From 90144525b541e914870bb41a0e5734ad92ec2093 Mon Sep 17 00:00:00 2001 From: aawdeh Date: Fri, 2 Feb 2024 10:01:31 -0500 Subject: [PATCH 1/7] Change machine type and number of output files for fastqprocess optimus --- tasks/skylab/FastqProcessing.wdl | 2 +- tasks/skylab/StarAlign.wdl | 86 ++++++++++---------------------- 2 files changed, 28 insertions(+), 60 deletions(-) diff --git a/tasks/skylab/FastqProcessing.wdl b/tasks/skylab/FastqProcessing.wdl index ac22cc38aa..7adbfef0a0 100644 --- a/tasks/skylab/FastqProcessing.wdl +++ b/tasks/skylab/FastqProcessing.wdl @@ -102,7 +102,7 @@ task FastqProcessing { fi fastqprocess \ - --bam-size 30.0 \ + --num-output-files 1 \ --sample-id "~{sample_id}" \ $FASTQS \ --white-list "~{whitelist}" \ diff --git a/tasks/skylab/StarAlign.wdl b/tasks/skylab/StarAlign.wdl index 8ab0c8d615..b61030f56c 100644 --- a/tasks/skylab/StarAlign.wdl +++ b/tasks/skylab/StarAlign.wdl @@ -227,12 +227,15 @@ task STARsoloFastq { # runtime values String docker = "us.gcr.io/broad-gotc-prod/star:1.0.1-2.7.11a-1692706072" - Int machine_mem_mb = 64000 - Int cpu = 8 + + String cpu_platform = "Intel Ice Lake" + Int machine_mem_mb = 512000 + Int cpu = 128 + Int disk = 2000 # multiply input size by 2.2 to account for output bam file + 20% overhead, add size of reference. - Int disk = ceil((size(tar_star_reference, "Gi") * 3)) + ceil(size(r1_fastq, "Gi") * 20) + ceil(size(r2_fastq, "Gi") * 20) + # Int disk = ceil((size(tar_star_reference, "Gi") * 3)) + ceil(size(r1_fastq, "Gi") * 20) + ceil(size(r2_fastq, "Gi") * 20) # by default request non preemptible machine to make sure the slow star alignment step completes - Int preemptible = 3 + Int preemptible = 1 } meta { @@ -292,7 +295,23 @@ task STARsoloFastq { ## single cell or whole cell COUNTING_MODE="Gene" echo "Running in ~{counting_mode} mode. The Star parameter --soloFeatures will be set to $COUNTING_MODE" - STAR \ + elif [[ "~{counting_mode}" == "sn_rna" ]] + then + ## single nuclei + if [[ ~{count_exons} == false ]] + then + COUNTING_MODE="GeneFull_Ex50pAS" + echo "Running in ~{counting_mode} mode. Count_exons is false and the Star parameter --soloFeatures will be set to $COUNTING_MODE" + else + COUNTING_MODE="GeneFull_Ex50pAS Gene" + echo "Running in ~{counting_mode} mode. Count_exons is true and the Star parameter --soloFeatures will be set to $COUNTING_MODE" + fi + else + echo Error: unknown counting mode: "$counting_mode". Should be either sn_rna or sc_rna. + exit 1; + fi + + STAR \ --soloType Droplet \ --soloStrand ~{star_strand_mode} \ --runThreadN ~{cpu} \ @@ -311,62 +330,10 @@ task STARsoloFastq { --soloBarcodeReadLength 0 \ --soloCellReadStats Standard \ ~{"--soloMultiMappers " + soloMultiMappers} - elif [[ "~{counting_mode}" == "sn_rna" ]] - then - ## single nuclei - if [[ ~{count_exons} == false ]] - then - COUNTING_MODE="GeneFull_Ex50pAS" - echo "Running in ~{counting_mode} mode. Count_exons is false and the Star parameter --soloFeatures will be set to $COUNTING_MODE" - STAR \ - --soloType Droplet \ - --soloStrand ~{star_strand_mode} \ - --runThreadN ~{cpu} \ - --genomeDir genome_reference \ - --readFilesIn "~{sep=',' r2_fastq}" "~{sep=',' r1_fastq}" \ - --readFilesCommand "gunzip -c" \ - --soloCBwhitelist ~{white_list} \ - --soloUMIlen $UMILen --soloCBlen $CBLen \ - --soloFeatures $COUNTING_MODE \ - --clipAdapterType CellRanger4 \ - --outFilterScoreMin 30 \ - --soloCBmatchWLtype 1MM_multi_Nbase_pseudocounts \ - --soloUMIdedup 1MM_Directional_UMItools \ - --outSAMtype BAM SortedByCoordinate \ - --outSAMattributes UB UR UY CR CB CY NH GX GN sF \ - --soloBarcodeReadLength 0 \ - --soloCellReadStats Standard \ - ~{"--soloMultiMappers " + soloMultiMappers} - else - COUNTING_MODE="GeneFull_Ex50pAS Gene" - echo "Running in ~{counting_mode} mode. Count_exons is true and the Star parameter --soloFeatures will be set to $COUNTING_MODE" - STAR \ - --soloType Droplet \ - --soloStrand ~{star_strand_mode} \ - --runThreadN ~{cpu} \ - --genomeDir genome_reference \ - --readFilesIn "~{sep=',' r2_fastq}" "~{sep=',' r1_fastq}" \ - --readFilesCommand "gunzip -c" \ - --soloCBwhitelist ~{white_list} \ - --soloUMIlen $UMILen --soloCBlen $CBLen \ - --soloFeatures $COUNTING_MODE \ - --clipAdapterType CellRanger4 \ - --outFilterScoreMin 30 \ - --soloCBmatchWLtype 1MM_multi_Nbase_pseudocounts \ - --soloUMIdedup 1MM_Directional_UMItools \ - --outSAMtype BAM SortedByCoordinate \ - --outSAMattributes UB UR UY CR CB CY NH GX GN sF \ - --soloBarcodeReadLength 0 \ - --soloCellReadStats Standard \ - ~{"--soloMultiMappers " + soloMultiMappers} - fi - else - echo Error: unknown counting mode: "$counting_mode". Should be either sn_rna or sc_rna. - exit 1; - fi echo "UMI LEN " $UMILen + # why is this here? touch barcodes_sn_rna.tsv touch features_sn_rna.tsv touch matrix_sn_rna.mtx @@ -434,10 +401,11 @@ task STARsoloFastq { runtime { docker: docker memory: "~{machine_mem_mb} MiB" - disks: "local-disk ~{disk} HDD" + disks: "local-disk ~{disk} SSD" disk: disk + " GB" # TES cpu: cpu preemptible: preemptible + cpuPlatform: cpu_platform } output { From ef45afa20df42cee91c72e07072f59aece433c75 Mon Sep 17 00:00:00 2001 From: aawdeh Date: Fri, 2 Feb 2024 12:08:15 -0500 Subject: [PATCH 2/7] removed functions not needed --- pipelines/skylab/optimus/Optimus.wdl | 113 ++++++++++++--------------- 1 file changed, 48 insertions(+), 65 deletions(-) diff --git a/pipelines/skylab/optimus/Optimus.wdl b/pipelines/skylab/optimus/Optimus.wdl index f4a07d840f..a99a696af4 100644 --- a/pipelines/skylab/optimus/Optimus.wdl +++ b/pipelines/skylab/optimus/Optimus.wdl @@ -110,70 +110,53 @@ workflow Optimus { tar_star_reference = tar_star_reference } - call FastqProcessing.FastqProcessing as SplitFastq { - input: - i1_fastq = i1_fastq, - r1_fastq = r1_fastq, - r2_fastq = r2_fastq, - whitelist = whitelist, - chemistry = tenx_chemistry_version, - sample_id = input_id, - read_struct = read_struct - } - - scatter(idx in range(length(SplitFastq.fastq_R1_output_array))) { - call StarAlign.STARsoloFastq as STARsoloFastq { + call StarAlign.STARsoloFastq as STARsoloFastq { input: - r1_fastq = [SplitFastq.fastq_R1_output_array[idx]], - r2_fastq = [SplitFastq.fastq_R2_output_array[idx]], + r1_fastq = r1_fastq, + r2_fastq = r2_fastq, star_strand_mode = star_strand_mode, white_list = whitelist, tar_star_reference = tar_star_reference, chemistry = tenx_chemistry_version, counting_mode = counting_mode, count_exons = count_exons, - output_bam_basename = output_bam_basename + "_" + idx, + output_bam_basename = output_bam_basename, soloMultiMappers = soloMultiMappers } - } - call Merge.MergeSortBamFiles as MergeBam { - input: - bam_inputs = STARsoloFastq.bam_output, - output_bam_filename = output_bam_basename + ".bam", - sort_order = "coordinate" - } + + call Metrics.CalculateGeneMetrics as GeneMetrics { input: - bam_input = MergeBam.output_bam, + bam_input = STARsoloFastq.bam_output, mt_genes = mt_genes, input_id = input_id } call Metrics.CalculateCellMetrics as CellMetrics { input: - bam_input = MergeBam.output_bam, + bam_input = STARsoloFastq.bam_output, mt_genes = mt_genes, original_gtf = annotations_gtf, input_id = input_id } - call StarAlign.MergeStarOutput as MergeStarOutputs { - input: - barcodes = STARsoloFastq.barcodes, - features = STARsoloFastq.features, - matrix = STARsoloFastq.matrix, - cell_reads = STARsoloFastq.cell_reads, - summary = STARsoloFastq.summary, - align_features = STARsoloFastq.align_features, - umipercell = STARsoloFastq.umipercell, - input_id = input_id - } + # call StarAlign.MergeStarOutput as MergeStarOutputs { + # input: + # barcodes = STARsoloFastq.barcodes, + # features = STARsoloFastq.features, + # matrix = STARsoloFastq.matrix, + # cell_reads = STARsoloFastq.cell_reads, + # summary = STARsoloFastq.summary, + # align_features = STARsoloFastq.align_features, + # umipercell = STARsoloFastq.umipercell, + # input_id = input_id + # } if (counting_mode == "sc_rna"){ call RunEmptyDrops.RunEmptyDrops { input: - sparse_count_matrix = MergeStarOutputs.sparse_counts, - row_index = MergeStarOutputs.row_index, - col_index = MergeStarOutputs.col_index, + sparse_count_matrix = STARsoloFastq.matrix, + row_index = STARsoloFastq.barcodes, + col_index = STARsoloFastq.features, emptydrops_lower = emptydrops_lower } } @@ -188,23 +171,23 @@ workflow Optimus { annotation_file = annotations_gtf, cell_metrics = CellMetrics.cell_metrics, gene_metrics = GeneMetrics.gene_metrics, - sparse_count_matrix = MergeStarOutputs.sparse_counts, - cell_id = MergeStarOutputs.row_index, - gene_id = MergeStarOutputs.col_index, + sparse_count_matrix = STARsoloFastq.matrix, + cell_id = STARsoloFastq.barcodes, + gene_id = STARsoloFastq.features, empty_drops_result = RunEmptyDrops.empty_drops_result, counting_mode = counting_mode, pipeline_version = "Optimus_v~{pipeline_version}" } } if (count_exons && counting_mode=="sn_rna") { - call StarAlign.MergeStarOutput as MergeStarOutputsExons { - input: - barcodes = STARsoloFastq.barcodes_sn_rna, - features = STARsoloFastq.features_sn_rna, - matrix = STARsoloFastq.matrix_sn_rna, - cell_reads = STARsoloFastq.cell_reads_sn_rna, - input_id = input_id - } + # call StarAlign.MergeStarOutput as MergeStarOutputsExons { + # input: + # barcodes = STARsoloFastq.barcodes_sn_rna, + # features = STARsoloFastq.features_sn_rna, + # matrix = STARsoloFastq.matrix_sn_rna, + # cell_reads = STARsoloFastq.cell_reads_sn_rna, + # input_id = input_id + # } call H5adUtils.SingleNucleusOptimusH5adOutput as OptimusH5adGenerationWithExons{ input: input_id = input_id, @@ -214,12 +197,12 @@ workflow Optimus { annotation_file = annotations_gtf, cell_metrics = CellMetrics.cell_metrics, gene_metrics = GeneMetrics.gene_metrics, - sparse_count_matrix = MergeStarOutputs.sparse_counts, - cell_id = MergeStarOutputs.row_index, - gene_id = MergeStarOutputs.col_index, - sparse_count_matrix_exon = MergeStarOutputsExons.sparse_counts, - cell_id_exon = MergeStarOutputsExons.row_index, - gene_id_exon = MergeStarOutputsExons.col_index, + sparse_count_matrix = STARsoloFastq.matrix, + cell_id = STARsoloFastq.barcodes, + gene_id = STARsoloFastq.features, + sparse_count_matrix_exon = STARsoloFastq.matrix_sn_rna, + cell_id_exon = STARsoloFastq.barcodes_sn_rna, + gene_id_exon = STARsoloFastq.features_sn_rna, pipeline_version = "Optimus_v~{pipeline_version}" } } @@ -231,18 +214,18 @@ workflow Optimus { # version of this pipeline String pipeline_version_out = pipeline_version File genomic_reference_version = ReferenceCheck.genomic_ref_version - File bam = MergeBam.output_bam - File matrix = MergeStarOutputs.sparse_counts - File matrix_row_index = MergeStarOutputs.row_index - File matrix_col_index = MergeStarOutputs.col_index + File bam = STARsoloFastq.bam_output + File matrix = STARsoloFastq.matrix + File matrix_row_index = STARsoloFastq.barcodes + File matrix_col_index = STARsoloFastq.features File cell_metrics = CellMetrics.cell_metrics File gene_metrics = GeneMetrics.gene_metrics File? cell_calls = RunEmptyDrops.empty_drops_result - File? aligner_metrics = MergeStarOutputs.cell_reads_out - Array[File?] multimappers_EM_matrix = STARsoloFastq.multimappers_EM_matrix - Array[File?] multimappers_Uniform_matrix = STARsoloFastq.multimappers_Uniform_matrix - Array[File?] multimappers_Rescue_matrix = STARsoloFastq.multimappers_Rescue_matrix - Array[File?] multimappers_PropUnique_matrix = STARsoloFastq.multimappers_PropUnique_matrix + File? aligner_metrics = STARsoloFastq.align_features + File? multimappers_EM_matrix = STARsoloFastq.multimappers_EM_matrix + File? multimappers_Uniform_matrix = STARsoloFastq.multimappers_Uniform_matrix + File? multimappers_Rescue_matrix = STARsoloFastq.multimappers_Rescue_matrix + File? multimappers_PropUnique_matrix = STARsoloFastq.multimappers_PropUnique_matrix # h5ad File h5ad_output_file = final_h5ad_output From 1491bd40167b4a9222ad4f6f7dddfe672076b439 Mon Sep 17 00:00:00 2001 From: aawdeh Date: Fri, 2 Feb 2024 12:13:43 -0500 Subject: [PATCH 3/7] Change array to file --- pipelines/skylab/multiome/Multiome.wdl | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/pipelines/skylab/multiome/Multiome.wdl b/pipelines/skylab/multiome/Multiome.wdl index 16113b5e8c..d24c39f289 100644 --- a/pipelines/skylab/multiome/Multiome.wdl +++ b/pipelines/skylab/multiome/Multiome.wdl @@ -138,10 +138,10 @@ workflow Multiome { File gene_metrics_gex = Optimus.gene_metrics File? cell_calls_gex = Optimus.cell_calls File h5ad_output_file_gex = JoinBarcodes.gex_h5ad_file - Array[File?] multimappers_EM_matrix = Optimus.multimappers_EM_matrix - Array[File?] multimappers_Uniform_matrix = Optimus.multimappers_Uniform_matrix - Array[File?] multimappers_Rescue_matrix = Optimus.multimappers_Rescue_matrix - Array[File?] multimappers_PropUnique_matrix = Optimus.multimappers_PropUnique_matrix + File? multimappers_EM_matrix = Optimus.multimappers_EM_matrix + File? multimappers_Uniform_matrix = Optimus.multimappers_Uniform_matrix + File? multimappers_Rescue_matrix = Optimus.multimappers_Rescue_matrix + File? multimappers_PropUnique_matrix = Optimus.multimappers_PropUnique_matrix File? gex_aligner_metrics = Optimus.aligner_metrics # cellbender outputs From 27fc9d64daa474f5e7ae505c8884ed2579f4feb0 Mon Sep 17 00:00:00 2001 From: aawdeh Date: Fri, 2 Feb 2024 12:32:48 -0500 Subject: [PATCH 4/7] changed variable name for memory_size for staralign --- tasks/skylab/StarAlign.wdl | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tasks/skylab/StarAlign.wdl b/tasks/skylab/StarAlign.wdl index b61030f56c..ab954e2a6f 100644 --- a/tasks/skylab/StarAlign.wdl +++ b/tasks/skylab/StarAlign.wdl @@ -230,6 +230,7 @@ task STARsoloFastq { String cpu_platform = "Intel Ice Lake" Int machine_mem_mb = 512000 + Int mem_size = 512 Int cpu = 128 Int disk = 2000 # multiply input size by 2.2 to account for output bam file + 20% overhead, add size of reference. @@ -400,7 +401,7 @@ task STARsoloFastq { runtime { docker: docker - memory: "~{machine_mem_mb} MiB" + memory: "~{mem_size} GiB" disks: "local-disk ~{disk} SSD" disk: disk + " GB" # TES cpu: cpu From a8e199495c7c510fbe4e88510667c607d184d5b6 Mon Sep 17 00:00:00 2001 From: aawdeh Date: Mon, 5 Feb 2024 20:46:52 -0500 Subject: [PATCH 5/7] added merge metrics steps back for consistency --- pipelines/skylab/optimus/Optimus.wdl | 71 ++++++++++++++-------------- 1 file changed, 35 insertions(+), 36 deletions(-) diff --git a/pipelines/skylab/optimus/Optimus.wdl b/pipelines/skylab/optimus/Optimus.wdl index a99a696af4..9bab6bddb1 100644 --- a/pipelines/skylab/optimus/Optimus.wdl +++ b/pipelines/skylab/optimus/Optimus.wdl @@ -140,23 +140,23 @@ workflow Optimus { input_id = input_id } - # call StarAlign.MergeStarOutput as MergeStarOutputs { - # input: - # barcodes = STARsoloFastq.barcodes, - # features = STARsoloFastq.features, - # matrix = STARsoloFastq.matrix, - # cell_reads = STARsoloFastq.cell_reads, - # summary = STARsoloFastq.summary, - # align_features = STARsoloFastq.align_features, - # umipercell = STARsoloFastq.umipercell, - # input_id = input_id - # } + call StarAlign.MergeStarOutput as MergeStarOutputs { + input: + barcodes = [STARsoloFastq.barcodes], + features = [STARsoloFastq.features], + matrix = [STARsoloFastq.matrix], + cell_reads = [STARsoloFastq.cell_reads], + summary = [STARsoloFastq.summary], + align_features = [STARsoloFastq.align_features], + umipercell = [STARsoloFastq.umipercell], + input_id = input_id + } if (counting_mode == "sc_rna"){ call RunEmptyDrops.RunEmptyDrops { input: - sparse_count_matrix = STARsoloFastq.matrix, - row_index = STARsoloFastq.barcodes, - col_index = STARsoloFastq.features, + sparse_count_matrix = MergeStarOutputs.sparse_counts, + row_index = MergeStarOutputs.row_index, + col_index = MergeStarOutputs.col_index, emptydrops_lower = emptydrops_lower } } @@ -171,23 +171,23 @@ workflow Optimus { annotation_file = annotations_gtf, cell_metrics = CellMetrics.cell_metrics, gene_metrics = GeneMetrics.gene_metrics, - sparse_count_matrix = STARsoloFastq.matrix, - cell_id = STARsoloFastq.barcodes, - gene_id = STARsoloFastq.features, + sparse_count_matrix = MergeStarOutputs.sparse_counts, + cell_id = MergeStarOutputs.row_index, + gene_id = MergeStarOutputs.col_index, empty_drops_result = RunEmptyDrops.empty_drops_result, counting_mode = counting_mode, pipeline_version = "Optimus_v~{pipeline_version}" } } if (count_exons && counting_mode=="sn_rna") { - # call StarAlign.MergeStarOutput as MergeStarOutputsExons { - # input: - # barcodes = STARsoloFastq.barcodes_sn_rna, - # features = STARsoloFastq.features_sn_rna, - # matrix = STARsoloFastq.matrix_sn_rna, - # cell_reads = STARsoloFastq.cell_reads_sn_rna, - # input_id = input_id - # } + call StarAlign.MergeStarOutput as MergeStarOutputsExons { + input: + barcodes = [STARsoloFastq.barcodes_sn_rna], + features = [STARsoloFastq.features_sn_rna], + matrix = [STARsoloFastq.matrix_sn_rna], + cell_reads = [STARsoloFastq.cell_reads_sn_rna], + input_id = input_id + } call H5adUtils.SingleNucleusOptimusH5adOutput as OptimusH5adGenerationWithExons{ input: input_id = input_id, @@ -197,31 +197,30 @@ workflow Optimus { annotation_file = annotations_gtf, cell_metrics = CellMetrics.cell_metrics, gene_metrics = GeneMetrics.gene_metrics, - sparse_count_matrix = STARsoloFastq.matrix, - cell_id = STARsoloFastq.barcodes, - gene_id = STARsoloFastq.features, - sparse_count_matrix_exon = STARsoloFastq.matrix_sn_rna, - cell_id_exon = STARsoloFastq.barcodes_sn_rna, - gene_id_exon = STARsoloFastq.features_sn_rna, + sparse_count_matrix = MergeStarOutputs.sparse_counts, + cell_id = MergeStarOutputs.row_index, + gene_id = MergeStarOutputs.col_index, + sparse_count_matrix_exon = MergeStarOutputsExons.sparse_counts, + cell_id_exon = MergeStarOutputsExons.row_index, + gene_id_exon = MergeStarOutputsExons.col_index, pipeline_version = "Optimus_v~{pipeline_version}" } } File final_h5ad_output = select_first([OptimusH5adGenerationWithExons.h5ad_output, OptimusH5adGeneration.h5ad_output]) - output { # version of this pipeline String pipeline_version_out = pipeline_version File genomic_reference_version = ReferenceCheck.genomic_ref_version File bam = STARsoloFastq.bam_output - File matrix = STARsoloFastq.matrix - File matrix_row_index = STARsoloFastq.barcodes - File matrix_col_index = STARsoloFastq.features + File matrix = MergeStarOutputs.sparse_counts + File matrix_row_index = MergeStarOutputs.row_index + File matrix_col_index = MergeStarOutputs.col_index File cell_metrics = CellMetrics.cell_metrics File gene_metrics = GeneMetrics.gene_metrics File? cell_calls = RunEmptyDrops.empty_drops_result - File? aligner_metrics = STARsoloFastq.align_features + File? aligner_metrics = MergeStarOutputs.cell_reads_out File? multimappers_EM_matrix = STARsoloFastq.multimappers_EM_matrix File? multimappers_Uniform_matrix = STARsoloFastq.multimappers_Uniform_matrix File? multimappers_Rescue_matrix = STARsoloFastq.multimappers_Rescue_matrix From 48ee62dbea279d63249e857f4a12abb8a5668bca Mon Sep 17 00:00:00 2001 From: aawdeh Date: Tue, 6 Feb 2024 10:37:43 -0500 Subject: [PATCH 6/7] update json --- .../optimus/test_inputs/Plumbing/human_v3_example.json | 5 ++++- .../optimus/test_inputs/Plumbing/mouse_v2_example.json | 5 ++++- .../optimus/test_inputs/Plumbing/mouse_v2_snRNA_example.json | 5 ++++- 3 files changed, 12 insertions(+), 3 deletions(-) diff --git a/pipelines/skylab/optimus/test_inputs/Plumbing/human_v3_example.json b/pipelines/skylab/optimus/test_inputs/Plumbing/human_v3_example.json index ff5a02caaf..cc3d2d75e5 100644 --- a/pipelines/skylab/optimus/test_inputs/Plumbing/human_v3_example.json +++ b/pipelines/skylab/optimus/test_inputs/Plumbing/human_v3_example.json @@ -16,5 +16,8 @@ "Optimus.tenx_chemistry_version": "3", "Optimus.annotations_gtf": "gs://gcp-public-data--broad-references/hg38/v0/star/v2_7_10a/modified_v43.annotation.gtf", "Optimus.star_strand_mode": "Forward", - "Optimus.ref_genome_fasta": "gs://gcp-public-data--broad-references/hg38/v0/GRCh38.primary_assembly.genome.fa" + "Optimus.ref_genome_fasta": "gs://gcp-public-data--broad-references/hg38/v0/GRCh38.primary_assembly.genome.fa", + "Optimus.STARsoloFastq.cpu_platform":"Intel Cascade Lake", + "Optimus.STARsoloFastq.cpu":"16", + "Optimus.STARsoloFastq.mem_size":"64" } diff --git a/pipelines/skylab/optimus/test_inputs/Plumbing/mouse_v2_example.json b/pipelines/skylab/optimus/test_inputs/Plumbing/mouse_v2_example.json index bbf625ef27..5769a42932 100644 --- a/pipelines/skylab/optimus/test_inputs/Plumbing/mouse_v2_example.json +++ b/pipelines/skylab/optimus/test_inputs/Plumbing/mouse_v2_example.json @@ -28,5 +28,8 @@ "Optimus.tenx_chemistry_version": "2", "Optimus.star_strand_mode": "Unstranded", "Optimus.annotations_gtf": "gs://gcp-public-data--broad-references/GRCm39/star/v2_7_10a/modified_vM32.annotation.gtf", - "Optimus.ref_genome_fasta": "gs://gcp-public-data--broad-references/GRCm39/GRCm39.primary_assembly.genome.fa.gz" + "Optimus.ref_genome_fasta": "gs://gcp-public-data--broad-references/GRCm39/GRCm39.primary_assembly.genome.fa.gz", + "Optimus.STARsoloFastq.cpu_platform":"Intel Cascade Lake", + "Optimus.STARsoloFastq.cpu":"16", + "Optimus.STARsoloFastq.mem_size":"64" } diff --git a/pipelines/skylab/optimus/test_inputs/Plumbing/mouse_v2_snRNA_example.json b/pipelines/skylab/optimus/test_inputs/Plumbing/mouse_v2_snRNA_example.json index 239b7d1fcb..a9e3319c2c 100644 --- a/pipelines/skylab/optimus/test_inputs/Plumbing/mouse_v2_snRNA_example.json +++ b/pipelines/skylab/optimus/test_inputs/Plumbing/mouse_v2_snRNA_example.json @@ -26,5 +26,8 @@ "Optimus.annotations_gtf": "gs://gcp-public-data--broad-references/GRCm39/star/v2_7_10a/modified_vM32.annotation.gtf", "Optimus.ref_genome_fasta": "gs://gcp-public-data--broad-references/GRCm39/GRCm39.primary_assembly.genome.fa.gz", "Optimus.counting_mode": "sn_rna", - "Optimus.count_exons": true + "Optimus.count_exons": true, + "Optimus.STARsoloFastq.cpu_platform":"Intel Cascade Lake", + "Optimus.STARsoloFastq.cpu":"16", + "Optimus.STARsoloFastq.mem_size":"64" } From 95bf7e351bd7f78c78e4ca3476c5169f81197f92 Mon Sep 17 00:00:00 2001 From: aawdeh Date: Tue, 6 Feb 2024 14:09:36 -0500 Subject: [PATCH 7/7] Update example jsons --- .../skylab/optimus/example_inputs/human_v2_example.json | 5 ++++- .../skylab/optimus/example_inputs/human_v3_example.json | 5 ++++- .../skylab/optimus/example_inputs/mouse_v2_example.json | 5 ++++- .../optimus/example_inputs/mouse_v2_snRNA_example.json | 5 ++++- 4 files changed, 16 insertions(+), 4 deletions(-) diff --git a/pipelines/skylab/optimus/example_inputs/human_v2_example.json b/pipelines/skylab/optimus/example_inputs/human_v2_example.json index 04e54e6d80..e40f2a0c51 100644 --- a/pipelines/skylab/optimus/example_inputs/human_v2_example.json +++ b/pipelines/skylab/optimus/example_inputs/human_v2_example.json @@ -16,5 +16,8 @@ "Optimus.input_id": "pbmc4k_human", "Optimus.chemistry": "tenX_v2", "Optimus.annotations_gtf": "gs://gcp-public-data--broad-references/hg38/v0/gencode.v27.primary_assembly.annotation.gtf", - "Optimus.ref_genome_fasta": "gs://gcp-public-data--broad-references/hg38/v0/GRCh38.primary_assembly.genome.fa" + "Optimus.ref_genome_fasta": "gs://gcp-public-data--broad-references/hg38/v0/GRCh38.primary_assembly.genome.fa", + "Optimus.STARsoloFastq.cpu_platform":"Intel Cascade Lake", + "Optimus.STARsoloFastq.cpu":"16", + "Optimus.STARsoloFastq.mem_size":"64" } diff --git a/pipelines/skylab/optimus/example_inputs/human_v3_example.json b/pipelines/skylab/optimus/example_inputs/human_v3_example.json index 82dd8c219a..15fc11cf8b 100644 --- a/pipelines/skylab/optimus/example_inputs/human_v3_example.json +++ b/pipelines/skylab/optimus/example_inputs/human_v3_example.json @@ -16,5 +16,8 @@ "Optimus.input_id": "pbmc_human_v3", "Optimus.chemistry": "tenX_v3", "Optimus.annotations_gtf": "gs://gcp-public-data--broad-references/hg38/v0/gencode.v27.primary_assembly.annotation.gtf", - "Optimus.ref_genome_fasta": "gs://gcp-public-data--broad-references/hg38/v0/GRCh38.primary_assembly.genome.fa" + "Optimus.ref_genome_fasta": "gs://gcp-public-data--broad-references/hg38/v0/GRCh38.primary_assembly.genome.fa", + "Optimus.STARsoloFastq.cpu_platform":"Intel Cascade Lake", + "Optimus.STARsoloFastq.cpu":"16", + "Optimus.STARsoloFastq.mem_size":"64" } diff --git a/pipelines/skylab/optimus/example_inputs/mouse_v2_example.json b/pipelines/skylab/optimus/example_inputs/mouse_v2_example.json index 45981c2ac7..d284509c2b 100644 --- a/pipelines/skylab/optimus/example_inputs/mouse_v2_example.json +++ b/pipelines/skylab/optimus/example_inputs/mouse_v2_example.json @@ -28,5 +28,8 @@ "Optimus.input_id": "neurons2k_mouse", "Optimus.chemistry": "tenX_v2", "Optimus.annotations_gtf": "gs://gcp-public-data--broad-references/mm10/v0/gencode.vM21.primary_assembly.annotation.gtf", - "Optimus.ref_genome_fasta": "gs://gcp-public-data--broad-references/mm10/v0/GRCm38.primary_assembly.genome.fa" + "Optimus.ref_genome_fasta": "gs://gcp-public-data--broad-references/mm10/v0/GRCm38.primary_assembly.genome.fa", + "Optimus.STARsoloFastq.cpu_platform":"Intel Cascade Lake", + "Optimus.STARsoloFastq.cpu":"16", + "Optimus.STARsoloFastq.mem_size":"64" } diff --git a/pipelines/skylab/optimus/example_inputs/mouse_v2_snRNA_example.json b/pipelines/skylab/optimus/example_inputs/mouse_v2_snRNA_example.json index 293c9f326f..557f0529c7 100644 --- a/pipelines/skylab/optimus/example_inputs/mouse_v2_snRNA_example.json +++ b/pipelines/skylab/optimus/example_inputs/mouse_v2_snRNA_example.json @@ -26,5 +26,8 @@ "Optimus.annotations_gtf": "gs://gcp-public-data--broad-references/mm10/v0/gencode.vM21.primary_assembly.annotation.gtf", "Optimus.ref_genome_fasta": "gs://gcp-public-data--broad-references/mm10/v0/GRCm38.primary_assembly.genome.fa", "Optimus.counting_mode": "sn_rna", - "Optimus.count_exons": true + "Optimus.count_exons": true, + "Optimus.STARsoloFastq.cpu_platform":"Intel Cascade Lake", + "Optimus.STARsoloFastq.cpu":"16", + "Optimus.STARsoloFastq.mem_size":"64" }