Simplify circrna_discovery subworkflow

bin/merge_tools.py

@@ -11,19 +11,14 @@
 
 args = parser.parse_args()
 
-columns = ['chr', 'start', 'end', 'strand', 'count']
+columns = ['chr', 'start', 'end', 'name', 'count', 'strand']
 dfs = [pd.read_csv(bed, sep='\t', header=None, names=columns) for bed in args.beds]
 df = pd.concat(dfs)
 
 df['tool_count'] = 1
-
-df = df.groupby(['chr', 'start', 'end', 'strand']).agg({'count': args.duplicates_fun,
+df = df.groupby(['chr', 'start', 'end', 'strand', 'name']).agg({'count': args.duplicates_fun,
                                                         'tool_count': 'sum'}).reset_index()
 df = df[df['tool_count'] >= args.tool_filter]
 
-df.drop('tool_count', axis=1, inplace=True)
-df["name"] = df["chr"] + ":" + df["start"].astype(str) + "-" + df["end"].astype(str) + ":" + df["strand"]
-
-df = df[['chr', 'start', 'end', 'name', 'count', 'strand']]
-
+df = df[columns]
 df.to_csv(args.output, sep='\t', index=False, header=False)

modules/local/circrna_finder/main.nf

@@ -0,0 +1,34 @@
+process CIRCRNA_FINDER {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda "bioconda::circrna_finder=1.2"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/circrna_finder%3A1.2--pl5321hdfd78af_1' :
+        'biocontainers/circrna_finder:1.2--pl5321hdfd78af_1' }"
+
+    input:
+    tuple val(meta), path(star_input, stageAs: 'input/')
+
+    output:
+    tuple val(meta), path("${prefix}.filteredJunctions.bed"), emit: results
+    path  "versions.yml"                                    , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    prefix = task.ext.prefix ?: "${meta.id}"
+    def VERSION = 'v1.2'
+    """
+    postProcessStarAlignment.pl --starDir input/ --outDir ./
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        awk: \$(awk --version | head -n1 | cut -d' ' -f3 | sed 's/,//g' )
+        cat: \$(cat --version | head -n 1 | sed -e 's/cat (GNU coreutils) //')
+        circRNA_finder: $VERSION
+    END_VERSIONS
+    """
+}

modules/local/count_matrix/combined/main.nf → modules/local/count_matrix/merge_samples/main.nf

@@ -1,4 +1,4 @@
-process COUNTS_COMBINED {
+process MERGE_SAMPLES {
     label "process_single"
 
     conda "bioconda::pandas=1.5.2"
@@ -16,7 +16,7 @@ process COUNTS_COMBINED {
 
     script:
     """
-    counts_combined.py --beds ${beds} --out_bed merged_counts.bed --out_tsv merged_counts.tsv
+    merge_samples.py --beds ${beds} --out_bed merged_counts.bed --out_tsv merged_counts.tsv
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":