name: rnaseq
version: "3.22.2"
description: "Gene expression quantification and differential expression analysis"

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

data_types:
  - RNA-seq
  - mRNA-seq
  - bulk RNA-seq

detection_hints:
  filename:
    - rna
    - rnaseq
    - mrna
    - expression
  directory:
    - rnaseq
    - rna
    - expression
    - transcriptome

samplesheet:
  input_types:
    - fastq

  columns:
    - name: sample
      required: true
      type: string
      inference: filename
      description: "Sample identifier"

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

    - name: fastq_2
      required: false
      type: path
      inference: auto
      description: "Absolute path to R2 FASTQ (empty for single-end)"

    - name: strandedness
      required: true
      type: enum
      allowed:
        - auto
        - forward
        - reverse
        - unstranded
      default: "auto"
      inference: default
      description: "Library strandedness (auto recommended)"

decision_points:
  - parameter: genome
    prompt: "Which reference genome matches your organism?"
    options:
      - value: GRCh38
        label: "Human GRCh38/hg38 (recommended for human)"
        description: "Latest human reference assembly"
      - value: GRCh37
        label: "Human GRCh37/hg19 (legacy)"
        description: "Older human reference for compatibility"
      - value: mm10
        label: "Mouse mm10/GRCm38"
        description: "Mouse reference genome"
      - value: BDGP6
        label: "Drosophila BDGP6"
        description: "Fruit fly reference"
    default: GRCh38
    recommendation: "Default to GRCh38 for human samples"

  - parameter: aligner
    prompt: "Which alignment strategy would you prefer?"
    options:
      - value: star_salmon
        label: "STAR + Salmon (recommended)"
        description: "Most accurate, standard for differential expression"
      - value: star_rsem
        label: "STAR + RSEM"
        description: "Better for isoform-level quantification"
      - value: hisat2
        label: "HISAT2"
        description: "Lower memory requirements, faster"
    default: star_salmon
    recommendation: "Use star_salmon unless memory-constrained or need isoforms"

test_profile:
  command: "nextflow run nf-core/rnaseq -r 3.22.2 -profile test,docker --outdir test_rnaseq"
  duration: "15 minutes"
  success_indicators:
    - "test_rnaseq/multiqc/multiqc_report.html"
  log_pattern: "Pipeline completed successfully"

run_command:
  template: |
    nextflow run nf-core/rnaseq \
        -r 3.22.2 \
        -profile docker \
        --input {samplesheet} \
        --outdir {outdir} \
        --genome {genome} \
        --aligner {aligner} \
        -resume

outputs:
  primary:
    - path: "star_salmon/salmon.merged.gene_counts.tsv"
      description: "Raw gene counts for DESeq2/edgeR"
    - path: "star_salmon/salmon.merged.gene_tpm.tsv"
      description: "TPM normalized expression values"
    - path: "star_salmon/*.bam"
      description: "Aligned reads"

  validation:
    - file: "multiqc/multiqc_report.html"
      check: exists
      description: "QC report must exist"
    - file: "star_salmon/salmon.merged.gene_counts.tsv"
      check: non_empty
      description: "Count matrix must have data"

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

troubleshooting:
  - error: "STAR index fails"
    fix: "Increase memory with --max_memory '64.GB' or provide pre-built --star_index"
  - error: "Low alignment rate"
    fix: "Verify genome matches species; check FastQC for adapter contamination"
  - error: "Strandedness detection fails"
    fix: "Specify explicitly with --strandedness reverse (or forward/unstranded)"