Viralrecon: add report example

public/examples/viralrecon/multiqc_config_illumina.yml

@@ -0,0 +1,308 @@
+report_comment: >
+  This report has been generated by the <a href="https://github.com/nf-core/viralrecon" target="_blank">nf-core/viralrecon</a>
+  analysis pipeline. For information about how to interpret these results, please see the
+  <a href="https://github.com/nf-core/viralrecon" target="_blank">documentation</a>.
+
+data_format: "yaml"
+
+max_table_rows: 10000
+
+run_modules:
+  - custom_content
+  - fastqc
+  - fastp
+  - kraken
+  - bowtie2
+  - samtools
+  - mosdepth
+  - bcftools
+  - snpeff
+  - quast
+  - pangolin
+  - cutadapt
+
+module_order:
+  - fastqc:
+      name: "PREPROCESS: FastQC (raw reads)"
+      info: "This section of the report shows FastQC results for the raw reads before adapter trimming."
+      path_filters:
+        - "*/fastqc/*.zip"
+  - fastp:
+      name: "PREPROCESS: fastp (adapter trimming)"
+      info: "This section of the report shows fastp results for reads after adapter and quality trimming."
+  - kraken:
+      name: "PREPROCESS: Kraken 2"
+      info: "This section of the report shows Kraken 2 classification results for reads after adapter trimming with fastp."
+  - bowtie2:
+      name: "VARIANTS: Bowtie 2"
+      info: "This section of the report shows Bowtie 2 mapping results for reads after adapter trimming and quality trimming."
+  - samtools:
+      name: "VARIANTS: SAMTools (raw)"
+      anchor: "samtools_bowtie2"
+      info: "This section of the report shows SAMTools counts/statistics after mapping with Bowtie 2."
+      path_filters:
+        - "*/bowtie2/*"
+  - samtools:
+      name: "VARIANTS: SAMTools (iVar)"
+      anchor: "samtools_ivar"
+      info: "This section of the report shows SAMTools counts/statistics after primer sequence removal with iVar."
+      path_filters:
+        - "*/ivar_trim/*"
+  - samtools:
+      name: "VARIANTS: SAMTools (MarkDuplicates)"
+      anchor: "samtools_markduplicates"
+      info: "This section of the report shows SAMTools counts/statistics after duplicate removal with picard MarkDuplicates."
+      path_filters:
+        - "*/picard_markduplicates/*"
+  - mosdepth:
+      name: "VARIANTS: mosdepth"
+      info: "This section of the report shows genome-wide coverage metrics generated by mosdepth."
+  - pangolin:
+      name: "VARIANTS: Pangolin"
+      info: "This section of the report shows Pangolin lineage analysis results for the called variants."
+      path_filters:
+        - "*/variants/*.pangolin.csv"
+  - bcftools:
+      name: "VARIANTS: BCFTools"
+      info: "This section of the report shows BCFTools stats results for the called variants."
+      path_filters:
+        - "*/variants/*.txt"
+  - snpeff:
+      name: "VARIANTS: SnpEff"
+      info: "This section of the report shows SnpEff results for the called variants."
+      path_filters:
+        - "*/variants/*.csv"
+  - quast:
+      name: "VARIANTS: QUAST"
+      anchor: "quast_variants"
+      info: "This section of the report shows QUAST QC results for the consensus sequence."
+      path_filters:
+        - "*/variants/*.tsv"
+  - cutadapt:
+      name: "ASSEMBLY: Cutadapt (primer trimming)"
+      info: "This section of the report shows Cutadapt results for reads after primer sequence trimming."
+  - quast:
+      name: "ASSEMBLY: QUAST (SPAdes)"
+      anchor: "quast_spades"
+      info: "This section of the report shows QUAST results from SPAdes de novo assembly."
+      path_filters:
+        - "*/assembly_spades/*.tsv"
+  - quast:
+      name: "ASSEMBLY: QUAST (Unicycler)"
+      anchor: "quast_unicycler"
+      info: "This section of the report shows QUAST results from Unicycler de novo assembly."
+      path_filters:
+        - "*/assembly_unicycler/*.tsv"
+  - quast:
+      name: "ASSEMBLY: QUAST (minia)"
+      anchor: "quast_minia"
+      info: "This section of the report shows QUAST results from minia de novo assembly."
+      path_filters:
+        - "*/assembly_minia/*.tsv"
+
+report_section_order:
+  fail_mapped_reads:
+    after: summary_variants_metrics
+  fail_mapped_samples:
+    after: summary_variants_metrics
+  summary_assembly_metrics:
+    before: summary_variants_metrics
+  amplicon_heatmap:
+    before: summary_assembly_metrics
+  ivar_variants:
+    before: mosdepth
+  software_versions:
+    order: -1001
+  nf-core-viralrecon-summary:
+    order: -1002
+
+bcftools:
+  collapse_complementary_changes: true
+
+# See https://github.com/ewels/MultiQC_TestData/blob/master/data/custom_content/with_config/table_headerconfig/multiqc_config.yaml
+custom_data:
+  amplicon_heatmap:
+    section_name: "Amplicon coverage heatmap"
+    description: "Heatmap to show median log10(coverage+1) per amplicon across samples."
+    plot_type: "heatmap"
+    pconfig:
+      id: "amplicon_heatmap"
+      xTitle: "Amplicon"
+      namespace: "Heatmap to show median log10(coverage+1) per amplicon across samples"
+      square: False
+      colstops:
+        [
+          [0, "#440154"],
+          [0.05, "#471365"],
+          [0.1, "#482475"],
+          [0.15, "#463480"],
+          [0.2, "#414487"],
+          [0.25, "#3b528b"],
+          [0.3, "#355f8d"],
+          [0.35, "#2f6c8e"],
+          [0.4, "#2a788e"],
+          [0.45, "#25848e"],
+          [0.5, "#21918c"],
+          [0.55, "#1e9c89"],
+          [0.6, "#22a884"],
+          [0.65, "#2fb47c"],
+          [0.7, "#44bf70"],
+          [0.75, "#5ec962"],
+          [0.8, "#7ad151"],
+          [0.85, "#9bd93c"],
+          [0.9, "#bddf26"],
+          [0.95, "#dfe318"],
+          [1, "#fde725"],
+        ]
+  summary_variants_metrics:
+    section_name: "Variant calling metrics"
+    description: "generated by the nf-core/viralrecon pipeline"
+    plot_type: "table"
+    headers:
+      "# Input reads":
+        description: "Total number of reads in raw fastq file"
+        format: "{:,.0f}"
+      "% Non-host reads (Kraken 2)":
+        description: "Total number of non-host reads identified by Kraken2"
+        format: "{:,.2f}"
+      "# Trimmed reads (fastp)":
+        description: "Total number of reads remaining after adapter/quality trimming with fastp"
+        format: "{:,.0f}"
+      "# Mapped reads":
+        description: "Total number of Bowtie2 mapped reads relative to the viral genome"
+        format: "{:,.0f}"
+      "% Mapped reads":
+        description: "Percentage of Bowtie2 mapped reads relative to the viral genome"
+        format: "{:,.2f}"
+      "# Trimmed reads (iVar)":
+        description: "Total number of reads remaining after primer trimming with iVar"
+        format: "{:,.0f}"
+      "Coverage median":
+        description: "Median coverage calculated by mosdepth"
+        format: "{:,.2f}"
+      "% Coverage > 1x":
+        description: "Coverage > 1x calculated by mosdepth"
+        format: "{:,.2f}"
+      "% Coverage > 10x":
+        description: "Coverage > 10x calculated by mosdepth"
+        format: "{:,.2f}"
+      "# SNPs":
+        description: "Total number of SNPs"
+        format: "{:,.0f}"
+      "# INDELs":
+        description: "Total number of INDELs"
+        format: "{:,.0f}"
+      "# Missense variants":
+        description: "Total number of variants identified as missense mutations with SnpEff"
+        format: "{:,.0f}"
+      "# Ns per 100kb consensus":
+        description: "Number of N bases per 100kb in consensus sequence"
+        format: "{:,.2f}"
+      "Pangolin lineage":
+        description: "Pangolin lineage inferred from the consensus sequence"
+      "Nextclade clade":
+        description: "Nextclade clade inferred from the consensus sequence"
+    pconfig:
+      id: "summary_variants_metrics_plot"
+      table_title: "Variant calling metrics"
+      namespace: "Variant calling metrics"
+      only_defined_headers: False
+      format: "{:.0f}"
+  summary_assembly_metrics:
+    section_name: "De novo assembly metrics"
+    description: "generated by the nf-core/viralrecon pipeline"
+    plot_type: "table"
+    headers:
+      "# Input reads":
+        description: "Total number of reads in raw fastq file"
+        format: "{:,.0f}"
+      "# Trimmed reads (Cutadapt)":
+        description: "Total number of reads remaining after adapter/quality trimming with fastp"
+        format: "{:,.0f}"
+      "% Non-host reads (Kraken 2)":
+        description: "Total number of non-host reads identified by Kraken2"
+        format: "{:,.2f}"
+      "# Contigs (SPAdes)":
+        description: "Total number of contigs in SPAdes assembly as calculated by QUAST"
+        format: "{:,.0f}"
+      "Largest contig (SPAdes)":
+        description: "Size of largest contig in SPAdes assembly as calculated by QUAST"
+        format: "{:,.0f}"
+      "% Genome fraction (SPAdes)":
+        description: "% genome fraction for SPAdes assembly as calculated by QUAST"
+        format: "{:,.2f}"
+      "N50 (SPAdes)":
+        description: "N50 metric for SPAdes assembly as calculated by QUAST"
+        format: "{:,.2f}"
+      "# Contigs (Unicycler)":
+        description: "Total number of contigs in Unicycler assembly as calculated by QUAST"
+        format: "{:,.0f}"
+      "Largest contig (Unicycler)":
+        description: "Size of largest contig in Unicycler assembly as calculated by QUAST"
+        format: "{:,.0f}"
+      "% Genome fraction (Unicycler)":
+        description: "% genome fraction for Unicycler assembly as calculated by QUAST"
+        format: "{:,.2f}"
+      "N50 (Unicycler)":
+        description: "N50 metric for Unicycler assembly as calculated by QUAST"
+        format: "{:,.2f}"
+      "# Contigs (minia)":
+        description: "Total number of contigs in minia assembly as calculated by QUAST"
+        format: "{:,.0f}"
+      "Largest contig (minia)":
+        description: "Size of largest contig in minia assembly as calculated by QUAST"
+        format: "{:,.0f}"
+      "% Genome fraction (minia)":
+        description: "% genome fraction for minia assembly as calculated by QUAST"
+        format: "{:,.2f}"
+      "N50 (minia)":
+        description: "N50 metric for minia assembly as calculated by QUAST"
+        format: "{:,.2f}"
+    pconfig:
+      id: "summary_assembly_metrics_plot"
+      table_title: "De novo assembly metrics"
+      namespace: "De novo assembly metrics"
+      only_defined_headers: False
+      format: "{:.0f}"
+  fail_mapped_reads:
+    section_name: "WARNING: Fail Reads Check"
+    description: "List of samples that had no reads after adapter trimming, and hence were ignored for the downstream processing steps."
+    plot_type: "table"
+    pconfig:
+      id: "fail_mapped_reads_table"
+      table_title: "Samples failed read threshold"
+      namespace: "Samples failed read threshold"
+      format: "{:,.0f}"
+  fail_mapped_samples:
+    section_name: "WARNING: Fail Alignment Check"
+    description: "List of samples that failed the Bowtie2 minimum mapped reads threshold specified via the '--min_mapped_reads' parameter, and hence were ignored for the downstream processing steps."
+    plot_type: "table"
+    pconfig:
+      id: "fail_mapped_samples_table"
+      table_title: "Samples failed mapped read threshold"
+      namespace: "Samples failed mapping read threshold"
+      format: "{:,.0f}"
+
+extra_fn_clean_exts:
+  - ".markduplicates"
+  - ".unclassified"
+  - "_MN908947.3"
+  - " MN908947.3"
+
+extra_fn_clean_trim:
+  - "Consensus_"
+
+# # Customise the module search patterns to speed up execution time
+# #  - Skip module sub-tools that we are not interested in
+# #  - Replace file-content searching with filename pattern searching
+# #  - Don't add anything that is the same as the MultiQC default
+# # See https://multiqc.info/docs/#optimise-file-search-patterns for details
+sp:
+  fastp:
+    fn: "*.fastp.json"
+  bowtie2:
+    fn: "*.bowtie2.log"
+  mosdepth/global_dist:
+    fn: "*.global.dist.txt"
+  cutadapt:
+    fn: "*.cutadapt.log"