Change to new-new test data

.gitlab-ci.yml

@@ -30,7 +30,7 @@ getBag:
   script:
   - ln -sfn `readlink -e ./test_data/auth/credential.json` ~/.deriva/credential.json
   - singularity run 'docker://gudmaprbk/deriva1.3:1.0.0' deriva-download-cli --version > version_deriva.txt
-  - singularity run 'docker://gudmaprbk/deriva1.3:1.0.0' deriva-download-cli dev.gudmap.org --catalog 2 ./workflow/conf/Replicate_For_Input_Bag.json . rid=16-WJRA
+  - singularity run 'docker://gudmaprbk/deriva1.3:1.0.0' deriva-download-cli dev.gudmap.org --catalog 2 ./workflow/conf/Replicate_For_Input_Bag.json . rid=16-DNBG
   - pytest -m getBag
   artifacts:
     name: "$CI_JOB_NAME"
@@ -49,8 +49,8 @@ getData:
   script:
   - singularity run 'docker://gudmaprbk/deriva1.3:1.0.0' bdbag --version > version_bdbag.txt
   - ln -sfn `readlink -e ./test_data/auth/cookies.txt` ~/.bdbag/deriva-cookies.txt
-  - unzip ./test_data/bag/16-WJRA_inputBag.zip
-  - singularity run 'docker://gudmaprbk/deriva1.3:1.0.0' bash ./workflow/scripts/bdbagFetch.sh 16-WJRA_inputBag 16-WJRA TEST
+  - unzip ./test_data/bag/16-DNBG_inputBag.zip
+  - singularity run 'docker://gudmaprbk/deriva1.3:1.0.0' bash ./workflow/scripts/bdbagFetch.sh 16-DNBG_inputBag 16-DNBG TEST
   - pytest -m getData
   artifacts:
     name: "$CI_JOB_NAME"
@@ -96,11 +96,11 @@ inferMetadata:
   script:
   - singularity run 'docker://gudmaprbk/rseqc4.0.0:1.0.0' infer_experiment.py --version > version_rseqc.txt
   - >
-    align=$(echo $(grep "Overall alignment rate" ./test_data/meta/16-WJRA_1M.se.alignSummary.txt | cut -f2 -d ':' | cut -f2 -d ' ' | tr -d '%')) &&
+    align=$(echo $(grep "Overall alignment rate" ./test_data/meta/16-DNBG_1M.se.alignSummary.txt | cut -f2 -d ':' | cut -f2 -d ' ' | tr -d '%')) &&
     if [[ ${align} == "" ]]; then exit 1; fi
   - >
-    singularity run 'docker://gudmaprbk/rseqc4.0.0:1.0.0' infer_experiment.py -r "/project/BICF/BICF_Core/shared/gudmap/references/GRCh38.p12.v31/bed/genome.bed" -i "./test_data/bam/small/16-WJRA_1M.se.sorted.deduped.bam" 1>> 16-WJRA_1M.se.inferMetadata.log &&
-    ended=`singularity run 'gudmaprbk/python3:1.0.0' python3 ./workflow/scripts/inferMeta.sh endness 16-WJRA_1M.se.inferMetadata.log` &&
+    singularity run 'docker://gudmaprbk/rseqc4.0.0:1.0.0' infer_experiment.py -r "/project/BICF/BICF_Core/shared/gudmap/references/GRCh38.p12.v31/bed/genome.bed" -i "./test_data/bam/small/16-DNBG_1M.se.sorted.deduped.bam" 1>> 16-DNBG_1M.se.inferMetadata.log &&
+    ended=`singularity run 'gudmaprbk/python3:1.0.0' python3 ./workflow/scripts/inferMeta.sh endness 16-DNBG_1M.se.inferMetadata.log` &&
     if [[ ${ended} == "" ]]; then exit 1; fi
   - pytest -m inferMetadata
   artifacts:
@@ -119,8 +119,8 @@ trimData:
     - merge_requests
   script:
   - singularity run 'docker://gudmaprbk/trimgalore0.6.5:1.0.0' trim_galore --version > version_trimgalore.txt
-  - singularity run 'docker://gudmaprbk/trimgalore0.6.5:1.0.0' trim_galore --gzip -q 25 --length 35 --basename 16-WJRA_1M.se ./test_data/fastq/small/16-WJRA_1M.R1.fastq.gz
-  - singularity run 'docker://gudmaprbk/trimgalore0.6.5:1.0.0' trim_galore --gzip -q 25 --length 35 --paired --basename 16-WJRA_1M.pe ./test_data/fastq/small/16-WJRA_1M.R1.fastq.gz ./test_data/fastq/small/16-WJRA_1M.R2.fastq.gz
+  - singularity run 'docker://gudmaprbk/trimgalore0.6.5:1.0.0' trim_galore --gzip -q 25 --length 35 --basename 16-DNBG_1M.se ./test_data/fastq/small/16-DNBG_1M.R1.fastq.gz
+  - singularity run 'docker://gudmaprbk/trimgalore0.6.5:1.0.0' trim_galore --gzip -q 25 --length 35 --paired --basename 16-DNBG_1M.pe ./test_data/fastq/small/16-DNBG_1M.R1.fastq.gz ./test_data/fastq/small/16-DNBG_1M.R2.fastq.gz
   - readLengthSE=$(zcat *_trimmed.fq.gz | awk '{if(NR%4==2) print length($1)}' | sort -n | awk '{a[NR]=$0}END{print(NR%2==1)?a[int(NR/2)+1]:(a[NR/2]+a[NR/2+1])/2}')
   - readLengthPE=$(zcat *_1.fq.gz | awk '{if(NR%4==2) print length($1)}' | sort -n | awk '{a[NR]=$0}END{print(NR%2==1)?a[int(NR/2)+1]:(a[NR/2]+a[NR/2+1])/2}')
   - pytest -m trimData
@@ -139,7 +139,7 @@ downsampleData:
   except:
     - merge_requests
   script:
-  - singularity run 'docker://gudmaprbk/seqtk1.3:1.0.0' seqtk sample -s100 ./test_data/fastq/small/16-WJRA_1M.se_trimmed.fq.gz 1000 1> sampled.1.fq
+  - singularity run 'docker://gudmaprbk/seqtk1.3:1.0.0' seqtk sample -s100 ./test_data/fastq/small/16-DNBG_1M.se_trimmed.fq.gz 1000 1> sampled.1.fq
   - pytest -m downsampleData
 
 alignData:
@@ -152,14 +152,14 @@ alignData:
   script:
   - singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' hisat2 --version > version_hisat2.txt
   - singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools --version > version_samtools.txt
-  - singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' hisat2 -p 20 --add-chrname --un-gz 16-WJRA_1M.se.unal.gz -S 16-WJRA_1M.se.sam -x /project/BICF/BICF_Core/shared/gudmap/references/GRCh38.p12.v31/hisat2/genome --rna-strandness F -U ./test_data/fastq/small/16-WJRA_1M.se_trimmed.fq.gz --summary-file 16-WJRA_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 16-WJRA_1M.se.bam 16-WJRA_1M.se.sam
-  - singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools sort -@ 20 -O BAM -o 16-WJRA_1M.se.sorted.bam 16-WJRA_1M.se.bam
-  - singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools index -@ 20 -b 16-WJRA_1M.se.sorted.bam 16-WJRA_1M.se.sorted.bam.bai
-  - singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' hisat2 -p 20 --add-chrname --un-gz 16-WJRA_1M.pe.unal.gz -S 16-WJRA_1M.pe.sam -x /project/BICF/BICF_Core/shared/gudmap/references/GRCh38.p12.v31/hisat2/genome --rna-strandness FR --no-mixed --no-discordant -1 ./test_data/fastq/small/16-WJRA_1M.pe_val_1.fq.gz -2 ./test_data/fastq/small/16-WJRA_1M.pe_val_2.fq.gz --summary-file 16-WJRA_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 16-WJRA_1M.pe.bam 16-WJRA_1M.pe.sam
-  - singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools sort -@ 20 -O BAM -o 16-WJRA_1M.pe.sorted.bam 16-WJRA_1M.pe.bam
-  - singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools index -@ 20 -b 16-WJRA_1M.pe.sorted.bam 16-WJRA_1M.pe.sorted.bam.bai
+  - singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' hisat2 -p 20 --add-chrname --un-gz 16-DNBG_1M.se.unal.gz -S 16-DNBG_1M.se.sam -x /project/BICF/BICF_Core/shared/gudmap/references/GRCh38.p12.v31/hisat2/genome --rna-strandness F -U ./test_data/fastq/small/16-DNBG_1M.se_trimmed.fq.gz --summary-file 16-DNBG_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 16-DNBG_1M.se.bam 16-DNBG_1M.se.sam
+  - singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools sort -@ 20 -O BAM -o 16-DNBG_1M.se.sorted.bam 16-DNBG_1M.se.bam
+  - singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools index -@ 20 -b 16-DNBG_1M.se.sorted.bam 16-DNBG_1M.se.sorted.bam.bai
+  - singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' hisat2 -p 20 --add-chrname --un-gz 16-DNBG_1M.pe.unal.gz -S 16-DNBG_1M.pe.sam -x /project/BICF/BICF_Core/shared/gudmap/references/GRCh38.p12.v31/hisat2/genome --rna-strandness FR --no-mixed --no-discordant -1 ./test_data/fastq/small/16-DNBG_1M.pe_val_1.fq.gz -2 ./test_data/fastq/small/16-DNBG_1M.pe_val_2.fq.gz --summary-file 16-DNBG_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 16-DNBG_1M.pe.bam 16-DNBG_1M.pe.sam
+  - singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools sort -@ 20 -O BAM -o 16-DNBG_1M.pe.sorted.bam 16-DNBG_1M.pe.bam
+  - singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools index -@ 20 -b 16-DNBG_1M.pe.sorted.bam 16-DNBG_1M.pe.sorted.bam.bai
   - pytest -m alignData
   artifacts:
     name: "$CI_JOB_NAME"
@@ -179,12 +179,12 @@ dedupData:
   script:
   - singularity run 'docker://gudmaprbk/picard2.23.9:1.0.0' samtools --version > version_samtools.txt
   - singularity run 'docker://gudmaprbk/picard2.23.9:1.0.0' java -jar /picard/build/libs/picard.jar MarkDuplicates --version 2> version_markdups.txt&
-  - singularity run 'docker://gudmaprbk/picard2.23.9:1.0.0' java -jar /picard/build/libs/picard.jar MarkDuplicates I=./test_data/bam/small/16-WJRA_1M.se.sorted.bam O=16-WJRA_1M.se.deduped.bam M=16-WJRA_1M.se.deduped.Metrics.txt REMOVE_DUPLICATES=true
-  - singularity run 'docker://gudmaprbk/picard2.23.9:1.0.0' samtools sort -@ 20 -O BAM -o 16-WJRA_1M.se.sorted.deduped.bam ./test_data/bam/small/16-WJRA_1M.se.deduped.bam
-  - singularity run 'docker://gudmaprbk/picard2.23.9:1.0.0' samtools index -@ 20 -b ./test_data/bam/small/16-WJRA_1M.se.sorted.deduped.bam 16-WJRA_1M.se.sorted.deduped.bam.bai
+  - singularity run 'docker://gudmaprbk/picard2.23.9:1.0.0' java -jar /picard/build/libs/picard.jar MarkDuplicates I=./test_data/bam/small/16-DNBG_1M.se.sorted.bam O=16-DNBG_1M.se.deduped.bam M=16-DNBG_1M.se.deduped.Metrics.txt REMOVE_DUPLICATES=true
+  - singularity run 'docker://gudmaprbk/picard2.23.9:1.0.0' samtools sort -@ 20 -O BAM -o 16-DNBG_1M.se.sorted.deduped.bam ./test_data/bam/small/16-DNBG_1M.se.deduped.bam
+  - singularity run 'docker://gudmaprbk/picard2.23.9:1.0.0' samtools index -@ 20 -b ./test_data/bam/small/16-DNBG_1M.se.sorted.deduped.bam 16-DNBG_1M.se.sorted.deduped.bam.bai
   - >
     for i in {"chr8","chr4","chrY"}; do
-      echo "samtools view -b 16-WJRA_1M.se.sorted.deduped.bam ${i} > 16-WJRA_1M.se.sorted.deduped.${i}.bam; samtools index -@ 20 -b 16-WJRA_1M.se.sorted.deduped.${i}.bam 16-WJRA_1M.se.sorted.deduped.${i}.bam.bai;";
+      echo "samtools view -b 16-DNBG_1M.se.sorted.deduped.bam ${i} > 16-DNBG_1M.se.sorted.deduped.${i}.bam; samtools index -@ 20 -b 16-DNBG_1M.se.sorted.deduped.${i}.bam 16-DNBG_1M.se.sorted.deduped.${i}.bam.bai;";
     done | singularity run 'docker://gudmaprbk/picard2.23.9:1.0.0' parallel -j 20 -k
   - pytest -m dedupData
   artifacts:
@@ -205,9 +205,9 @@ countData:
   script:
   - ln -s /project/BICF/BICF_Core/shared/gudmap/references/GRCh38.p12.v31/geneID.tsv
   - ln -s /project/BICF/BICF_Core/shared/gudmap/references/GRCh38.p12.v31/Entrez.tsv
-  - singularity run 'docker://gudmaprbk/subread2.0.1:1.0.0' featureCounts -T 20 -a /project/BICF/BICF_Core/shared/gudmap/references/GRCh38.p12.v31/genome.gtf -G /project/BICF/BICF_Core/shared/gudmap/references/GRCh38.p12.v31/genome.fna -g 'gene_name' --extraAttributes 'gene_id' -o 16-WJRA_1M.se.countData -s 1 -R SAM --primary --ignoreDup ./test_data/bam/small/16-WJRA_1M.se.sorted.deduped.bam
-  - singularity run 'docker://gudmaprbk/subread2.0.1:1.0.0' Rscript ./workflow/scripts/calculateTPM.R --count ./test_data/counts/small/16-WJRA_1M.se.countData
-  - singularity run 'docker://gudmaprbk/subread2.0.1:1.0.0' Rscript ./workflow/scripts/convertGeneSymbols.R --repRID 16-WJRA_1M.se
+  - singularity run 'docker://gudmaprbk/subread2.0.1:1.0.0' featureCounts -T 20 -a /project/BICF/BICF_Core/shared/gudmap/references/GRCh38.p12.v31/genome.gtf -G /project/BICF/BICF_Core/shared/gudmap/references/GRCh38.p12.v31/genome.fna -g 'gene_name' --extraAttributes 'gene_id' -o 16-DNBG_1M.se.countData -s 1 -R SAM --primary --ignoreDup ./test_data/bam/small/16-DNBG_1M.se.sorted.deduped.bam
+  - singularity run 'docker://gudmaprbk/subread2.0.1:1.0.0' Rscript ./workflow/scripts/calculateTPM.R --count ./test_data/counts/small/16-DNBG_1M.se.countData
+  - singularity run 'docker://gudmaprbk/subread2.0.1:1.0.0' Rscript ./workflow/scripts/convertGeneSymbols.R --repRID 16-DNBG_1M.se
   - assignedReads=$(grep -m 1 'Assigned' *.summary | grep -oe '\([0-9.]*\)')
   - singularity run 'docker://gudmaprbk/subread2.0.1:1.0.0' featureCounts -v &> version_featurecounts.txt
   - singularity run 'docker://gudmaprbk/subread2.0.1:1.0.0' R --version > version_r.txt
@@ -229,7 +229,7 @@ makeBigWig:
     - merge_requests
   script:
   - singularity run 'docker://gudmaprbk/deeptools3.5.0:1.0.0' deeptools --version > version_deeptools.txt
-  - singularity run 'docker://gudmaprbk/deeptools3.5.0:1.0.0' bamCoverage -p 20 -b ./test_data/bam/small/16-WJRA_1M.se.sorted.deduped.bam -o 16-WJRA_1M.se.bw
+  - singularity run 'docker://gudmaprbk/deeptools3.5.0:1.0.0' bamCoverage -p 20 -b ./test_data/bam/small/16-DNBG_1M.se.sorted.deduped.bam -o 16-DNBG_1M.se.bw
   - pytest -m makeBigWig
   artifacts:
     name: "$CI_JOB_NAME"
@@ -247,7 +247,7 @@ fastqc:
     - merge_requests
   script:
   - singularity run 'docker://gudmaprbk/fastqc0.11.9:1.0.0' fastqc --version > version_fastqc.txt
-  - singularity run 'docker://gudmaprbk/fastqc0.11.9:1.0.0' fastqc ./test_data/fastq/small/16-WJRA_1M.R1.fastq.gz -o .
+  - singularity run 'docker://gudmaprbk/fastqc0.11.9:1.0.0' fastqc ./test_data/fastq/small/16-DNBG_1M.R1.fastq.gz -o .
   - pytest -m fastqc
   artifacts:
     name: "$CI_JOB_NAME"
@@ -265,11 +265,11 @@ dataQC:
   except:
     - merge_requests
   script:
-  - echo -e  "geneID\tchrom\ttx_start\ttx_end\tTIN" > 16-WJRA_1M.se.sorted.deduped.tin.xls
+  - echo -e  "geneID\tchrom\ttx_start\ttx_end\tTIN" > 16-DNBG_1M.se.sorted.deduped.tin.xls
   - >
     for i in {"chr8","chr4","chrY"}; do
-      echo "tin.py -i ./test_data/bam/small/16-WJRA_1M.se.sorted.deduped.${i}.bam -r /project/BICF/BICF_Core/shared/gudmap/references/GRCh38.p12.v31/bed/genome.bed; cat 16-WJRA_1M.se.sorted.deduped.${i}.tin.xls | tr -s \"\\w\" \"\\t\" | grep -P \"\\t${i}\\t\";"
-    done | singularity run 'docker://gudmaprbk/rseqc4.0.0:1.0.0' parallel -j 20 -k >> 16-WJRA_1M.se.sorted.deduped.tin.xls
+      echo "tin.py -i ./test_data/bam/small/16-DNBG_1M.se.sorted.deduped.${i}.bam -r /project/BICF/BICF_Core/shared/gudmap/references/GRCh38.p12.v31/bed/genome.bed; cat 16-DNBG_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 >> 16-DNBG_1M.se.sorted.deduped.tin.xls
   - pytest -m dataQC
 
 uploadInputBag:
@@ -655,7 +655,7 @@ override_inputBag:
   script:
   - hostname
   - ulimit -a
-  - nextflow -q run ./workflow/rna-seq.nf --deriva ./test_data/auth/credential.json --bdbag ./test_data/auth/cookies.txt --repRID 16-WJRA --inputBagForce ./test_data/bag/16-WJRA_inputBag_20201228.zip --upload false --ci true
+  - nextflow -q run ./workflow/rna-seq.nf --deriva ./test_data/auth/credential.json --bdbag ./test_data/auth/cookies.txt --repRID 16-DNBG --inputBagForce ./test_data/bag/16-DNBG_inputBag_20201228.zip --upload false --ci true
   - find . -type f -name "multiqc_data.json" -exec cp {} ./inputBagOverride_PE_multiqc_data.json \;
   artifacts:
     name: "$CI_JOB_NAME"
@@ -677,7 +677,7 @@ override_fastq:
   script:
   - hostname
   - ulimit -a
-  - nextflow -q run ./workflow/rna-seq.nf --deriva ./test_data/auth/credential.json --bdbag ./test_data/auth/cookies.txt --repRID 16-WJRA --fastqsForce './test_data/fastq/small/16-WJRA_1M.R{1,2}.fastq.gz' --upload false --ci true
+  - nextflow -q run ./workflow/rna-seq.nf --deriva ./test_data/auth/credential.json --bdbag ./test_data/auth/cookies.txt --repRID 16-DNBG --fastqsForce './test_data/fastq/small/16-DNBG_1M.R{1,2}.fastq.gz' --upload false --ci true
   - find . -type f -name "multiqc_data.json" -exec cp {} ./fastqOverride_PE_multiqc_data.json \;
   artifacts:
     name: "$CI_JOB_NAME"

test_data/createTestData.sh

 #!/bin/bash
 
-#This script regenerates test data from replicate RID 16-WJRA
+#This script regenerates test data from replicate RID 16-DNBG
 
 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=16-WJRA
-cp 16-WJRA_inputBag.zip ./NEW_test_data/bag/16-WJRA_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=16-DNBG
+cp 16-DNBG_inputBag.zip ./NEW_test_data/bag/16-DNBG_inputBag.zip
 
 mkdir -p ./NEW_test_data/fastq
-unzip ./NEW_test_data/bag/16-WJRA_inputBag.zip
-singularity run 'docker://gudmaprbk/deriva1.3:1.0.0' bash ../workflow/scripts/bdbagFetch.sh 16-WJRA_inputBag 16-WJRA
-cp 16-WJRA.R1.fastq.gz ./NEW_test_data/fastq/16-WJRA.R1.fastq.gz
-cp 16-WJRA.R2.fastq.gz ./NEW_test_data/fastq/16-WJRA.R2.fastq.gz
+unzip ./NEW_test_data/bag/16-DNBG_inputBag.zip
+singularity run 'docker://gudmaprbk/deriva1.3:1.0.0' bash ../workflow/scripts/bdbagFetch.sh 16-DNBG_inputBag 16-DNBG
+cp 16-DNBG.R1.fastq.gz ./NEW_test_data/fastq/16-DNBG.R1.fastq.gz
+cp 16-DNBG.R2.fastq.gz ./NEW_test_data/fastq/16-DNBG.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/16-WJRA.R1.fastq.gz 1000000 1> 16-WJRA_1M.R1.fastq
-singularity exec 'docker://gudmaprbk/seqtk1.3:1.0.0' seqtk sample -s100 ./NEW_test_data/fastq/16-WJRA.R2.fastq.gz 1000000 1> 16-WJRA_1M.R2.fastq
-pigz 16-WJRA_1M.R1.fastq
-pigz 16-WJRA_1M.R2.fastq
-cp 16-WJRA_1M.R1.fastq.gz ./NEW_test_data/fastq/small/16-WJRA_1M.R1.fastq.gz
-cp 16-WJRA_1M.R2.fastq.gz ./NEW_test_data/fastq/small/16-WJRA_1M.R2.fastq.gz
+singularity exec 'docker://gudmaprbk/seqtk1.3:1.0.0' seqtk sample -s100 ./NEW_test_data/fastq/16-DNBG.R1.fastq.gz 1000000 1> 16-DNBG_1M.R1.fastq
+singularity exec 'docker://gudmaprbk/seqtk1.3:1.0.0' seqtk sample -s100 ./NEW_test_data/fastq/16-DNBG.R2.fastq.gz 1000000 1> 16-DNBG_1M.R2.fastq
+pigz 16-DNBG_1M.R1.fastq
+pigz 16-DNBG_1M.R2.fastq
+cp 16-DNBG_1M.R1.fastq.gz ./NEW_test_data/fastq/small/16-DNBG_1M.R1.fastq.gz
+cp 16-DNBG_1M.R2.fastq.gz ./NEW_test_data/fastq/small/16-DNBG_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 16-WJRA_1M.se -j 20 ./NEW_test_data/fastq/small/16-WJRA_1M.R1.fastq.gz
-singularity run 'docker://gudmaprbk/trimgalore0.6.5:1.0.0' trim_galore --gzip -q 25 --illumina --length 35 --paired --basename 16-WJRA_1M.pe -j 20 ./NEW_test_data/fastq/small/16-WJRA_1M.R1.fastq.gz ./NEW_test_data/fastq/small/16-WJRA_1M.R2.fastq.gz
-cp 16-WJRA_1M.se_trimmed.fq.gz ./NEW_test_data/fastq/small/16-WJRA_1M.se_trimmed.fq.gz
-cp 16-WJRA_1M.pe_val_1.fq.gz ./NEW_test_data/fastq/small/16-WJRA_1M.pe_val_1.fq.gz
-cp 16-WJRA_1M.pe_val_2.fq.gz ./NEW_test_data/fastq/small/16-WJRA_1M.pe_val_2.fq.gz
-cp 16-WJRA_1M.R1.fastq.gz_trimming_report.txt ./NEW_test_data/meta/16-WJRA_1M.R1.fastq.gz_trimming_report.txt
-cp 16-WJRA_1M.R2.fastq.gz_trimming_report.txt ./NEW_test_data/meta/16-WJRA_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 16-DNBG_1M.se -j 20 ./NEW_test_data/fastq/small/16-DNBG_1M.R1.fastq.gz
+singularity run 'docker://gudmaprbk/trimgalore0.6.5:1.0.0' trim_galore --gzip -q 25 --illumina --length 35 --paired --basename 16-DNBG_1M.pe -j 20 ./NEW_test_data/fastq/small/16-DNBG_1M.R1.fastq.gz ./NEW_test_data/fastq/small/16-DNBG_1M.R2.fastq.gz
+cp 16-DNBG_1M.se_trimmed.fq.gz ./NEW_test_data/fastq/small/16-DNBG_1M.se_trimmed.fq.gz
+cp 16-DNBG_1M.pe_val_1.fq.gz ./NEW_test_data/fastq/small/16-DNBG_1M.pe_val_1.fq.gz
+cp 16-DNBG_1M.pe_val_2.fq.gz ./NEW_test_data/fastq/small/16-DNBG_1M.pe_val_2.fq.gz
+cp 16-DNBG_1M.R1.fastq.gz_trimming_report.txt ./NEW_test_data/meta/16-DNBG_1M.R1.fastq.gz_trimming_report.txt
+cp 16-DNBG_1M.R2.fastq.gz_trimming_report.txt ./NEW_test_data/meta/16-DNBG_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 16-WJRA_1M.se.unal.gz -S 16-WJRA_1M.se.sam -x /project/BICF/BICF_Core/shared/gudmap/references/GRCh38.p12.v31/hisat2/genome --rna-strandness F -U ./NEW_test_data/fastq/small/16-WJRA_1M.se_trimmed.fq.gz --summary-file 16-WJRA_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 16-WJRA_1M.se.bam 16-WJRA_1M.se.sam
-singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools sort -@ 20 -O BAM -o 16-WJRA_1M.se.sorted.bam 16-WJRA_1M.se.bam
-singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools index -@ 20 -b 16-WJRA_1M.se.sorted.bam 16-WJRA_1M.se.sorted.bam.bai
-singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' hisat2 -p 20 --add-chrname --un-gz 16-WJRA_1M.pe.unal.gz -S 16-WJRA_1M.pe.sam -x /project/BICF/BICF_Core/shared/gudmap/references/GRCh38.p12.v31/hisat2/genome --rna-strandness FR --no-mixed --no-discordant -1 ./NEW_test_data/fastq/small/16-WJRA_1M.pe_val_1.fq.gz -2 ./NEW_test_data/fastq/small/16-WJRA_1M.pe_val_2.fq.gz --summary-file 16-WJRA_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 16-WJRA_1M.pe.bam 16-WJRA_1M.pe.sam
-singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools sort -@ 20 -O BAM -o 16-WJRA_1M.pe.sorted.bam 16-WJRA_1M.pe.bam
-singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools index -@ 20 -b 16-WJRA_1M.pe.sorted.bam 16-WJRA_1M.pe.sorted.bam.bai
-cp 16-WJRA_1M.se.bam ./NEW_test_data/bam/small/16-WJRA_1M.se.bam
-cp 16-WJRA_1M.pe.bam ./NEW_test_data/bam/small/16-WJRA_1M.pe.bam
-cp 16-WJRA_1M.se.sorted.bam ./NEW_test_data/bam/small/16-WJRA_1M.se.sorted.bam
-cp 16-WJRA_1M.se.sorted.bam.bai ./NEW_test_data/bam/small/16-WJRA_1M.se.sorted.bam.bai
-cp 16-WJRA_1M.pe.sorted.bam ./NEW_test_data/bam/small/16-WJRA_1M.pe.sorted.bam
-cp 16-WJRA_1M.pe.sorted.bam.bai ./NEW_test_data/bam/small/16-WJRA_1M.pe.sorted.bam.bai
-cp 16-WJRA_1M.se.alignSummary.txt ./NEW_test_data/meta/16-WJRA_1M.se.alignSummary.txt
-cp 16-WJRA_1M.pe.alignSummary.txt ./NEW_test_data/meta/16-WJRA_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/16-WJRA_1M.se.sorted.bam O=16-WJRA_1M.se.deduped.bam M=16-WJRA_1M.se.deduped.Metrics.txt REMOVE_DUPLICATES=true
-singularity run 'docker://gudmaprbk/picard2.23.9:1.0.0' samtools sort -@ 20 -O BAM -o 16-WJRA_1M.se.sorted.deduped.bam 16-WJRA_1M.se.deduped.bam
-singularity run 'docker://gudmaprbk/picard2.23.9:1.0.0' samtools index -@ 20 -b 16-WJRA_1M.se.sorted.deduped.bam 16-WJRA_1M.se.sorted.deduped.bam.bai
-cp 16-WJRA_1M.se.deduped.bam ./NEW_test_data/bam/small/16-WJRA_1M.se.deduped.bam
-cp 16-WJRA_1M.se.sorted.deduped.bam ./NEW_test_data/bam/small/16-WJRA_1M.se.sorted.deduped.bam
-cp 16-WJRA_1M.se.sorted.deduped.bam.bai ./NEW_test_data/bam/small/16-WJRA_1M.se.sorted.deduped.bam.bai
-cp 16-WJRA_1M.se.deduped.Metrics.txt ./NEW_test_data/meta/16-WJRA_1M.se.deduped.Metrics.txt
+singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' hisat2 -p 20 --add-chrname --un-gz 16-DNBG_1M.se.unal.gz -S 16-DNBG_1M.se.sam -x /project/BICF/BICF_Core/shared/gudmap/references/GRCh38.p12.v31/hisat2/genome --rna-strandness F -U ./NEW_test_data/fastq/small/16-DNBG_1M.se_trimmed.fq.gz --summary-file 16-DNBG_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 16-DNBG_1M.se.bam 16-DNBG_1M.se.sam
+singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools sort -@ 20 -O BAM -o 16-DNBG_1M.se.sorted.bam 16-DNBG_1M.se.bam
+singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools index -@ 20 -b 16-DNBG_1M.se.sorted.bam 16-DNBG_1M.se.sorted.bam.bai
+singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' hisat2 -p 20 --add-chrname --un-gz 16-DNBG_1M.pe.unal.gz -S 16-DNBG_1M.pe.sam -x /project/BICF/BICF_Core/shared/gudmap/references/GRCh38.p12.v31/hisat2/genome --rna-strandness FR --no-mixed --no-discordant -1 ./NEW_test_data/fastq/small/16-DNBG_1M.pe_val_1.fq.gz -2 ./NEW_test_data/fastq/small/16-DNBG_1M.pe_val_2.fq.gz --summary-file 16-DNBG_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 16-DNBG_1M.pe.bam 16-DNBG_1M.pe.sam
+singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools sort -@ 20 -O BAM -o 16-DNBG_1M.pe.sorted.bam 16-DNBG_1M.pe.bam
+singularity run 'docker://gudmaprbk/hisat2.2.1:1.0.0' samtools index -@ 20 -b 16-DNBG_1M.pe.sorted.bam 16-DNBG_1M.pe.sorted.bam.bai
+cp 16-DNBG_1M.se.bam ./NEW_test_data/bam/small/16-DNBG_1M.se.bam
+cp 16-DNBG_1M.pe.bam ./NEW_test_data/bam/small/16-DNBG_1M.pe.bam
+cp 16-DNBG_1M.se.sorted.bam ./NEW_test_data/bam/small/16-DNBG_1M.se.sorted.bam
+cp 16-DNBG_1M.se.sorted.bam.bai ./NEW_test_data/bam/small/16-DNBG_1M.se.sorted.bam.bai
+cp 16-DNBG_1M.pe.sorted.bam ./NEW_test_data/bam/small/16-DNBG_1M.pe.sorted.bam
+cp 16-DNBG_1M.pe.sorted.bam.bai ./NEW_test_data/bam/small/16-DNBG_1M.pe.sorted.bam.bai
+cp 16-DNBG_1M.se.alignSummary.txt ./NEW_test_data/meta/16-DNBG_1M.se.alignSummary.txt
+cp 16-DNBG_1M.pe.alignSummary.txt ./NEW_test_data/meta/16-DNBG_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/16-DNBG_1M.se.sorted.bam O=16-DNBG_1M.se.deduped.bam M=16-DNBG_1M.se.deduped.Metrics.txt REMOVE_DUPLICATES=true
+singularity run 'docker://gudmaprbk/picard2.23.9:1.0.0' samtools sort -@ 20 -O BAM -o 16-DNBG_1M.se.sorted.deduped.bam 16-DNBG_1M.se.deduped.bam
+singularity run 'docker://gudmaprbk/picard2.23.9:1.0.0' samtools index -@ 20 -b 16-DNBG_1M.se.sorted.deduped.bam 16-DNBG_1M.se.sorted.deduped.bam.bai
+cp 16-DNBG_1M.se.deduped.bam ./NEW_test_data/bam/small/16-DNBG_1M.se.deduped.bam
+cp 16-DNBG_1M.se.sorted.deduped.bam ./NEW_test_data/bam/small/16-DNBG_1M.se.sorted.deduped.bam
+cp 16-DNBG_1M.se.sorted.deduped.bam.bai ./NEW_test_data/bam/small/16-DNBG_1M.se.sorted.deduped.bam.bai
+cp 16-DNBG_1M.se.deduped.Metrics.txt ./NEW_test_data/meta/16-DNBG_1M.se.deduped.Metrics.txt
 
 for i in {"chr8","chr4","chrY"}; do 
-      echo "samtools view -b ./NEW_test_data/bam/small/16-WJRA_1M.se.sorted.deduped.bam ${i} > 16-WJRA_1M.se.sorted.deduped.${i}.bam; samtools index -@ 20 -b 16-WJRA_1M.se.sorted.deduped.${i}.bam 16-WJRA_1M.se.sorted.deduped.${i}.bam.bai;";
+      echo "samtools view -b ./NEW_test_data/bam/small/16-DNBG_1M.se.sorted.deduped.bam ${i} > 16-DNBG_1M.se.sorted.deduped.${i}.bam; samtools index -@ 20 -b 16-DNBG_1M.se.sorted.deduped.${i}.bam 16-DNBG_1M.se.sorted.deduped.${i}.bam.bai;";
       done | singularity run 'docker://gudmaprbk/picard2.23.9:1.0.0' parallel -j 20 -k
-cp 16-WJRA_1M.se.sorted.deduped.chr4.bam ./NEW_test_data/bam/small/16-WJRA_1M.se.sorted.deduped.chr4.bam
-cp 16-WJRA_1M.se.sorted.deduped.chr4.bam.bai ./NEW_test_data/bam/small/16-WJRA_1M.se.sorted.deduped.chr4.bam.bai
-cp 16-WJRA_1M.se.sorted.deduped.chr8.bam ./NEW_test_data/bam/small/16-WJRA_1M.se.sorted.deduped.chr8.bam
-cp 16-WJRA_1M.se.sorted.deduped.chr8.bam.bai ./NEW_test_data/bam/small/16-WJRA_1M.se.sorted.deduped.chr8.bam.bai
-cp 16-WJRA_1M.se.sorted.deduped.chrY.bam ./NEW_test_data/bam/small/16-WJRA_1M.se.sorted.deduped.chrY.bam
-cp 16-WJRA_1M.se.sorted.deduped.chrY.bam.bai ./NEW_test_data/bam/small/16-WJRA_1M.se.sorted.deduped.chrY.bam.bai
+cp 16-DNBG_1M.se.sorted.deduped.chr4.bam ./NEW_test_data/bam/small/16-DNBG_1M.se.sorted.deduped.chr4.bam
+cp 16-DNBG_1M.se.sorted.deduped.chr4.bam.bai ./NEW_test_data/bam/small/16-DNBG_1M.se.sorted.deduped.chr4.bam.bai
+cp 16-DNBG_1M.se.sorted.deduped.chr8.bam ./NEW_test_data/bam/small/16-DNBG_1M.se.sorted.deduped.chr8.bam
+cp 16-DNBG_1M.se.sorted.deduped.chr8.bam.bai ./NEW_test_data/bam/small/16-DNBG_1M.se.sorted.deduped.chr8.bam.bai
+cp 16-DNBG_1M.se.sorted.deduped.chrY.bam ./NEW_test_data/bam/small/16-DNBG_1M.se.sorted.deduped.chrY.bam
+cp 16-DNBG_1M.se.sorted.deduped.chrY.bam.bai ./NEW_test_data/bam/small/16-DNBG_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/GRCh38.p12.v31/geneID.tsv
 ln -s /project/BICF/BICF_Core/shared/gudmap/references/GRCh38.p12.v31/Entrez.tsv
-singularity run 'docker://gudmaprbk/subread2.0.1:1.0.0' featureCounts -T 20 -a /project/BICF/BICF_Core/shared/gudmap/references/GRCh38.p12.v31/genome.gtf -G /project/BICF/BICF_Core/shared/gudmap/references/GRCh38.p12.v31/genome.fna -g 'gene_name' --extraAttributes 'gene_id' -o 16-WJRA_1M.se_countData -s 1 -R SAM --primary --ignoreDup ./NEW_test_data/bam/small/16-WJRA_1M.se.sorted.deduped.bam 
-singularity run 'docker://gudmaprbk/subread2.0.1:1.0.0' Rscript ../workflow/scripts/calculateTPM.R --count 16-WJRA_1M.se_countData
-singularity run 'docker://gudmaprbk/subread2.0.1:1.0.0' Rscript ../workflow/scripts/convertGeneSymbols.R --repRID 16-WJRA_1M.se
-cp 16-WJRA_1M.se_countData ./NEW_test_data/counts/small/16-WJRA_1M.se_countData
-cp 16-WJRA_1M.se.countTable.csv ./NEW_test_data/counts/small/16-WJRA_1M.se.countTable.csv
-cp 16-WJRA_1M.se_tpmTable.csv ./NEW_test_data/counts/small/16-WJRA_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/GRCh38.p12.v31/genome.gtf -G /project/BICF/BICF_Core/shared/gudmap/references/GRCh38.p12.v31/genome.fna -g 'gene_name' --extraAttributes 'gene_id' -o 16-DNBG_1M.se_countData -s 1 -R SAM --primary --ignoreDup ./NEW_test_data/bam/small/16-DNBG_1M.se.sorted.deduped.bam 
+singularity run 'docker://gudmaprbk/subread2.0.1:1.0.0' Rscript ../workflow/scripts/calculateTPM.R --count 16-DNBG_1M.se_countData
+singularity run 'docker://gudmaprbk/subread2.0.1:1.0.0' Rscript ../workflow/scripts/convertGeneSymbols.R --repRID 16-DNBG_1M.se
+cp 16-DNBG_1M.se_countData ./NEW_test_data/counts/small/16-DNBG_1M.se_countData
+cp 16-DNBG_1M.se.countTable.csv ./NEW_test_data/counts/small/16-DNBG_1M.se.countTable.csv
+cp 16-DNBG_1M.se_tpmTable.csv ./NEW_test_data/counts/small/16-DNBG_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/16-WJRA_1M.se.sorted.deduped.bam -o 16-WJRA_1M.se.bw
-cp 16-WJRA_1M.se.bw ./NEW_test_data/bw/small/16-WJRA_1M.se.bw
+singularity run 'docker://gudmaprbk/deeptools3.5.0:1.0.0' bamCoverage -p 20 -b ./NEW_test_data/bam/small/16-DNBG_1M.se.sorted.deduped.bam -o 16-DNBG_1M.se.bw
+cp 16-DNBG_1M.se.bw ./NEW_test_data/bw/small/16-DNBG_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/16-WJRA_1M.R1.fastq.gz -o .
-cp 16-WJRA_1M.R1_fastqc.html ./NEW_test_data/fastqc/small/16-WJRA_1M.R1_fastqc.html
-cp 16-WJRA_1M.R1_fastqc.zip ./NEW_test_data/fastqc/small/16-WJRA_1M.R1_fastqc.zip
+singularity run 'docker://gudmaprbk/fastqc0.11.9:1.0.0' fastqc ./NEW_test_data/fastq/small/16-DNBG_1M.R1.fastq.gz -o .
+cp 16-DNBG_1M.R1_fastqc.html ./NEW_test_data/fastqc/small/16-DNBG_1M.R1_fastqc.html
+cp 16-DNBG_1M.R1_fastqc.zip ./NEW_test_data/fastqc/small/16-DNBG_1M.R1_fastqc.zip
 
-echo -e  "geneID\tchrom\ttx_start\ttx_end\tTIN" > 16-WJRA_1M.se.sorted.deduped.tin.xls
+echo -e  "geneID\tchrom\ttx_start\ttx_end\tTIN" > 16-DNBG_1M.se.sorted.deduped.tin.xls
 for i in {"chr8","chr4","chrY"}; do
-echo "tin.py -i ./NEW_test_data/bam/small/16-WJRA_1M.se.sorted.deduped.${i}.bam -r /project/BICF/BICF_Core/shared/gudmap/references/GRCh38.p12.v31/bed/genome.bed; cat 16-WJRA_1M.se.sorted.deduped.${i}.tin.xls | tr -s \"\\w\" \"\\t\" | grep -P \"\\t${i}\\t\";"; done | singularity run 'docker://gudmaprbk/rseqc4.0.0:1.0.0' parallel -j 20 -k >> 16-WJRA_1M.se.sorted.deduped.tin.xls
-cp 16-WJRA_1M.se.sorted.deduped.tin.xls ./NEW_test_data/meta/16-WJRA_1M.se.sorted.deduped.tin.xls
+echo "tin.py -i ./NEW_test_data/bam/small/16-DNBG_1M.se.sorted.deduped.${i}.bam -r /project/BICF/BICF_Core/shared/gudmap/references/GRCh38.p12.v31/bed/genome.bed; cat 16-DNBG_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 >> 16-DNBG_1M.se.sorted.deduped.tin.xls
+cp 16-DNBG_1M.se.sorted.deduped.tin.xls ./NEW_test_data/meta/16-DNBG_1M.se.sorted.deduped.tin.xls
 
 chgrp -R BICF_Core ./NEW_test_data
 chmod -R 750 ./NEW_test_data

workflow/tests/test_alignReads.py

@@ -12,18 +12,18 @@ data_output_path = os.path.dirname(os.path.abspath(__file__)) + \
 @pytest.mark.alignData
 def test_alignData_se():
     assert os.path.exists(os.path.join(
-        data_output_path, '16-WJRA_1M.se.unal.gz'))
+        data_output_path, '16-DNBG_1M.se.unal.gz'))
     assert os.path.exists(os.path.join(
-        data_output_path, '16-WJRA_1M.se.sorted.bam'))
+        data_output_path, '16-DNBG_1M.se.sorted.bam'))
     assert os.path.exists(os.path.join(
-        data_output_path, '16-WJRA_1M.se.sorted.bam.bai'))
+        data_output_path, '16-DNBG_1M.se.sorted.bam.bai'))
 
 
 @pytest.mark.alignData
 def test_alignData_pe():
     assert os.path.exists(os.path.join(
-        data_output_path, '16-WJRA_1M.pe.unal.gz'))
+        data_output_path, '16-DNBG_1M.pe.unal.gz'))
     assert os.path.exists(os.path.join(
-        data_output_path, '16-WJRA_1M.pe.sorted.bam'))
+        data_output_path, '16-DNBG_1M.pe.sorted.bam'))
     assert os.path.exists(os.path.join(
-        data_output_path, '16-WJRA_1M.pe.sorted.bam.bai'))
+        data_output_path, '16-DNBG_1M.pe.sorted.bam.bai'))

workflow/tests/test_dataQC.py

@@ -12,9 +12,9 @@ test_output_path = os.path.dirname(os.path.abspath(__file__)) + \
 @pytest.mark.dataQC
 def test_dataQC():
     assert os.path.exists(os.path.join(
-        test_output_path, '16-WJRA_1M.se.sorted.deduped.tin.xls'))
+        test_output_path, '16-DNBG_1M.se.sorted.deduped.tin.xls'))
     assert countLines(os.path.join(test_output_path,
-                                   '16-WJRA_1M.se.sorted.deduped.tin.xls'))
+                                   '16-DNBG_1M.se.sorted.deduped.tin.xls'))
 
 
 def countLines(fileName):

workflow/tests/test_dedupReads.py

@@ -12,18 +12,18 @@ data_output_path = os.path.dirname(os.path.abspath(__file__)) + \
 @pytest.mark.dedupData
 def test_dedupData():
     assert os.path.exists(os.path.join(
-        data_output_path, '16-WJRA_1M.se.sorted.deduped.bam'))
+        data_output_path, '16-DNBG_1M.se.sorted.deduped.bam'))
     assert os.path.exists(os.path.join(
-        data_output_path, '16-WJRA_1M.se.sorted.deduped.bam.bai'))
+        data_output_path, '16-DNBG_1M.se.sorted.deduped.bam.bai'))
     assert os.path.exists(os.path.join(
-        data_output_path, '16-WJRA_1M.se.sorted.deduped.chr8.bam'))
+        data_output_path, '16-DNBG_1M.se.sorted.deduped.chr8.bam'))
     assert os.path.exists(os.path.join(
-        data_output_path, '16-WJRA_1M.se.sorted.deduped.chr8.bam.bai'))
+        data_output_path, '16-DNBG_1M.se.sorted.deduped.chr8.bam.bai'))
     assert os.path.exists(os.path.join(
-        data_output_path, '16-WJRA_1M.se.sorted.deduped.chr4.bam'))
+        data_output_path, '16-DNBG_1M.se.sorted.deduped.chr4.bam'))
     assert os.path.exists(os.path.join(
-        data_output_path, '16-WJRA_1M.se.sorted.deduped.chr4.bam.bai'))
+        data_output_path, '16-DNBG_1M.se.sorted.deduped.chr4.bam.bai'))
     assert os.path.exists(os.path.join(
-        data_output_path, '16-WJRA_1M.se.sorted.deduped.chrY.bam'))
+        data_output_path, '16-DNBG_1M.se.sorted.deduped.chrY.bam'))
     assert os.path.exists(os.path.join(
-        data_output_path, '16-WJRA_1M.se.sorted.deduped.chrY.bam.bai'))
+        data_output_path, '16-DNBG_1M.se.sorted.deduped.chrY.bam.bai'))

workflow/tests/test_fastqc.py

@@ -12,4 +12,4 @@ test_output_path = os.path.dirname(os.path.abspath(__file__)) + \
 @pytest.mark.fastqc
 def test_fastqc():
     assert os.path.exists(os.path.join(
-        test_output_path, '16-WJRA_1M.R1_fastqc.zip'))
+        test_output_path, '16-DNBG_1M.R1_fastqc.zip'))

workflow/tests/test_getBag.py

@@ -12,4 +12,4 @@ test_output_path = os.path.dirname(os.path.abspath(__file__)) + \
 @pytest.mark.getBag
 def test_getBag():
     assert os.path.exists(os.path.join(
-        test_output_path, '16-WJRA_inputBag.zip'))
+        test_output_path, '16-DNBG_inputBag.zip'))

workflow/tests/test_getData.py

@@ -12,6 +12,6 @@ test_output_path = os.path.dirname(os.path.abspath(__file__)) + \
 @pytest.mark.getData
 def test_getData():
     assert os.path.exists(os.path.join(
-        test_output_path, '16-WJRA_inputBag/bagit.txt'))
+        test_output_path, '16-DNBG_inputBag/bagit.txt'))
     assert os.path.exists(os.path.join(
-        test_output_path, '16-WJRA_inputBag/data/assets/Study/Q-Y4GY/Experiment/Q-Y4DP/Replicate/16-WJRA/mMARIS_Six2-#3.gene.rpkm.txt'))
+        test_output_path, '16-DNBG_inputBag/data/assets/Study/16-DMQG/Experiment/16-DMW0Replicate/16-DNBG/22967_gene_counts.txt'))

workflow/tests/test_inferMetadata.py

@@ -12,4 +12,4 @@ test_output_path = os.path.dirname(os.path.abspath(__file__)) + \
 @pytest.mark.inferMetadata
 def test_inferMetadata():
     assert os.path.exists(os.path.join(
-        test_output_path, '16-WJRA_1M.se.inferMetadata.log'))
+        test_output_path, '16-DNBG_1M.se.inferMetadata.log'))

workflow/tests/test_makeBigWig.py

@@ -11,4 +11,4 @@ data_output_path = os.path.dirname(os.path.abspath(__file__)) + \
 
 @pytest.mark.makeBigWig
 def test_makeBigWig():
-    assert os.path.exists(os.path.join(data_output_path, '16-WJRA_1M.se.bw'))
+    assert os.path.exists(os.path.join(data_output_path, '16-DNBG_1M.se.bw'))

workflow/tests/test_makeFeatureCounts.py

@@ -12,8 +12,8 @@ data_output_path = os.path.dirname(os.path.abspath(__file__)) + \
 @pytest.mark.makeFeatureCounts
 def test_makeFeatureCounts():
     assert os.path.exists(os.path.join(
-        data_output_path, '16-WJRA_1M.se.countData'))
+        data_output_path, '16-DNBG_1M.se.countData'))
     assert os.path.exists(os.path.join(
-        data_output_path, '16-WJRA_1M.se.countTable.csv'))
+        data_output_path, '16-DNBG_1M.se.countTable.csv'))
     assert os.path.exists(os.path.join(
-        data_output_path, '16-WJRA_1M.se_tpmTable.csv'))
+        data_output_path, '16-DNBG_1M.se_tpmTable.csv'))

workflow/tests/test_trimData.py

@@ -12,12 +12,12 @@ test_output_path = os.path.dirname(os.path.abspath(__file__)) + \
 @pytest.mark.trimData
 def test_trimData_se():
     assert os.path.exists(os.path.join(
-        test_output_path, '16-WJRA_1M.se_trimmed.fq.gz'))
+        test_output_path, '16-DNBG_1M.se_trimmed.fq.gz'))
 
 
 @pytest.mark.trimData
 def test_trimData_pe():
     assert os.path.exists(os.path.join(
-        test_output_path, '16-WJRA_1M.pe_val_1.fq.gz'))
+        test_output_path, '16-DNBG_1M.pe_val_1.fq.gz'))
     assert os.path.exists(os.path.join(
-        test_output_path, '16-WJRA_1M.pe_val_2.fq.gz'))
+        test_output_path, '16-DNBG_1M.pe_val_2.fq.gz'))