name: atacseq
version: "2.1.2"
description: "Chromatin accessibility analysis and peak calling"

# Documentation and source - NOTE: Update version in URLs when upgrading pipeline
urls:
  documentation: "https://nf-co.re/atacseq/{version}/"
  parameters: "https://nf-co.re/atacseq/{version}/parameters/"
  output_docs: "https://nf-co.re/atacseq/{version}/docs/output/"
  github: "https://github.com/nf-core/atacseq"
  releases: "https://github.com/nf-core/atacseq/releases"

data_types:
  - ATAC-seq
  - chromatin accessibility
  - open chromatin

detection_hints:
  filename:
    - atac
    - atacseq
    - chromatin
    - accessibility
  directory:
    - atac
    - atacseq
    - chromatin
    - epigenome
    - epigenetics

samplesheet:
  input_types:
    - fastq

  columns:
    - name: sample
      required: true
      type: string
      inference: filename
      description: "Condition/group identifier (replicates share same name)"

    - name: fastq_1
      required: true
      type: path
      inference: auto
      description: "Absolute path to R1 FASTQ"

    - name: fastq_2
      required: true
      type: path
      inference: auto
      description: "Absolute path to R2 FASTQ (paired-end required)"

    - name: replicate
      required: true
      type: integer
      default: 1
      inference: filename
      description: "Replicate number (integer)"

decision_points:
  - parameter: genome
    prompt: "Which reference genome matches your organism?"
    options:
      - value: GRCh38
        label: "Human GRCh38/hg38 (recommended)"
        description: "Latest human reference"
      - value: GRCh37
        label: "Human GRCh37/hg19 (legacy)"
        description: "Older human reference"
      - value: mm10
        label: "Mouse mm10"
        description: "Mouse reference genome"
    default: GRCh38
    recommendation: "Default to GRCh38 for human samples"

  - parameter: read_length
    prompt: "What is the read length of your sequencing data?"
    options:
      - value: 50
        label: "50 bp"
        description: "Short reads"
      - value: 75
        label: "75 bp"
        description: "Standard length"
      - value: 100
        label: "100 bp"
        description: "Common for modern sequencers"
      - value: 150
        label: "150 bp"
        description: "Long reads"
    default: 50
    recommendation: "Check FASTQ files or sequencing report for exact length"

  - parameter: narrow_peak
    prompt: "What type of peaks are you expecting?"
    options:
      - value: "true"
        label: "Narrow peaks (default for ATAC-seq)"
        description: "Standard ATAC-seq open chromatin regions"
      - value: "false"
        label: "Broad peaks"
        description: "For histone marks or broader accessibility regions"
    default: "true"
    recommendation: "Use narrow peaks for standard ATAC-seq"

test_profile:
  command: "nextflow run nf-core/atacseq -r 2.1.2 -profile test,docker --outdir test_atacseq"
  duration: "15 minutes"
  success_indicators:
    - "test_atacseq/multiqc/multiqc_report.html"
  log_pattern: "Pipeline completed successfully"

run_command:
  template: |
    nextflow run nf-core/atacseq \
        -r 2.1.2 \
        -profile docker \
        --input {samplesheet} \
        --outdir {outdir} \
        --genome {genome} \
        --read_length {read_length} \
        -resume

outputs:
  primary:
    - path: "bwa/mergedLibrary/*.mLb.mkD.sorted.bam"
      description: "Filtered, deduplicated alignments"
    - path: "bwa/mergedLibrary/bigwig/*.bigWig"
      description: "Coverage tracks for genome browsers"
    - path: "macs2/narrowPeak/*.narrowPeak"
      description: "Peak calls (BED format)"
    - path: "macs2/narrowPeak/consensus/consensus_peaks.bed"
      description: "Consensus peaks across replicates"

  validation:
    - file: "multiqc/multiqc_report.html"
      check: exists
      description: "QC report must exist"
    - file: "macs2/narrowPeak"
      check: exists
      description: "Peak calls directory"

quality_metrics:
  - name: mapped_reads
    good: ">80%"
    acceptable: "60-80%"
    poor: "<60%"
  - name: mitochondrial
    good: "<20%"
    acceptable: "20-40%"
    poor: ">40%"
  - name: duplicates
    good: "<30%"
    acceptable: "30-50%"
    poor: ">50%"
  - name: frip
    good: ">30%"
    acceptable: "15-30%"
    poor: "<15%"
  - name: tss_enrichment
    good: ">6"
    acceptable: "4-6"
    poor: "<4"

resources:
  min_memory: "8.GB"
  recommended_memory: "32.GB"
  min_cpus: 4
  recommended_cpus: 8
  disk_space: "100.GB"

troubleshooting:
  - error: "Low FRiP score"
    fix: "Check library complexity in plotFingerprint. May indicate over-transposition or low quality"
  - error: "Few peaks called"
    fix: "Lower threshold with --macs_qvalue 0.1 or use --narrow_peak false for broader peaks"
  - error: "High duplicates"
    fix: "Normal for low-input samples. Pipeline removes by default. Consider deeper sequencing"
  - error: "High mitochondrial reads"
    fix: "Sample quality issue. Pipeline filters mito by default (--keep_mito false)"

replicate_patterns:
  - "_rep(\\d+)"
  - "_R(\\d+)_"
  - "_(\\d+)$"
  - "_replicate(\\d+)"