update bambu version v2.0.6 to v3.0.8

IGDRion · Jul 28, 2023 · 143ba94 · 143ba94
1 parent 9fc18a5
commit 143ba94
Show file tree

Hide file tree

Showing 4 changed files with 13 additions and 13 deletions.
diff --git a/bin/filter_gtf_ndr.py b/bin/filter_gtf_ndr.py
@@ -1,4 +1,4 @@
-#! /usr/bin/env python3
+#! /usr/bin/env python3 
 from typing import Set
 from GTF import GTF
 
@@ -39,7 +39,7 @@ def filter_count_matrix(file, transcripts, wr):
     print(next(file), file=wr)
     for line in file:
         line_splitted = line.split("\t")
-        if line_splitted[0].startswith("tx.") and line_splitted[0] not in transcripts:
+        if line_splitted[0].startswith("BambuTx") and line_splitted[0] not in transcripts:
             continue
         print(line.rstrip(), file=wr)
 

diff --git a/bin/qc_gtf.py b/bin/qc_gtf.py
@@ -1,4 +1,4 @@
-#! /usr/bin/env python3
+#! /usr/bin/env python3 
 from GTF import GTF
 
 
@@ -55,15 +55,15 @@ def qc_gtf(gtf, gene_counts, ref):
 
         g_id = gene["gene_id"]
         g_biotype = gene["gene_biotype"]
-        g_status = "novel" if g_id.startswith("gene.") else "known"
+        g_status = "novel" if g_id.startswith(('BambuGene','unstranded.Gene')) else "known"
         g_count = gene_counts[g_id]["counts"]  # Counts in all samples
         g_samples = gene_counts[g_id]["validates"]  # Found in x samples
         g_nb_tx = len(gene.transcripts)  # Number of isoforms
 
         # Compute genomic extension with start/end in ref
         ext_5 = 0
         ext_3 = 0
-        if not g_id.startswith("gene."):
+        if not g_id.startswith(('BambuGene','unstranded.Gene')):
             if gene.strand == "+":
                 ext_5 = ref_start_end[gene["gene_id"]]["start"] - gene.start
                 ext_3 = gene.end - ref_start_end[gene["gene_id"]]["end"]
@@ -82,7 +82,7 @@ def qc_gtf(gtf, gene_counts, ref):
         for transcript in gene.transcripts:
             tx_id = transcript["transcript_id"]
             tx_biotype = transcript["transcript_biotype"]
-            tx_status = "novel" if tx_id.startswith("tx.") else "known"
+            tx_status = "novel" if tx_id.startswith("BambuTx") else "known"
             tx_nb_exons = len(transcript.exons)
             tx_length = sum([len(exon) for exon in transcript.exons])
 

diff --git a/modules/bambu/bambu.nf b/modules/bambu/bambu.nf
@@ -1,8 +1,8 @@
 process BAMBU {
-  conda (params.enable_conda ? "bioconda::bioconductor-bambu=2.0.6" : null)
-  container "${ workflow.containerEngine == 'singularity' ? 
-                'https://depot.galaxyproject.org/singularity/bioconductor-bambu:2.0.6--r41h619a076_0' : 
-                'quay.io/biocontainers/bioconductor-bambu:2.0.6--r41h619a076_0' }"
+    conda "conda-forge::r-base=4.0.3 bioconda::bioconductor-bambu=3.0.8 bioconda::bioconductor-bsgenome=1.66.0"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/bioconductor-bambu:3.0.8--r42hc247a5b_0' :
+        'quay.io/biocontainers/bioconductor-bambu:3.0.8--r42hc247a5b_0' }"
   publishDir "$params.outdir/bambu", mode: 'copy'
   cpus params.maxCpu
   memory params.maxMemory

diff --git a/modules/bambu/split.nf b/modules/bambu/split.nf
@@ -8,8 +8,8 @@ process BAMBU_SPLIT_RESULTS {
 
   shell:
   '''
-  grep "tx\\." !{extended_annotation} | awk '$3=="exon"' > novel.gtf
-  grep "gene\\." novel.gtf > novel_genes.gtf
-  grep -v "gene\\." novel.gtf > novel_isoforms.gtf
+  grep "BambuTx" !{extended_annotation} | awk '$3=="exon"' > novel.gtf
+  grep -e "BambuGene" -e "unstranded.Gene" novel.gtf > novel_genes.gtf
+  grep -v -e "BambuGene" -e "unstranded.Gene" novel.gtf > novel_isoforms.gtf
   '''
 }