plan_version: "1"
source:
  kind: freeform
  name: "Ebola Virus Infection RNA-seq Analysis (A549 WT vs PTPN13-KO)"
  derived_from: intent
  notes: "Synthesized from user interview intent and design briefs for paired-end RNA-seq with Salmon and DESeq2."
workflow:
  title: "Ebola Virus Infection RNA-seq Analysis (A549 WT vs PTPN13-KO)"
  label_source: draft
  notes: "Input and output labels match concrete galaxy-workflow.gxwf.yml."
test_cases:
  - id: test_ebola_rnaseq_pe
    doc: "Execute Salmon quantification on paired reads and run DESeq2 differential analysis across conditions."
    derived_from: intent
    provenance: "Interview intent and IWC transcriptomics test fixture conventions."
    job_inputs:
      - workflow_label: reads_paired_collection
        label_status: resolved
        description: "Collection of paired-end FASTQ reads across experimental samples."
        collection_shape: "list:paired"
        datatype: fastqsanger.gz
        fixture:
          storage: remote-url
          location: "https://zenodo.org/records/13987631/files/SRR5085167_forward.fastqsanger.gz"
          checksum: "SHA-1:f910a2a7764249b690e28d8dcf4d7097d3c533f6"
          provenance: "IWC rnaseq-pe Zenodo record 13987631"
      - workflow_label: salmon_index
        label_status: resolved
        description: "Reference transcriptome FASTA sequence for Salmon indexing."
        collection_shape: null
        datatype: fasta
        fixture:
          storage: remote-url
          location: "https://zenodo.org/records/13987631/files/Saccharomyces_cerevisiae.R64-1-1.cdna.all.fa"
          checksum: null
          provenance: "IWC transcriptomics cDNA FASTA"
      - workflow_label: sample_metadata
        label_status: resolved
        description: "Tabular sample metadata specifying factors for DESeq2."
        collection_shape: null
        datatype: tabular
        fixture:
          storage: in-repo
          location: "test-data/sample_metadata.tabular"
          checksum: null
          provenance: "Synthesized sample annotation matching FASTQ identifiers"
      - workflow_label: tx2gene_map
        label_status: resolved
        description: "Tabular mapping between transcript IDs and gene IDs."
        collection_shape: null
        datatype: tabular
        fixture:
          storage: in-repo
          location: "test-data/tx2gene.tabular"
          checksum: null
          provenance: "Synthesized tx2gene table for transcript aggregation"
    expected_outputs:
      - workflow_label: salmon_quant_collection
        label_status: resolved
        description: "Collection of per-sample Salmon transcript quantification tables."
        output_kind: collection
        collection_shape: list
        assertion_intent:
          - family: has_n_lines
            intent: "Each quant.sf table contains quantified transcript rows."
            expected_value: 10
            tolerance:
              kind: delta
              magnitude: 50
              rationale: "Depends on fixture transcriptome size"
            element_identifier: SRR5085167
            evidence: intent
            confidence: medium
      - workflow_label: deseq2_norm_counts
        label_status: resolved
        description: "Size-factor normalized counts table from DESeq2."
        output_kind: dataset
        collection_shape: null
        assertion_intent:
          - family: has_n_columns
            intent: "Normalized count matrix contains sample columns."
            expected_value: 3
            tolerance: null
            element_identifier: null
            evidence: intent
            confidence: medium
      - workflow_label: deseq2_differential_results
        label_status: resolved
        description: "DESeq2 statistical test results table."
        output_kind: dataset
        collection_shape: null
        assertion_intent:
          - family: has_text
            intent: "Output contains expected DESeq2 header columns (baseMean, log2FoldChange, pvalue, padj)."
            expected_value: "baseMean"
            tolerance: null
            element_identifier: null
            evidence: intent
            confidence: high
      - workflow_label: deseq2_plots
        label_status: resolved
        description: "DESeq2 diagnostic PCA and dispersion plots."
        output_kind: dataset
        collection_shape: null
        assertion_intent:
          - family: has_size
            intent: "Valid diagnostic PDF is generated with non-zero size."
            expected_value: 5000
            tolerance:
              kind: delta
              magnitude: 500000
              rationale: "PDF binary size varies with R graphics device"
            element_identifier: null
            evidence: intent
            confidence: medium
unresolved: []
omissions:
  - target: deseq2_plots
    reason: "Exact pixel or stream equality of R graphics is non-deterministic; verified by file size and existence."
    category: nondeterministic
warnings: []