Update to Innuca's recipe modules

changelog.md

@@ -11,10 +11,13 @@
 ### New components
 
 - `Kraken2`: Taxonomic identification on FastQ files
+- `insert_size`: calculates the inser size of a sample from mapping the reads
+back to an assembly
 
 ### Bug fixes
 
-- Fix bug in `momps`component related to added in the introduction of the clear input parameter
+- Fix bug in `momps`component related to added in the introduction of the clear 
+input parameter
 - Fixed bug with the `-ft` parameters not retrieving the dockerhub tags for 
 all the components.
 - Fixed bug in the `megahit` process where the fastg mode would break the process
@@ -25,7 +28,12 @@ position in the `nextflow run` command inside the .nextflow.log file.
 
 ### Minor/Other changes
 
-- Added option to `dengue_typing` to retrive closest referece sequence and link it 
+- `integrity_coverage` now checks the integrity of the compressed read files with the 
+appropriate software. 
+- `mlst` components now has it's own process template
+- `assembly_mapping` now verifies the percentage of mapped reads, issuing a quality 
+control warning when it falls bellow 95% 
+- Added option to `dengue_typing` to retrieve closest reference sequence and link it 
 with a secondary channel into `mafft`
 - New version of DEN-IM recipe
 - Now prints an ordered list of components

flowcraft/generator/components/mapping.py

@@ -5,15 +5,16 @@
 
 
 class Bowtie(Process):
-    """bowtie2 to align short paired-end sequencing reads to long reference sequences
+    """
+    bowtie2 to align short paired-end sequencing reads to long reference sequences
 
         This process is set with:
 
             - ``input_type``: fastq
             - ``output_type``: bam
             - ``ptype``: mapping
 
-        """
+    """
 
     def __init__(self, **kwargs):
 
@@ -65,7 +66,8 @@ def __init__(self, **kwargs):
 
 
 class RetrieveMapped(Process):
-    """Samtools process to  to align short paired-end sequencing reads to
+    """
+    Samtools process to  to align short paired-end sequencing reads to
     long reference sequences
 
         This process is set with:
@@ -74,7 +76,7 @@ class RetrieveMapped(Process):
             - ``output_type``: fastq
             - ``ptype``: mapping
 
-        """
+    """
 
     def __init__(self, **kwargs):
 
@@ -108,3 +110,64 @@ def __init__(self, **kwargs):
         self.status_channels = [
             "retrieve_mapped"
         ]
+
+
+class InsertSize(Process):
+    """
+    Determines the sequencing insert size by reads mapping
+    to an assembly file
+
+        This process is set with:
+
+            - ``input_type``: fasta
+            - ``output_type``:
+            - ``ptype``: mapping
+
+        It contains one **secondary channel link end**:
+
+        - ``MAIN_fq`` (alias: ``_MAIN_assembly``): Receives the FastQ files
+        from the last process with ``fastq`` output type.
+
+    """
+
+    def __init__(self, **kwargs):
+
+        super().__init__(**kwargs)
+
+        self.input_type = "fasta"
+        self.output_type = None
+
+        self.link_end.append({"link": "__fastq", "alias": "_LAST_fastq"})
+
+        self.params = {
+            "distribution_plot": {
+                "default": "false",
+                "description": "Produces a distribution plot of the insert sizes."
+            },
+            "clearInput": {
+                "default": "false",
+                "description":
+                    "Permanently removes temporary input files. This option "
+                    "is only useful to remove temporary files in large "
+                    "workflows and prevents nextflow's resume functionality. "
+                    "Use with caution."
+            }
+        }
+
+        self.directives = {
+            "assembly_mapping_statistics": {
+                "container": "flowcraft/bowtie2_samtools",
+                "version": "1.0.0-1",
+                "memory": "{1.Gb*task.cpus*task.attempt}",
+                "cpus": 1
+            },
+            "insert_size": {
+                "container": "flowcraft/plotly",
+                "version": "3.5.0-1"
+            }
+        }
+
+        self.status_channels = [
+            "assembly_mapping_statistics",
+            "insert_size"
+        ]

flowcraft/generator/components/mlst.py

@@ -27,7 +27,8 @@ def __init__(self, **kwargs):
         self.output_type = "fasta"
 
         self.directives = {"mlst": {
-            "container": "ummidock/mlst",
+            "container": "flowcraft/mlst",
+            "version": "2.15.1-1"
         }}
 
         self.params = {

flowcraft/generator/components/reads_quality_control.py

@@ -45,6 +45,11 @@ def __init__(self, **kwargs):
 
         self.link_start.extend(["SIDE_phred", "SIDE_max_len"])
 
+        self.directives = {"integrity_coverage": {
+            "container": "flowcraft/integrity_coverage",
+            "version": "1.0-1"
+        }}
+
 
 class CheckCoverage(Process):
     """Process template interface for additional integrity_coverage process
@@ -112,7 +117,7 @@ def __init__(self, **kwargs):
                 "cpus": 4,
                 "memory": "'1GB'",
                 "container": "flowcraft/true_coverage",
-                "version": "3.2-1"
+                "version": "3.3-1"
             }
         }
 

flowcraft/generator/templates/insert_size.nf

@@ -0,0 +1,72 @@
+IN_plot{{ pid }} = params.distribution_plot{{ param_id }} ? "True" : "False"
+
+
+process assembly_mapping_statistics_{{ pid }} {
+
+    // Send POST request to platform
+    {% include "post.txt" ignore missing %}
+
+    tag { sample_id }
+
+    input:
+    set sample_id, file(assembly), file(fastq) from {{ input_channel }}.join(_LAST_fastq_{{ pid }})
+
+    output:
+    set sample_id, file("samtools_stats.txt") into IN_insert_size_{{ pid }}
+    {% with task_name="assembly_mapping_statistics" %}
+    {%- include "compiler_channels.txt" ignore missing -%}
+    {% endwith %}
+
+    script:
+    """
+    {
+        echo [DEBUG] BUILDING BOWTIE INDEX FOR ASSEMBLY: $assembly >> .command.log 2>&1
+        bowtie2-build --threads ${task.cpus} $assembly genome_index >> .command.log 2>&1
+
+        echo [DEBUG] MAPPING READS FROM $fastq >> .command.log 2>&1
+        bowtie2 -q --very-fast --threads ${task.cpus} -x genome_index -1 ${fastq[0]} -2 ${fastq[1]} \
+        --fr -I 0 -X 2000 --no-discordant --no-mixed --no-unal -S alignment.sam >> .command.log 2>&1
+
+        echo [DEBUG] GET STATISTICS FROM SAM: alignment.sam
+        samtools stats alignment.sam > samtools_stats.txt
+
+        if [ -f "alignment.sam" ] && [ -f "samtools_stats.txt" ]
+        then
+            echo pass > .status
+        else
+            echo fail > .status
+        fi
+
+        echo -n "" > .report.json
+        echo -n "" > .versions
+    } || {
+        echo fail > .status
+    }
+    """
+}
+
+
+process insert_size_{{ pid }} {
+
+    // Send POST request to platform
+    {% include "post.txt" ignore missing %}
+
+    tag { sample_id }
+
+    publishDir "results/assembly/insert_size_{{ pid }}/"
+
+    input:
+    set sample_id, file(sam_stats) from IN_insert_size_{{ pid }}
+    val plot from IN_plot{{ pid }}
+
+    output:
+    file ("*insert_size_report.tab")
+    file ("*insert_size_distribution.html") optional true
+    {% with task_name="insert_size" %}
+    {%- include "compiler_channels.txt" ignore missing -%}
+    {% endwith %}
+
+    script:
+    template "insert_size.py"
+
+}

flowcraft/generator/templates/mlst.nf

@@ -1,3 +1,9 @@
+// If a species is not provided, it bypasses the species verification
+if (params.mlstSpecies{{ param_id }} == null){
+   IN_expected_species_{{ pid }} = Channel.value("PASS")
+} else {
+    IN_expected_species_{{ pid }} = Channel.value(params.mlstSpecies{{ param_id }})
+}
 
 process mlst_{{ pid }} {
 
@@ -10,6 +16,7 @@ process mlst_{{ pid }} {
 
     input:
     set sample_id, file(assembly) from {{ input_channel }}
+    val expected_species from IN_expected_species_{{ pid }}
 
     output:
     file '*.mlst.txt' into LOG_mlst_{{ pid }}
@@ -19,30 +26,8 @@ process mlst_{{ pid }} {
     {% endwith %}
 
     script:
-    """
-    {
-        expectedSpecies=${params.mlstSpecies{{ param_id }}}
-        mlst $assembly >> ${sample_id}.mlst.txt
-        mlstSpecies=\$(cat *.mlst.txt | cut -f2)
-        json_str="{'expectedSpecies':\'\$expectedSpecies\',\
-            'species':'\$mlstSpecies',\
-            'st':'\$(cat *.mlst.txt | cut -f3)',\
-            'tableRow':[{'sample':'${sample_id}','data':[\
-                {'header':'MLST species','value':'\$mlstSpecies','table':'typing'},\
-                {'header':'MLST ST','value':'\$(cat *.mlst.txt | cut -f3)','table':'typing'}]}]}"
-        echo \$json_str > .report.json
-
-        if [ ! \$mlstSpecies = \$expectedSpecies ];
-        then
-            printf fail > .status
-        else
-            printf pass > .status
-        fi
-
-    } || {
-        printf fail > .status
-    }
-    """
+    template "run_mlst.py"
+
 }
 
 process compile_mlst_{{ pid }} {