update to decoy fasta

mskcc · Oct 10, 2024 · 3d97ab8 · 3d97ab8
1 parent 95e737e
commit 3d97ab8
Show file tree

Hide file tree

Showing 5 changed files with 48 additions and 4 deletions.
diff --git a/conf/igenomes.config b/conf/igenomes.config
@@ -35,8 +35,8 @@ params {
         }
         'GRCh38' {
             ensembl_version      = 111
-            //fasta                = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38Decoy/Sequence/WholeGenomeFasta/genome.fa"
-            fasta                = "https://ftp.ensembl.org/pub/release-111/fasta/homo_sapiens/dna/Homo_sapiens.GRCh38.dna.primary_assembly.fa.gz"
+            fasta                = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38Decoy/Sequence/WholeGenomeFasta/genome.fa"
+            //fasta                = "https://ftp.ensembl.org/pub/release-111/fasta/homo_sapiens/dna/Homo_sapiens.GRCh38.dna.primary_assembly.fa.gz"
             gtf                  = "https://ftp.ensembl.org/pub/release-111/gtf/homo_sapiens/Homo_sapiens.GRCh38.111.gtf.gz"
             //forte will generate refflat from gtf
             refflat              = null

diff --git a/modules/local/fastaremoveprefix/environment.yml b/modules/local/fastaremoveprefix/environment.yml
@@ -0,0 +1,5 @@
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - conda-forge::gawk=5.3.0
diff --git a/modules/local/fastaremoveprefix/main.nf b/modules/local/fastaremoveprefix/main.nf
@@ -0,0 +1,32 @@
+process FASTAREMOVEPREFIX {
+    tag "$fasta"
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/gawk:5.3.0' :
+        'biocontainers/gawk:5.3.0' }"
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    input:
+    tuple val(meta), path(fasta, name: 'input/*')
+
+    output:
+    tuple val(meta), path("*.{fa,fasta}"), emit: fasta
+    path "versions.yml"                  , emit: versions
+
+    script:
+    def modified_fasta = fasta.fileName.name
+    """
+    cat ${fasta} | sed "s/^>chr/>/g" > ${modified_fasta}
+
+    cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            gawk: \$(awk -Wversion | sed '1!d; s/.*Awk //; s/,.*//')
+    END_VERSIONS
+    """
+
+
+}
diff --git a/modules/local/prepare_rrna/main.nf b/modules/local/prepare_rrna/main.nf
@@ -14,6 +14,7 @@ process PREPARE_RRNA {
     path "rna.bed", emit: rRNA_bed
 
     script:
+    def extra_filter_chr = params.genome == "GRCh38" ? "|^GL000220|^KI270733" : ""
     if (gtf) {
         """
         (${"${gtf}".endsWith(".gz") ? "z" : ""}grep "rRNA" ${gtf} || true) | \\
@@ -23,7 +24,7 @@ process PREPARE_RRNA {
                 /transcript_id "([^"]+)"/ or die "no transcript_id on \$.";
                 print join "\t", (@F[0,1,2,3], \$1)
             ' | \\
-            (grep -vP "^HG|^HSCHR" || true) | \\
+            (grep -vP "^HG|^HSCHR${extra_filter_chr}" || true) | \\
             sort -k1V -k2n -k3n \\
             > rna.bed
 
@@ -32,7 +33,7 @@ process PREPARE_RRNA {
         """
         (${"${refflat}".endsWith(".gz") ? "z" : ""}grep -P "^RNA5|^RNA1|^RNA2" ${refflat} || true) | \\
             awk -F"\\t" -v OFS="\\t" '{ print \$3,\$5,\$6,\$4,\$2 }' | \\
-            (grep -vP "^HG|^HSCHR" || true) | \\
+            (grep -vP "^HG|^HSCHR${extra_filter_chr}" || true) | \\
             sort -k1V -k2n -k3n \\
             > rna.bed
         """

diff --git a/subworkflows/local/prepare_references.nf b/subworkflows/local/prepare_references.nf
@@ -19,6 +19,7 @@ include { AGFUSION_DOWNLOAD              } from '../../modules/local/agfusion/do
 include { AGAT_SPADDINTRONS              } from '../../modules/nf-core/agat/spaddintrons/main'
 include { METAFUSION_GENEBED             } from '../../modules/local/metafusion/genebed/main'
 include { METAFUSION_GENEINFO            } from '../../modules/local/metafusion/geneinfo/main'
+include { FASTAREMOVEPREFIX              } from '../../modules/local/fastaremoveprefix/main'
 
 workflow PREPARE_REFERENCES {
 
@@ -32,6 +33,11 @@ workflow PREPARE_REFERENCES {
         fasta = Channel.of([[id:params.genome],params.fasta]).first()
     }
 
+    if (params.genome == "GRCh38" ){
+        FASTAREMOVEPREFIX(fasta)
+	fasta = FASTAREMOVEPREFIX.out.fasta
+    }
+
     if (params.gtf.endsWith(".gz")){
         GUNZIP_GTF([[id:params.genome],params.gtf])
         gtf = GUNZIP_GTF.out.gunzip.first()