Pipeline checkpoint, all working until FASTP step. From now on input …

…DNA/RNA will be separated for their corresponding pre-processing steps
nrhorner · Aug 16, 2022 · 9dde0a1 · 9dde0a1
1 parent 1a12c5b
commit 9dde0a1
Show file tree

Hide file tree

Showing 13 changed files with 573 additions and 290 deletions.
diff --git a/.gitignore b/.gitignore
@@ -6,3 +6,7 @@ results/
 testing/
 testing*
 *.pyc
+.idea/
+null/
+test/
+res-test
diff --git a/conf/slurm.config b/conf/slurm.config
@@ -3,15 +3,30 @@ singularity {
   autoMounts = true
 }
 process {
-  withName:  'NFCORE_RNADNAVAR:RNADNAVAR:GATK4_BEDTOINTERVALLIST'
-    {
-    ext.args = '--DROP_MISSING_CONTIGS TRUE'
-    }
   executor = 'slurm'
-  clusterOptions = "--account caldas-sl2-cpu"
+  clusterOptions = "--account caldas-sl2-cpu --partition cclake"
+  pollInterval      = '1 min'
+  queueStatInterval = '5 min'
 }
 params {
+  config_profile_name        = 'Slurm test profile'
+  config_profile_description = 'Minimal real dataset to check pipeline function'
   max_time = 12.h
   max_cpus = 12
-  max_memory = 100.GB
+  max_memory = 120.GB
+
+  // Input data
+  input  = '/rds/project/rds-upenYb9rdtk/Work/rm889/rna_mutect/nextflow/rnadnavar/assets/samplesheet_mytest.csv'
+  outdir = 'results'
+  skip_intervallisttools = true
+  genome = 'GRCh38'
+  fasta = '/rds/project/rds-upenYb9rdtk/Work/rm889/resources/genome/hg38/chr3.fa'
+  gtf = '/rds/project/rds-upenYb9rdtk/Work/rm889/resources/Homo_sapiens/NCBI/GRCh38Decoy/Annotation/Genes.gencode/gencode.v33.annotation.chr3.gtf'
+  known_indels = '/rds/project/rds-upenYb9rdtk/Work/rm889/resources/Homo_sapiens_assembly38.known_indels.vcf.gz'
+  known_indels_tbi = '/rds/project/rds-upenYb9rdtk/Work/rm889/resources/Homo_sapiens_assembly38.known_indels.vcf.gz.tbi'
+  pon = '/rds/project/rds-upenYb9rdtk/Work/rm889/resources/1000g_pon.hg38.vcf.gz'
+  pon_tbi = '/rds/project/rds-upenYb9rdtk/Work/rm889/resources/1000g_pon.hg38.vcf.gz.tbi'
+  germline_resource = '/rds/project/rds-upenYb9rdtk/Work/rm889/resources/af-only-gnomad.hg38.vcf.gz'
+  germline_resource_tbi = '/rds/project/rds-upenYb9rdtk/Work/rm889/resources/af-only-gnomad.hg38.vcf.gz.tbi'
+  nucleotides_per_second = 1000
 }
diff --git a/modules/nf-core/modules/fastqc/main.nf b/modules/nf-core/modules/fastqc/main.nf
diff --git a/modules/nf-core/modules/gatk4/haplotypecaller/main.nf b/modules/nf-core/modules/gatk4/haplotypecaller/main.nf
diff --git a/modules/nf-core/modules/gatk4/haplotypecaller/meta.yml b/modules/nf-core/modules/gatk4/haplotypecaller/meta.yml
diff --git a/modules/nf-core/modules/gatk4/mergevcfs/main.nf b/modules/nf-core/modules/gatk4/mergevcfs/main.nf
diff --git a/modules/nf-core/modules/gatk4/mergevcfs/meta.yml b/modules/nf-core/modules/gatk4/mergevcfs/meta.yml
diff --git a/modules/nf-core/modules/gatk4/splitncigarreads/main.nf b/modules/nf-core/modules/gatk4/splitncigarreads/main.nf
diff --git a/modules/nf-core/modules/samtools/stats/main.nf b/modules/nf-core/modules/samtools/stats/main.nf
diff --git a/subworkflows/local/input_check.nf b/subworkflows/local/input_check.nf
@@ -37,7 +37,8 @@ def create_fastq_channel(LinkedHashMap row) {
          exit 1, "ERROR: Please check input samplesheet -> Read 1 BAM file do not exist!\n${row.bam}"
         }
         file_meta = [ meta, [ file(row.bam) ] ]
-        file_meta = [ meta, [ file(row.bam), file(row.bai) ] ]
+//        file_meta = [ meta, [ file(row.bam), file(row.bai) ] ] TODO: do we need this somewhere else apart from fastqc?
+        meta.single_end = row.single_end.toBoolean()
         }
     else {
     if (!file(row.fastq_1).exists())