From c7b99ce10f39b04d505376cf2f60cbe029e21abd Mon Sep 17 00:00:00 2001 From: golu099 Date: Thu, 12 Jan 2023 13:57:10 -0500 Subject: [PATCH 01/29] optimizing array for deblur step --- pipes/WDL/tasks/tasks_16S_amplicon.wdl | 42 ++++++++++++-------------- 1 file changed, 20 insertions(+), 22 deletions(-) diff --git a/pipes/WDL/tasks/tasks_16S_amplicon.wdl b/pipes/WDL/tasks/tasks_16S_amplicon.wdl index 07c8d59cd..06ffd5b2d 100755 --- a/pipes/WDL/tasks/tasks_16S_amplicon.wdl +++ b/pipes/WDL/tasks/tasks_16S_amplicon.wdl @@ -151,8 +151,7 @@ task deblur { description: "Perform sequence quality control for Illumina data using the Deblur workflow with a 16S reference as a positive filter." } input { - File joined_end_reads_qza - String joined_end_basename = basename(joined_end_reads_qza, '.qza') + Array[File] joined_end_reads_qza Int trim_length_var = 300 Int memory_mb = 2000 Int cpu = 1 @@ -163,27 +162,27 @@ task deblur { set -ex -o pipefail qiime deblur denoise-16S \ - --i-demultiplexed-seqs ~{joined_end_reads_qza} \ + --i-demultiplexed-seqs ~{sep=' ' joined_end_reads_qza} \ ~{"--p-trim-length " + trim_length_var} \ --p-sample-stats \ - --o-representative-sequences "~{joined_end_basename}_rep_seqs.qza" \ - --o-table "~{joined_end_basename}_table.qza" \ - --o-stats "~{joined_end_basename}_stats.qza" + --o-representative-sequences "rep_seqs.qza" \ + --o-table "table.qza" \ + --o-stats "stats.qza" #Generate feature table- give you the number of features per sample qiime feature-table summarize \ - --i-table "~{joined_end_basename}_table.qza" \ - --o-visualization "~{joined_end_basename}_table.qzv" + --i-table "table.qza" \ + --o-visualization "table.qzv" #Generate visualization of deblur stats qiime deblur visualize-stats \ - --i-deblur-stats "~{joined_end_basename}_stats.qza" \ - --o-visualization "~{joined_end_basename}_stats.qzv" + --i-deblur-stats "stats.qza" \ + --o-visualization "stats.qzv" >>> output { - File representative_seqs_qza = "~{joined_end_basename}_rep_seqs.qza" - File representative_table_qza = "~{joined_end_basename}_table.qza" - File feature_table = "~{joined_end_basename}_table.qzv" - File visualize_stats = "~{joined_end_basename}_stats.qzv" + File representative_seqs_qza = "rep_seqs.qza" + File representative_table_qza = "table.qza" + File feature_table = "table.qzv" + File visualize_stats = "stats.qzv" } runtime { @@ -259,7 +258,6 @@ task tax_analysis { File trained_classifier File representative_seqs_qza File representative_table_qza - String basename = basename(trained_classifier, '.qza') Int memory_mb = 5 Int cpu = 1 Int disk_size_gb = 375 @@ -270,24 +268,24 @@ task tax_analysis { qiime feature-classifier classify-sklearn \ --i-classifier ~{trained_classifier} \ --i-reads ~{representative_seqs_qza} \ - --o-classification "~{basename}_tax.qza" + --o-classification "taxonomy.qza" qiime feature-table tabulate-seqs \ --i-data ~{representative_seqs_qza} \ - --o-visualization "~{basename}_rep_seqs.qzv" + --o-visualization "list_rep_seqs.qzv" qiime taxa barplot \ --i-table ~{representative_table_qza} \ - --i-taxonomy "~{basename}_tax.qza" \ - --o-visualization "~{basename}_bar_plots.qzv" + --i-taxonomy "taxonomy.qza" \ + --o-visualization "taxa_bar_plots.qzv" >>> output { - File rep_seq_list = "~{basename}_rep_seqs.qzv" - File tax_classification_graph = "~{basename}_bar_plots.qzv" + File rep_seq_list = "list_rep_seqs.qzv" + File tax_classification_graph = "taxa_bar_plots.qzv" } runtime { docker: docker - memory: "7 GB" + memory: "10 GB" cpu: cpu disk: disk_size_gb + " GB" disks: "local-disk " + disk_size_gb + " HDD" From 4291a1a2848a44864f37963a9b8c6b5583991edd Mon Sep 17 00:00:00 2001 From: golu099 Date: Thu, 12 Jan 2023 17:51:36 -0500 Subject: [PATCH 02/29] Attempting array deblur --- pipes/WDL/tasks/tasks_16S_amplicon.wdl | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/pipes/WDL/tasks/tasks_16S_amplicon.wdl b/pipes/WDL/tasks/tasks_16S_amplicon.wdl index 06ffd5b2d..44a4adf31 100755 --- a/pipes/WDL/tasks/tasks_16S_amplicon.wdl +++ b/pipes/WDL/tasks/tasks_16S_amplicon.wdl @@ -151,7 +151,7 @@ task deblur { description: "Perform sequence quality control for Illumina data using the Deblur workflow with a 16S reference as a positive filter." } input { - Array[File] joined_end_reads_qza + Array[File]+ joined_end_reads_qza Int trim_length_var = 300 Int memory_mb = 2000 Int cpu = 1 @@ -290,4 +290,4 @@ task tax_analysis { disk: disk_size_gb + " GB" disks: "local-disk " + disk_size_gb + " HDD" } -} \ No newline at end of file +} \ No newline at end of file From 30c5bf904c2b7300ce8fdef29280093ee7b35b2c Mon Sep 17 00:00:00 2001 From: golu099 Date: Thu, 19 Jan 2023 12:12:53 -0500 Subject: [PATCH 03/29] Array of BAM file --- pipes/WDL/tasks/tasks_16S_amplicon.wdl | 22 +++++++++++--------- pipes/WDL/workflows/amplicon16S_analysis.wdl | 4 +--- 2 files changed, 13 insertions(+), 13 deletions(-) diff --git a/pipes/WDL/tasks/tasks_16S_amplicon.wdl b/pipes/WDL/tasks/tasks_16S_amplicon.wdl index 44a4adf31..c31c612d1 100755 --- a/pipes/WDL/tasks/tasks_16S_amplicon.wdl +++ b/pipes/WDL/tasks/tasks_16S_amplicon.wdl @@ -5,8 +5,7 @@ task qiime_import_from_bam { description: "Parsing demultiplexed fastq BAM files into qiime readable files." } input { - File reads_bam - String sample_name + Array[File] reads_bam Int memory_mb = 2000 Int cpu = 1 Int disk_size_gb = ceil(2*size(reads_bam, "GiB")) + 5 @@ -19,11 +18,13 @@ task qiime_import_from_bam { command <<< set -ex -o pipefail #Part 1A | BAM -> FASTQ [Simple samtools command] - samtools fastq -1 $(pwd)/R1.fastq.gz -2 $(pwd)/R2.fastq.gz -0 /dev/null ~{reads_bam} - #making new bash variable | regex: (_) -> (-) - NEWSAMPLENAME=$(echo "~{sample_name}" | perl -lape 's/[_]/-/g') - #All names added to one giant file - echo ${NEWSAMPLENAME} > NEWSAMPLENAME.txt + for bam in ${sep=' ' reads_bam}; do + samtools fastq -1 $(pwd)/R1.fastq.gz -2 $(pwd)/R2.fastq.gz -0 /dev/null + #making new bash variable | regex: (_) -> (-) + NEWSAMPLENAME=$(echo "(basename $bam .bam)" | perl -lape 's/[_]/-/g') + #All names added to one giant file + echo ${NEWSAMPLENAME} > NEWSAMPLENAME.txt + done #Make a manifest.txt that contains [1.sampleid 2.R1_fastq 3.R2.fastq] #> =overwrite or writes new file echo -e "sample-id\tforward-absolute-filepath\treverse-absolute-filepath" > manifest.tsv @@ -36,7 +37,8 @@ task qiime_import_from_bam { --type 'SampleData[PairedEndSequencesWithQuality]' \ --input-path manifest.tsv \ --input-format PairedEndFastqManifestPhred33V2 \ - --output-path "~{sample_name}.qza" + #this should be the batch name since multiple FASTA files are going into one .qza file + --output-path "batch.qza" >>> output { @@ -151,7 +153,7 @@ task deblur { description: "Perform sequence quality control for Illumina data using the Deblur workflow with a 16S reference as a positive filter." } input { - Array[File]+ joined_end_reads_qza + File joined_end_reads_qza Int trim_length_var = 300 Int memory_mb = 2000 Int cpu = 1 @@ -162,7 +164,7 @@ task deblur { set -ex -o pipefail qiime deblur denoise-16S \ - --i-demultiplexed-seqs ~{sep=' ' joined_end_reads_qza} \ + --i-demultiplexed-seqs ~{joined_end_reads_qza}\ ~{"--p-trim-length " + trim_length_var} \ --p-sample-stats \ --o-representative-sequences "rep_seqs.qza" \ diff --git a/pipes/WDL/workflows/amplicon16S_analysis.wdl b/pipes/WDL/workflows/amplicon16S_analysis.wdl index b0635eafb..659662dee 100755 --- a/pipes/WDL/workflows/amplicon16S_analysis.wdl +++ b/pipes/WDL/workflows/amplicon16S_analysis.wdl @@ -13,14 +13,12 @@ workflow amplicon16S_analysis { input { File reads_bam File trained_classifier - String sample_name Boolean keep_untrimmed_reads } call qiime.qiime_import_from_bam { input: - reads_bam = reads_bam, - sample_name = sample_name + reads_bam = reads_bam } #__________________________________________ call qiime.trim_reads { From fd8310dd0588808aee9d7239011e9cbb90e23410 Mon Sep 17 00:00:00 2001 From: golu099 Date: Thu, 19 Jan 2023 12:14:07 -0500 Subject: [PATCH 04/29] removing sampleNme --- pipes/WDL/tasks/tasks_16S_amplicon.wdl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pipes/WDL/tasks/tasks_16S_amplicon.wdl b/pipes/WDL/tasks/tasks_16S_amplicon.wdl index c31c612d1..e463c87ba 100755 --- a/pipes/WDL/tasks/tasks_16S_amplicon.wdl +++ b/pipes/WDL/tasks/tasks_16S_amplicon.wdl @@ -42,7 +42,7 @@ task qiime_import_from_bam { >>> output { - File reads_qza = "~{sample_name}.qza" + File reads_qza = "batch.qza" String samplename_master_sheet = read_string("NEWSAMPLENAME.txt") } runtime { From 0ac435d182282eb4f06d48cde07ac23c40d58a13 Mon Sep 17 00:00:00 2001 From: golu099 Date: Thu, 19 Jan 2023 13:06:07 -0500 Subject: [PATCH 05/29] chanigng array in wfl --- pipes/WDL/workflows/amplicon16S_analysis.wdl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pipes/WDL/workflows/amplicon16S_analysis.wdl b/pipes/WDL/workflows/amplicon16S_analysis.wdl index 659662dee..a24269c1e 100755 --- a/pipes/WDL/workflows/amplicon16S_analysis.wdl +++ b/pipes/WDL/workflows/amplicon16S_analysis.wdl @@ -11,7 +11,7 @@ workflow amplicon16S_analysis { allowNestedInputs: true } input { - File reads_bam + Array[File] reads_bam File trained_classifier Boolean keep_untrimmed_reads } From ea7f0f6eccf5dc44b03fad41556a911ca5025ee0 Mon Sep 17 00:00:00 2001 From: golu099 Date: Thu, 19 Jan 2023 14:03:09 -0500 Subject: [PATCH 06/29] worked on for loop --- pipes/WDL/tasks/tasks_16S_amplicon.wdl | 50 +++++++++----------- pipes/WDL/workflows/amplicon16S_analysis.wdl | 2 +- 2 files changed, 24 insertions(+), 28 deletions(-) diff --git a/pipes/WDL/tasks/tasks_16S_amplicon.wdl b/pipes/WDL/tasks/tasks_16S_amplicon.wdl index e463c87ba..f65cd5657 100755 --- a/pipes/WDL/tasks/tasks_16S_amplicon.wdl +++ b/pipes/WDL/tasks/tasks_16S_amplicon.wdl @@ -7,31 +7,30 @@ task qiime_import_from_bam { input { Array[File] reads_bam Int memory_mb = 2000 - Int cpu = 1 + Int cpu = 3 Int disk_size_gb = ceil(2*size(reads_bam, "GiB")) + 5 String docker = "quay.io/broadinstitute/qiime2:conda" } parameter_meta { - reads_bam: {description: "Input BAM file"} + reads_bam: { + description: "Input BAM files" + patterns:["*.bam"]} } command <<< set -ex -o pipefail #Part 1A | BAM -> FASTQ [Simple samtools command] + echo -e "sample-id\tforward-absolute-filepath\treverse-absolute-filepath" > manifest.tsv for bam in ${sep=' ' reads_bam}; do - samtools fastq -1 $(pwd)/R1.fastq.gz -2 $(pwd)/R2.fastq.gz -0 /dev/null + samtools fastq $bam -1 $(pwd)/R1.fastq.gz -2 $(pwd)/R2.fastq.gz -0 /dev/null #making new bash variable | regex: (_) -> (-) NEWSAMPLENAME=$(echo "(basename $bam .bam)" | perl -lape 's/[_]/-/g') #All names added to one giant file - echo ${NEWSAMPLENAME} > NEWSAMPLENAME.txt - done - #Make a manifest.txt that contains [1.sampleid 2.R1_fastq 3.R2.fastq] - #> =overwrite or writes new file - echo -e "sample-id\tforward-absolute-filepath\treverse-absolute-filepath" > manifest.tsv - #>>= appends - #\t= tabs next value - echo -e "$NEWSAMPLENAME\t$(pwd)/R1.fastq.gz\t$(pwd)/R2.fastq.gz" >> manifest.tsv - + echo ${NEWSAMPLENAME} >> NEWSAMPLENAME.txt + #>>= appends + #\t= tabs next value + echo -e "$NEWSAMPLENAME\t$(pwd)/R1.fastq.gz\t$(pwd)/R2.fastq.gz" >> manifest.tsv + done #fastq -> bam (provided by qiime tools import fxn) qiime tools import \ --type 'SampleData[PairedEndSequencesWithQuality]' \ @@ -65,15 +64,13 @@ task trim_reads { input { File reads_qza - - String qza_basename = basename(reads_qza, '.qza') #Boolean not_default = false String forward_adapter = "CTGCTGCCTCCCGTAGGAGT" String reverse_adapter = "AGAGTTTGATCCTGGCTCAG" Int min_length = 1 Boolean keep_untrimmed_reads = false Int memory_mb = 2000 - Int cpu = 1 + Int cpu = 3 Int disk_size_gb = ceil(2*size(reads_qza, "GiB")) + 5 String docker = "quay.io/broadinstitute/qiime2:conda" } @@ -86,18 +83,18 @@ task trim_reads { --p-front-r "~{reverse_adapter}" \ ~{"--p-minimum-length " + min_length} \ ~{true='--p-no-discard-untrimmed' false='--p-discard-untrimmed' keep_untrimmed_reads} \ - --o-trimmed-sequences "~{qza_basename}_trimmed.qza" + --o-trimmed-sequences "trimmed.qza" #trim_visual qiime demux summarize \ - --i-data "~{qza_basename}_trimmed.qza" \ - --o-visualization "~{qza_basename}_trim_summary.qzv" + --i-data "trimmed.qza" \ + --o-visualization "~trim_summary.qzv" >>> output { #trimmed_sequences = paired ends for vsearch - File trimmed_reads_qza = "~{qza_basename}_trimmed.qza" - File trimmed_visualization = "~{qza_basename}_trim_summary.qzv" + File trimmed_reads_qza = "trimmed.qza" + File trimmed_visualization = "trim_summary.qzv" } runtime { @@ -117,7 +114,6 @@ task join_paired_ends { input { #Input File: Merge paired reads File trimmed_reads_qza - String reads_basename = basename(trimmed_reads_qza, '.qza') Int memory_mb = 2000 Int cpu = 1 Int disk_size_gb = ceil(2*size(trimmed_reads_qza, "GiB")) + 5 @@ -128,15 +124,15 @@ task join_paired_ends { set -ex -o pipefail qiime vsearch join-pairs \ --i-demultiplexed-seqs ~{trimmed_reads_qza} \ - --o-joined-sequences "~{reads_basename}_joined.qza" + --o-joined-sequences "joined.qza" qiime demux summarize \ - --i-data "~{reads_basename}_joined.qza" \ - --o-visualization "~{reads_basename}_visualization.qzv" + --i-data "joined.qza" \ + --o-visualization "visualization.qzv" >>> output { - File joined_end_reads_qza = "~{reads_basename}_joined.qza" - File joined_end_visualization = "~{reads_basename}_visualization.qzv" + File joined_end_reads_qza = "joined.qza" + File joined_end_visualization = "visualization.qzv" } runtime { docker: docker @@ -153,7 +149,7 @@ task deblur { description: "Perform sequence quality control for Illumina data using the Deblur workflow with a 16S reference as a positive filter." } input { - File joined_end_reads_qza + File joined_end_reads_qza Int trim_length_var = 300 Int memory_mb = 2000 Int cpu = 1 diff --git a/pipes/WDL/workflows/amplicon16S_analysis.wdl b/pipes/WDL/workflows/amplicon16S_analysis.wdl index a24269c1e..281f5b0c0 100755 --- a/pipes/WDL/workflows/amplicon16S_analysis.wdl +++ b/pipes/WDL/workflows/amplicon16S_analysis.wdl @@ -13,7 +13,7 @@ workflow amplicon16S_analysis { input { Array[File] reads_bam File trained_classifier - Boolean keep_untrimmed_reads + Boolean keep_untrimmed_reads } call qiime.qiime_import_from_bam { From 045b2a4d960320863d09aa102b4ce430ea95b9d0 Mon Sep 17 00:00:00 2001 From: golu099 Date: Thu, 19 Jan 2023 14:08:54 -0500 Subject: [PATCH 07/29] remove patterns in parameter_meta --- pipes/WDL/tasks/tasks_16S_amplicon.wdl | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/pipes/WDL/tasks/tasks_16S_amplicon.wdl b/pipes/WDL/tasks/tasks_16S_amplicon.wdl index f65cd5657..644d2bbbb 100755 --- a/pipes/WDL/tasks/tasks_16S_amplicon.wdl +++ b/pipes/WDL/tasks/tasks_16S_amplicon.wdl @@ -13,8 +13,7 @@ task qiime_import_from_bam { } parameter_meta { reads_bam: { - description: "Input BAM files" - patterns:["*.bam"]} + description: "Input BAM files"} } command <<< From 4a48412ca73c949863a8e9b54b341360fdd74e0c Mon Sep 17 00:00:00 2001 From: golu099 Date: Thu, 19 Jan 2023 15:09:01 -0500 Subject: [PATCH 08/29] fix for loops --- pipes/WDL/tasks/tasks_16S_amplicon.wdl | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/pipes/WDL/tasks/tasks_16S_amplicon.wdl b/pipes/WDL/tasks/tasks_16S_amplicon.wdl index 644d2bbbb..6dcd566a6 100755 --- a/pipes/WDL/tasks/tasks_16S_amplicon.wdl +++ b/pipes/WDL/tasks/tasks_16S_amplicon.wdl @@ -5,31 +5,31 @@ task qiime_import_from_bam { description: "Parsing demultiplexed fastq BAM files into qiime readable files." } input { - Array[File] reads_bam + Array[File] reads_bam Int memory_mb = 2000 Int cpu = 3 Int disk_size_gb = ceil(2*size(reads_bam, "GiB")) + 5 String docker = "quay.io/broadinstitute/qiime2:conda" } parameter_meta { - reads_bam: { - description: "Input BAM files"} + reads_bam: {description: "Input BAM files"} } command <<< set -ex -o pipefail #Part 1A | BAM -> FASTQ [Simple samtools command] echo -e "sample-id\tforward-absolute-filepath\treverse-absolute-filepath" > manifest.tsv - for bam in ${sep=' ' reads_bam}; do - samtools fastq $bam -1 $(pwd)/R1.fastq.gz -2 $(pwd)/R2.fastq.gz -0 /dev/null + for bam in ~{sep=' ' reads_bam}; do #making new bash variable | regex: (_) -> (-) NEWSAMPLENAME=$(echo "(basename $bam .bam)" | perl -lape 's/[_]/-/g') + samtools fastq $bam -1 $NEWSAMPLENAME.R1.fastq.gz -2 $NEWSAMPLENAME.R2.fastq.gz -0 /dev/null #All names added to one giant file - echo ${NEWSAMPLENAME} >> NEWSAMPLENAME.txt + echo $NEWSAMPLENAME >> NEWSAMPLENAME.txt + #>=replaces #>>= appends #\t= tabs next value - echo -e "$NEWSAMPLENAME\t$(pwd)/R1.fastq.gz\t$(pwd)/R2.fastq.gz" >> manifest.tsv - done + echo -e "$NEWSAMPLENAME\t$(pwd)/$NEWSAMPLENAME.R1.fastq.gz\t$(pwd)/$NEWSAMPLENAME.R2.fastq.gz" >> manifest.tsv + done #fastq -> bam (provided by qiime tools import fxn) qiime tools import \ --type 'SampleData[PairedEndSequencesWithQuality]' \ @@ -45,7 +45,7 @@ task qiime_import_from_bam { } runtime { docker: docker - memory: "${memory_mb} MiB" + memory: "~{memory_mb} MiB" cpu: cpu disk: disk_size_gb + " GB" disks: "local-disk " + disk_size_gb + " HDD" From d9c4ffde38b0d1d7721f20901604d47292cae3e4 Mon Sep 17 00:00:00 2001 From: golu099 Date: Fri, 20 Jan 2023 17:53:03 -0500 Subject: [PATCH 09/29] samtools issue --- pipes/WDL/tasks/tasks_16S_amplicon.wdl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pipes/WDL/tasks/tasks_16S_amplicon.wdl b/pipes/WDL/tasks/tasks_16S_amplicon.wdl index 6dcd566a6..e2bfcb4d5 100755 --- a/pipes/WDL/tasks/tasks_16S_amplicon.wdl +++ b/pipes/WDL/tasks/tasks_16S_amplicon.wdl @@ -22,7 +22,7 @@ task qiime_import_from_bam { for bam in ~{sep=' ' reads_bam}; do #making new bash variable | regex: (_) -> (-) NEWSAMPLENAME=$(echo "(basename $bam .bam)" | perl -lape 's/[_]/-/g') - samtools fastq $bam -1 $NEWSAMPLENAME.R1.fastq.gz -2 $NEWSAMPLENAME.R2.fastq.gz -0 /dev/null + samtools fastq -1 $NEWSAMPLENAME.R1.fastq.gz -2 $NEWSAMPLENAME.R2.fastq.gz -0 /dev/null $bam #All names added to one giant file echo $NEWSAMPLENAME >> NEWSAMPLENAME.txt #>=replaces From b2a6f85c7c81c50f543e9af916c3ab30108563d4 Mon Sep 17 00:00:00 2001 From: golu099 Date: Tue, 24 Jan 2023 22:59:23 -0500 Subject: [PATCH 10/29] samtools fix --- pipes/WDL/tasks/tasks_16S_amplicon.wdl | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/pipes/WDL/tasks/tasks_16S_amplicon.wdl b/pipes/WDL/tasks/tasks_16S_amplicon.wdl index e2bfcb4d5..666e3e811 100755 --- a/pipes/WDL/tasks/tasks_16S_amplicon.wdl +++ b/pipes/WDL/tasks/tasks_16S_amplicon.wdl @@ -21,8 +21,8 @@ task qiime_import_from_bam { echo -e "sample-id\tforward-absolute-filepath\treverse-absolute-filepath" > manifest.tsv for bam in ~{sep=' ' reads_bam}; do #making new bash variable | regex: (_) -> (-) - NEWSAMPLENAME=$(echo "(basename $bam .bam)" | perl -lape 's/[_]/-/g') - samtools fastq -1 $NEWSAMPLENAME.R1.fastq.gz -2 $NEWSAMPLENAME.R2.fastq.gz -0 /dev/null $bam + NEWSAMPLENAME=$(echo "($bam)" | perl -lape 's/[_]/-/g') + samtools fastq -1 $bam.R1.fastq.gz -2 $bam.R2.fastq.gz -0 /dev/null $bam #All names added to one giant file echo $NEWSAMPLENAME >> NEWSAMPLENAME.txt #>=replaces From f05915ee43a7adf3a47bdf6f8ddfeb8810535deb Mon Sep 17 00:00:00 2001 From: golu099 Date: Tue, 24 Jan 2023 23:20:41 -0500 Subject: [PATCH 11/29] samtools fix --- pipes/WDL/tasks/tasks_16S_amplicon.wdl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pipes/WDL/tasks/tasks_16S_amplicon.wdl b/pipes/WDL/tasks/tasks_16S_amplicon.wdl index 666e3e811..78d90bf0a 100755 --- a/pipes/WDL/tasks/tasks_16S_amplicon.wdl +++ b/pipes/WDL/tasks/tasks_16S_amplicon.wdl @@ -28,7 +28,7 @@ task qiime_import_from_bam { #>=replaces #>>= appends #\t= tabs next value - echo -e "$NEWSAMPLENAME\t$(pwd)/$NEWSAMPLENAME.R1.fastq.gz\t$(pwd)/$NEWSAMPLENAME.R2.fastq.gz" >> manifest.tsv + echo -e "$NEWSAMPLENAME\t/$NEWSAMPLENAME.R1.fastq.gz\t/$NEWSAMPLENAME.R2.fastq.gz" >> manifest.tsv done #fastq -> bam (provided by qiime tools import fxn) qiime tools import \ From ad1ba90a54e0fe7b8efbaee0f8485cac9d827ebb Mon Sep 17 00:00:00 2001 From: golu099 Date: Thu, 26 Jan 2023 13:24:37 -0500 Subject: [PATCH 12/29] samtools fix --- pipes/WDL/tasks/tasks_16S_amplicon.wdl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pipes/WDL/tasks/tasks_16S_amplicon.wdl b/pipes/WDL/tasks/tasks_16S_amplicon.wdl index 78d90bf0a..09bd8e970 100755 --- a/pipes/WDL/tasks/tasks_16S_amplicon.wdl +++ b/pipes/WDL/tasks/tasks_16S_amplicon.wdl @@ -21,7 +21,7 @@ task qiime_import_from_bam { echo -e "sample-id\tforward-absolute-filepath\treverse-absolute-filepath" > manifest.tsv for bam in ~{sep=' ' reads_bam}; do #making new bash variable | regex: (_) -> (-) - NEWSAMPLENAME=$(echo "($bam)" | perl -lape 's/[_]/-/g') + NEWSAMPLENAME=$(echo "$bam" | perl -lape 's/[_]/-/g') samtools fastq -1 $bam.R1.fastq.gz -2 $bam.R2.fastq.gz -0 /dev/null $bam #All names added to one giant file echo $NEWSAMPLENAME >> NEWSAMPLENAME.txt From b601cb918df3692d9145f9b4e4389383684df2f9 Mon Sep 17 00:00:00 2001 From: golu099 Date: Thu, 26 Jan 2023 13:28:01 -0500 Subject: [PATCH 13/29] samtools fix --- pipes/WDL/tasks/tasks_16S_amplicon.wdl | 2 ++ 1 file changed, 2 insertions(+) diff --git a/pipes/WDL/tasks/tasks_16S_amplicon.wdl b/pipes/WDL/tasks/tasks_16S_amplicon.wdl index 09bd8e970..60c585e45 100755 --- a/pipes/WDL/tasks/tasks_16S_amplicon.wdl +++ b/pipes/WDL/tasks/tasks_16S_amplicon.wdl @@ -18,12 +18,14 @@ task qiime_import_from_bam { command <<< set -ex -o pipefail #Part 1A | BAM -> FASTQ [Simple samtools command] + touch "batch.qza" echo -e "sample-id\tforward-absolute-filepath\treverse-absolute-filepath" > manifest.tsv for bam in ~{sep=' ' reads_bam}; do #making new bash variable | regex: (_) -> (-) NEWSAMPLENAME=$(echo "$bam" | perl -lape 's/[_]/-/g') samtools fastq -1 $bam.R1.fastq.gz -2 $bam.R2.fastq.gz -0 /dev/null $bam #All names added to one giant file + #up to here works...not reading the manifest tsv for some reason echo $NEWSAMPLENAME >> NEWSAMPLENAME.txt #>=replaces #>>= appends From d66f81474b2cabf43ed05f93f110536db6ad8c7b Mon Sep 17 00:00:00 2001 From: golu099 Date: Thu, 26 Jan 2023 13:39:10 -0500 Subject: [PATCH 14/29] conda env --- pipes/WDL/tasks/tasks_16S_amplicon.wdl | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/pipes/WDL/tasks/tasks_16S_amplicon.wdl b/pipes/WDL/tasks/tasks_16S_amplicon.wdl index 60c585e45..ef24f82db 100755 --- a/pipes/WDL/tasks/tasks_16S_amplicon.wdl +++ b/pipes/WDL/tasks/tasks_16S_amplicon.wdl @@ -17,8 +17,15 @@ task qiime_import_from_bam { command <<< set -ex -o pipefail + #testing to see if source is correct + # obtain the name of the qiime conda environment in the container flexible about version + CONDA_ENV_NAME=$(conda info --envs -q | awk -F" " '/qiime.*/{ print $1 }') + # activate the qiime conda environment + # seemingly necessary because of: + #https://github.com/chanzuckerberg/miniwdl/issues/603 + #manual activation of bash per suggestion: https://github.com/conda/conda/issues/7980 + conda activate ${CONDA_ENV_NAME} #Part 1A | BAM -> FASTQ [Simple samtools command] - touch "batch.qza" echo -e "sample-id\tforward-absolute-filepath\treverse-absolute-filepath" > manifest.tsv for bam in ~{sep=' ' reads_bam}; do #making new bash variable | regex: (_) -> (-) @@ -36,9 +43,7 @@ task qiime_import_from_bam { qiime tools import \ --type 'SampleData[PairedEndSequencesWithQuality]' \ --input-path manifest.tsv \ - --input-format PairedEndFastqManifestPhred33V2 \ - #this should be the batch name since multiple FASTA files are going into one .qza file - --output-path "batch.qza" + --input-format PairedEndFastqManifestPhred33V2 --output-path "batch.qza" >>> output { From b9e930c16c10f8850c850cdf10d4511cbb286ba5 Mon Sep 17 00:00:00 2001 From: golu099 Date: Thu, 26 Jan 2023 13:53:12 -0500 Subject: [PATCH 15/29] conda env --- pipes/WDL/tasks/tasks_16S_amplicon.wdl | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/pipes/WDL/tasks/tasks_16S_amplicon.wdl b/pipes/WDL/tasks/tasks_16S_amplicon.wdl index ef24f82db..aa30ef2b6 100755 --- a/pipes/WDL/tasks/tasks_16S_amplicon.wdl +++ b/pipes/WDL/tasks/tasks_16S_amplicon.wdl @@ -29,7 +29,7 @@ task qiime_import_from_bam { echo -e "sample-id\tforward-absolute-filepath\treverse-absolute-filepath" > manifest.tsv for bam in ~{sep=' ' reads_bam}; do #making new bash variable | regex: (_) -> (-) - NEWSAMPLENAME=$(echo "$bam" | perl -lape 's/[_]/-/g') + NEWSAMPLENAME=$(echo "basename $bam .bam" | perl -lape 's/[_]/-/g') samtools fastq -1 $bam.R1.fastq.gz -2 $bam.R2.fastq.gz -0 /dev/null $bam #All names added to one giant file #up to here works...not reading the manifest tsv for some reason @@ -37,7 +37,8 @@ task qiime_import_from_bam { #>=replaces #>>= appends #\t= tabs next value - echo -e "$NEWSAMPLENAME\t/$NEWSAMPLENAME.R1.fastq.gz\t/$NEWSAMPLENAME.R2.fastq.gz" >> manifest.tsv + echo -e "${NEWSAMPLENAME}\t/${NEWSAMPLENAME}.R1.fastq.gz\t/${NEWSAMPLENAME}.R2.fastq.gz" + echo -e "${NEWSAMPLENAME}\t/${NEWSAMPLENAME}.R1.fastq.gz\t/${NEWSAMPLENAME}.R2.fastq.gz" >> manifest.tsv done #fastq -> bam (provided by qiime tools import fxn) qiime tools import \ From f5dc4026e67855812b56e5cfa5d5624ca244e063 Mon Sep 17 00:00:00 2001 From: golu099 Date: Thu, 26 Jan 2023 13:59:21 -0500 Subject: [PATCH 16/29] conda removed --- pipes/WDL/tasks/tasks_16S_amplicon.wdl | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/pipes/WDL/tasks/tasks_16S_amplicon.wdl b/pipes/WDL/tasks/tasks_16S_amplicon.wdl index aa30ef2b6..0b6826c38 100755 --- a/pipes/WDL/tasks/tasks_16S_amplicon.wdl +++ b/pipes/WDL/tasks/tasks_16S_amplicon.wdl @@ -17,15 +17,9 @@ task qiime_import_from_bam { command <<< set -ex -o pipefail - #testing to see if source is correct - # obtain the name of the qiime conda environment in the container flexible about version - CONDA_ENV_NAME=$(conda info --envs -q | awk -F" " '/qiime.*/{ print $1 }') - # activate the qiime conda environment - # seemingly necessary because of: - #https://github.com/chanzuckerberg/miniwdl/issues/603 - #manual activation of bash per suggestion: https://github.com/conda/conda/issues/7980 - conda activate ${CONDA_ENV_NAME} + #Part 1A | BAM -> FASTQ [Simple samtools command] + manifest_TSV=manifest.tsv echo -e "sample-id\tforward-absolute-filepath\treverse-absolute-filepath" > manifest.tsv for bam in ~{sep=' ' reads_bam}; do #making new bash variable | regex: (_) -> (-) From fff698205105b274d9d56ca375c656357d208168 Mon Sep 17 00:00:00 2001 From: golu099 Date: Thu, 26 Jan 2023 14:40:08 -0500 Subject: [PATCH 17/29] fix --- pipes/WDL/tasks/tasks_16S_amplicon.wdl | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/pipes/WDL/tasks/tasks_16S_amplicon.wdl b/pipes/WDL/tasks/tasks_16S_amplicon.wdl index 0b6826c38..88ff1523d 100755 --- a/pipes/WDL/tasks/tasks_16S_amplicon.wdl +++ b/pipes/WDL/tasks/tasks_16S_amplicon.wdl @@ -23,7 +23,8 @@ task qiime_import_from_bam { echo -e "sample-id\tforward-absolute-filepath\treverse-absolute-filepath" > manifest.tsv for bam in ~{sep=' ' reads_bam}; do #making new bash variable | regex: (_) -> (-) - NEWSAMPLENAME=$(echo "basename $bam .bam" | perl -lape 's/[_]/-/g') + NEWSAMPLENAME=$(basename $bam .bam | perl -lape 's/[_]/-/g') + echo $NEWSAMPLENAME samtools fastq -1 $bam.R1.fastq.gz -2 $bam.R2.fastq.gz -0 /dev/null $bam #All names added to one giant file #up to here works...not reading the manifest tsv for some reason @@ -31,14 +32,17 @@ task qiime_import_from_bam { #>=replaces #>>= appends #\t= tabs next value - echo -e "${NEWSAMPLENAME}\t/${NEWSAMPLENAME}.R1.fastq.gz\t/${NEWSAMPLENAME}.R2.fastq.gz" - echo -e "${NEWSAMPLENAME}\t/${NEWSAMPLENAME}.R1.fastq.gz\t/${NEWSAMPLENAME}.R2.fastq.gz" >> manifest.tsv + echo -e "$NEWSAMPLENAME\t$(pwd)/$NEWSAMPLENAME.R1.fastq.gz\t$(pwd)/$NEWSAMPLENAME.R2.fastq.gz" + echo -e "$NEWSAMPLENAME\t$(pwd)/$NEWSAMPLENAME.R1.fastq.gz\t$(pwd)/$NEWSAMPLENAME.R2.fastq.gz" >> manifest.tsv done + # debug + cat manifest.tsv #fastq -> bam (provided by qiime tools import fxn) qiime tools import \ --type 'SampleData[PairedEndSequencesWithQuality]' \ --input-path manifest.tsv \ - --input-format PairedEndFastqManifestPhred33V2 --output-path "batch.qza" + --input-format PairedEndFastqManifestPhred33V2 \ + --output-path "batch.qza" >>> output { From a0415faae1c1c02beebae99a9708c9a6988921e1 Mon Sep 17 00:00:00 2001 From: golu099 Date: Thu, 26 Jan 2023 15:03:03 -0500 Subject: [PATCH 18/29] list fix --- pipes/WDL/tasks/tasks_16S_amplicon.wdl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pipes/WDL/tasks/tasks_16S_amplicon.wdl b/pipes/WDL/tasks/tasks_16S_amplicon.wdl index 88ff1523d..c3bada573 100755 --- a/pipes/WDL/tasks/tasks_16S_amplicon.wdl +++ b/pipes/WDL/tasks/tasks_16S_amplicon.wdl @@ -25,7 +25,7 @@ task qiime_import_from_bam { #making new bash variable | regex: (_) -> (-) NEWSAMPLENAME=$(basename $bam .bam | perl -lape 's/[_]/-/g') echo $NEWSAMPLENAME - samtools fastq -1 $bam.R1.fastq.gz -2 $bam.R2.fastq.gz -0 /dev/null $bam + samtools fastq -1 $NEWSAMPLENAME.R1.fastq.gz -2 $NEWSAMPLENAME.R2.fastq.gz -0 /dev/null $bam #All names added to one giant file #up to here works...not reading the manifest tsv for some reason echo $NEWSAMPLENAME >> NEWSAMPLENAME.txt From 0b6a8a69fb3d224566fd777398b61e792cc62400 Mon Sep 17 00:00:00 2001 From: golu099 Date: Thu, 26 Jan 2023 20:53:30 -0500 Subject: [PATCH 19/29] trim seq fix --- pipes/WDL/tasks/tasks_16S_amplicon.wdl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pipes/WDL/tasks/tasks_16S_amplicon.wdl b/pipes/WDL/tasks/tasks_16S_amplicon.wdl index c3bada573..fe44d981b 100755 --- a/pipes/WDL/tasks/tasks_16S_amplicon.wdl +++ b/pipes/WDL/tasks/tasks_16S_amplicon.wdl @@ -93,7 +93,7 @@ task trim_reads { #trim_visual qiime demux summarize \ --i-data "trimmed.qza" \ - --o-visualization "~trim_summary.qzv" + --o-visualization "trim_summary.qzv" >>> output { From c14f7530519597bb2f1d20e5b16533f5f73b829c Mon Sep 17 00:00:00 2001 From: golu099 Date: Fri, 3 Feb 2023 11:37:45 -0500 Subject: [PATCH 20/29] commiting fixes --- test/input/WDL/test_inputs-qiime_import_bam-local.json | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/test/input/WDL/test_inputs-qiime_import_bam-local.json b/test/input/WDL/test_inputs-qiime_import_bam-local.json index 000c9f95a..41139fddd 100644 --- a/test/input/WDL/test_inputs-qiime_import_bam-local.json +++ b/test/input/WDL/test_inputs-qiime_import_bam-local.json @@ -1,4 +1,3 @@ { - "qiime_import_bam.reads_bam": "test/input/G5012.3.subset.bam", - "qiime_import_bam.sample_name": "G5012.3.subset.bam" + "qiime_import_bam.reads_bam": "test/input/G5012.3.subset.bam" } From 1cac96a226792e1dbeb873fe4efe677db1070562 Mon Sep 17 00:00:00 2001 From: golu099 Date: Fri, 3 Feb 2023 18:26:39 -0500 Subject: [PATCH 21/29] removing sample name --- pipes/WDL/workflows/qiime_import_bam.wdl | 2 -- 1 file changed, 2 deletions(-) diff --git a/pipes/WDL/workflows/qiime_import_bam.wdl b/pipes/WDL/workflows/qiime_import_bam.wdl index caaee2cdb..63b605e2e 100644 --- a/pipes/WDL/workflows/qiime_import_bam.wdl +++ b/pipes/WDL/workflows/qiime_import_bam.wdl @@ -12,12 +12,10 @@ meta{ } input { File reads_bam - String sample_name } call infile.qiime_import_from_bam { input: reads_bam = reads_bam, - sample_name = sample_name } } \ No newline at end of file From 46c2af6aa27c0828c70fd525958ad479d1b77d23 Mon Sep 17 00:00:00 2001 From: golu099 Date: Fri, 3 Feb 2023 18:27:21 -0500 Subject: [PATCH 22/29] fixing input request --- pipes/WDL/workflows/qiime_import_bam.wdl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pipes/WDL/workflows/qiime_import_bam.wdl b/pipes/WDL/workflows/qiime_import_bam.wdl index 63b605e2e..cb696760c 100644 --- a/pipes/WDL/workflows/qiime_import_bam.wdl +++ b/pipes/WDL/workflows/qiime_import_bam.wdl @@ -16,6 +16,6 @@ input { call infile.qiime_import_from_bam { input: - reads_bam = reads_bam, + reads_bam = reads_bam } } \ No newline at end of file From 2be4ff8714f6cf5c3eb29a782dd95444024af8b2 Mon Sep 17 00:00:00 2001 From: golu099 Date: Tue, 7 Feb 2023 17:27:24 -0500 Subject: [PATCH 23/29] Updating array file on import --- pipes/WDL/workflows/qiime_import_bam.wdl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pipes/WDL/workflows/qiime_import_bam.wdl b/pipes/WDL/workflows/qiime_import_bam.wdl index cb696760c..650925c1b 100644 --- a/pipes/WDL/workflows/qiime_import_bam.wdl +++ b/pipes/WDL/workflows/qiime_import_bam.wdl @@ -11,7 +11,7 @@ meta{ allowNestedInputs: true } input { - File reads_bam + Array[File] reads_bam } call infile.qiime_import_from_bam { From 083757d369adca8fc56aab2d02fee56bc47f67a4 Mon Sep 17 00:00:00 2001 From: golu099 Date: Wed, 8 Feb 2023 22:50:20 -0500 Subject: [PATCH 24/29] optimizing disk size --- pipes/WDL/tasks/tasks_16S_amplicon.wdl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pipes/WDL/tasks/tasks_16S_amplicon.wdl b/pipes/WDL/tasks/tasks_16S_amplicon.wdl index fe44d981b..d2b010170 100755 --- a/pipes/WDL/tasks/tasks_16S_amplicon.wdl +++ b/pipes/WDL/tasks/tasks_16S_amplicon.wdl @@ -8,7 +8,7 @@ task qiime_import_from_bam { Array[File] reads_bam Int memory_mb = 2000 Int cpu = 3 - Int disk_size_gb = ceil(2*size(reads_bam, "GiB")) + 5 + Int disk_size_gb = ceil(2*3) + 5 String docker = "quay.io/broadinstitute/qiime2:conda" } parameter_meta { From cda833d02baf1f652906325a427b6f2e000349f4 Mon Sep 17 00:00:00 2001 From: golu099 Date: Thu, 9 Feb 2023 14:36:48 -0500 Subject: [PATCH 25/29] JSON updates --- test/input/WDL/test_inputs-qiime_import_bam-local.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/test/input/WDL/test_inputs-qiime_import_bam-local.json b/test/input/WDL/test_inputs-qiime_import_bam-local.json index 41139fddd..b73faee50 100644 --- a/test/input/WDL/test_inputs-qiime_import_bam-local.json +++ b/test/input/WDL/test_inputs-qiime_import_bam-local.json @@ -1,3 +1,3 @@ { - "qiime_import_bam.reads_bam": "test/input/G5012.3.subset.bam" + "qiime_import_bam.reads_bam": ["test/input/G5012.3.subset.bam"] } From 66f74703f8e1d0ca77df1c2c4f8697e3c4838cc4 Mon Sep 17 00:00:00 2001 From: golu099 Date: Fri, 10 Feb 2023 10:14:12 -0500 Subject: [PATCH 26/29] optimzing run time --- pipes/WDL/tasks/tasks_16S_amplicon.wdl | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/pipes/WDL/tasks/tasks_16S_amplicon.wdl b/pipes/WDL/tasks/tasks_16S_amplicon.wdl index d2b010170..aaed18ac7 100755 --- a/pipes/WDL/tasks/tasks_16S_amplicon.wdl +++ b/pipes/WDL/tasks/tasks_16S_amplicon.wdl @@ -6,9 +6,9 @@ task qiime_import_from_bam { } input { Array[File] reads_bam - Int memory_mb = 2000 - Int cpu = 3 - Int disk_size_gb = ceil(2*3) + 5 + Int memory_mb = 7000 + Int cpu = 5 + Int disk_size_gb = ceil(2*20) + 5 String docker = "quay.io/broadinstitute/qiime2:conda" } parameter_meta { From 62fa8e8af896ee2dd1dc4985627548febca02c75 Mon Sep 17 00:00:00 2001 From: golu099 Date: Tue, 14 Feb 2023 16:44:25 -0500 Subject: [PATCH 27/29] addressing Danny's suggestions --- pipes/WDL/tasks/tasks_16S_amplicon.wdl | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/pipes/WDL/tasks/tasks_16S_amplicon.wdl b/pipes/WDL/tasks/tasks_16S_amplicon.wdl index aaed18ac7..610b0a509 100755 --- a/pipes/WDL/tasks/tasks_16S_amplicon.wdl +++ b/pipes/WDL/tasks/tasks_16S_amplicon.wdl @@ -9,10 +9,10 @@ task qiime_import_from_bam { Int memory_mb = 7000 Int cpu = 5 Int disk_size_gb = ceil(2*20) + 5 - String docker = "quay.io/broadinstitute/qiime2:conda" + String docker = "quay.io/broadinstitute/qiime2" } parameter_meta { - reads_bam: {description: "Input BAM files"} + reads_bam: {description: "Unaligned reads parsed into FASTQ format and then through a .qza format for QIIME requirements."} } command <<< @@ -75,9 +75,9 @@ task trim_reads { Int min_length = 1 Boolean keep_untrimmed_reads = false Int memory_mb = 2000 - Int cpu = 3 + Int cpu = 4 Int disk_size_gb = ceil(2*size(reads_qza, "GiB")) + 5 - String docker = "quay.io/broadinstitute/qiime2:conda" + String docker = "quay.io/broadinstitute/qiime2" } command <<< @@ -121,8 +121,8 @@ task join_paired_ends { File trimmed_reads_qza Int memory_mb = 2000 Int cpu = 1 - Int disk_size_gb = ceil(2*size(trimmed_reads_qza, "GiB")) + 5 - String docker = "quay.io/broadinstitute/qiime2:conda" + Int disk_size_gb = ceil(2*size(trimmed_reads_qza, "GiB")) + 50 + String docker = "quay.io/broadinstitute/qiime2" } command <<< @@ -159,7 +159,7 @@ task deblur { Int memory_mb = 2000 Int cpu = 1 Int disk_size_gb = ceil(2*size(joined_end_reads_qza, "GiB")) + 5 - String docker = "quay.io/broadinstitute/qiime2:conda" + String docker = "quay.io/broadinstitute/qiime2" } command <<< set -ex -o pipefail @@ -211,7 +211,7 @@ task train_classifier { Int memory_mb = 2000 Int cpu = 1 Int disk_size_gb = ceil(2*size(otu_ref, "GiB")) + 5 - String docker = "quay.io/broadinstitute/qiime2:conda" + String docker = "quay.io/broadinstitute/qiime2" } command <<< set -ex -o pipefail @@ -264,7 +264,7 @@ task tax_analysis { Int memory_mb = 5 Int cpu = 1 Int disk_size_gb = 375 - String docker = "quay.io/broadinstitute/qiime2:conda" + String docker = "quay.io/broadinstitute/qiime2" } command <<< set -ex -o pipefail From 3dff80832f84c26e3ee8f418ada3d2842edf11b4 Mon Sep 17 00:00:00 2001 From: golu099 Date: Tue, 14 Feb 2023 18:43:02 -0500 Subject: [PATCH 28/29] Update pipes/WDL/tasks/tasks_16S_amplicon.wdl Co-authored-by: Daniel Park --- pipes/WDL/tasks/tasks_16S_amplicon.wdl | 1 - 1 file changed, 1 deletion(-) diff --git a/pipes/WDL/tasks/tasks_16S_amplicon.wdl b/pipes/WDL/tasks/tasks_16S_amplicon.wdl index 610b0a509..f71a3de2b 100755 --- a/pipes/WDL/tasks/tasks_16S_amplicon.wdl +++ b/pipes/WDL/tasks/tasks_16S_amplicon.wdl @@ -27,7 +27,6 @@ task qiime_import_from_bam { echo $NEWSAMPLENAME samtools fastq -1 $NEWSAMPLENAME.R1.fastq.gz -2 $NEWSAMPLENAME.R2.fastq.gz -0 /dev/null $bam #All names added to one giant file - #up to here works...not reading the manifest tsv for some reason echo $NEWSAMPLENAME >> NEWSAMPLENAME.txt #>=replaces #>>= appends From 73a5d77f07ec5dc65594a4e701a60d6c47cac51d Mon Sep 17 00:00:00 2001 From: golu099 Date: Wed, 15 Feb 2023 16:17:39 -0500 Subject: [PATCH 29/29] Update pipes/WDL/tasks/tasks_16S_amplicon.wdl Co-authored-by: Daniel Park --- pipes/WDL/tasks/tasks_16S_amplicon.wdl | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/pipes/WDL/tasks/tasks_16S_amplicon.wdl b/pipes/WDL/tasks/tasks_16S_amplicon.wdl index f71a3de2b..0d123d28e 100755 --- a/pipes/WDL/tasks/tasks_16S_amplicon.wdl +++ b/pipes/WDL/tasks/tasks_16S_amplicon.wdl @@ -12,7 +12,8 @@ task qiime_import_from_bam { String docker = "quay.io/broadinstitute/qiime2" } parameter_meta { - reads_bam: {description: "Unaligned reads parsed into FASTQ format and then through a .qza format for QIIME requirements."} + reads_bam: {description: "Unaligned reads in BAM format, one sample per BAM file."} + reads_qza: {description: "All unaligned reads in a single QZA (QIIME) file"} } command <<<