norm "results/figures/coef_table/tmp_cov_table_design_exp_all_replicates_${nbed}_100bin_10000_nt-around-25-bin_bin0_norm.txt"
mv results/figures/metagene_${cname}_30bin_10000_nt-around-25-bin_file_norm.pdf results/figures/all_replicates_metagene_${cname}_100bin_10000_nt-around-25-bin_file_norm.pdf
done
## Recap
python3 -m src.visu \
--design data/design_exp_all_replicates.txt \
--bw_folder data/bigwig/ \
--region_bed results/bed_file/CTCF_2000_both_ddx_down_with0_gene-dup.bed results/bed_file/oexon_2000_CTCF_2000_both_ddx_down_with0_gene-dup.bed results/bed_file/Far_CTCF_2000_both_ddx_down_with0_gene-dup.bed \
--region_name ddx_down_ctcf other_ddx_down_ctcf ddx_down \
--output results/figures/ \
--border_name TSS TTS \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm '0'
rm results/figures/metagene_ddx_down_ctcf-other_ddx_down_ctcf-ddx_down_100bin_10000_nt-around-25-bin_b0_norm.pdf
python3 -m src.visu \
--design data/design_exp_all_replicates.txt \
--bw_folder data/bigwig/ \
--region_bed results/bed_file/CTCF_2000_both_ddx_down_with0_exon.bed results/bed_file/oexon_2000_CTCF_2000_both_ddx_down_with0_exon.bed results/bed_file/Far_CTCF_2000_both_ddx_down_with0_exon.bed \
--region_name ddx_down_ctcf other_ddx_down_ctcf ddx_down \
--output results/figures/ \
--border_name exon_start exon_stop \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm 'results/figures/coef_table/tmp_cov_table_design_exp_all_replicates_CTCF_2000_both_ddx_down_with0_gene-dup-oexon_2000_CTCF_2000_both_ddx_down_with0_gene-dup-Far_CTCF_2000_both_ddx_down_with0_gene-dup_100bin_10000_nt-around-25-bin_bin0_norm.txt'
mv results/figures/metagene_ddx_down_ctcf-other_ddx_down_ctcf-ddx_down_100bin_10000_nt-around-25-bin_file_norm.pdf results/figures/all_replicates_metagene_ddx_down_ctcf-other_ddx_down_ctcf-ddx_down_100bin_10000_nt-around-25-bin_file_norm.pdf
###############################################################################
# Bigwig from MCF7 rnaseq
###############################################################################
# Create a bed file containing all gene containing one DDX-down exons
echo -e "#ref\tstart\tend\tid\tscore\tstrand" > results/bed_file/ddx_down_gene.bed
cat results/bed_file/CTCF_2000_both_ddx_down_with0_gene.bed \
results/bed_file/Far_CTCF_2000_both_ddx_down_with0_gene.bed | \
sort -u | \
grep -v "#ref" >> results/bed_file/ddx_down_gene.bed
# Zoom on the 1500 pb at the beginning of the exons.
python3 -m src.bed_handler.bed_resize \
-b results/bed_file/ddx_down_gene.bed \
-s 1500 \
-o ddx_down_gene_size1500.bed
python3 -m src.visu \
--design data/bam_mcf7_rnaseq/design_exp_all_replicates.txt \
--bw_folder data/bam_mcf7_rnaseq \
--region_bed results/bed_file/ddx_down_gene.bed \
--region_name all_ddx_down \
--output results/figures/ \
--border_name TSS TTS \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm 'None'
mv results/figures/metagene_all_ddx_down_100bin_10000_nt-around-25-bin.pdf results/figures/metagene_MCF_rnaseq_all_ddx_down.pdf
python3 -m src.visu \
--design data/bam_mcf7_rnaseq/design_exp_all_replicates.txt \
--bw_folder data/bam_mcf7_rnaseq \
--region_bed results/bed_file/ddx_down_gene_size1500.bed \
--region_name all_ddx_down \
--output results/figures/ \
--border_name TSS TSS_1.5kb \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm 'None'
mv results/figures/metagene_all_ddx_down_100bin_10000_nt-around-25-bin.pdf results/figures/metagene_MCF_rnaseq_all_ddx_down_tss1.5kb.pdf
#### Readthrough
# Create readthrough bed files
python3 -m src.bed_handler.filter_bed -b data/bed/gene.bed -f data/readthrough_gene.txt -c score -o readthrough_gene.bed
python3 -m src.bed_handler.filter_bed -b data/bed/gene.bed -f data/readthrough_gene.txt -c score -o no_readthrough_gene.bed -k 'n'
# Filtering only expressed genes with basemean > 5.
python3 -m src.bed_handler.filter_bed -b results/bed_file/readthrough_gene.bed -f data/5y_expressed_genes_basemean\>5.txt -c id -o readthrough_expressed_gene.bed
python3 -m src.bed_handler.filter_bed -b results/bed_file/no_readthrough_gene.bed -f data/5y_expressed_genes_basemean\>5.txt -c id -o no_readthrough_expressed_gene.bed
# Create bed file corresponding to the 10kb downstream regions of the previous beds
python3 -m src.bed_handler.bed_resize \
-b results/bed_file/no_readthrough_expressed_gene.bed \
-s 10000 \
-r "end" \
-t "outer" \
-o no_readthrough_expressed_gene_10kb.bed
python3 -m src.bed_handler.bed_resize \
-b results/bed_file/readthrough_expressed_gene.bed \
-s 10000 \
-r "end" \
-t "outer" \
-o readthrough_expressed_gene_10kb.bed
exps=(all_replicates siCTRL siDDX)
bins=(0 99)
for exp in ${exps[*]}; do
for bin in ${bins[*]}; do
python3 -m src.visu \
--design data/design_exp_${exp}.txt \
--bw_folder data/bigwig/ \
--region_bed results/bed_file/readthrough_expressed_gene.bed results/bed_file/no_readthrough_expressed_gene.bed \
--region_name readthrough no_readthrough \
--output results/figures/ \
--border_name TSS TTS \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm ${bin}
mv results/figures/metagene_readthrough-no_readthrough_100bin_10000_nt-around-25-bin_b${bin}_norm.pdf results/figures/${exp}_metagene_readthrough-no_readthrough_100bin_10000_nt-around-25-bin_b${bin}_norm.pdf
done
done
exps=(all_replicates siCTRL siDDX)
bins=(0 99)
loc=(TSS TTS)
for exp in ${exps[*]}; do
for i in ${!bins[@]}; do
python3 -m src.visu \
--design data/design_exp_${exp}.txt \
--bw_folder data/bigwig/ \
--region_bed results/bed_file/readthrough_expressed_gene_10kb.bed results/bed_file/no_readthrough_expressed_gene_10kb.bed \
--region_name readthrough no_readthrough \
--output results/figures/ \
--border_name TTS '' \
--environment 0 0 \
--show_replicate n \
--figure_type metagene \
--nb_bin 25 \
--norm "results/figures/coef_table/tmp_cov_table_design_exp_${exp}_readthrough_expressed_gene-no_readthrough_expressed_gene_100bin_10000_nt-around-25-bin_bin${bins[$i]}_norm.txt"
mv results/figures/metagene_readthrough-no_readthrough_25bin_0_nt-around-0-bin_file_norm.pdf results/figures/${exp}_TTS10kb_readthrough-no_readthrough_${loc[$i]}_norm.pdf
done
done
# Figure 1C
names=(IP)
designs=(data/designnew_exp_all_replicates_IP.txt)
bins=(99) # 0)
beds=(readthrough) # no_readthrough)
for bed in ${beds[*]}; do
for bin in ${bins[*]}; do
for i in ${!designs[@]}; do
python3 -m src.visu \
--design ${designs[i]} \
--bw_folder data/bigwig_newnorm/ \
--region_bed results/bed_file/${bed}_expressed_gene.bed \
--region_name ${bed} \
--output results/figures/ \
--border_name TSS TTS \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm ${bin} \
--stat True
mv results/figures/metagene_${bed}_100bin_10000_nt-around-25-bin_b${bin}_norm.pdf results/figures/Fig1C_${bed}_b${bin}_norm_${names[$i]}.pdf
done
done
done
names=(IP)
designs=(data/designnew_exp_all_replicates_IP.txt)
beds=(readthrough) # no_readthrough)
bins=(99) # 0)
loc=(TTS) # TSS)
for bed in ${beds[*]}; do
for i in ${!bins[@]}; do
for j in ${!designs[@]}; do
python3 -m src.visu \
--design ${designs[i]} \
--bw_folder data/bigwig_newnorm/ \
--region_bed results/bed_file/${bed}_expressed_gene_10kb.bed \
--region_name ${bed} \
--output results/figures/ \
--border_name TTS '' \
--environment 0 0 \
--show_replicate n \
--figure_type metagene \
--nb_bin 25 \
--norm "results/figures/coef_table/tmp_cov_table_designnew_exp_all_replicates_${names[$j]}_${bed}_expressed_gene_100bin_10000_nt-around-25-bin_bin${bins[$i]}_norm.txt" \
--stat True
mv results/figures/metagene_${bed}_25bin_0_nt-around-0-bin_file_norm.pdf results/figures/Fig_1C_TTS10kb_${bed}_${loc[$i]}-bin_norm_${names[$j]}.pdf
done
done
done
# Graphics
##############################
# SHY5Y #
##############################
# Creating a bed file only containing expressed gene in 5y cells
python3 -m src.bed_handler.filter_bed \
-b data/bed/gene.bed \
-f data/5y_expressed_genes_basemean\>5.txt \
-c id \
-o 5y_expressed_gene.bed
# Create a bed file containing
bins=('None' 0 99)
bin_names=('' '_b0_norm' '_b99_norm')
for i in ${!bins[@]}; do
python3 -m src.visu \
--design data/bigwig_SHY5Y/design_exp_all_replicates.txt \
--bw_folder data/bigwig_SHY5Y/ \
--region_bed results/bed_file/5y_expressed_gene.bed \
--region_name all_expressed_gene \
--output results/figures/ \
--border_name TSS TTS \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm ${bins[$i]}
mv results/figures/metagene_all_expressed_gene_100bin_10000_nt-around-25-bin${bin_names[$i]}.pdf results/figures/metagene_5y_rnaseq_all_expressed_gene${bin_names[$i]}.pdf
done
tts_sizes=(10000 50000)
bins=(25 25)
for i in ${!tts_sizes[@]}; do
size=${tts_sizes[$i]}
bin=${bins[$i]}
kb_size=$(python -c "print(int(${size}/1000)) if ${size}/1000 == int(${size}/1000) else print(${size}/1000)")
# Create a bed file containing all gene containing one DDX-down exons
python3 -m src.bed_handler.bed_resize \
-b results/bed_file/5y_expressed_gene.bed \
-s ${size} \
-r "end" \
-t "outer" \
-o all_expressed_gene_end${size}.bed
python3 -m src.visu \
--design data/bigwig_SHY5Y/design_exp_all_replicates.txt \
--bw_folder data/bigwig_SHY5Y/ \
--region_bed results/bed_file/all_expressed_gene_end${size}.bed \
--region_name all_expressed_gene \
--output results/figures/ \
--border_name TTS '' \
--environment 0 0 \
--show_replicate n \
--figure_type metagene \
--nb_bin ${bin} \
--norm "results/figures/coef_table/tmp_cov_table_design_exp_all_replicates_5y_expressed_gene_100bin_10000_nt-around-25-bin_bin99_norm.txt"
mv results/figures/metagene_all_expressed_gene_${bin}bin_0_nt-around-0-bin_file_norm.pdf results/figures/metagene_5y_rnaseq_TTS2${kb_size}kb_expressed_gene_${bin}bin_bin_TTS_norm.pdf
done
# 2kb region after TSS
python3 -m src.bed_handler.bed_resize \
-b data/bed/gene.bed \
-s 2000 \
-r "start" \
-o all_gene_TSS-2kb.bed
python3 -m src.visu \
--design data/bigwig_SHY5Y/design_exp_all_replicates.txt \
--bw_folder data/bigwig_SHY5Y/ \
--region_bed results/bed_file/all_gene_TSS-2kb.bed \
--region_name all_gene \
--output results/figures/ \
--border_name TSS '' \
--environment 0 0 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm "None" \
--stat True
mv results/figures/metagene_all_gene_100bin_0_nt-around-0-bin.pdf results/figures/metagene_5y_rnaseq_TSS-2kb_all_gene.pdf
#####################################################
# Metagene figure of last exons in readthrough genes near (<=2000 nt) or far (> 2000nt) from a CTCF file and last exons from non readthrough genes
# figures 5C
#####################################################
# Bed file containing the last exons of expressed gene with readthrough
python3 -m src.bed_handler.get_last_exons -g results/bed_file/readthrough_expressed_gene.bed -o results/bed_file/readthrough_expressed_last_exon.bed
# Bed file containing the last exons of expressed gene without readthrough
python3 -m src.bed_handler.get_last_exons -g results/bed_file/no_readthrough_expressed_gene.bed -o results/bed_file/no_readthrough_expressed_last_exon.bed
# Bed file containing the last exon in expressed genes with readthrough near CTCF (<=2000nt)
python3 -m src.bed_handler.select_regulated_near_ctcf_exons -e results/bed_file/readthrough_expressed_last_exon.bed -t 2000 -l both -i True -N True -n readthrough_last_exon
# Bed file containing the last exon in expressed genes with readthrough near CTCF (>2000nt)
python3 -m src.bed_handler.select_regulated_near_ctcf_exons -e results/bed_file/readthrough_expressed_last_exon.bed -t 2000 -l both -i True -N False -n readthrough_last_exon
cp results/bed_file/no_readthrough_expressed_gene.bed results/bed_file/no_readthrough_expressed_last_gene-dup.bed
list_names=(readthrough_ctcf readthrough no_readthrough)
bed_names=(readthrough_last_exon_near_CTCF_2000_both_ddx_with0_exon.bed readthrough_last_exon_far_CTCF_2000_both_ddx_with0_exon.bed no_readthrough_expressed_last_exon.bed)
for i in ${!list_names[*]}; do
cname=${list_names[i]}
bed=${bed_names[i]}
gbed=${bed/exon\.bed/gene-dup.bed}
nbed=${gbed/\.bed/}
python3 -m src.visu \
--design data/designnew_exp_all_replicates_IP.txt \
--bw_folder data/bigwig_newnorm \
--region_bed results/bed_file/${gbed} \
--region_name ${cname} \
--output results/figures/ \
--border_name TSS TTS \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm '0'
rm results/figures/metagene_${cname}_100bin_10000_nt-around-25-bin_b0_norm.pdf
python3 -m src.visu \
--design data/designnew_exp_all_replicates_IP.txt \
--bw_folder data/bigwig_newnorm \
--region_bed results/bed_file/${bed} \
--region_name ${cname} \
--output results/figures/ \
--border_name " " " " \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 30 \
--stat True \
-y 0.15 0.4 \
--norm "results/figures/coef_table/tmp_cov_table_designnew_exp_all_replicates_IP_${nbed}_100bin_10000_nt-around-25-bin_bin0_norm.txt" \
--stat True
mv results/figures/metagene_${cname}_30bin_10000_nt-around-25-bin_file_norm.pdf results/figures/all_replicates_metaexon_${cname}_30bin_10000_nt-around-25-bin_file_norm.pdf
done
###########################################################
# Figures siPP vs siCTRL pour ddx_down_ctcf,
# , ddx_down figure 5B
###########################################################
list_names=(ddx_down_ctcf ddx_down)
bed_names=(CTCF_2000_both_ddx_down_with0_exon.bed Far_CTCF_2000_both_ddx_down_with0_exon.bed)
for i in ${!list_names[*]}; do
cname=${list_names[i]}
bed=${bed_names[i]}
gbed=${bed/exon\.bed/gene-dup.bed}
nbed=${gbed/\.bed/}
python3 -m src.visu \
--design data/designnew_exp_all_replicates_IP.txt \
--bw_folder data/bigwig_newnorm/ \
--region_bed results/bed_file/${gbed} \
--region_name ${cname} \
--output results/figures/ \
--border_name TSS TTS \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 100 \
--norm '0'
rm results/figures/metagene_${cname}_100bin_10000_nt-around-25-bin_b0_norm.pdf
python3 -m src.visu \
--design data/designnew_exp_all_replicates_IP.txt \
--bw_folder data/bigwig_newnorm/ \
--region_bed results/bed_file/${bed} \
--region_name ${cname} \
--output results/figures/ \
--border_name " " " " \
--environment 10000 25 \
--show_replicate n \
--figure_type metagene \
--nb_bin 30 \
-y 0.15 0.4 \
--stat True \
--norm "results/figures/coef_table/tmp_cov_table_designnew_exp_all_replicates_IP_${nbed}_100bin_10000_nt-around-25-bin_bin0_norm.txt" \
--stat True
mv results/figures/metagene_${cname}_30bin_10000_nt-around-25-bin_file_norm.pdf results/figures/all_replicates_metagene_${cname}_100bin_10000_nt-around-25-bin_file_norm.pdf
done
python3 -m src.gc_content -B results/bed_file/readthrough_last_exon_near_CTCF_2000_both_ddx_with0_exon.bed results/bed_file/readthrough_last_exon_far_CTCF_2000_both_ddx_with0_exon.bed results/bed_file/no_readthrough_expressed_last_exon.bed -b readthrough_ctcf readthrough no_readthrough -g data/Homo_sapiens.GRCh37.dna.primary_assembly.fa -f "exons" -e 2000