Trainmultiqc

modules/local/custommodule.nf

@@ -0,0 +1,70 @@
+process CUSTOMMODULE {
+    label 'process_single'
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/jq:1.6':
+        'biocontainers/jq:1.6' }"
+
+
+    input:
+    path(json)
+
+    output:
+    path "*_mqc.tsv",  emit: tsv
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    """
+    echo "# id: 'base content summary'" > gc_summary_mqc.tsv
+    echo "# section_name: 'base and contigs summary statistics'" >> gc_summary_mqc.tsv
+    echo "# format: 'tsv'" >> gc_summary_mqc.tsv
+    echo "# plot_type: 'bargraph'" >> gc_summary_mqc.tsv
+    echo "# description: 'This plot shows a brief summary of each base content/percentage in the query genomes'" >> gc_summary_mqc.tsv
+    echo "# pconfig:" >> gc_summary_mqc.tsv
+    echo "#    id: 'base content summary'" >> gc_summary_mqc.tsv
+    echo "#    title: 'per_base content and percentage'" >> gc_summary_mqc.tsv
+    echo "#    ylab: ''" >> gc_summary_mqc.tsv
+    echo "id\tpercent_A\tpercent_C\tpercent_G\tpercent_T\tpercent_N\tcontig_non_ACGTN" >> gc_summary_mqc.tsv
+    for i in $json
+    do
+        printf "\$(basename \$i .json)\t" >> gc_summary_mqc.tsv
+        jq -r '[.contig_percent_a, .contig_percent_c, .contig_percent_g, .contig_percent_t, .contig_percent_n, .contig_non_acgtn] | @tsv' \$i >> gc_summary_mqc.tsv
+    done
+
+    echo "# id: 'contigs length statistics'" > contig_length_mqc.tsv
+    echo "# section_name: 'base and contigs summary statistics'" >> contig_length_mqc.tsv
+    echo "# format: 'tsv'" >> contig_length_mqc.tsv
+    echo "# plot_type: 'heatmap'" >> contig_length_mqc.tsv
+    echo "# description: 'This plot shows a short statistics abouth the length of contigs in the query genomes'" >> contig_length_mqc.tsv
+    echo "# pconfig:" >> contig_length_mqc.tsv
+    echo "#    id: 'contigs length statistics'" >> contig_length_mqc.tsv
+    echo "#    title: 'contigs length statistics'" >> contig_length_mqc.tsv
+    echo "#    ylab: 'length'" >> contig_length_mqc.tsv
+    echo "id\tTOTALcontiglen\tMINcontiglen\tMAXcontiglen" >> contig_length_mqc.tsv
+    for i in $json
+    do
+        printf "\$(basename \$i .json)\t" >> contig_length_mqc.tsv
+        jq -r '[.total_contig_length, .min_contig_length, .max_contig_length] | @tsv' \$i >> contig_length_mqc.tsv
+    done
+
+    echo "# id: 'contigs number'" > contig_total_mqc.tsv
+    echo "# section_name: 'base and contigs summary statistics'" >> contig_total_mqc.tsv
+    echo "# format: 'tsv'" >> contig_total_mqc.tsv
+    echo "# plot_type: 'heatmap'" >> contig_total_mqc.tsv
+    echo "#    id: 'contigs length statistics'" >> contig_length_mqc.tsv
+    echo "# description: 'This plot shows the total number of contigs in each test with threshold length'" >> contig_total_mqc.tsv
+    echo "# pconfig:" >> contig_total_mqc.tsv
+    echo "#    id: 'number of contigs'" >> contig_total_mqc.tsv
+    echo "#    title: 'number of contigs'" >> contig_total_mqc.tsv
+    echo "#    ylab: 'number'" >> contig_total_mqc.tsv
+    echo "id\ttotalcontigs\tcontigs>1k\tcontigs>10k" >> contig_total_mqc.tsv
+    for i in $json
+    do
+        printf "\$(basename \$i .json)\t" >> contig_total_mqc.tsv
+        jq -r '[.total_contig, .contigs_greater_1k, .contigs_greater_10k] | @tsv' \$i >> contig_total_mqc.tsv
+    done
+    """
+}

modules/local/custommoduletrain.nf

@@ -0,0 +1,43 @@
+process CUSTOMMODULETRAIN {
+    label 'process_single'
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/last:1542--h43eeafb_1':
+        'biocontainers/last:1542--h43eeafb_1' }"
+
+
+    input:
+    path(param_file)
+
+    output:
+    path "*_mqc.tsv",  emit: tsv
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    """
+    echo "# id: 'alignment parameters'" > lastid_mqc.tsv
+    echo "# section_name: 'Alignment parameters and summary'" >> lastid_mqc.tsv
+    echo "# format: 'tsv'" >> lastid_mqc.tsv
+    echo "# plot_type: 'table'" >> lastid_mqc.tsv
+    echo "# description: 'This plot shows the last alignment parameters'" >> lastid_mqc.tsv
+    echo "# pconfig:" >> lastid_mqc.tsv
+    echo "#    id: 'alingment parameters'" >> lastid_mqc.tsv
+    echo "#    title: 'alingment parameters'" >> lastid_mqc.tsv
+    echo "#    ylab: ''" >> lastid_mqc.tsv
+    echo "id\tsubstitution_percent_identity\tlast -t\tlast -a\tlast -A\tlast -b\tlast -B\tlast -S" >> lastid_mqc.tsv
+    for i in $param_file
+    do
+        printf "\$(basename \$i .target.train)\t" >> lastid_mqc.tsv
+        grep 'substitution percent identity' \$i | tail -n 1 | awk '{print \$5}' | tr '\n' '\t' >> lastid_mqc.tsv
+        grep 'last -t' \$i | tail -n 1 | awk '{print \$2}' | sed -e 's/-t//' | tr '\n' '\t' >> lastid_mqc.tsv
+        grep 'last -a' \$i | tail -n 1 | awk '{print \$3}' | tr '\n' '\t' >> lastid_mqc.tsv
+        grep 'last -A' \$i | tail -n 1 | awk '{print \$3}' | tr '\n' '\t' >> lastid_mqc.tsv
+        grep 'last -b' \$i | tail -n 1 | awk '{print \$3}' | tr '\n' '\t' >> lastid_mqc.tsv
+        grep 'last -B' \$i | tail -n 1 | awk '{print \$3}' | tr '\n' '\t' >> lastid_mqc.tsv
+        grep 'last -S' \$i | tail -n 1 | awk '{print \$3}' >> lastid_mqc.tsv
+    done
+    """
+}

subworkflows/local/pairalign_m2m/main.nf

@@ -109,6 +109,8 @@ workflow PAIRALIGN_M2M {
 
     emit:
 
+    train = LAST_TRAIN.out.param_file
+    tsv = LAST_TRAIN.out.tsv
     m2m = LAST_LASTAL_M2M.out.maf
     m2o = LAST_SPLIT_M2O.out.maf
     o2m = LAST_SPLIT_O2M.out.maf

subworkflows/local/pairalign_m2o/main.nf

@@ -73,6 +73,8 @@ workflow PAIRALIGN_M2O {
 
     emit:
 
+    tsv = LAST_TRAIN.out.tsv
+    train = LAST_TRAIN.out.param_file
     m2o = LAST_LASTAL_M2O.out.maf
     o2o = LAST_SPLIT_O2O.out.maf
 }

workflows/pairgenomealign.nf

@@ -5,6 +5,7 @@
 */
 
 include { ASSEMBLYSCAN           } from '../modules/nf-core/assemblyscan/main'
+include { CUSTOMMODULE           } from '../modules/local/custommodule.nf'
 include { PAIRALIGN_M2M          } from '../subworkflows/local/pairalign_m2m/main'
 include { SEQTK_CUTN as SEQTK_CUTN_TARGET  } from '../modules/nf-core/seqtk/cutn/main'
 include { SEQTK_CUTN as SEQTK_CUTN_QUERY  } from '../modules/nf-core/seqtk/cutn/main'
@@ -52,7 +53,15 @@ workflow PAIRGENOMEALIGN {
     ASSEMBLYSCAN (
         ch_samplesheet
     )
-    ch_multiqc_files = ch_multiqc_files.mix(ASSEMBLYSCAN.out.json.collect{it[1]})
+
+    //
+    // MODULE: CUSTOMMODULE
+    //
+    CUSTOMMODULE (
+        ASSEMBLYSCAN.out.json.collect{it[1]}
+    )
+
+    ch_multiqc_files = ch_multiqc_files.mix(CUSTOMMODULE.out.tsv)
     ch_versions = ch_versions.mix(ASSEMBLYSCAN.out.versions.first())
 
     // Prefix id with target genome name before producing alignment files
@@ -67,6 +76,7 @@ workflow PAIRGENOMEALIGN {
         ch_targetgenome,
         ch_samplesheet
     )
+    ch_train = PAIRALIGN_M2O.out.tsv
     } else {
 
     //
@@ -76,8 +86,9 @@ workflow PAIRGENOMEALIGN {
         ch_targetgenome,
         ch_samplesheet
     )
+    ch_train = PAIRALIGN_M2M.out.tsv
     }
-
+    ch_multiqc_files = ch_multiqc_files.mix(ch_train.collect{it[1]})
     // Collate and save software versions
     //
     softwareVersionsToYAML(ch_versions)