The ENCODE Blacklist: Identification of Problematic Regions of the Genome
https://github.com/Boyle-Lab/Blacklist/tree/master
ATAC-seq footprinting unravels kinetics of transcription factor binding during zygotic genome activation
https://www.nature.com/articles/s41467-020-18035-1#Abs1
https://github.com/loosolab/TOBIAS
conda activate cutrun pip install tobias
### parameter
genome=/home/zz950/reference/refdata-gex-GRCh38-2020-A/fasta/genome.fa
blacklist=/home/zz950/reference/hg38-blacklist.v2.bed
bed=/home/zz950/projects/BAF_SOX9/diffbind/keyRdata/all.ATAC.234648.peaks.bed
### create folders
out_dir_qc=0.fastqc_report
out_dir1=1.clean_fastq
# out_dir2=2.Ecoli_bam
out_dir3=3.bam
out_dir4=4.frag
out_dir5=5.bigwig
out_dir6=6.peak # do it in another script
out_dir7=7.footprinting
mkdir $out_dir7
# ######################### main loop #############################
cat $SampleCSV | while IFS="," read sample fq1 fq2; do
###################################################################
#
/home/zz950/softwares/miniconda3/envs/cutrun/bin/TOBIAS ATACorrect --bam $out_dir3/${sample}.sorted.mapped.bam \
--genome $genome \
--peaks $bed \
--blacklist $blacklist \
--outdir $out_dir7 \
--cores 20
/home/zz950/softwares/miniconda3/envs/cutrun/bin/TOBIAS FootprintScores --signal $out_dir7/${sample}.sorted.mapped_corrected.bw \
--regions $bed \
--output $out_dir7/${sample}_footprints.bw \
--cores 20
# filter peaks # grep 'chr' /home/zz950/projects/BAF_SOX9/diffbind/keyRdata/all.ATAC.234648.peaks.bed > all.ATAC.234648.peaks.bed genome=/home/zz950/reference/refdata-gex-GRCh38-2020-A/fasta/genome.fa blacklist=/home/zz950/reference/hg38-blacklist.v2.bed bed=/home/zz950/projects/BAF_SOX9/diffbind/keyRdata/all.ATAC.234648.peaks.bed motif=/home/zz950/reference/JASPAR2024_CORE_vertebrates_non-redundant_pfms_jaspar.txt /home/zz950/softwares/miniconda3/envs/cutrun/bin/TOBIAS BINDetect --motifs $motif \ --signals DMSO_1_footprints.bw D4_1_footprints.bw \ --genome $genome \ --peaks $bed \ --outdir BINDetect_output \ --cond_names DMSO_1 D4_1 \ --cores 20 # # --peak_header test_data/merged_peaks_annotated_header.txt \
TOBIAS PlotAggregate --TFBS BINDetect_output/SOX9_MA0077.2/beds/SOX9_MA0077.2_all.bed --signals DMSO_1_footprints.bw D4_1_footprints.bw --output SOX9_footprint_comparison.pdf --share_y both --plot_boundaries --signal-on-x --flank 70 TOBIAS PlotAggregate --TFBS BINDetect_output/SOX8_MA0868.3/beds/SOX8_MA0868.3_all.bed --signals DMSO_1_footprints.bw D4_1_footprints.bw --output SOX8_footprint_comparison.pdf --share_y both --plot_boundaries --signal-on-x --flank 70 TOBIAS PlotAggregate --TFBS BINDetect_output/BATF_MA1634.2/beds/BATF_MA1634.2_all.bed --signals DMSO_1_footprints.bw D4_1_footprints.bw --output BATF_footprint_comparison.pdf --share_y both --plot_boundaries --signal-on-x --flank 70 TOBIAS PlotAggregate --TFBS BINDetect_output/JUND_MA0491.3/beds/JUND_MA0491.3_all.bed --signals DMSO_1_footprints.bw D4_1_footprints.bw --output JUND_1_footprint_comparison.pdf --share_y both --plot_boundaries --signal-on-x --flank 70
参考：/home/zz950/projects/BAF_SOX9/data/atac_pipeline
标签：--,ATAC,bed,bw,TOBIAS,footprint,home,zz950,out From： https://www.cnblogs.com/leezx/p/18299495