Feat umi collapse

modules/local/UMICollapse/main.nf

@@ -0,0 +1,37 @@
+process UMICOLLAPSE {
+    tag "$meta.id"
+    label "process_high"
+
+    container 'elly1502/umicollapse:latest'
+
+    input:
+    tuple val(meta), path(bam), path(bai)
+
+    output:
+    tuple val(meta), path("*.bam")             , emit: bam
+    tuple val(meta), path("*.log")             , emit: log
+    path  "versions.yml"                       , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    java -jar /UMICollapse/umicollapse.jar \\
+        bam \\
+        -i $bam \\
+        -o ${prefix}.bam \\
+        $args
+
+    mv .command.log ${prefix}_UMICollapse.log
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        umicollapse: NA
+    END_VERSIONS
+    """
+}
+

modules/local/umitools_dedup/meta.yml → modules/local/UMICollapse/meta.yml

@@ -1,14 +1,13 @@
-name: umitools_dedup
+name: umicollapse
 description: Deduplicate reads based on the mapping co-ordinate and the UMI attached to the read.
 keywords:
-  - umitools
+  - umicollapse
   - deduplication
 tools:
-  - umi_tools:
+  - umicollapse:
       description: >
-        UMI-tools contains tools for dealing with Unique Molecular Identifiers (UMIs)/Random Molecular Tags (RMTs)
-        and single cell RNA-Seq cell barcodes
-      documentation: https://umi-tools.readthedocs.io/en/latest/
+        UMICollapse contains tools for dealing with Unique Molecular Identifiers (UMIs)/Random Molecular Tags (RMTs).
+      documentation: https://github.com/Daniel-Liu-c0deb0t/UMICollapse
       license: ["MIT"]
 input:
   - meta:
@@ -36,28 +35,11 @@ output:
       type: file
       description: BAM file with deduplicated UMIs.
       pattern: "*.{bam}"
-  - tsv_edit_distance:
-      type: file
-      description: Reports the (binned) average edit distance between the UMIs at each position.
-      pattern: "*edit_distance.tsv"
-  - tsv_per_umi:
-      type: file
-      description: UMI-level summary statistics.
-      pattern: "*per_umi.tsv"
-  - tsv_umi_per_position:
-      type: file
-      description: Tabulates the counts for unique combinations of UMI and position.
-      pattern: "*per_position.tsv"
-  - log:
-      type: file
-      description: Log file
-      pattern: "*.log"
   - versions:
       type: file
       description: File containing software versions
       pattern: "versions.yml"
 
 authors:
-  - "@drpatelh"
-  - "@grst"
-  - "@klkeys"
+  - "@Daniel-Liu-c0deb0t"
+  - "@CharlotteAnne"

modules/local/clipqc/templates/clipqc.py

@@ -89,18 +89,19 @@
 
     with open(dedup_log, 'r') as logfile:
 
-        exp = re.sub('.log', '', os.path.basename(dedup_log))
+        exp = re.sub('_UMICollapse.log', '', os.path.basename(dedup_log))
 
         lines = logfile.readlines()
 
-        input_reads = [i for i in lines if 'INFO Reads: Input Reads:' in i]
+        input_reads = [i for i in lines if 'Number of input reads' in i]
         input_reads = int(re.findall(r'\\d+', input_reads[0])[-1])
 
-        output_reads = [i for i in lines if 'Number of reads out:' in i]
+        output_reads = [i for i in lines if 'Number of reads after deduplicating' in i]
         output_reads = int(re.findall(r'\\d+', output_reads[0])[-1])
 
-        mean_umis = [i for i in lines if 'Mean number of unique UMIs per position:' in i]
-        mean_umis = float(re.findall(r'\\d+', mean_umis[0])[-1])
+        mean_umis = [i for i in lines if 'Average number of UMIs per alignment position' in i]
+        mean_umis = float(re.findall(r'\\d+\\.*\\d*', mean_umis[0])[-1])
+        mean_umis = np.round(mean_umis, 2)
 
         dedup['exp'].append(exp)
         dedup['input_reads'].append(input_reads)

subworkflows/clipqualitycheck.nf

@@ -15,7 +15,7 @@ workflow CLIP_QUALITY_CHECK {
         trimgalore_log
         bowtie_align_log
         star_align_log_final
-        umitools_dedup_log
+        umicollapse_log
         crosslinks
         icount_peaks
         paraclu_peaks
@@ -26,7 +26,7 @@ workflow CLIP_QUALITY_CHECK {
     CLIPQC (
         bowtie_align_log.map(strip_meta).collect(),
         star_align_log_final.map(strip_meta).collect(),
-        umitools_dedup_log.map(strip_meta).collect(),
+        umicollapse_log.map(strip_meta).collect(),
         crosslinks.map(strip_meta).collect(),
         icount_peaks.map(strip_meta).collect(),
         paraclu_peaks.map(strip_meta).collect(),

subworkflows/primaryclipanalysis.config

@@ -1,6 +1,6 @@
 includeConfig '../conf/base.config'
 
-def umi_separator = params.containsKey("umi_separator") ? params.umi_separator : "rbc"
+def umi_separator = params.containsKey("umi_separator") ? params.umi_separator : "rbc:"
 
 process {
     withName: "TRIMGALORE" {
@@ -15,15 +15,11 @@ process {
         ext.args = "--readFilesCommand zcat --outSAMtype BAM SortedByCoordinate --quantMode TranscriptomeSAM --outFilterMultimapNmax 1 --outFilterMultimapScoreRange 1 --outSAMattributes All --alignSJoverhangMin 8 --alignSJDBoverhangMin 1 --outFilterType BySJout --alignIntronMin 20 --alignIntronMax 1000000 --outFilterScoreMin 10  --alignEndsType Extend5pOfRead1 --twopassMode Basic"
     }
 
-    withName: "UMITOOLS_DEDUP" {
-        ext.args = "--umi-separator='${umi_separator}:'"
+    withName: "UMICOLLAPSE" {
+        ext.args = "--umi-sep '${umi_separator}' --two-pass"
     }
 
-    withName: "TOME_UMITOOLS_DEDUP" {
-        ext.args = "--umi-separator='${umi_separator}:'"
-    }
-
-    withName: "GET_UMI_LENGTH" {
-        ext.args = "${umi_separator}:"
+    withName: "TOME_UMICOLLAPSE" {
+        ext.args = "--umi-sep '${umi_separator}' --two-pass"
     }
 }

subworkflows/primaryclipanalysis.json

@@ -31,7 +31,7 @@
                     "format": "text",
                     "required": false,
                     "default": "rbc",
-                    "description": "Separator used in UMI-tools Dedup."
+                    "description": "Separator used in UMICollapse."
                 }
             }
         }