Adapt processes and naming of processes

bin/extract_umis.py

@@ -78,6 +78,13 @@ def parse_args(argv):
         required=False,
         help="Output directory"
     )
+    parser.add_argument(
+        "--output_filename",
+        dest="OUT_FILENAME",
+        type=str,
+        required=False,
+        help="Output filename"
+    )
     parser.add_argument(
         "--output_format",
         dest="OUT_FORMAT",
@@ -324,7 +331,7 @@ def extract_umis(
     input_file = args.INPUT_FA
     umi_fwd = args.FWD_UMI
     umi_rev = args.REV_UMI
-    output_file_name = "detected_umis"
+    output_file_name = args.OUT_FILENAME
     format = args.OUT_FORMAT
 
     output_file = os.path.join(

bin/filter_reads.py

@@ -69,7 +69,20 @@ def parse_args(argv):
     )
 
     parser.add_argument(
-        "-o", "--output", dest="OUT", type=str, required=False, help="Output folder"
+        "-o",
+        "--output",
+        dest="OUT",
+        type=str,
+        required=False,
+        help="Output folder"
+    )
+
+    parser.add_argument(
+        "--output_filename",
+        dest="OUT_FILENAME",
+        type=str,
+        required=False,
+        help="Output filename"
     )
 
     parser.add_argument(
@@ -118,9 +131,9 @@ def parse_bed(bed_regions):
             return region
 
 
-def write_read(read, output, region, type, format):
+def write_read(read, output, type, format):
     output_fastx = os.path.join(
-        output, "{}_{}.{}".format(region["name"], type, format)
+        output, "{}.{}".format(type, format)
     )
 
     # see if appending line is no problem by running it with nextflow (Otherwise delete files before appending for the first time)
@@ -178,6 +191,7 @@ def filter_reads(args):
     output = args.OUT
     out_format = args.OUT_FORMAT
     tsv = args.TSV
+    output_filename = args.OUT_FILENAME
     stats_out_filename = "umi_filter_reads_stats"
 
     n_non_reads = 0
@@ -207,38 +221,38 @@ def filter_reads(args):
             n_total += 1
             if read.is_unmapped:
                 n_unmapped += 1
-                write_read(read, output, region, "unmapped", out_format)
+                write_read(read, output, "unmapped", out_format)
                 continue
 
             if read.is_secondary:
                 n_secondary += 1
                 if not incl_sec:
-                    write_read(read, output, region, "secondary", out_format)
+                    write_read(read, output, "secondary", out_format)
                     continue
 
             if read.is_supplementary:
                 n_supplementary += 1
-                write_read(read, output, region, "supplementary", out_format)
+                write_read(read, output, "supplementary", out_format)
                 continue
 
             n_ontarget += 1
             if read.query_alignment_length < (read.query_length - 2 * adapter_length):
                 n_concatamer += 1
-                write_read(read, output, region, "concatamer", out_format)
+                write_read(read, output, "concatamer", out_format)
                 continue
 
             if read.query_alignment_length < (region_length * min_overlap):
                 n_short += 1
-                write_read(read, output, region, "short", out_format)
+                write_read(read, output, "short", out_format)
                 continue
 
             if read.query_length > (region_length * ( 2 - min_overlap) + 2 * adapter_length):
                 n_long += 1
-                write_read(read, output, region, "long", out_format)
+                write_read(read, output, "long", out_format)
                 continue
 
             n_reads_region += 1
-            write_read(read, output, region, "filtered", out_format)
+            write_read(read, output, output_filename, out_format)
 
     if tsv:
         stats_out_filename = os.path.join(

lib/processes/detect_umi_fastq.nf

@@ -20,6 +20,7 @@ process DETECT_UMI_FASTQ {
         --max-error ${params.umi_errors} \
         --adapter_length ${params.adapter_length} \
         --output_format ${params.output_format} \
+        --output_filename ${fastq.baseName}_umis \
         $write_report \
         -o . ${fastq}
     """

lib/processes/merge_input.nf

@@ -1,17 +1,17 @@
-merged_fastq="merged.fastq"
 process MERGE_FASTQ {
 
     input:
         tuple val ( sample ), path ( fastq_path )
 
     output:
-        tuple val( "${sample}" ), val( "target" ), path( "${merged_fastq}"), emit: merged_fastq
+        tuple val( "${sample}" ), val( "target" ), path( "*fastq" ), emit: merged_fastq
 
     script:
+    def fastq_name = params.live ? "filtered_$fastq_path.Name" : "merged.fastq"
     """
         catfishq \
             --min-length ${params.min_read_length} \
             --min-qscore ${params.min_qscore} \
-            ${fastq_path} > ${merged_fastq}
+            ${fastq_path} > ${fastq_name}
     """
 }

lib/processes/split_reads.nf

@@ -10,7 +10,7 @@ process SPLIT_READS {
 
     output:
         path "*.tsv"
-        tuple val ( "${sample}" ), val( "target" ), path ( "*filtered.${params.output_format}" ), emit: split_reads_fastx
+        tuple val ( "${sample}" ), val( "target" ), path ( "${bam.baseName}.${params.output_format}" ), emit: split_reads_fastx
         path "*${params.output_format}"
 
     script:
@@ -21,6 +21,7 @@ process SPLIT_READS {
           --min_overlap ${params.min_overlap} \
           --output_format ${params.output_format} \
           --adapter_length ${params.adapter_length} \
+          --output_filename ${bam.baseName} \
           $include_secondary_reads \
           $write_report \
           -o . ${bed} \