Pipeline for 55 Ind

Mispriming

• Get 10 basepairs upstream: wrap_Upstream10Bases.sh
  
• Find sequence for these regions: Nuc10BasesUp.sh
  
• find which are bad run_filterMissprimingInNuc10.sh
• filter bed file run_filterSortBedbyCleanedBed.sh
• sort clean bed file sort_filterSortBedbyCleanedBed.sh
• filter bam files wrap_filterBamforMP.pysam2.sh
  
• sort and index clean bam SortIndexBam_noMP.sh
• merge clean bam files mergeBamFiles_noMP.sh
  
• sort and index merged SortIndexMergedBam_noMP.sh

Make Peaks

• create BW mergedBam2Bedgraph.sh
  
• make it a coverage file run_bgtocov_noMP.sh
• call peaks run_callPeaksYL_noMP.sh
  
• filter peaks
  • cat /project2/gilad/briana/threeprimeseq/data/mergedPeaks_noMP/*.bed > /project2/gilad/briana/threeprimeseq/data/mergedPeaks_noMP/APApeaks_merged_allchrom_noMP.bed
  • make SAF file bed2saf_noMP.py
  • run feature counts peak_fc_noMP.sh
  • filter peaks run_filter_peaks_noMP.sh
    
• name peaks

x = wc -l /project2/gilad/briana/threeprimeseq/data/mergedPeaks_noMP_filtered/Filtered_APApeaks_merged_allchrom_noMP.bed

seq 1 x > peak.num.txt

sort -k1,1 -k2,2n Filtered_APApeaks_merged_allchrom_noMP.bed > Filtered_APApeaks_merged_allchrom_noMP.sort.bed

paste /project2/gilad/briana/threeprimeseq/data/mergedPeaks_noMP_filtered/Filtered_APApeaks_merged_allchrom_noMP.sort.bed peak.num.txt | column -s $'\t' -t > temp
awk '{print $1 "\t" $2 "\t" $3 "\t" $7  "\t"  $4 "\t"  $5 "\t" $6}' temp >   /project2/gilad/briana/threeprimeseq/data/mergedPeaks_noMP_filtered/Filtered_APApeaks_merged_allchrom_noMP.sort.named.bed

#cut the chr  

sed 's/^chr//' /project2/gilad/briana/threeprimeseq/data/mergedPeaks_noMP_filtered/Filtered_APApeaks_merged_allchrom_noMP.sort.named.bed > /project2/gilad/briana/threeprimeseq/data/mergedPeaks_noMP_filtered/Filtered_APApeaks_merged_allchrom_noMP.sort.named.noCHR.bed

Assign Gene to peak

• Gene assignments mapnoMPPeaks2GenomeLoc.sh

Get Peak Counts and Usage

• make SAF processGenLocPeakAnno2SAF.py
  
• feature counts GeneLocAnno_fc_TN_noMP.sh
  • fix header fix_head_fc_geneLoc_tot_noMP.py
  • fix header fix_head_fc_geneLoc_nuc_noMP.py
  • create_fileid_geneLocAnno_total.py

fout = file("/project2/gilad/briana/threeprimeseq/data/filtPeakOppstrand_cov_noMP_GeneLocAnno/file_id_mapping_total_Transcript_head.txt",'w')
infile= open("/project2/gilad/briana/threeprimeseq/data/filtPeakOppstrand_cov_noMP_GeneLocAnno/filtered_APApeaks_merged_allchrom_refseqGenes.GeneLocAnno_NoMP_sm_quant.Total.fixed.fc", "r")
for line, i in enumerate(infile):
    if line == 0:
        i_list=i.split()
        files= i_list[10:-2]
        for each in files:
            full = each.split("/")[7]
            samp= full.split("-")[2:4]
            lim="_"
            samp_st=lim.join(samp)
            outLine= full[:-1] + "\t" + samp_st
            fout.write(outLine + "\n")
fout.close()

- create_fileid_geneLocAnno_nuclear.py  

fout = file("/project2/gilad/briana/threeprimeseq/data/filtPeakOppstrand_cov_noMP_GeneLocAnno/file_id_mapping_nuclear_Transcript_head.txt",'w')
infile= open("/project2/gilad/briana/threeprimeseq/data/filtPeakOppstrand_cov_noMP_GeneLocAnno/filtered_APApeaks_merged_allchrom_refseqGenes.GeneLocAnno_NoMP_sm_quant.Nuclear.fixed.fc", "r")
for line, i in enumerate(infile):
    if line == 0:
        i_list=i.split()
        files= i_list[10:-2]
        for each in files:
            full = each.split("/")[7]
            samp= full.split("-")[2:4]
            lim="_"
            samp_st=lim.join(samp)
            outLine= full[:-1] + "\t" + samp_st
            fout.write(outLine + "\n")
fout.close()

• make phenotype run_makePhen_sep_GeneLocAnno_noMP.sh
  
• convert to usage pheno2CountOnly_genelocAnno.R
  • counts to numeric convertCount2Numeric_noMP_GeneLocAnno.py

Make script to filter 5%

• filter_5percUsagePeaks.R

library(tidyverse)

totalPeakUs=read.table("/project2/gilad/briana/threeprimeseq/data/phenotypes_filtPeakTranscript_noMP_GeneLocAnno/filtered_APApeaks_merged_allchrom_refseqGenes.GeneLocAnno_NoMP_sm_quant.Total.fixed.pheno.fc", header = T, stringsAsFactors = F) %>% separate(chrom, sep = ":", into = c("chr", "start", "end", "id")) %>% separate(id, sep="_", into=c("gene", "strand", "peak"))

nuclearPeakUs=read.table("/project2/gilad/briana/threeprimeseq/data/phenotypes_filtPeakTranscript_noMP_GeneLocAnno/filtered_APApeaks_merged_allchrom_refseqGenes.GeneLocAnno_NoMP_sm_quant.Nuclear.fixed.pheno.fc", header = T, stringsAsFactors = F) %>% separate(chrom, sep = ":", into = c("chr", "start", "end", "id")) %>% separate(id, sep="_", into=c("gene", "strand", "peak"))

ind=colnames(totalPeakUs)[7:dim(totalPeakUs)[2]]
totalPeakUs_CountNum=read.table("/project2/gilad/briana/threeprimeseq/data/phenotypes_filtPeakTranscript_noMP_GeneLocAnno/filtered_APApeaks_merged_allchrom_refseqGenes.GeneLocAnno_NoMP_sm_quant.Total.fixed.pheno.CountsOnlyNumeric.txt", col.names = ind)

nuclearPeakUs_CountNum=read.table("/project2/gilad/briana/threeprimeseq/data/phenotypes_filtPeakTranscript_noMP_GeneLocAnno/filtered_APApeaks_merged_allchrom_refseqGenes.GeneLocAnno_NoMP_sm_quant.Nuclear.fixed.pheno.CountsOnlyNumeric.txt", col.names = ind)


#numeric with anno
totalPeak=as.data.frame(cbind(totalPeakUs[,1:6], totalPeakUs_CountNum))
nuclearPeak=as.data.frame(cbind(nuclearPeakUs[,1:6], nuclearPeakUs_CountNum))

#mean
totalPeakUs_CountNum_mean=rowMeans(totalPeakUs_CountNum)
nuclearPeakUs_CountNum_mean=rowMeans(nuclearPeakUs_CountNum)


#append mean to anno
TotalPeakUSMean=as.data.frame(cbind(totalPeakUs[,1:6],totalPeakUs_CountNum_mean))
NuclearPeakUSMean=as.data.frame(cbind(nuclearPeakUs[,1:6],nuclearPeakUs_CountNum_mean))

NuclearPeakUSMean_5perc=NuclearPeakUSMean %>% filter(nuclearPeakUs_CountNum_mean>=.05)
write.table(NuclearPeakUSMean_5perc,file="/project2/gilad/briana/threeprimeseq/data/phenotypes_filtPeakTranscript_noMP_GeneLocAnno/filtered_APApeaks_merged_allchrom_refseqGenes.GeneLocAnno.NoMP_sm_quant.Nuclear_fixed.pheno.5percPeaks.txt", row.names=F, col.names=F, quote = F)


TotalPeakUSMean_5per= TotalPeakUSMean %>% filter(totalPeakUs_CountNum_mean>=.05) 
write.table(TotalPeakUSMean_5per,file="/project2/gilad/briana/threeprimeseq/data/phenotypes_filtPeakTranscript_noMP_GeneLocAnno/filtered_APApeaks_merged_allchrom_refseqGenes.GeneLocAnno.NoMP_sm_quant.Total_fixed.pheno.5percPeaks.txt", row.names=F, col.names=F, quote = F)

• run_filter_5percUsagePeaks.sh

#!/bin/bash

#SBATCH --job-name=run_filter_5percUsagePeaks
#SBATCH --account=pi-yangili1
#SBATCH --time=24:00:00
#SBATCH --output=run_filter_5percUsagePeaks.out
#SBATCH --error=run_filter_5percUsagePeaks.err
#SBATCH --partition=broadwl
#SBATCH --mem=12G
#SBATCH --mail-type=END

module load Anaconda3
source activate three-prime-env


Rscript filter_5percUsagePeaks.R

• filterPheno_bothFraction_GeneLocAnno_5perc.py

QTL analysis

In /project2/gilad/briana/threeprimeseq/data/phenotypes_filtPeakTranscript_noMP_GeneLocAnno_5percUs/

#zip file 
gzip filtered_APApeaks_merged_allchrom_refseqGenes.GeneLocAnno_NoMP_sm_quant.Nuclear.fixed.pheno_5perc.fc
gzip filtered_APApeaks_merged_allchrom_refseqGenes.GeneLocAnno_NoMP_sm_quant.Total.fixed.pheno_5perc.fc


module load python
#leafcutter script
python /project2/gilad/briana/threeprimeseq/code/prepare_phenotype_table.py filtered_APApeaks_merged_allchrom_refseqGenes.GeneLocAnno_NoMP_sm_quant.Nuclear.fixed.pheno_5perc.fc.gz

python /project2/gilad/briana/threeprimeseq/code/prepare_phenotype_table.py filtered_APApeaks_merged_allchrom_refseqGenes.GeneLocAnno_NoMP_sm_quant.Total.fixed.pheno_5perc.fc.gz




#source activate three-prime-env
 sh filtered_APApeaks_merged_allchrom_refseqGenes.GeneLocAnno_NoMP_sm_quant.Nuclear.fixed.pheno_5perc.fc.gz_prepare.sh
sh filtered_APApeaks_merged_allchrom_refseqGenes.GeneLocAnno_NoMP_sm_quant.Total.fixed.pheno_5perc.fc.gz_prepare.sh


#keep only 2 PCs
head -n 3 filtered_APApeaks_merged_allchrom_refseqGenes.GeneLocAnno_NoMP_sm_quant.Nuclear.fixed.pheno_5perc.fc.gz.PCs > filtered_APApeaks_merged_allchrom_refseqGenes.GeneLocAnno_NoMP_sm_quant.Nuclear.fixed.pheno_5perc.fc.gz.2PCs
head -n 3 filtered_APApeaks_merged_allchrom_refseqGenes.GeneLocAnno_NoMP_sm_quant.Total.fixed.pheno_5perc.fc.gz.PCs > filtered_APApeaks_merged_allchrom_refseqGenes.GeneLocAnno_NoMP_sm_quant.Total.fixed.pheno_5perc.fc.gz.2PCs

• Make sample list makeSampleList_newGeneAnno.py

#make a sample list  

fout = open("/project2/gilad/briana/threeprimeseq/data/phenotypes_filtPeakTranscript_noMP_GeneLocAnno_5percUs/SAMPLE.txt",'w')

for ln in open("/project2/gilad/briana/threeprimeseq/data/filtPeakOppstrand_cov_noMP_GeneLocAnno/file_id_mapping_total_Transcript_head.txt", "r"):
    bam, sample = ln.split()
    line=sample[:-2]
    fout.write("NA"+line + "\n")
fout.close()

(current - need to remove 19092 and 19193)
- APAqtl_nominal_GeneLocAnno_noMP_5percUsage.sh
- APAqtl_perm_GeneLocAnno_noMP_5percUsage.sh
- run_APAqtlpermCorrectQQplot_GeneLocAnno_noMP_5perUs.sh

Session information

sessionInfo()

R version 3.5.1 (2018-07-02)
Platform: x86_64-apple-darwin15.6.0 (64-bit)
Running under: macOS  10.14.1

Matrix products: default
BLAS: /Library/Frameworks/R.framework/Versions/3.5/Resources/lib/libRblas.0.dylib
LAPACK: /Library/Frameworks/R.framework/Versions/3.5/Resources/lib/libRlapack.dylib

locale:
[1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

loaded via a namespace (and not attached):
 [1] workflowr_1.1.1   Rcpp_0.12.19      digest_0.6.17    
 [4] rprojroot_1.3-2   R.methodsS3_1.7.1 backports_1.1.2  
 [7] git2r_0.23.0      magrittr_1.5      evaluate_0.11    
[10] stringi_1.2.4     whisker_0.3-2     R.oo_1.22.0      
[13] R.utils_2.7.0     rmarkdown_1.10    tools_3.5.1      
[16] stringr_1.3.1     yaml_2.2.0        compiler_3.5.1   
[19] htmltools_0.3.6   knitr_1.20