# Nearest IWC exemplar(s) — bounded subgraphs
#
# Corpus:      https://github.com/galaxyproject/iwc
# Corpus HEAD: fe41a79 (galaxyproject/iwc main, shallow clone taken 2026-09-16)
# Produced by: gxwf convert <workflow>.ga --to format2 --compact, then bounded to the
#              relevant subgraph and stripped of tool_state keys that carry no structural
#              signal. Load-bearing tool_state is kept verbatim.
#
# THIS FILE IS A READING AID, NOT A RUNNABLE WORKFLOW. Steps have been removed and
# tool_state elided; every elision is marked with a `# [elided]` comment. For the full
# exemplars, convert the corpus files named in each document header.
#
# The subject workflow (C. auris Scf1 RNA-seq DE: FastQC -> Cutadapt -> RNA STAR ->
# featureCounts -> DESeq2 -> significance filter) spans a journey that IWC publishes as
# TWO workflows joined at the count-table boundary. Both halves are given below.
# See iwc-comparison-notes.md for the structural diff and the ranking.

---
# ============================================================================
# DOCUMENT 1 — PRIMARY EXEMPLAR (High confidence) for the DE tail (nodes H, I)
#
# IWC workflow ID: transcriptomics/rnaseq-de/rnaseq-de-filtering-plotting
# Release:         0.12
# Steps covered:   Differential Analysis, the two compose_text_param parameter
#                  bridges, Annotate DESeq2 table, Filter with p-adj threshold,
#                  Filter with log2 FC threshold
# Steps dropped:   volcano plot, both heatmaps, the normalized-counts join/cut
#                  chain, and the recurring-header generator (visualization tail;
#                  the subject brief exposes no counterpart)
#
# This is the document that settles `fold-change-threshold-linear-vs-deseq2-log2fc`
# and `deseq2-contrast-realization-unsettled`.
# ============================================================================
class: GalaxyWorkflow
label: RNA-Seq Differential Expression Analysis with Visualization
doc: >-
  Identifies differentially expressed genes between exactly two experimental conditions
  from count tables. [elided: full doc string]
inputs:
  # NOTE: the condition grouping lives in the INTERFACE, as two pre-grouped `list`
  # collections of per-sample count tables. There is no metadata-driven split anywhere
  # in this workflow. Contrast with the subject's data-flow brief section 4.
  - id: Counts from changed condition
    type: collection
    collection_type: list
    optional: false
    doc: Counts from experimental condition or changed condition.
  - id: Counts from reference condition
    type: collection
    collection_type: list
    optional: false
    doc: Counts from reference condition or base condition.
  - id: Count files have header
    type: boolean
    optional: false
    doc: >-
      featureCounts count files have a header line; RNA-STAR count files do not.
  - id: Gene Annotaton
    type: data
    optional: false
    doc: The same annotation GTF used for mapping and counting
  - id: Adjusted p-value threshold
    type: float
    optional: false
    default: 0.05
  # *** THE log2FC ANSWER ***
  # IWC states the effect-size threshold in log2 units at the interface. It does NOT
  # expose a linear fold change and convert internally. Default 1.0 == linear 2-fold,
  # which is exactly the subject paper's |FC| > 2 criterion.
  - id: log2 fold change threshold
    type: float
    optional: false
    default: 1
    doc: >-
      log2 fold change threshold to filter for highly regulated genes.
      A log2 FC of 3 equals to an absolute fold change of 8 (2^3).
outputs:
  - id: DESeq2 Plots
    outputSource: Differential Analysis/plots
  - id: DESeq2 Normalized Counts
    outputSource: Differential Analysis/counts_out
  - id: Annotated DESeq2 results table
    outputSource: Annotate DESeq2 table/out_file1
  - id: Significantly differentially expressed genes
    outputSource: Filter with log2 FC threshold/out_file1
steps:
  # --- Node H equivalent: ONE DESeq2 job == ONE contrast ---------------------
  # `how: datasets_per_level` with a `rep_factorLevel` repeat: each level port takes a
  # COLLECTION of per-sample count files, reduced into the tool's multiple=true input.
  # Exactly two levels here, and `deseq_out` is a single dataset (proved downstream: it
  # feeds deg_annotate / tp_cat / Filter1, all single-dataset tools, and the sibling
  # -tests.yml asserts has_text_matching on it as a dataset, not as a collection).
  - id: Differential Analysis
    label: Differential Analysis
    tool_id: toolshed.g2.bx.psu.edu/repos/iuc/deseq2/deseq2/2.11.40.8+galaxy4
    tool_version: 2.11.40.8+galaxy4
    tool_shed_repository:
      changeset_revision: 05f9e54d7e81
      name: deseq2
      owner: iuc
      tool_shed: toolshed.g2.bx.psu.edu
    in:
      - id: header
        source: Count files have header
      - id: output_options|alpha_ma
        source: Adjusted p-value threshold
      - id: select_data|rep_factorName_0|rep_factorLevel_0|countsFile
        source: Counts from changed condition
      - id: select_data|rep_factorName_0|rep_factorLevel_1|countsFile
        source: Counts from reference condition
    out:
      - id: deseq_out
        hide: true
    tool_state:
      # [elided] advanced_options, batch_factors, tximport
      output_options:
        output_selector:
          - pdf
          - normCounts
        alpha_ma:
          __class__: ConnectedValue
      select_data:
        how: datasets_per_level
        __current_case__: 1
        rep_factorName:
          - __index__: 0
            factorName: DEFactor
            rep_factorLevel:
              - __index__: 0
                factorLevel: MainFactor
                countsFile:
                  __class__: ConnectedValue
              - __index__: 1
                factorLevel: BaseFactor
                countsFile:
                  __class__: ConnectedValue

  # --- Annotation: gene positions / biotype / symbol onto the results table --
  # Appends columns 8-13; columns 1-7 (GeneID, BaseMean, log2FC, StdErr, Wald, pval,
  # padj) are unchanged, so the c3 / c7 filter indices below hold with or without it.
  - id: _unlabeled_step_11
    tool_id: toolshed.g2.bx.psu.edu/repos/iuc/deg_annotate/deg_annotate/1.1.0+galaxy1
    tool_version: 1.1.0+galaxy1
    in:
      - id: annotation
        source: Gene Annotaton
      - id: input_table
        source: Differential Analysis/deseq_out
    out:
      - id: output
        hide: true
    tool_state:
      advanced_parameters:
        gff_feature_type: exon
        gff_feature_attribute: gene_id
        gff_transcript_attribute: transcript_id
        gff_attributes: gene_biotype, gene_name
      mode: degseq
      # [elided] chromInfo, ConnectedValue stubs

  - id: Annotate DESeq2 table
    label: Annotate DESeq2 table
    tool_id: toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_cat/9.11+galaxy0
    tool_version: 9.11+galaxy0
    in:
      # [elided] `inputs` comes from a generated single-line header dataset
      - id: queries_0|inputs2
        source: _unlabeled_step_11
    out:
      - id: out_file1
        change_datatype: tabular
        rename: Annotated DESeq2 results

  # --- PARAMETER -> FILTER EXPRESSION BRIDGE --------------------------------
  # `Filter1` takes its predicate as a TEXT parameter, so a numeric workflow input
  # cannot reach it directly. The corpus idiom is one compose_text_param step per
  # filter: a literal prefix plus the connected float. Two steps per threshold.
  - id: _unlabeled_step_8
    tool_id: toolshed.g2.bx.psu.edu/repos/iuc/compose_text_param/compose_text_param/0.1.1
    tool_version: 0.1.1
    in:
      - id: components_1|param_type|component_value
        source: Adjusted p-value threshold
    out:
      - id: out1
        hide: true
    tool_state:
      components:
        - __index__: 0
          param_type:
            select_param_type: text
            __current_case__: 0
            component_value: c7<          # c7 == P-adj
        - __index__: 1
          param_type:
            select_param_type: float
            __current_case__: 2
            component_value:
              __class__: ConnectedValue

  - id: _unlabeled_step_10
    tool_id: toolshed.g2.bx.psu.edu/repos/iuc/compose_text_param/compose_text_param/0.1.1
    tool_version: 0.1.1
    in:
      - id: components_1|param_type|component_value
        source: log2 fold change threshold
    out:
      - id: out1
        hide: true
    tool_state:
      components:
        - __index__: 0
          param_type:
            select_param_type: text
            __current_case__: 0
            component_value: abs(c3)>     # c3 == log2(FC); NO conversion applied
        - __index__: 1
          param_type:
            select_param_type: float
            __current_case__: 2
            component_value:
              __class__: ConnectedValue

  # --- Node I equivalent: TWO CHAINED Filter1 STEPS, not one ----------------
  - id: Filter with p-adj threshold
    label: Filter with p-adj threshold
    tool_id: Filter1
    tool_version: 1.1.1
    in:
      - id: cond
        source: _unlabeled_step_8/out1
      - id: input
        source: Annotate DESeq2 table/out_file1
    out:
      - id: out_file1
        hide: true
        rename: Genes filtered with adj p-value threshold
    tool_state:
      header_lines: "1"

  - id: Filter with log2 FC threshold
    label: Filter with log2 FC threshold
    tool_id: Filter1
    tool_version: 1.1.1
    in:
      - id: cond
        source: _unlabeled_step_10/out1
      - id: input
        source: Filter with p-adj threshold/out_file1
    out:
      - id: out_file1
        rename: Genes filtered with adj p-value and log2(FC) thresholds
    tool_state:
      header_lines: "1"
tags:
  - transcriptomics
  - RNAseq
license: MIT
release: "0.12"

---
# ============================================================================
# DOCUMENT 2 — SECONDARY EXEMPLAR (Medium confidence) for the map-over head
#              (nodes A-D)
#
# IWC workflow ID: transcriptomics/rnaseq-pe/rnaseq-pe
# Steps covered:   __FLATTEN__, fastp (the trimmer slot), RNA STAR, the
#                  map_param_value strandedness bridge, featureCounts, and the
#                  `More QC` subworkflow reduced to its Falco (FastQC-equivalent) step
# Steps dropped:   Cufflinks, StringTie, all coverage/bigwig generation, MultiQC,
#                  Picard / RSeQC / idxstats QC, the reference-genome text bridge
#                  (the subject brief has no counterpart for any of these)
#
# This is the document that settles `fastqc-per-read-fanout-not-a-flat-list` and
# supplies the strandedness-parameter idiom.
# ============================================================================
class: GalaxyWorkflow
label: "RNA-Seq Analysis: Paired-End Read Processing and Quantification"
inputs:
  - id: Collection paired FASTQ files
    type: collection
    collection_type: list:paired
    optional: false
    doc: Should be a list of paired-end RNA-seq fastqs
  # Built-in STAR index selected by name. `restrictOnConnections: true` narrows the
  # option list to the genomes STAR actually has indexed on the server.
  # The subject's C. auris B8441 has no such entry — see iwc-comparison-notes.md.
  - id: Reference genome
    type: string
    optional: false
    restrictOnConnections: true
  - id: GTF file of annotation
    type: data
    optional: false
  - id: Strandedness
    type: string
    optional: false
    restrictions:
      - stranded - forward
      - stranded - reverse
      - unstranded
outputs:
  - id: Mapped Reads
    outputSource: "STAR: map and count and coverage splitted/mapped_reads"
  - id: Counts Table
    outputSource: _unlabeled_step_25/Counts Table   # [elided] relabel step
steps:
  # --- *** THE FastQC FAN-OUT ANSWER *** ------------------------------------
  # IWC does NOT promote a nested collection from per-fastq QC. It flattens the
  # list:paired collection FIRST, with an explicit join_identifier, and runs the
  # single-dataset QC tool over the resulting flat `list`. Element identifiers
  # become <sample>_forward / <sample>_reverse.
  - id: _unlabeled_step_11
    tool_id: __FLATTEN__
    tool_version: 1.0.0
    in:
      - id: input
        source: Collection paired FASTQ files
    out:
      - id: output
        hide: true
    tool_state:
      input:
        __class__: ConnectedValue
      join_identifier: _

  # --- Trimmer slot. rnaseq-pe uses fastp, the subject's paper names Cutadapt. ---
  # Both emit ONE paired-inner collection when driven by a list:paired input:
  # fastp -> output_paired_coll; Cutadapt (lparsons/cutadapt, library.type
  # `paired_collection`) -> out_pairs + report. See the Cutadapt excerpt below.
  - id: remove adapters + bad quality bases
    label: remove adapters + bad quality bases
    tool_id: toolshed.g2.bx.psu.edu/repos/iuc/fastp/fastp/1.3.6+galaxy0
    tool_version: 1.3.6+galaxy0
    in:
      - id: single_paired|paired_input
        source: Collection paired FASTQ files
      # [elided] adapter_sequence1 / adapter_sequence2 from optional string inputs
    out:
      - id: output_paired_coll
        hide: true
      - id: report_json
        hide: true
    tool_state:
      filter_options:
        quality_filtering_options:
          disable_quality_filtering: false
          qualified_quality_phred: "30"
      # [elided] duplicated_reads, read_mod_options, output_options

  # --- Aligner. ENCODE long-RNA parameter set, INDEXED reference. -----------
  - id: "STAR: map and count and coverage splitted"
    label: "STAR: map and count and coverage splitted"
    tool_id: toolshed.g2.bx.psu.edu/repos/iuc/rgrnastar/rna_star/2.7.11b+galaxy1
    tool_version: 2.7.11b+galaxy1
    tool_shed_repository:
      changeset_revision: 55c9ac3aa8f4
      name: rgrnastar
      owner: iuc
      tool_shed: toolshed.g2.bx.psu.edu
    in:
      - id: refGenomeSource|GTFconditional|genomeDir
        source: Reference genome
      - id: refGenomeSource|GTFconditional|sjdbGTFfile
        source: GTF file of annotation
      - id: singlePaired|input
        source: remove adapters + bad quality bases/output_paired_coll
    out:
      - id: output_log            # Log.final.out — the assertable text behind the BAM
        hide: true
      - id: reads_per_gene
        hide: true
        rename: Reads per gene from STAR
      - id: mapped_reads
        rename: Mapped Reads
      # [elided] signal_unique_str1/2, signal_uniquemultiple_str1/2, splice_junctions
    tool_state:
      refGenomeSource:
        geneSource: indexed         # <-- every STAR step in IWC uses `indexed`
        __current_case__: 0
        GTFconditional:
          GTFselect: without-gtf-with-gtf
          __current_case__: 1
          genomeDir:
            __class__: ConnectedValue
          sjdbGTFfile:
            __class__: ConnectedValue
          sjdbGTFfeatureExon: exon
          sjdbOverhang: "100"
      # [elided] full ENCODE algo.params block (seed / align / junction settings)

  # --- User-facing strandedness string -> per-tool parameter value ----------
  # One map_param_value step per consumer (featureCounts, Cufflinks, StringTie).
  # Keeps ONE user-facing vocabulary while each wrapper gets its own encoding.
  - id: Get featureCounts strandedness parameter
    label: Get featureCounts strandedness parameter
    tool_id: toolshed.g2.bx.psu.edu/repos/iuc/map_param_value/map_param_value/0.2.0
    tool_version: 0.2.0
    in:
      - id: input_param_type|input_param
        source: Strandedness
    out:
      - id: output_param_text
    tool_state:
      # [elided] the value_map repeat: 'unstranded'->0, 'stranded - forward'->1,
      # 'stranded - reverse'->2
      output_param_type: text
      unmapped:
        on_unmapped: fail
        __current_case__: 1

  - id: _unlabeled_step_21
    tool_id: toolshed.g2.bx.psu.edu/repos/iuc/featurecounts/featurecounts/2.1.1+galaxy1
    tool_version: 2.1.1+galaxy1
    tool_shed_repository:
      changeset_revision: 37d067694d40
      name: featurecounts
      owner: iuc
      tool_shed: toolshed.g2.bx.psu.edu
    in:
      - id: alignment
        source: "STAR: map and count and coverage splitted/mapped_reads"
      - id: anno|reference_gene_sets
        source: GTF file of annotation
      - id: strand_specificity
        source: Get featureCounts strandedness parameter/output_param_text
      - id: when
        source: Use featureCounts for generating count tables
    out:
      - id: output_short           # subject interface output 7
        hide: true
      - id: output_summary         # subject interface output 8
        hide: true
    tool_state:
      anno:
        anno_select: history       # GTF from the history, same dataset as STAR's
        __current_case__: 2
        reference_gene_sets:
          __class__: ConnectedValue
        gff_feature_type: exon
        gff_feature_attribute: gene_id
        summarization_level: false
      format: tabdel_short
      pe_parameters:
        paired_end_status: PE_fragments
        __current_case__: 2
        exclude_chimerics: true
      # [elided] extended_parameters, read_filtering_parameters
    when: $(inputs.when)

  # --- QC subworkflow, reduced to the per-fastq QC step --------------------
  - id: More QC
    label: More QC
    run:
      class: GalaxyWorkflow
      label: RNA-seq-QC
      inputs:
        - id: FASTQ collection
          type: collection
          collection_type: list      # <-- FLAT, because of __FLATTEN__ upstream
          optional: false
      outputs:
        - id: Falco text output
          outputSource: _unlabeled_step_3/text_file
      steps:
        # Falco is a drop-in FastQC reimplementation; same single-dataset input,
        # same html_file + text_file output pair the subject promotes as outputs 1-2.
        - id: _unlabeled_step_3
          tool_id: toolshed.g2.bx.psu.edu/repos/iuc/falco/falco/1.3.2+galaxy0
          tool_version: 1.3.2+galaxy0
          in:
            - id: input_file
              source: FASTQ collection
          out:
            - id: html_file
              hide: true
            - id: text_file
              hide: true
      # [elided] gtftobed12, samtools view/idxstats, Picard MarkDuplicates,
      # RSeQC read_distribution and geneBody_coverage, and their three other inputs
    in:
      - id: FASTQ collection
        source: _unlabeled_step_11        # the FLATTEN output
      - id: STAR BAM
        source: "STAR: map and count and coverage splitted/mapped_reads"
      - id: reference_annotation_gtf
        source: GTF file of annotation
      - id: when
        source: Generate additional QC reports
    when: $(inputs.when)

---
# ============================================================================
# DOCUMENT 3 — TOOL-LEVEL EVIDENCE ONLY (cross-domain, NOT a domain exemplar)
#
# IWC workflow ID: epigenetics/cutandrun/cutandrun
# Steps covered:   the Cutadapt step only
#
# Cited for one fact the subject needs and the transcriptomics exemplars cannot
# supply, because neither uses Cutadapt: the output shape of the IUC Cutadapt
# wrapper when mapped over a list:paired collection. This settles
# `trimmed-reads-paired-reassembly-conditional`. CUT&RUN is a different domain
# and this document must not be read as a structural exemplar for anything else.
# ============================================================================
class: GalaxyWorkflow
label: CUT&RUN / CUT&TAG analysis
inputs:
  - id: PE fastq input
    type: collection
    collection_type: list:paired
    optional: false
steps:
  - id: Cutadapt (remove adapter + bad quality bases)
    label: Cutadapt (remove adapter + bad quality bases)
    tool_id: toolshed.g2.bx.psu.edu/repos/lparsons/cutadapt/cutadapt/5.2+galaxy2
    tool_version: 5.2+galaxy2
    in:
      - id: library|input_1
        source: PE fastq input
      # [elided] library|r1|adapters_0|... and library|r2|adapters2_0|... adapter
      #          sequences, wired from two text parameter inputs
    out:
      # ONE paired collection out, shape `input` (i.e. same as the input collection),
      # plus one report per element. No re-pair node is needed downstream.
      - id: out_pairs
      - id: report
        rename: cutadapt report
    tool_state:
      library:
        type: paired_collection
        __current_case__: 2
        input_1:
          __class__: ConnectedValue
        pair_adapters: false
        # [elided] r1 / r2 adapter repeats