workspace configs

data/23Q4/RNAconfig/Aggregate_Fusion_Calls/config.json

@@ -0,0 +1,15 @@
+{
+ "inputs": {
+  "aggregate_set_files_workflow.aggregate_set_files.aggregate_files_script": "workspace.aggregate_fusions_script",
+  "aggregate_set_files_workflow.aggregate_set_files.disk_space": "250",
+  "aggregate_set_files_workflow.aggregate_set_files.memory": "3",
+  "aggregate_set_files_workflow.aggregate_set_files.num_preempt": "5",
+  "aggregate_set_files_workflow.aggregate_set_files.output_file_name": "\"Fusions.aggregated.tsv\"",
+  "aggregate_set_files_workflow.aggregate_set_files.sample_files": "this.samples.fusion_predictions_abridged"
+ },
+ "outputs": {
+  "aggregate_set_files_workflow.aggregate_set_files.output_merged_file": "this.fusions_star"
+ },
+ "prerequisites": {},
+ "rootEntityType": "sample_set"
+}

data/23Q4/RNAconfig/Aggregate_Fusion_Calls/method.wdl

@@ -0,0 +1,34 @@
+# Given a set of samples, combine segment files into a single file
+workflow aggregate_set_files_workflow {
+    call aggregate_set_files
+}
+
+task aggregate_set_files {
+    Array[File] sample_files
+    String output_file_name
+    File aggregate_files_script
+
+    Int memory
+    Int disk_space
+    Int num_preempt
+
+
+    command {
+        Rscript ${aggregate_files_script} "${output_file_name}" ${write_lines(sample_files)} 
+    }
+
+    output {
+        File output_merged_file="${output_file_name}"
+    }
+
+    runtime {
+        docker: "flyingrobin/cds_shiny"
+        memory: "${memory}GB"
+        disks: "local-disk ${disk_space} HDD"
+        preemptible: "${num_preempt}"
+    }
+
+    meta {
+        author: "Guillaume Kugener"
+    }
+}

data/23Q4/RNAconfig/ExonUsage_hg38_fixed/config.json

@@ -0,0 +1,15 @@
+{
+ "inputs": {
+  "ExonUsage_workflow.ExonUsage.exon_usage_script": "workspace.exon_usage_script",
+  "ExonUsage_workflow.ExonUsage.exonsFN": "\"gs://fc-ca01b420-53e8-4922-b152-8d5e9bdcc07f/references/exons_gencodev26_GRCh38.RData\"",
+  "ExonUsage_workflow.ExonUsage.juncReadFN": "this.star_junctions",
+  "ExonUsage_workflow.ExonUsage.minCov": "10",
+  "ExonUsage_workflow.ExonUsage.sample_id": "this.name"
+ },
+ "outputs": {
+  "ExonUsage_workflow.ExonUsage.outFN": "this.exon_usage_hg38_outFN",
+  "ExonUsage_workflow.ExonUsage.outRobjFN": "this.exon_usage_hg38_outRobjFN"
+ },
+ "prerequisites": {},
+ "rootEntityType": "sample"
+}

data/23Q4/RNAconfig/ExonUsage_hg38_fixed/method.wdl

@@ -0,0 +1,31 @@
+task ExonUsage {
+  String sample_id
+  File exon_usage_script
+  File juncReadFN
+  File exonsFN
+  Int minCov
+
+  command {
+    set -euo pipefail
+
+    touch ${sample_id}_outputFN.txt
+    touch ${sample_id}_outputFN.RData
+    Rscript ${exon_usage_script} ${juncReadFN} ${exonsFN} ${sample_id}_outputFN.txt ${sample_id}_outputFN.RData ${minCov}
+  }
+
+  output {
+    File outFN = "${sample_id}_outputFN.txt"
+    File outRobjFN = "${sample_id}_outputFN.RData"
+  }
+
+  runtime {
+    docker: "mghandi/ccle_docker_r"
+    memory: "10GB"
+    disks: "local-disk 50 HDD"
+    preemptible: "5"
+  }
+}
+
+workflow ExonUsage_workflow {
+  call ExonUsage
+}

data/23Q4/RNAconfig/RNA_pipeline/config.json

@@ -0,0 +1,80 @@
+{
+ "inputs": {
+  "RNA_pipeline.StarFusion.disk_space": "500",
+  "RNA_pipeline.StarFusion.docker": "\"trinityctat/starfusion:1.7.0\"",
+  "RNA_pipeline.StarFusion.memory": "64",
+  "RNA_pipeline.StarFusion.num_preempt": "2",
+  "RNA_pipeline.StarFusion.num_threads": "8",
+  "RNA_pipeline.ctat_genome_lib_build_dir_files": "workspace.hg38_star_fusion_ctat_files_v33",
+  "RNA_pipeline.genes_gtf": "workspace.genes_gtf",
+  "RNA_pipeline.input_bam_cram": "this.hg19_bam_filepath",
+  "RNA_pipeline.ref_genome_fa_star_idx_files": "workspace.hg38_star_fusion_ctat_star_index_files_v33",
+  "RNA_pipeline.reference_fasta": "workspace.ref_fasta",
+  "RNA_pipeline.rnaseqc2.disk_space": "75",
+  "RNA_pipeline.rnaseqc2.memory": "8",
+  "RNA_pipeline.rnaseqc2.num_preempt": "1",
+  "RNA_pipeline.rnaseqc2.num_threads": "4",
+  "RNA_pipeline.rsem.disk_space": "500",
+  "RNA_pipeline.rsem.estimate_rspd": "\"true\"",
+  "RNA_pipeline.rsem.max_frag_len": "1000",
+  "RNA_pipeline.rsem.memory": "128",
+  "RNA_pipeline.rsem.num_preempt": "1",
+  "RNA_pipeline.rsem.num_threads": "32",
+  "RNA_pipeline.rsem_reference": "\"gs://ccleparams/rsem_reference_hg38_gencode_38_noALT_noHLA_noDecoy_ERCC.tar.gz\"",
+  "RNA_pipeline.sample_id": "this.name",
+  "RNA_pipeline.samtofastq.disk_space": "400",
+  "RNA_pipeline.samtofastq.memory": "64",
+  "RNA_pipeline.samtofastq.num_preempt": "5",
+  "RNA_pipeline.samtofastq.num_threads": "8",
+  "RNA_pipeline.star.alignIntronMax": "1000000",
+  "RNA_pipeline.star.alignIntronMin": "20",
+  "RNA_pipeline.star.alignMatesGapMax": "1000000",
+  "RNA_pipeline.star.alignSJDBoverhangMin": "1",
+  "RNA_pipeline.star.alignSJoverhangMin": "8",
+  "RNA_pipeline.star.alignSoftClipAtReferenceEnds": "\"Yes\"",
+  "RNA_pipeline.star.chimJunctionOverhangMin": "15",
+  "RNA_pipeline.star.chimMainSegmentMultNmax": "1",
+  "RNA_pipeline.star.chimOutJunctionFormat": "1",
+  "RNA_pipeline.star.chimOutType": "\"Junctions WithinBAM SoftClip\"",
+  "RNA_pipeline.star.chimSegmentMin": "15",
+  "RNA_pipeline.star.disk_space": "500",
+  "RNA_pipeline.star.limitSjdbInsertNsj": "1200000",
+  "RNA_pipeline.star.memory": "64",
+  "RNA_pipeline.star.num_preempt": "1",
+  "RNA_pipeline.star.num_threads": "16",
+  "RNA_pipeline.star.outFilterIntronMotifs": "\"None\"",
+  "RNA_pipeline.star.outFilterMatchNminOverLread": "0.33",
+  "RNA_pipeline.star.outFilterMismatchNmax": "999",
+  "RNA_pipeline.star.outFilterMismatchNoverLmax": "0.1",
+  "RNA_pipeline.star.outFilterMultimapNmax": "20",
+  "RNA_pipeline.star.outFilterScoreMinOverLread": "0.33",
+  "RNA_pipeline.star.outFilterType": "\"BySJout\"",
+  "RNA_pipeline.star.outSAMattrRGline": "\"ID:rg1 SM:sm1\"",
+  "RNA_pipeline.star.outSAMattributes": "\"NH HI AS nM NM ch\"",
+  "RNA_pipeline.star.outSAMstrandField": "\"intronMotif\"",
+  "RNA_pipeline.star.quantMode": "\"TranscriptomeSAM GeneCounts\"",
+  "RNA_pipeline.star_index": "\"gs://ccleparams/star_index_hg38_noALT_noHLA_noDecoy_ERCC.tar.gz\""
+ },
+ "outputs": {
+  "RNA_pipeline.bam_file": "this.internal_bam_filepath",
+  "RNA_pipeline.bam_index": "this.internal_bai_filepath",
+  "RNA_pipeline.chimeric_bam_file": "this.star_chimeric_bam_file",
+  "RNA_pipeline.chimeric_junctions": "this.star_chimeric_junctions",
+  "RNA_pipeline.exon_counts": "this.rnaseqc2_exon_counts",
+  "RNA_pipeline.fusion_predictions": "this.fusion_predictions",
+  "RNA_pipeline.fusion_predictions_abridged": "this.fusion_predictions_abridged",
+  "RNA_pipeline.gene_counts": "this.rnaseqc2_gene_counts",
+  "RNA_pipeline.gene_tpm": "this.rnaseqc2_gene_tpm",
+  "RNA_pipeline.genes": "this.rsem_genes",
+  "RNA_pipeline.insertsize_distr": "this.rnaseqc2_insertsize_distr",
+  "RNA_pipeline.isoforms": "this.rsem_isoforms",
+  "RNA_pipeline.junctions": "this.star_junctions",
+  "RNA_pipeline.junctions_pass1": "this.star_junctions_pass1",
+  "RNA_pipeline.logs": "this.star_logs",
+  "RNA_pipeline.metrics": "this.rnaseqc2_metrics",
+  "RNA_pipeline.read_counts": "this.star_read_counts",
+  "RNA_pipeline.transcriptome_bam": "this.star_transcriptome_bam"
+ },
+ "prerequisites": {},
+ "rootEntityType": "sample"
+}

data/23Q4/RNAconfig/RNA_pipeline/hg38_STAR_fusion_wdl1-0.wdl

@@ -0,0 +1,81 @@
+version 1.0
+
+task StarFusion {
+
+    input {
+        File left_fastq
+        File right_fastq
+        Array[File] ctat_genome_lib_build_dir_files
+        Array[File] ref_genome_fa_star_idx_files
+
+        String prefix
+
+        Int memory=64
+        Int disk_space=500
+        Int num_threads=8
+        Int num_preempt=2
+        String docker="trinityctat/starfusion:1.7.0"
+    }
+
+    command {
+        # We need to recreate the directory structure for STAR-Fusion
+        mkdir ctat_genome_lib_build_dir
+        for path in "${sep='" "' ctat_genome_lib_build_dir_files}"; do
+            mv $path ctat_genome_lib_build_dir
+        done
+        mkdir ctat_genome_lib_build_dir/ref_genome.fa.star.idx
+        for path in "${sep='" "' ref_genome_fa_star_idx_files}"; do
+            mv $path ctat_genome_lib_build_dir/ref_genome.fa.star.idx
+        done
+
+        ls ctat_genome_lib_build_dir | xargs echo
+
+        # Run STAR fusion
+        /usr/local/src/STAR-Fusion/STAR-Fusion --genome_lib_dir ctat_genome_lib_build_dir \
+             --left_fq ${left_fastq} \
+             --right_fq ${right_fastq} \
+             --min_FFPM 0 \
+             --no_annotation_filter \
+             --output_dir star_fusion_outdir
+
+        cp star_fusion_outdir/star-fusion.fusion_predictions.abridged.tsv "${prefix}.star-fusion.fusion_predictions.abridged.tsv"
+        cp star_fusion_outdir/star-fusion.fusion_predictions.tsv "${prefix}.star-fusion.fusion_predictions.tsv"
+    }
+
+    output {
+        File fusion_predictions = "${prefix}.star-fusion.fusion_predictions.tsv"
+        File fusion_predictions_abridged = "${prefix}.star-fusion.fusion_predictions.abridged.tsv"
+    }
+
+    runtime {
+        docker: "${docker}"
+        memory: "${memory}GB"
+        disks: "local-disk ${disk_space} HDD"
+        cpu: "${num_threads}"
+        preemptible: "${num_preempt}"
+    }
+}
+
+#FusionFilter is what was used to generate the reference used in this pipeline.
+workflow trinity_cleaned {
+
+    input {
+        String prefix
+        File fastq1
+        File fastq2
+        Array[File] ctat_genome_lib_build_dir_files
+        Array[File] ref_genome_fa_star_idx_files
+    }
+    call StarFusion {
+        input: 
+            prefix = prefix,
+            left_fastq=fastq1,
+            right_fastq=fastq2,
+            ctat_genome_lib_build_dir_files=ctat_genome_lib_build_dir_files,
+            ref_genome_fa_star_idx_files=ref_genome_fa_star_idx_files
+    }
+    output {
+        File fusion_predictions = StarFusion.fusion_predictions
+        File fusion_predictions_abridged = StarFusion.fusion_predictions_abridged
+    }
+}