From 1e1f543826fc98c5b54d029f3477c2b2d36240e2 Mon Sep 17 00:00:00 2001
From: "Gervaise H. Henry" <gervaise.henry@utsouthwestern.edu>
Date: Tue, 29 Dec 2020 09:20:41 -0600
Subject: [PATCH] New test data with txt

---
 .gitlab-ci.yml              |   2 +-
 test_data/createTestData.sh | 130 ++++++++++++++++++------------------
 2 files changed, 66 insertions(+), 66 deletions(-)

diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
index 352305f..bd9fea3 100644
--- a/.gitlab-ci.yml
+++ b/.gitlab-ci.yml
@@ -76,7 +76,7 @@ parseMetadata:
   - stranded=$(singularity run 'docker://gudmaprbk/python3:1.0.0' python3 ./workflow/scripts/parseMeta.py -r Replicate_RID -m "./test_data/meta/metaTest.csv" -p stranded)
   - spike=$(singularity run 'docker://gudmaprbk/python3:1.0.0' python3 ./workflow/scripts/parseMeta.py -r Replicate_RID -m "./test_data/meta/metaTest.csv" -p spike)
   - species=$(singularity run 'docker://gudmaprbk/python3:1.0.0' python3 ./workflow/scripts/parseMeta.py -r Replicate_RID -m "./test_data/meta/metaTest.csv" -p species)
-  - readLength=$(singularity run 'docker://gudmaprbk/python3:1.0.0' python3 ./workflow/scripts/parseMeta.py -r Replicate_RID -m "./test_data/meta/metaTest.stageNew.csv" -p readLength)
+  - readLength=$(singularity run 'docker://gudmaprbk/python3:1.0.0' python3 ./workflow/scripts/parseMeta.py -r Replicate_RID -m "./test_data/meta/metaTest.csv" -p readLength)
   - echo -e "${endsMeta},${endsManual},${stranded},${spike},${species},${readLength},${exp},${study},${rep}" > design.csv
   - pytest -m parseMetadata
   artifacts:
diff --git a/test_data/createTestData.sh b/test_data/createTestData.sh
index a72202c..731f2ad 100644
--- a/test_data/createTestData.sh
+++ b/test_data/createTestData.sh
@@ -1,6 +1,6 @@
 #!/bin/bash
 
-#This script regenerates test data from replicate RID Q-Y5F4
+#This script regenerates test data from replicate RID Q-Y5F6
 
 module load singularity/3.5.3
 module load pigz/2.4
@@ -12,31 +12,31 @@ mkdir -p NEW_test_data
 ln -sfn ./test_data/auth/credential.json ~/.deriva/credential.json
 
 mkdir -p ./NEW_test_data/bag
-singularity run 'docker://gudmaprbk/deriva1.3:1.0.0' deriva-download-cli staging.gudmap.org --catalog 2 ../workflow/conf/Replicate_For_Input_Bag.json . rid=Q-Y5F4
-cp Q-Y5F4_inputBag.zip ./NEW_test_data/bag/Q-Y5F4_inputBag.zip
+singularity run 'docker://gudmaprbk/deriva1.3:1.0.0' deriva-download-cli staging.gudmap.org --catalog 2 ../workflow/conf/Replicate_For_Input_Bag.json . rid=Q-Y5F6
+cp Q-Y5F6_inputBag.zip ./NEW_test_data/bag/Q-Y5F6_inputBag.zip
 
 mkdir -p ./NEW_test_data/fastq
-unzip ./NEW_test_data/bag/Q-Y5F4_inputBag.zip
-singularity run 'docker://gudmaprbk/deriva1.3:1.0.0' bash ../workflow/scripts/bdbagFetch.sh Q-Y5F4_inputBag Q-Y5F4
-cp Q-Y5F4.R1.fastq.gz ./NEW_test_data/fastq/Q-Y5F4.R1.fastq.gz
-cp Q-Y5F4.R2.fastq.gz ./NEW_test_data/fastq/Q-Y5F4.R2.fastq.gz
+unzip ./NEW_test_data/bag/Q-Y5F6_inputBag.zip
+singularity run 'docker://gudmaprbk/deriva1.3:1.0.0' bash ../workflow/scripts/bdbagFetch.sh Q-Y5F6_inputBag Q-Y5F6
+cp Q-Y5F6.R1.fastq.gz ./NEW_test_data/fastq/Q-Y5F6.R1.fastq.gz
+cp Q-Y5F6.R2.fastq.gz ./NEW_test_data/fastq/Q-Y5F6.R2.fastq.gz
 
 mkdir -p ./NEW_test_data/fastq/small
-singularity exec 'docker://gudmaprbk/seqtk1.3:1.0.0' seqtk sample -s100 ./NEW_test_data/fastq/Q-Y5F4.R1.fastq.gz 1000000 1> Q-Y5F4_1M.R1.fastq
-singularity exec 'docker://gudmaprbk/seqtk1.3:1.0.0' seqtk sample -s100 ./NEW_test_data/fastq/Q-Y5F4.R2.fastq.gz 1000000 1> Q-Y5F4_1M.R2.fastq
-pigz Q-Y5F4_1M.R1.fastq
-pigz Q-Y5F4_1M.R2.fastq
-cp Q-Y5F4_1M.R1.fastq.gz ./NEW_test_data/fastq/small/Q-Y5F4_1M.R1.fastq.gz
-cp Q-Y5F4_1M.R2.fastq.gz ./NEW_test_data/fastq/small/Q-Y5F4_1M.R2.fastq.gz
+singularity exec 'docker://gudmaprbk/seqtk1.3:1.0.0' seqtk sample -s100 ./NEW_test_data/fastq/Q-Y5F6.R1.fastq.gz 1000000 1> Q-Y5F6_1M.R1.fastq
+singularity exec 'docker://gudmaprbk/seqtk1.3:1.0.0' seqtk sample -s100 ./NEW_test_data/fastq/Q-Y5F6.R2.fastq.gz 1000000 1> Q-Y5F6_1M.R2.fastq
+pigz Q-Y5F6_1M.R1.fastq
+pigz Q-Y5F6_1M.R2.fastq
+cp Q-Y5F6_1M.R1.fastq.gz ./NEW_test_data/fastq/small/Q-Y5F6_1M.R1.fastq.gz
+cp Q-Y5F6_1M.R2.fastq.gz ./NEW_test_data/fastq/small/Q-Y5F6_1M.R2.fastq.gz
 
 mkdir -p ./NEW_test_data/meta
-singularity run 'docker://gudmaprbk/trimgalore0.6.5:1.0.0' trim_galore --gzip -q 25 --illumina --length 35 --basename Q-Y5F4_1M.se -j 20 ./NEW_test_data/fastq/small/Q-Y5F4_1M.R1.fastq.gz
-singularity run 'docker://gudmaprbk/trimgalore0.6.5:1.0.0' trim_galore --gzip -q 25 --illumina --length 35 --paired --basename Q-Y5F4_1M.pe -j 20 ./NEW_test_data/fastq/small/Q-Y5F4_1M.R1.fastq.gz ./NEW_test_data/fastq/small/Q-Y5F4_1M.R2.fastq.gz
-cp Q-Y5F4_1M.se_trimmed.fq.gz ./NEW_test_data/fastq/small/Q-Y5F4_1M.se_trimmed.fq.gz
-cp Q-Y5F4_1M.pe_val_1.fq.gz ./NEW_test_data/fastq/small/Q-Y5F4_1M.pe_val_1.fq.gz
-cp Q-Y5F4_1M.pe_val_2.fq.gz ./NEW_test_data/fastq/small/Q-Y5F4_1M.pe_val_2.fq.gz
-cp Q-Y5F4_1M.R1.fastq.gz_trimming_report.txt ./NEW_test_data/meta/Q-Y5F4_1M.R1.fastq.gz_trimming_report.txt
-cp Q-Y5F4_1M.R2.fastq.gz_trimming_report.txt ./NEW_test_data/meta/Q-Y5F4_1M.R2.fastq.gz_trimming_report.txt
+singularity run 'docker://gudmaprbk/trimgalore0.6.5:1.0.0' trim_galore --gzip -q 25 --illumina --length 35 --basename Q-Y5F6_1M.se -j 20 ./NEW_test_data/fastq/small/Q-Y5F6_1M.R1.fastq.gz
+singularity run 'docker://gudmaprbk/trimgalore0.6.5:1.0.0' trim_galore --gzip -q 25 --illumina --length 35 --paired --basename Q-Y5F6_1M.pe -j 20 ./NEW_test_data/fastq/small/Q-Y5F6_1M.R1.fastq.gz ./NEW_test_data/fastq/small/Q-Y5F6_1M.R2.fastq.gz
+cp Q-Y5F6_1M.se_trimmed.fq.gz ./NEW_test_data/fastq/small/Q-Y5F6_1M.se_trimmed.fq.gz
+cp Q-Y5F6_1M.pe_val_1.fq.gz ./NEW_test_data/fastq/small/Q-Y5F6_1M.pe_val_1.fq.gz
+cp Q-Y5F6_1M.pe_val_2.fq.gz ./NEW_test_data/fastq/small/Q-Y5F6_1M.pe_val_2.fq.gz
+cp Q-Y5F6_1M.R1.fastq.gz_trimming_report.txt ./NEW_test_data/meta/Q-Y5F6_1M.R1.fastq.gz_trimming_report.txt
+cp Q-Y5F6_1M.R2.fastq.gz_trimming_report.txt ./NEW_test_data/meta/Q-Y5F6_1M.R2.fastq.gz_trimming_report.txt
 
 touch metaTest.csv
 echo 'Replicate_RID,Experiment_RID,Study_RID,Paired_End,File_Type,Has_Strand_Specific_Information,Used_Spike_Ins,Species' > metaTest.csv
@@ -45,67 +45,67 @@ cp metaTest.csv ./NEW_test_data/meta/metaTest.csv
 
 mkdir -p ./NEW_test_data/bam
 mkdir -p ./NEW_test_data/bam/small
-singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' hisat2 -p 20 --add-chrname --un-gz Q-Y5F4_1M.se.unal.gz -S Q-Y5F4_1M.se.sam -x /project/BICF/BICF_Core/shared/gudmap/references/GRCm38.p6.vM22/hisat2/genome --rna-strandness F -U ./NEW_test_data/fastq/small/Q-Y5F4_1M.se_trimmed.fq.gz --summary-file Q-Y5F4_1M.se.alignSummary.txt --new-summary
-singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools view -1 -@ 20 -F 4 -F 8 -F 256 -o Q-Y5F4_1M.se.bam Q-Y5F4_1M.se.sam
-singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools sort -@ 20 -O BAM -o Q-Y5F4_1M.se.sorted.bam Q-Y5F4_1M.se.bam
-singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools index -@ 20 -b Q-Y5F4_1M.se.sorted.bam Q-Y5F4_1M.se.sorted.bam.bai
-singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' hisat2 -p 20 --add-chrname --un-gz Q-Y5F4_1M.pe.unal.gz -S Q-Y5F4_1M.pe.sam -x /project/BICF/BICF_Core/shared/gudmap/references/GRCm38.p6.vM22/hisat2/genome --rna-strandness FR --no-mixed --no-discordant -1 ./NEW_test_data/fastq/small/Q-Y5F4_1M.pe_val_1.fq.gz -2 ./NEW_test_data/fastq/small/Q-Y5F4_1M.pe_val_2.fq.gz --summary-file Q-Y5F4_1M.pe.alignSummary.txt --new-summary
-singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools view -1 -@ 20 -F 4 -F 8 -F 256 -o Q-Y5F4_1M.pe.bam Q-Y5F4_1M.pe.sam
-singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools sort -@ 20 -O BAM -o Q-Y5F4_1M.pe.sorted.bam Q-Y5F4_1M.pe.bam
-singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools index -@ 20 -b Q-Y5F4_1M.pe.sorted.bam Q-Y5F4_1M.pe.sorted.bam.bai
-cp Q-Y5F4_1M.se.bam ./NEW_test_data/bam/small/Q-Y5F4_1M.se.bam
-cp Q-Y5F4_1M.pe.bam ./NEW_test_data/bam/small/Q-Y5F4_1M.pe.bam
-cp Q-Y5F4_1M.se.sorted.bam ./NEW_test_data/bam/small/Q-Y5F4_1M.se.sorted.bam
-cp Q-Y5F4_1M.se.sorted.bam.bai ./NEW_test_data/bam/small/Q-Y5F4_1M.se.sorted.bam.bai
-cp Q-Y5F4_1M.pe.sorted.bam ./NEW_test_data/bam/small/Q-Y5F4_1M.pe.sorted.bam
-cp Q-Y5F4_1M.pe.sorted.bam.bai ./NEW_test_data/bam/small/Q-Y5F4_1M.pe.sorted.bam.bai
-cp Q-Y5F4_1M.se.alignSummary.txt ./NEW_test_data/meta/Q-Y5F4_1M.se.alignSummary.txt
-cp Q-Y5F4_1M.pe.alignSummary.txt ./NEW_test_data/meta/Q-Y5F4_1M.pe.alignSummary.txt
-
-singularity run 'docker://gudmaprbk/picard2.23.9:1.0.0' java -jar /picard/build/libs/picard.jar MarkDuplicates I=./NEW_test_data/bam/small/Q-Y5F4_1M.se.sorted.bam O=Q-Y5F4_1M.se.deduped.bam M=Q-Y5F4_1M.se.deduped.Metrics.txt REMOVE_DUPLICATES=true
-singularity run 'docker://gudmaprbk/picard2.23.9:1.0.0' samtools sort -@ 20 -O BAM -o Q-Y5F4_1M.se.sorted.deduped.bam Q-Y5F4_1M.se.deduped.bam
-singularity run 'docker://gudmaprbk/picard2.23.9:1.0.0' samtools index -@ 20 -b Q-Y5F4_1M.se.sorted.deduped.bam Q-Y5F4_1M.se.sorted.deduped.bam.bai
-cp Q-Y5F4_1M.se.deduped.bam ./NEW_test_data/bam/small/Q-Y5F4_1M.se.deduped.bam
-cp Q-Y5F4_1M.se.sorted.deduped.bam ./NEW_test_data/bam/small/Q-Y5F4_1M.se.sorted.deduped.bam
-cp Q-Y5F4_1M.se.sorted.deduped.bam.bai ./NEW_test_data/bam/small/Q-Y5F4_1M.se.sorted.deduped.bam.bai
-cp Q-Y5F4_1M.se.deduped.Metrics.txt ./NEW_test_data/meta/Q-Y5F4_1M.se.deduped.Metrics.txt
+singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' hisat2 -p 20 --add-chrname --un-gz Q-Y5F6_1M.se.unal.gz -S Q-Y5F6_1M.se.sam -x /project/BICF/BICF_Core/shared/gudmap/references/GRCm38.p6.vM22/hisat2/genome --rna-strandness F -U ./NEW_test_data/fastq/small/Q-Y5F6_1M.se_trimmed.fq.gz --summary-file Q-Y5F6_1M.se.alignSummary.txt --new-summary
+singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools view -1 -@ 20 -F 4 -F 8 -F 256 -o Q-Y5F6_1M.se.bam Q-Y5F6_1M.se.sam
+singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools sort -@ 20 -O BAM -o Q-Y5F6_1M.se.sorted.bam Q-Y5F6_1M.se.bam
+singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools index -@ 20 -b Q-Y5F6_1M.se.sorted.bam Q-Y5F6_1M.se.sorted.bam.bai
+singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' hisat2 -p 20 --add-chrname --un-gz Q-Y5F6_1M.pe.unal.gz -S Q-Y5F6_1M.pe.sam -x /project/BICF/BICF_Core/shared/gudmap/references/GRCm38.p6.vM22/hisat2/genome --rna-strandness FR --no-mixed --no-discordant -1 ./NEW_test_data/fastq/small/Q-Y5F6_1M.pe_val_1.fq.gz -2 ./NEW_test_data/fastq/small/Q-Y5F6_1M.pe_val_2.fq.gz --summary-file Q-Y5F6_1M.pe.alignSummary.txt --new-summary
+singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools view -1 -@ 20 -F 4 -F 8 -F 256 -o Q-Y5F6_1M.pe.bam Q-Y5F6_1M.pe.sam
+singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools sort -@ 20 -O BAM -o Q-Y5F6_1M.pe.sorted.bam Q-Y5F6_1M.pe.bam
+singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools index -@ 20 -b Q-Y5F6_1M.pe.sorted.bam Q-Y5F6_1M.pe.sorted.bam.bai
+cp Q-Y5F6_1M.se.bam ./NEW_test_data/bam/small/Q-Y5F6_1M.se.bam
+cp Q-Y5F6_1M.pe.bam ./NEW_test_data/bam/small/Q-Y5F6_1M.pe.bam
+cp Q-Y5F6_1M.se.sorted.bam ./NEW_test_data/bam/small/Q-Y5F6_1M.se.sorted.bam
+cp Q-Y5F6_1M.se.sorted.bam.bai ./NEW_test_data/bam/small/Q-Y5F6_1M.se.sorted.bam.bai
+cp Q-Y5F6_1M.pe.sorted.bam ./NEW_test_data/bam/small/Q-Y5F6_1M.pe.sorted.bam
+cp Q-Y5F6_1M.pe.sorted.bam.bai ./NEW_test_data/bam/small/Q-Y5F6_1M.pe.sorted.bam.bai
+cp Q-Y5F6_1M.se.alignSummary.txt ./NEW_test_data/meta/Q-Y5F6_1M.se.alignSummary.txt
+cp Q-Y5F6_1M.pe.alignSummary.txt ./NEW_test_data/meta/Q-Y5F6_1M.pe.alignSummary.txt
+
+singularity run 'docker://gudmaprbk/picard2.23.9:1.0.0' java -jar /picard/build/libs/picard.jar MarkDuplicates I=./NEW_test_data/bam/small/Q-Y5F6_1M.se.sorted.bam O=Q-Y5F6_1M.se.deduped.bam M=Q-Y5F6_1M.se.deduped.Metrics.txt REMOVE_DUPLICATES=true
+singularity run 'docker://gudmaprbk/picard2.23.9:1.0.0' samtools sort -@ 20 -O BAM -o Q-Y5F6_1M.se.sorted.deduped.bam Q-Y5F6_1M.se.deduped.bam
+singularity run 'docker://gudmaprbk/picard2.23.9:1.0.0' samtools index -@ 20 -b Q-Y5F6_1M.se.sorted.deduped.bam Q-Y5F6_1M.se.sorted.deduped.bam.bai
+cp Q-Y5F6_1M.se.deduped.bam ./NEW_test_data/bam/small/Q-Y5F6_1M.se.deduped.bam
+cp Q-Y5F6_1M.se.sorted.deduped.bam ./NEW_test_data/bam/small/Q-Y5F6_1M.se.sorted.deduped.bam
+cp Q-Y5F6_1M.se.sorted.deduped.bam.bai ./NEW_test_data/bam/small/Q-Y5F6_1M.se.sorted.deduped.bam.bai
+cp Q-Y5F6_1M.se.deduped.Metrics.txt ./NEW_test_data/meta/Q-Y5F6_1M.se.deduped.Metrics.txt
 
 for i in {"chr8","chr4","chrY"}; do 
-      echo "samtools view -b ./NEW_test_data/bam/small/Q-Y5F4_1M.se.sorted.deduped.bam ${i} > Q-Y5F4_1M.se.sorted.deduped.${i}.bam; samtools index -@ 20 -b Q-Y5F4_1M.se.sorted.deduped.${i}.bam Q-Y5F4_1M.se.sorted.deduped.${i}.bam.bai;";
+      echo "samtools view -b ./NEW_test_data/bam/small/Q-Y5F6_1M.se.sorted.deduped.bam ${i} > Q-Y5F6_1M.se.sorted.deduped.${i}.bam; samtools index -@ 20 -b Q-Y5F6_1M.se.sorted.deduped.${i}.bam Q-Y5F6_1M.se.sorted.deduped.${i}.bam.bai;";
       done | singularity run 'docker://gudmaprbk/picard2.23.9:1.0.0' parallel -j 20 -k
-cp Q-Y5F4_1M.se.sorted.deduped.chr4.bam ./NEW_test_data/bam/small/Q-Y5F4_1M.se.sorted.deduped.chr4.bam
-cp Q-Y5F4_1M.se.sorted.deduped.chr4.bam.bai ./NEW_test_data/bam/small/Q-Y5F4_1M.se.sorted.deduped.chr4.bam.bai
-cp Q-Y5F4_1M.se.sorted.deduped.chr8.bam ./NEW_test_data/bam/small/Q-Y5F4_1M.se.sorted.deduped.chr8.bam
-cp Q-Y5F4_1M.se.sorted.deduped.chr8.bam.bai ./NEW_test_data/bam/small/Q-Y5F4_1M.se.sorted.deduped.chr8.bam.bai
-cp Q-Y5F4_1M.se.sorted.deduped.chrY.bam ./NEW_test_data/bam/small/Q-Y5F4_1M.se.sorted.deduped.chrY.bam
-cp Q-Y5F4_1M.se.sorted.deduped.chrY.bam.bai ./NEW_test_data/bam/small/Q-Y5F4_1M.se.sorted.deduped.chrY.bam.bai
+cp Q-Y5F6_1M.se.sorted.deduped.chr4.bam ./NEW_test_data/bam/small/Q-Y5F6_1M.se.sorted.deduped.chr4.bam
+cp Q-Y5F6_1M.se.sorted.deduped.chr4.bam.bai ./NEW_test_data/bam/small/Q-Y5F6_1M.se.sorted.deduped.chr4.bam.bai
+cp Q-Y5F6_1M.se.sorted.deduped.chr8.bam ./NEW_test_data/bam/small/Q-Y5F6_1M.se.sorted.deduped.chr8.bam
+cp Q-Y5F6_1M.se.sorted.deduped.chr8.bam.bai ./NEW_test_data/bam/small/Q-Y5F6_1M.se.sorted.deduped.chr8.bam.bai
+cp Q-Y5F6_1M.se.sorted.deduped.chrY.bam ./NEW_test_data/bam/small/Q-Y5F6_1M.se.sorted.deduped.chrY.bam
+cp Q-Y5F6_1M.se.sorted.deduped.chrY.bam.bai ./NEW_test_data/bam/small/Q-Y5F6_1M.se.sorted.deduped.chrY.bam.bai
 
 mkdir -p ./NEW_test_data/counts
 mkdir -p ./NEW_test_data/counts/small
 ln -s /project/BICF/BICF_Core/shared/gudmap/references/GRCm38.p6.vM22/geneID.tsv
 ln -s /project/BICF/BICF_Core/shared/gudmap/references/GRCm38.p6.vM22/Entrez.tsv
-singularity run 'docker://gudmaprbk/subread2.0.1:1.0.0' featureCounts -T 20 -a /project/BICF/BICF_Core/shared/gudmap/references/GRCm38.p6.vM22/genome.gtf -G /project/BICF/BICF_Core/shared/gudmap/references/GRCm38.p6.vM22/genome.fna -g 'gene_name' --extraAttributes 'gene_id' -o Q-Y5F4_1M.se_countData -s 1 -R SAM --primary --ignoreDup ./NEW_test_data/bam/small/Q-Y5F4_1M.se.sorted.deduped.bam 
-singularity run 'docker://gudmaprbk/subread2.0.1:1.0.0' Rscript ../workflow/scripts/calculateTPM.R --count Q-Y5F4_1M.se_countData
-singularity run 'docker://gudmaprbk/subread2.0.1:1.0.0' Rscript ../workflow/scripts/convertGeneSymbols.R --repRID Q-Y5F4_1M.se
-cp Q-Y5F4_1M.se_countData ./NEW_test_data/counts/small/Q-Y5F4_1M.se_countData
-cp Q-Y5F4_1M.se.countTable.csv ./NEW_test_data/counts/small/Q-Y5F4_1M.se.countTable.csv
-cp Q-Y5F4_1M.se_tpmTable.csv ./NEW_test_data/counts/small/Q-Y5F4_1M.se_tpmTable.csv
+singularity run 'docker://gudmaprbk/subread2.0.1:1.0.0' featureCounts -T 20 -a /project/BICF/BICF_Core/shared/gudmap/references/GRCm38.p6.vM22/genome.gtf -G /project/BICF/BICF_Core/shared/gudmap/references/GRCm38.p6.vM22/genome.fna -g 'gene_name' --extraAttributes 'gene_id' -o Q-Y5F6_1M.se_countData -s 1 -R SAM --primary --ignoreDup ./NEW_test_data/bam/small/Q-Y5F6_1M.se.sorted.deduped.bam 
+singularity run 'docker://gudmaprbk/subread2.0.1:1.0.0' Rscript ../workflow/scripts/calculateTPM.R --count Q-Y5F6_1M.se_countData
+singularity run 'docker://gudmaprbk/subread2.0.1:1.0.0' Rscript ../workflow/scripts/convertGeneSymbols.R --repRID Q-Y5F6_1M.se
+cp Q-Y5F6_1M.se_countData ./NEW_test_data/counts/small/Q-Y5F6_1M.se_countData
+cp Q-Y5F6_1M.se.countTable.csv ./NEW_test_data/counts/small/Q-Y5F6_1M.se.countTable.csv
+cp Q-Y5F6_1M.se_tpmTable.csv ./NEW_test_data/counts/small/Q-Y5F6_1M.se_tpmTable.csv
 
 mkdir -p ./NEW_test_data/bw
 mkdir -p ./NEW_test_data/bw/small
-singularity run 'docker://gudmaprbk/deeptools3.5.0:1.0.0' bamCoverage -p 20 -b ./NEW_test_data/bam/small/Q-Y5F4_1M.se.sorted.deduped.bam -o Q-Y5F4_1M.se.bw
-cp Q-Y5F4_1M.se.bw ./NEW_test_data/bw/small/Q-Y5F4_1M.se.bw
+singularity run 'docker://gudmaprbk/deeptools3.5.0:1.0.0' bamCoverage -p 20 -b ./NEW_test_data/bam/small/Q-Y5F6_1M.se.sorted.deduped.bam -o Q-Y5F6_1M.se.bw
+cp Q-Y5F6_1M.se.bw ./NEW_test_data/bw/small/Q-Y5F6_1M.se.bw
 
 mkdir -p ./NEW_test_data/fastqc
 mkdir -p ./NEW_test_data/fastqc/small
-singularity run 'docker://gudmaprbk/fastqc0.11.9:1.0.0' fastqc ./NEW_test_data/fastq/small/Q-Y5F4_1M.R1.fastq.gz -o .
-cp Q-Y5F4_1M.R1_fastqc.html ./NEW_test_data/fastqc/small/Q-Y5F4_1M.R1_fastqc.html
-cp Q-Y5F4_1M.R1_fastqc.zip ./NEW_test_data/fastqc/small/Q-Y5F4_1M.R1_fastqc.zip
+singularity run 'docker://gudmaprbk/fastqc0.11.9:1.0.0' fastqc ./NEW_test_data/fastq/small/Q-Y5F6_1M.R1.fastq.gz -o .
+cp Q-Y5F6_1M.R1_fastqc.html ./NEW_test_data/fastqc/small/Q-Y5F6_1M.R1_fastqc.html
+cp Q-Y5F6_1M.R1_fastqc.zip ./NEW_test_data/fastqc/small/Q-Y5F6_1M.R1_fastqc.zip
 
-echo -e  "geneID\tchrom\ttx_start\ttx_end\tTIN" > Q-Y5F4_1M.se.sorted.deduped.tin.xls
+echo -e  "geneID\tchrom\ttx_start\ttx_end\tTIN" > Q-Y5F6_1M.se.sorted.deduped.tin.xls
 for i in {"chr8","chr4","chrY"}; do
-echo "tin.py -i ./NEW_test_data/bam/small/Q-Y5F4_1M.se.sorted.deduped.${i}.bam -r /project/BICF/BICF_Core/shared/gudmap/references/GRCm38.p6.vM22/bed/genome.bed; cat Q-Y5F4_1M.se.sorted.deduped.${i}.tin.xls | tr -s \"\\w\" \"\\t\" | grep -P \"\\t${i}\\t\";"; done | singularity run 'docker://gudmaprbk/rseqc4.0.0:1.0.0' parallel -j 20 -k >> Q-Y5F4_1M.se.sorted.deduped.tin.xls
-cp Q-Y5F4_1M.se.sorted.deduped.tin.xls ./NEW_test_data/meta/Q-Y5F4_1M.se.sorted.deduped.tin.xls
+echo "tin.py -i ./NEW_test_data/bam/small/Q-Y5F6_1M.se.sorted.deduped.${i}.bam -r /project/BICF/BICF_Core/shared/gudmap/references/GRCm38.p6.vM22/bed/genome.bed; cat Q-Y5F6_1M.se.sorted.deduped.${i}.tin.xls | tr -s \"\\w\" \"\\t\" | grep -P \"\\t${i}\\t\";"; done | singularity run 'docker://gudmaprbk/rseqc4.0.0:1.0.0' parallel -j 20 -k >> Q-Y5F6_1M.se.sorted.deduped.tin.xls
+cp Q-Y5F6_1M.se.sorted.deduped.tin.xls ./NEW_test_data/meta/Q-Y5F6_1M.se.sorted.deduped.tin.xls
 
 chgrp -R BICF_Core ./NEW_test_data
 chmod -R 750 ./NEW_test_data
-- 
GitLab