multiqc_config.yaml

custom_logo: './bicf_logo.png'
custom_logo_url: 'https/utsouthwestern.edu/labs/bioinformatics/'
custom_logo_title: 'Bioinformatics Core Facility'

report_header_info:
  - Contact Email: 'bicf@utsouthwestern.edu'
  - Application Type: 'RNA-Seq Analytic Pipeline for GUDMAP/RBK'
  - Department: 'Bioinformatic Core Facility, Department of Bioinformatics, University of Texas Southwestern Medical Center'

title: RNA-Seq Analytic Pipeline for GUDMAP/RBK

report_comment: >
  This report has been generated by the <a href="https://doi.org/10.5281/zenodo.3625056">GUDMAP/RBK RNA-Seq Pipeline</a>

top_modules:
  - fastqc:
      name: 'Raw'
      info: 'Replicate Raw fastq QC Results'
  - cutadapt:
      name: 'Trim'
      info: 'Replicate Trim Adapter QC Results'
  - hisat2:
      name: 'Align'
      info: 'Replicate Alignment QC Results'
      path_filters:
        - '*alignSummary*'
  - picard:
      name: 'Dedup'
      info: 'Replicate Alignement Deduplication QC Results'
  - rseqc:
      name: 'Inner Distance'
      info: 'Replicate Paired End Inner Distance Distribution Results'
      path_filters:
        - '*insertSize*'
  - custom_content
  - featureCounts:
      name: 'Count'
      info: 'Replicate Feature Count QC Results'
  - hisat2:
      name: 'Inference: Align'
      info: 'Inference Alignment (1M downsampled reads) QC Results'
      path_filters:
        - '*alignSampleSummary*'
  - rseqc:
      name: 'Inference: Stranded'
      info: '1M Downsampled Reads Strandedness Inference Results'
      path_filters:
        - '*infer_experiment*'

report_section_order:
    run:
      order: 4000
    rid:
      order: 3000
    meta:
      order: 2000
    ref:
      order: 1000
    software_versions:
      order: -1000
    software_references:
      order: -2000

skip_generalstats: true

custom_data:
    run:
        file_format: 'tsv'
        section_name: 'Run'
        description: 'This is the run information'
        plot_type: 'table'
        pconfig:
            id: 'run'
            scale: false
            format: '{}'
        headers:
            Session:
                description: ''
            Session ID:
                description: 'Nextflow session ID'
            Pipeline Version:
                description: 'BICF pipeline version'
            Input:
                description: 'Input overrides'
    rid:
        file_format: 'tsv'
        section_name: 'RID'
        description: 'This is the identifying RIDs'
        plot_type: 'table'
        pconfig:
            id: 'rid'
            scale: false
            format: '{}'
        headers:
            Replicate:
                description: ''
            Replicate RID:
                description: 'Replicate RID'
            Experiment RID:
                description: 'Experiment RID'
            Study RID:
                description: 'Study RID'
    meta:
        file_format: 'tsv'
        section_name: 'Metadata'
        description: 'This is the comparison of infered metadata, submitter provided, and calculated'
        plot_type: 'table'
        pconfig:
            id: 'meta'
            scale: false
            format: '{:,.0f}'
        headers:
            Source:
                description: 'Metadata source'
            Species:
                description: 'Species'
            Ends:
                description: 'Single or paired end sequencing'
            Stranded:
                description: 'Stranded (forward/reverse) or unstranded library prep'
            Spike-in:
                description: 'ERCC spike in'
            Raw Reads:
                description: 'Number of reads of the sequencer'
            Assigned Reads:
                description: 'Final reads after fintering'
            Median Read Length:
                description: 'Average read length'
            Median TIN:
                description: 'Average transcript integrity number'

    ref:
        file_format: 'tsv'
        section_name: 'Reference'
        description: 'This is the reference version information'
        plot_type: 'table'
        pconfig:
            id: 'ref'
            scale: false
            format: '{}'
        headers:
            Species:
                description: 'Reference species'
            Genome Reference Consortium Build:
                description: 'Reference source build'
            Genome Reference Consortium Patch:
                description: 'Reference source patch version'
            GENCODE Annotation Release:
                description: 'Annotation release version'
    tin:
        file_format: 'tsv'
        section_name: 'TIN'
        description: 'This is the distribution of TIN values calculated by the tool RSeQC'
        plot_type: 'bargraph'
        pconfig:
            id: 'tin'
        headers:
            chrom
            1 - 10
            11 - 20
            21 - 30
            31 - 40
            41 - 50
            51 - 60
            61 - 70
            71 - 80
            81 - 90
            91 - 100

sp:
    run:
        fn: "run.tsv"
    rid:
        fn: 'rid.tsv'
    meta:
        fn: 'metadata.tsv'
    ref:
        fn: 'reference.tsv'
    tin:
        fn: '*_tin.hist.tsv'