ChIP-seq using HOMER (-style factor, findPeaks + default getDifferentialPeaksReplicates.pl)

gene_x 0 like s 846 view s

Tags:

  1. nextflow ChIP-seq run for NHDF_p783

    1. #under Raw_Data for ChIP-seq 
    2. ln -s ./230306_NB501882_0417_AHMVHHBGXN/2023_022_nf_denise/nf859/3_NHDF_Donor_1_p783_input_S5_R1_001.fastq.gz p783_input_DonorI.fastq.gz
    3. ln -s ./230306_NB501882_0417_AHMVHHBGXN/2023_022_nf_denise/nf860/4_NHDF_Donor_2_p783_input_S6_R1_001.fastq.gz p783_input_DonorII.fastq.gz
    4. ln -s ./230306_NB501882_0417_AHMVHHBGXN/2023_022_nf_denise/nf861/5_NHDF_Donor_1_p783_ChIP_S7_R1_001.fastq.gz p783_ChIP_DonorI.fastq.gz
    5. ln -s ./230306_NB501882_0417_AHMVHHBGXN/2023_022_nf_denise/nf862/6_NHDF_Donor_2_p783_ChIP_S8_R1_001.fastq.gz p783_ChIP_DonorII.fastq.gz
    7. #'hg38'      { bwa = "/home/jhuang/REFs/Homo_sapiens/UCSC/hg38/Sequence/BWAIndex/"
    8. #          blacklist = "/home/jhuang/REFs/Homo_sapiens/UCSC/hg38/blacklists/hg38-blacklist.bed"
    9. #          gtf = "/home/jhuang/REFs/Homo_sapiens/UCSC/hg38/Annotation/Genes/genes.gtf"
    10. #        }
    11. ln -s /home/jhuang/Tools/NGI-ChIPseq/ .
    12. (chipseq) nextflow run NGI-ChIPseq/main.nf --reads '/home/jhuang/DATA/Data_Denise_LT_DNA_Binding/Raw_Data/*.fastq.gz' --genome hg38 --macsconfig macs.config --singleEnd --blacklist_filtering -profile standard --project Denise_LT_DNA_Bindung --outdir results_LT_DNA_Bindung_hg38 -resume
    14. #By the way: nextflow RNA-seq run for NHDF_p783 (NOT the topics of the post).
    15. #under Raw_Data for RNA-seq
    16. cp ~/DATA/Data_Denise_tx_epi_MCPyV_PUBLISHING/Data_Denise_RNASeq/Raw_Data/V_8_2_4_p600_d8_DonorI.fastq.gz ./
    17. cp ~/DATA/Data_Denise_tx_epi_MCPyV_PUBLISHING/Data_Denise_RNASeq/Raw_Data/V_8_2_3_p600_d8_DonorII.fastq.gz ./
    18. #under Raw_Data_p783_RNAseq for RNA-seq
    19. ln -s ../Raw_Data/V_8_2_4_p600_d8_DonorI.fastq.gz  ctrl_DonorI.fastq.gz   
    20. ln -s ../Raw_Data/V_8_2_3_p600_d8_DonorII.fastq.gz ctrl_DonorII.fastq.gz
    21. ln -s ../Raw_Data/230306_NB501882_0417_AHMVHHBGXN/2023_022_nf_denise/nf857/1_NHDF_Donor_1_p783_S1_R1_001.fastq.gz p783_DonorI.fastq.gz
    22. ln -s ../Raw_Data/230306_NB501882_0417_AHMVHHBGXN/2023_022_nf_denise/nf858/2_NHDF_Donor_2_p783_S2_R1_001.fastq.gz p783_DonorII.fastq.gz
    23. #Note that we need to regenerate MultiQC.html after ignoring 'Biotype Counts', since --fcGroupFeaturesType gene_name cannot generate the real biotype counts!
    24. (rnaseq_2021) nextflow run rnaseq --reads '/home/jhuang/DATA/Data_Denise_LT_DNA_Binding/Raw_Data_p783/RNA_seq/*.fastq.gz'  --fasta "/home/jhuang/REFs/Homo_sapiens/UCSC/hg38/Sequence/WholeGenomeFasta/genome.fa" --gtf "/home/jhuang/REFs/Homo_sapiens/UCSC/hg38/Annotation/Genes/genes.gtf"  --bed12 "/home/jhuang/REFs/Homo_sapiens/UCSC/hg38/Annotation/Genes/genes.bed" --singleEnd -profile standard --aligner star --saveReference -resume --saveAlignedIntermediates --skip_rseqc --skip_dupradar --skip_genebody_coverage --skip_preseq --skip_edger --fcGroupFeaturesType gene_name

  2. nextflow ChIP-seq run for data of truncated LT-Ag + sT expression of WaGa and HEK293

    1. #160719_SN7001212_0156_AC8K76ACXX
    3. cat ../160719_SN7001212_0156_AC8K76ACXX/Sample_293_input_1_10_p197_1/293_input_1_10_p197_1_GTAGAG_L002_R1_001.fastq.gz ../160719_SN7001212_0156_AC8K76ACXX/Sample_293_input_1_10_p197_1/293_input_1_10_p197_1_GTAGAG_L003_R1_001.fastq.gz > HEK293_Input_p197_r1.fastq.gz
    4. cat ../160719_SN7001212_0156_AC8K76ACXX/Sample_293_input_1_10_p197_2/293_input_1_10_p197_2_GTCCGC_L002_R1_001.fastq.gz ../160719_SN7001212_0156_AC8K76ACXX/Sample_293_input_1_10_p197_2/293_input_1_10_p197_2_GTCCGC_L003_R1_001.fastq.gz > HEK293_Input_p197_r2.fastq.gz
    5. cat ../160719_SN7001212_0156_AC8K76ACXX/Sample_293_input_1_10_p197_3/293_input_1_10_p197_3_GTGAAA_L002_R1_001.fastq.gz ../160719_SN7001212_0156_AC8K76ACXX/Sample_293_input_1_10_p197_3/293_input_1_10_p197_3_GTGAAA_L003_R1_001.fastq.gz > HEK293_Input_p197_r3.fastq.gz
    7. cat ../160719_SN7001212_0156_AC8K76ACXX/Sample_293_lt_p197_1/293_lt_p197_1_TAGCTT_L002_R1_001.fastq.gz ../160719_SN7001212_0156_AC8K76ACXX/Sample_293_lt_p197_1/293_lt_p197_1_TAGCTT_L003_R1_001.fastq.gz > HEK293_LT_p197_r1.fastq.gz
    8. cat ../160719_SN7001212_0156_AC8K76ACXX/Sample_293_lt_p197_2/293_lt_p197_2_GGCTAC_L002_R1_001.fastq.gz ../160719_SN7001212_0156_AC8K76ACXX/Sample_293_lt_p197_2/293_lt_p197_2_GGCTAC_L003_R1_001.fastq.gz > HEK293_LT_p197_r2.fastq.gz
    9. cat ../160719_SN7001212_0156_AC8K76ACXX/Sample_293_lt_p197_3/293_lt_p197_3_AGTCAA_L002_R1_001.fastq.gz ../160719_SN7001212_0156_AC8K76ACXX/Sample_293_lt_p197_3/293_lt_p197_3_AGTCAA_L003_R1_001.fastq.gz > HEK293_LT_p197_r3.fastq.gz
    11. #140117_SN7001212_0097_AC3ECBACXX
    13. cat ../140117_SN7001212_0097_AC3ECBACXX/Sample_waga_igg/waga_igg_TAGCTT_L003_R1_001.fastq.gz ../140117_SN7001212_0097_AC3ECBACXX/Sample_waga_igg/waga_igg_TAGCTT_L004_R1_001.fastq.gz > WaGa_IgG.fastq.gz
    15. cat ../140117_SN7001212_0097_AC3ECBACXX/Sample_waga_lt/waga_lt_GGTAGC_L003_R1_001.fastq.gz ../140117_SN7001212_0097_AC3ECBACXX/Sample_waga_lt/waga_lt_GGTAGC_L004_R1_001.fastq.gz > WaGa_LT.fastq.gz
    17. ln -s /home/jhuang/Tools/NGI-ChIPseq/ .
    18. (chipseq) nextflow run NGI-ChIPseq/main.nf --reads '/home/jhuang/DATA/Data_Denise_LT_DNA_Binding/LTtr-ChIP/Raw_Data/*.fastq.gz' --genome hg38 --macsconfig macs.config --singleEnd --blacklist_filtering -profile standard --project Denise_LTtr_DNA_Bindung --outdir results_LTtr_DNA_Bindung_hg38 -resume

  3. makeTagDirectory

    1. conda activate myperl
    2. mkdir results_ChIPseq_K331A_hg38/homer; cd results_ChIPseq_K331A_hg38/homer
    4. #makeTagDirectory <output directory> <input file> -genome hg38
    5. for sample in p783_ChIP_DonorI p783_ChIP_DonorII p783_input_DonorI p783_input_DonorII; do
    6.   makeTagDirectory ${sample} ../picard/${sample}.dedup.sorted.bam -genome hg38
    7. done

  4. generate bigwigs

    1. #makeUCSCfile peaks.txt -f peaks.bed -o auto -noadj -bigWig sample.bw -genome hg38
    2. for sample in p783_ChIP_DonorI p783_ChIP_DonorII p783_input_DonorI p783_input_DonorII; do
    3. makeUCSCfile ${sample} -pseudo 1 -bigWig /home/jhuang/REFs/hg38.chromSizes -o auto -style chipseq    -norm 1e7 -normLength 100 -fsize 1
    4. done
    5. mv ./p783_ChIP_DonorI/p783_ChIP_DonorI.ucsc.bigWig     ./p783_ChIP_DonorI/LT_K331A_DI.bigWig
    6. mv ./p783_ChIP_DonorII/p783_ChIP_DonorII.ucsc.bigWig   ./p783_ChIP_DonorII/LT_K331A_DII.bigWig
    7. mv ./p783_input_DonorI/p783_input_DonorI.ucsc.bigWig   ./p783_input_DonorI/LT_K331A_DI_input.bigWig
    8. mv ./p783_input_DonorII/p783_input_DonorII.ucsc.bigWig ./p783_input_DonorII/LT_K331A_DII_input.bigWig

  5. peak calling, get peaks.txt

    1.   #findPeaks <tag directory> -i <input file> -o <output file> -genome hg38
    2.   findPeaks p783_ChIP_DonorI  -style factor    -o auto -i p783_input_DonorI
    3.   findPeaks p783_ChIP_DonorII -style factor    -o auto -i p783_input_DonorII
    4.   cp ../reproduce_2023/tagDirectories/ ./
    5.   cd homer
    6.   ln -s ../tagDirectories/NHDF_LT_Donor1 ./
    7.   ln -s ../tagDirectories/NHDF_LT_Donor2 ./
    8.   ln -s ../tagDirectories/NHDF_LT_Donor1_Input ./
    9.   ln -s ../tagDirectories/NHDF_LT_Donor2_Input ./
    10.   ln -s ../tagDirectories/Pfsk-1B_LT+sT_r1 ./
    11.   ln -s ../tagDirectories/Pfsk-1B_LT+sT_r2 ./
    12.   ln -s ../tagDirectories/Pfsk-1B_LT+sT_r1_Input ./
    13.   ln -s ../tagDirectories/Pfsk-1B_LT+sT_r2_Input ./
    14.   ln -s ../tagDirectories/HEK293_LT+sT_r2 ./
    15.   ln -s ../tagDirectories/HEK293_LT+sT_r3 ./
    16.   ln -s ../tagDirectories/HEK293_LT+sT_r2_Input ./
    17.   ln -s ../tagDirectories/HEK293_LT+sT_r3_Input ./
    19.   findPeaks NHDF_LT_Donor1  -style factor      -o auto -i NHDF_LT_Donor1_Input
    20.   findPeaks NHDF_LT_Donor2  -style factor      -o auto -i NHDF_LT_Donor2_Input
    22.   findPeaks Pfsk-1B_LT+sT_r1  -style factor    -o auto -i Pfsk-1B_LT+sT_r1_Input
    23.   findPeaks Pfsk-1B_LT+sT_r2  -style factor    -o auto -i Pfsk-1B_LT+sT_r2_Input
    25.   findPeaks HEK293_LT+sT_r2 -style factor      -o auto -i HEK293_LT+sT_r2_Input
    26.   findPeaks HEK293_LT+sT_r3 -style factor      -o auto -i HEK293_LT+sT_r3_Input

  6. peak calling using getDifferentialPeaksReplicates.pl

    1. cp -r ../../reproduce_2023/tagDirectories/NHDF_LT_Donor1_Input ./
    2. cp -r ../../reproduce_2023/tagDirectories/NHDF_LT_Donor2_Input ./
    3. cp -r ../../reproduce_2023/tagDirectories/NHDF_LT_Donor1 ./
    4. cp -r ../../reproduce_2023/tagDirectories/NHDF_LT_Donor2 ./
    5. #-annStats annStats.txt 
    6. conda activate myperl
    7. getDifferentialPeaksReplicates.pl -t p783_ChIP_DonorI p783_ChIP_DonorII -i p783_input_DonorI p783_input_DonorII      -genome hg38 -use peaks.txt > peaks_K331A_LT.txt
    8. mv peaks_K331A_LT.txt peaks_NHDF_K331A_LT.txt
    9. getDifferentialPeaksReplicates.pl -t NHDF_LT_Donor1 NHDF_LT_Donor2      -i NHDF_LT_Donor1_Input NHDF_LT_Donor2_Input -genome hg38 -use peaks.txt > peaks_NHDF_LT.txt
    10. getDifferentialPeaksReplicates.pl -t Pfsk-1B_LT+sT_r1 Pfsk-1B_LT+sT_r2  -i Pfsk-1B_LT+sT_r1_Input Pfsk-1B_LT+sT_r2_Input -genome hg38 -use peaks.txt > peaks_PFSK-1_LT+sT.txt
    11. getDifferentialPeaksReplicates.pl -t HEK293_LT+sT_r2 HEK293_LT+sT_r3  -i HEK293_LT+sT_r2_Input HEK293_LT+sT_r3_Input -genome hg38 -use peaks.txt > peaks_HEK293_LT+sT.txt

  7. merge peaks: tried 0, 200, 500, 1000, 2000

    1. #http://homer.ucsd.edu/homer/ngs/mergePeaks.html
    2. mergePeaks -d 1000 peaks_PFSK-1_LT+sT.txt peaks_HEK293_LT+sT.txt peaks_NHDF_LT.txt -prefix celllines -venn celllines.txt -matrix celllines
    4. #-- generate bed files --
    5. awk 'BEGIN {OFS="\t"} {print $2,$3,$4,$1,$6}' peaks_NHDF_LT.txt > peaks_NHDF.bed;        
    6. awk 'BEGIN {OFS="\t"} {print $2,$3,$4,$1,$6}' peaks_HEK293_LT+sT.txt > peaks_HEK293.bed;
    7. awk 'BEGIN {OFS="\t"} {print $2,$3,$4,$1,$6}' peaks_PFSK-1_LT+sT.txt > peaks_PFSK-1.bed;
    8. awk 'BEGIN {OFS="\t"} {print $2,$3,$4,$1,$6}' celllines_peaks_HEK293_LT+sT.txt > peaks_HEK293_only.bed;
    9. awk 'BEGIN {OFS="\t"} {print $2,$3,$4,$1,$6}' celllines_peaks_HEK293_LT+sT.txt_peaks_NHDF_LT.txt > peaks_HEK293_NHDF.bed;
    10. awk 'BEGIN {OFS="\t"} {print $2,$3,$4,$1,$6}' celllines_peaks_NHDF_LT.txt > peaks_NHDF_only.bed;
    11. awk 'BEGIN {OFS="\t"} {print $2,$3,$4,$1,$6}' celllines_peaks_PFSK-1_LT+sT.txt > peaks_PFSK-1_only.bed;
    12. awk 'BEGIN {OFS="\t"} {print $2,$3,$4,$1,$6}' celllines_peaks_PFSK-1_LT+sT.txt_peaks_HEK293_LT+sT.txt > peaks_PFSK-1_HEK293.bed;
    13. awk 'BEGIN {OFS="\t"} {print $2,$3,$4,$1,$6}' celllines_peaks_PFSK-1_LT+sT.txt_peaks_HEK293_LT+sT.txt_peaks_NHDF_LT.txt > peaks_PFSK-1_HEK293_NHDF.bed;
    14. awk 'BEGIN {OFS="\t"} {print $2,$3,$4,$1,$6}' celllines_peaks_PFSK-1_LT+sT.txt_peaks_NHDF_LT.txt > peaks_PFSK-1_NHDF.bed;
    16. #-- annotate the peaks --
    17. annotatePeaks.pl peaks_NHDF_LT.txt hg38 > annotatedPeaks_NHDF.txt
    18. annotatePeaks.pl peaks_HEK293_LT+sT.txt hg38 > annotatedPeaks_HEK293.txt
    19. annotatePeaks.pl peaks_PFSK-1_LT+sT.txt hg38 > annotatedPeaks_PFSK-1.txt
    20. annotatePeaks.pl celllines_peaks_HEK293_LT+sT.txt hg38 > annotatedPeaks_HEK293_only.txt
    21. annotatePeaks.pl celllines_peaks_HEK293_LT+sT.txt_peaks_NHDF_LT.txt hg38 > annotatedPeaks_HEK293_NHDF.txt
    22. annotatePeaks.pl celllines_peaks_NHDF_LT.txt hg38 > annotatedPeaks_NHDF_only.txt
    23. annotatePeaks.pl celllines_peaks_PFSK-1_LT+sT.txt hg38 > annotatedPeaks_PFSK-1_only.txt
    24. annotatePeaks.pl celllines_peaks_PFSK-1_LT+sT.txt_peaks_HEK293_LT+sT.txt hg38 > annotatedPeaks_PFSK-1_HEK293.txt
    25. annotatePeaks.pl celllines_peaks_PFSK-1_LT+sT.txt_peaks_HEK293_LT+sT.txt_peaks_NHDF_LT.txt hg38 > annotatedPeaks_PFSK-1_HEK293_NHDF.txt
    26. annotatePeaks.pl celllines_peaks_PFSK-1_LT+sT.txt_peaks_NHDF_LT.txt hg38 > annotatedPeaks_PFSK-1_NHDF.txt
    28. mkdir ../beds_PFSK-1_HEK293_NHDF;
    29. for sample in peaks_HEK293_only peaks_PFSK-1_only peaks_NHDF_only    peaks_HEK293 peaks_PFSK-1 peaks_NHDF    peaks_PFSK-1_HEK293 peaks_PFSK-1_NHDF peaks_HEK293_NHDF     peaks_PFSK-1_HEK293_NHDF; do
    30.   grep -v "cmd" ${sample}.bed > ../beds_PFSK-1_HEK293_NHDF/${sample}_.bed
    31. done
    33. #Chr     Start   End     PeakID (cmd=annotatePeaks.pl common_peaks_NHDF.txt hg38)        Peak Score      Strand
    34. ~/Tools/csv2xls-0.4/csv_to_xls.py celllines.txt annotatedPeaks_HEK293_only.txt annotatedPeaks_PFSK-1_only.txt annotatedPeaks_NHDF_only.txt    annotatedPeaks_HEK293.txt annotatedPeaks_PFSK-1.txt annotatedPeaks_NHDF.txt    annotatedPeaks_PFSK-1_HEK293.txt annotatedPeaks_PFSK-1_NHDF.txt annotatedPeaks_HEK293_NHDF.txt     annotatedPeaks_PFSK-1_HEK293_NHDF.txt  -d$'\t' -o  annotatedPeaks_PFSK-1_HEK293_NHDF.xls
    36. #IMPORTANT: DELETE the column 'Strand' marked with '+' in the merged Excel file!

like unlike

点赞本文的读者

还没有人对此文章表态

本文有评论

没有评论

看文章，发评论，不要沉默

最受欢迎文章

  1. Why Do Significant Gene Lists Change After Adding Additional Conditions in Differential Gene Expression Analysis?
  2. Motif Discovery in Biological Sequences: A Comparison of MEME and HOMER
  3. Calling peaks using findPeaks of HOMER
  4. Updating Human Gene Identifiers using Ensembl BioMart: A Step-by-Step Guide
  5. pheatmap vs heatmap.2
  6. Setup conda environments
  7. Should the inputs for GSVA be normalized or raw?
  8. File format for single channel analysis of Agilent microarray data with Limma?
  9. Kraken2 Installation and Usage Guide
  10. 洛那法尼(lonafarnib)：从抗癌症到抗病毒的多功能药物

最新文章

最多评论文章

推荐相似文章

Sorry, 没有相似文章

© 2023 XGenes.com Impressum