Remove _R1 suffix from unmapped SE read filename

Author: torres-alexis

RNAseq/Pipeline_GL-DPPD-7101_Versions/GL-DPPD-7101-G.md

@@ -422,8 +422,9 @@ STAR --twopassMode Basic \
  --readFilesIn /path/to/trimmed_forward_reads \
  /path/to/trimmed_reverse_reads # only needed for PE studies
 
-mv <sample_id>_Unmapped.out.mate1 <sample_id>_R1_unmapped.fastq
-mv <sample_id>_Unmapped.out.mate2 <sample_id>_R2_unmapped.fastq  # only needed for PE studies
+mv <sample_id>_Unmapped.out.mate1 <sample_id>_R1_unmapped.fastq  # Only needed for PE studies
+mv <sample_id>_Unmapped.out.mate2 <sample_id>_R2_unmapped.fastq  # Only needed for PE studies
+# mv <sample_id>_Unmapped.out.mate1 <sample_id>_unmapped.fastq    # Only needed for SE studies
 gzip *_unmapped.fastq
 ```
 

RNAseq/Pipeline_GL-DPPD-7115_Versions/GL-DPPD-7115.md

@@ -331,7 +331,7 @@ bowtie2 -x /path/to/bowtie2/index \
 # Rename unmapped reads
 mv <sample_id>.unmapped.fastq.1.gz <sample_id>_R1_unmapped.fastq.gz  # For paired-end data
 mv <sample_id>.unmapped.fastq.2.gz <sample_id>_R2_unmapped.fastq.gz  # For paired-end data
-# mv <sample_id>.unmapped.fastq.gz <sample_id>_R1_unmapped.fastq.gz  # For single-end data
+# mv <sample_id>.unmapped.fastq.gz <sample_id>_unmapped.fastq.gz      # For single-end data
 ```
 
 **Parameter Definitions:**

RNAseq/Workflow_Documentation/NF_RCP/workflow_code/bin/update_assay_table.py

@@ -652,13 +652,13 @@ def add_unmapped_reads_column(df, glds_prefix, runsheet_df=None, mode=""):
             if is_paired:
                 values = [f"{glds_prefix}sample{i+1}_R1_unmapped.fastq.gz,{glds_prefix}sample{i+1}_R2_unmapped.fastq.gz" for i in range(len(df))]
             else:
-                values = [f"{glds_prefix}sample{i+1}_R1_unmapped.fastq.gz" for i in range(len(df))]
+                values = [f"{glds_prefix}sample{i+1}_unmapped.fastq.gz" for i in range(len(df))]
         else:
             # Default mode (STAR)
             if is_paired:
                 values = [f"{glds_prefix}sample{i+1}_R1_unmapped.fastq.gz,{glds_prefix}sample{i+1}_R2_unmapped.fastq.gz" for i in range(len(df))]
             else:
-                values = [f"{glds_prefix}sample{i+1}_R1_unmapped.fastq.gz" for i in range(len(df))]
+                values = [f"{glds_prefix}sample{i+1}_unmapped.fastq.gz" for i in range(len(df))]
     else:
         # Get sample names from assay table
         assay_sample_names = df[sample_col].tolist()

RNAseq/Workflow_Documentation/NF_RCP/workflow_code/bin/vv_bowtie2_alignment.py

@@ -685,7 +685,7 @@ def check_bowtie2_existence(outdir, samples, paired_end, log_path):
                 f"{sample}_R2_unmapped.fastq.gz"
             ])
         else:
-            required_files.append(f"{sample}_R1_unmapped.fastq.gz")
+            required_files.append(f"{sample}_unmapped.fastq.gz")
 
         # Check each required file
         for file_name in required_files:

RNAseq/Workflow_Documentation/NF_RCP/workflow_code/bin/vv_star_alignment.py

@@ -158,7 +158,7 @@ def check_star_output_existence(outdir, samples, paired_end, log_path, assay_suf
             "{sample}/{sample}_R2_unmapped.fastq.gz"
         ])
     else:
-        expected_patterns.append("{sample}/{sample}_R1_unmapped.fastq.gz")
+        expected_patterns.append("{sample}/{sample}_unmapped.fastq.gz")
 
     # Dataset-level files (directly in the alignment directory)
     dataset_files = [

RNAseq/Workflow_Documentation/NF_RCP/workflow_code/modules/align_bowtie2.nf

@@ -40,7 +40,7 @@ process ALIGN_BOWTIE2 {
       mv "${meta.id}.unmapped.fastq.2.gz" "${meta.id}_R2_unmapped.fastq.gz"
     else
       # For single-end data
-      mv "${meta.id}.unmapped.fastq.gz" "${meta.id}_R1_unmapped.fastq.gz"
+      mv "${meta.id}.unmapped.fastq.gz" "${meta.id}_unmapped.fastq.gz"
     fi
 
     echo '"${task.process}":' > versions.yml

RNAseq/Workflow_Documentation/NF_RCP/workflow_code/modules/align_star.nf

@@ -47,7 +47,7 @@ process ALIGN_STAR {
       mv "${ meta.id }/${ meta.id }_Unmapped.out.mate1" "${ meta.id }/${ meta.id }_R1_unmapped.fastq"
       mv "${ meta.id }/${ meta.id }_Unmapped.out.mate2" "${ meta.id }/${ meta.id }_R2_unmapped.fastq"
     else
-      mv "${ meta.id }/${ meta.id }_Unmapped.out.mate1" "${ meta.id }/${ meta.id }_R1_unmapped.fastq"
+      mv "${ meta.id }/${ meta.id }_Unmapped.out.mate1" "${ meta.id }/${ meta.id }_unmapped.fastq"
     fi
     gzip ${ meta.id }/${ meta.id }_*_unmapped.fastq