workflows.yaml file for brc

workflows.yaml

workflows:
- trs_id: '#workflow/github.com/iwc-workflows/assembly-with-flye/main/versions/v0.2'
  workflow_categories:
  - ASSEMBLY
  workflow_name: Genome assembly with Flye
  workflow_description: Assemble long reads with Flye, then view assembly statistics
    and assembly graph
  ploidy: any
  parameters:
    Input sequence reads:
      class: File
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/atacseq/main/versions/v1.0'
  workflow_categories:
  - REGULATION
  workflow_name: ATACseq
  workflow_description: 'This workflow takes as input a collection of paired fastq.
    It will remove bad quality and adapters with cutadapt. Map with Bowtie2 end-to-end.
    Will remove reads on MT and unconcordant pairs and pairs with mapping quality
    below 30 and PCR duplicates. Will compute the pile-up on 5'' +- 100bp. Will call
    peaks and count the number of reads falling in the 1kb region centered on the
    summit. Will compute 2 normalization for coverage: normalized by million reads
    and normalized by million reads in peaks. Will plot the number of reads for each
    fragment length.'
  ploidy: any
  parameters:
    PE fastq input:
      class: Collection
    reference_genome:
      class: text
    effective_genome_size:
      class: integer
    bin_size:
      class: integer
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/average-bigwig-between-replicates/main/versions/v0.2'
  workflow_categories:
  - REGULATION
  - TRANSCRIPTOMICS
  workflow_name: Average Bigwig between replicates
  workflow_description: 'We assume the identifiers of the input list are like:

    sample_name_replicateID.

    The identifiers of the output list will be:

    sample_name'
  ploidy: any
  parameters:
    Bigwig to average:
      class: Collection
    bin_size:
      class: integer
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/bacterial-genome-assembly/main/versions/v1.1.5'
  workflow_categories:
  - ASSEMBLY
  workflow_name: Bacterial Genome Assembly using Shovill
  workflow_description: Assembly of bacterial paired-end short read data with generation
    of quality metrics and reports
  ploidy: any
  parameters:
    Input adapter trimmed sequence reads (forward):
      class: File
      ext:
      - fastq
      - fastq.gz
      - fastqsanger
      - fastqsanger.gz
    Input adapter trimmed sequence reads (reverse):
      class: File
      ext:
      - fastq
      - fastq.gz
      - fastqsanger
      - fastqsanger.gz
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/baredsc/baredSC-1d-logNorm/versions/v0.5'
  workflow_categories:
  - TRANSCRIPTOMICS
  workflow_name: baredSC_1d_logNorm
  workflow_description: Run baredSC in 1 dimension in logNorm for 1 to N gaussians
    and combine models.
  ploidy: any
  parameters:
    Tabular with raw expression values:
      class: File
      ext: tabular
    Gene name:
      class: text
    Maximum value in logNorm:
      class: float
    Maximum number of Gaussians to study:
      class: integer
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/baredsc/baredSC-2d-logNorm/versions/v0.5'
  workflow_categories:
  - TRANSCRIPTOMICS
  workflow_name: baredSC_2d_logNorm
  workflow_description: Run baredSC in 2 dimensions in logNorm for 1 to N gaussians
    and combine models.
  ploidy: any
  parameters:
    Tabular with raw expression values:
      class: File
      ext: tabular
    Gene name for x axis:
      class: text
    maximum value in logNorm for x-axis:
      class: float
    Gene name for y axis:
      class: text
    maximum value in logNorm for y-axis:
      class: float
    Maximum number of Gaussians to study:
      class: integer
    compute p-value:
      class: boolean
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/brew3r/main/versions/v0.2'
  workflow_categories:
  - TRANSCRIPTOMICS
  workflow_name: BREW3R
  workflow_description: This workflow takes a collection of BAM (output of STAR) and
    a gtf. It extends the input gtf using de novo annotation.
  ploidy: any
  parameters:
    Input gtf:
      class: File
      ext: gtf
    BAM collection:
      class: Collection
      ext: bam
    strandedness:
      class: text
    minimum coverage:
      class: integer
    minimum FPKM for merge:
      class: float
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/chipseq-pe/main/versions/v0.12'
  workflow_categories:
  - REGULATION
  workflow_name: ChIPseq_PE
  workflow_description: This workflow takes as input a collection of paired fastqs.
    Remove adapters with cutadapt, map pairs with bowtie2. Keep MAPQ30 and concordant
    pairs. MACS2 for paired bam.
  ploidy: any
  parameters:
    PE fastq input:
      class: Collection
    adapter_forward:
      class: text
    adapter_reverse:
      class: text
    reference_genome:
      class: text
    effective_genome_size:
      class: integer
    normalize_profile:
      class: boolean
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/chipseq-sr/main/versions/v0.12'
  workflow_categories:
  - REGULATION
  workflow_name: ChIPseq_SR
  workflow_description: This workflow takes as input a collection of fastqs (single
    reads). Remove adapters with cutadapt, map with bowtie2. Keep MAPQ30. MACS2 for
    bam with fixed extension or model.
  ploidy: any
  parameters:
    SR fastq input:
      class: Collection
    adapter_forward:
      class: text
    reference_genome:
      class: text
    effective_genome_size:
      class: integer
    normalize_profile:
      class: boolean
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/consensus-peaks/consensus-peaks-atac-cutandrun/versions/v1.2'
  workflow_categories:
  - REGULATION
  workflow_name: Get Confident Peaks From ATAC or CUTandRUN replicates
  workflow_description: This workflow takes as input BAM from ATAC-seq or CUT&RUN.
    It calls peaks on each replicate and intersect them. In parallel, each BAM is
    subsetted to smallest number of reads. Peaks are called using all subsets combined.
    Only peaks called using a combination of all subsets which have summits intersecting
    the intersection of at least x replicates will be kept.
  ploidy: any
  parameters:
    n rmDup BAM:
      class: Collection
      ext: bam
    Minimum number of overlap:
      class: integer
    effective_genome_size:
      class: integer
    bin_size:
      class: integer
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/consensus-peaks/consensus-peaks-chip-pe/versions/v1.2'
  workflow_categories:
  - REGULATION
  workflow_name: Get Confident Peaks From ChIP_PE replicates
  workflow_description: This workflow takes as input PE BAM from ChIP-seq. It calls
    peaks on each replicate and intersect them. In parallel, each BAM is subsetted
    to smallest number of reads. Peaks are called using all subsets combined. Only
    peaks called using a combination of all subsets which have summits intersecting
    the intersection of at least x replicates will be kept.
  ploidy: any
  parameters:
    n rmDup BAMPE:
      class: Collection
      ext: bam
    Minimum number of overlap:
      class: integer
    effective_genome_size:
      class: integer
    bin_size:
      class: integer
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/consensus-peaks/consensus-peaks-chip-sr/versions/v1.2'
  workflow_categories:
  - REGULATION
  workflow_name: Get Confident Peaks From ChIP_SR replicates
  workflow_description: This workflow takes as input SR BAM from ChIP-seq. It calls
    peaks on each replicate and intersect them. In parallel, each BAM is subsetted
    to smallest number of reads. Peaks are called using all subsets combined. Only
    peaks called using a combination of all subsets which have summits intersecting
    the intersection of at least x replicates will be kept.
  ploidy: any
  parameters:
    n rmDup BAMSR:
      class: Collection
      ext: bam
    Minimum number of overlap:
      class: integer
    effective_genome_size:
      class: integer
    bin_size:
      class: integer
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/cutandrun/main/versions/v0.13'
  workflow_categories:
  - REGULATION
  workflow_name: CUTandRUN
  workflow_description: This workflow take as input a collection of paired fastq.
    Remove adapters with cutadapt, map pairs with bowtie2 allowing dovetail. Keep
    MAPQ30 and concordant pairs. BAM to BED. MACS2 with "ATAC" parameters.
  ploidy: any
  parameters:
    PE fastq input:
      class: Collection
    adapter_forward:
      class: text
    adapter_reverse:
      class: text
    reference_genome:
      class: text
    effective_genome_size:
      class: integer
    normalize_profile:
      class: boolean
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/fastq-to-matrix-10x/scrna-seq-fastq-to-matrix-10x-cellplex/versions/v0.5'
  workflow_categories:
  - TRANSCRIPTOMICS
  workflow_name: scRNA-seq_preprocessing_10X_cellPlex
  workflow_description: This workflow processes the CMO fastqs with CITE-seq-Count
    and include the translation step required for cellPlex processing. In parallel
    it processes the Gene Expresion fastqs with STARsolo, filter cells with DropletUtils
    and reformat all outputs to be easily used by the function 'Read10X' from Seurat.
  ploidy: any
  parameters:
    fastq PE collection GEX:
      class: Collection
    reference genome:
      class: text
    gtf:
      class: File
    cellranger_barcodes_3M-february-2018.txt:
      class: File
    Barcode Size is same size of the Read:
      class: boolean
    fastq PE collection CMO:
      class: Collection
    sample name and CMO sequence collection:
      class: Collection
      ext: csv
    Number of expected cells:
      class: integer
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/fastq-to-matrix-10x/scrna-seq-fastq-to-matrix-10x-v3/versions/v0.5'
  workflow_categories:
  - TRANSCRIPTOMICS
  workflow_name: scRNA-seq_preprocessing_10X_v3_Bundle
  workflow_description: This workflow processes the Gene Expresion fastqs with STARsolo,
    filter cells with DropletUtils and reformat all outputs to be easily used by the
    function 'Read10X' from Seurat.
  ploidy: any
  parameters:
    fastq PE collection:
      class: Collection
    reference genome:
      class: text
    gtf:
      class: File
    cellranger_barcodes_3M-february-2018.txt:
      class: File
    Barcode Size is same size of the Read:
      class: boolean
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/generic-variant-calling-wgs-pe/main/versions/v0.1.1'
  workflow_categories:
  - VARIANT_CALLING
  workflow_name: Generic variation analysis on WGS PE data
  workflow_description: Workflow for variant analysis against  a reference genome
    in GenBank format
  ploidy: any
  parameters:
    Paired Collection:
      class: Collection
      ext:
      - fastqsanger
      - fastqsanger.gz
    GenBank genome:
      class: File
      ext: genbank
    Name for genome database:
      class: text
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/goseq/main/versions/v0.1'
  workflow_categories:
  - TRANSCRIPTOMICS
  workflow_name: Goseq GO-KEGG Enrichment Analysis
  workflow_description: This workflow is used for GO and KEGG enrichment analysis
    using GOseq tools.
  ploidy: any
  parameters:
    Select genome to use:
      class: text
    Differential expression result:
      class: File
      ext: tabular
    Select gene ID format:
      class: text
    gene length:
      class: File
      ext: tabular
    KEGG pathways:
      class: File
      ext: tabular
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/haploid-variant-calling-wgs-pe/main/versions/v0.1'
  workflow_categories:
  - VARIANT_CALLING
  workflow_name: Paired end variant calling in haploid system
  workflow_description: Workflow for variant analysis against a reference genome in
    GenBank format
  ploidy: any
  parameters:
    Paired Collection:
      class: Collection
      ext:
      - fastqsanger
      - fastqsanger.gz
    Annotation GTF:
      class: File
    Genome fasta:
      class: File
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/hic-hicup-cooler/chic-fastq-to-cool-hicup-cooler/versions/v0.3'
  workflow_categories:
  - REGULATION
  workflow_name: cHi-C_fastqToCool_hicup_cooler
  workflow_description: This workflow take as input a collection of paired fastq.
    It uses HiCUP to go from fastq to validPair file. The pairs are filtered for MAPQ
    and for the region captured. Then, they are sorted by cooler to generate a tabix
    dataset. Cooler is used to generate a balanced cool file to the desired resolution.
  ploidy: any
  parameters:
    PE fastq input:
      class: Collection
    genome name:
      class: text
    Restriction enzyme:
      class: text
    No fill-in:
      class: boolean
    minimum MAPQ:
      class: integer
    Bin size in bp:
      class: integer
    Interactions to consider to calculate weights in normalization step:
      class: text
    capture region (chromosome):
      class: text
    capture region (start):
      class: integer
    capture region (end):
      class: integer
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/hic-hicup-cooler/hic-fastq-to-cool-hicup-cooler/versions/v0.3'
  workflow_categories:
  - REGULATION
  workflow_name: Hi-C_fastqToCool_hicup_cooler
  workflow_description: This workflow takes as input a collection of paired fastq.
    It uses HiCUP to go from fastq to validPair file using the middle of the fragment
    as coordinates. The pairs are filtered for MAPQ and sorted by cooler to generate
    a tabix dataset. Cooler is used to generate a balanced cool file to the desired
    resolution.
  ploidy: any
  parameters:
    PE fastq input:
      class: Collection
    genome name:
      class: text
    Restriction enzyme:
      class: text
    No fill-in:
      class: boolean
    minimum MAPQ:
      class: integer
    Bin size in bp:
      class: integer
    Interactions to consider to calculate weights in normalization step:
      class: text
    region for matrix plotting:
      class: text
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/hic-hicup-cooler/hic-fastq-to-pairs-hicup/versions/v0.3'
  workflow_categories:
  - REGULATION
  workflow_name: Hi-C_fastqToPairs_hicup
  workflow_description: This workflow takes as input a collection of paired fastq.
    It uses HiCUP to go from fastq to validPair file. First truncate the fastq using
    the cutting sequence to guess the fill-in. Then map the truncated fastq. Then
    asign to fragment and filter the self-ligated and dandling ends or internal (it
    can also filter for the size). Then it removes the duplicates. Convert the output
    to be compatible with juicebox or cooler using the middle of the fragment as coordinates.
    Finally filter for mapping quality
  ploidy: any
  parameters:
    PE fastq input:
      class: Collection
    genome name:
      class: text
    Restriction enzyme:
      class: text
    No fill-in:
      class: boolean
    minimum MAPQ:
      class: integer
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/hic-hicup-cooler/hic-juicermediumtabix-to-cool-cooler/versions/v0.3'
  workflow_categories:
  - REGULATION
  workflow_name: Hi-C_juicermediumtabixToCool_cooler
  workflow_description: This workflow uses as input a collection of juicer medium
    tabix files and a genome name. It builds balanced cool file to the desired resolution.
  ploidy: any
  parameters:
    Bin size in bp:
      class: integer
    genome name:
      class: text
    Juicer Medium Tabix with validPairs:
      class: Collection
    Interactions to consider to calculate weights in normalization step:
      class: text
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/polish-with-long-reads/main/versions/v0.1'
  workflow_categories:
  - ASSEMBLY
  workflow_name: Assembly polishing with long reads
  workflow_description: Racon polish with long reads, x4
  ploidy: any
  parameters:
    Assembly to be polished:
      class: File
    long reads:
      class: File
    'minimap setting (for long reads) ':
      class: text
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/pseudobulk-worflow-decoupler-edger/main/versions/v0.1.1'
  workflow_categories:
  - TRANSCRIPTOMICS
  workflow_name: Differential gene expression for single-cell data using pseudo-bulk
    counts with edgeR
  workflow_description: This workflow uses the decoupler tool in Galaxy to generate
    pseudobulk counts from an annotated AnnData file obtained from scRNA-seq analysis.
    Following the pseudobulk step, differential expression genes (DEG) are calculated
    using the edgeR tool. The workflow also includes data sanitation steps to ensure
    smooth operation of edgeR and minimizing potential issues. Additionally, a Volcano
    plot tool is used to visualize the results after the DEG analysis.
  ploidy: any
  parameters:
    Source AnnData file:
      class: File
      ext:
      - h5
      - h5ad
    'Pseudo-bulk: Fields to merge':
      class: text
    Group by column:
      class: text
    Sample key column:
      class: text
    Name Your Raw Counts Layer:
      class: text
    Factor fields:
      class: text
    Formula:
      class: text
    Gene symbol column:
      class: text
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/quality-and-contamination-control/main/versions/v1.1.6'
  workflow_categories:
  - ASSEMBLY
  workflow_name: Quality and Contamination Control For Genome Assembly
  workflow_description: Short paired-end read analysis to provide quality analysis,
    read cleaning and taxonomy assignation
  ploidy: any
  parameters:
    Input sequence reads (forward):
      class: File
      ext:
      - fastq
      - fastq.gz
      - fastqsanger
      - fastqsanger.gz
    Input sequence reads (reverse):
      class: File
      ext:
      - fastq
      - fastq.gz
      - fastqsanger
      - fastqsanger.gz
    Select a taxonomy database:
      class: text
    Select a NCBI taxonomy database:
      class: text
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/rnaseq-de/main/versions/v0.2'
  workflow_categories:
  - TRANSCRIPTOMICS
  workflow_name: RNAseq_DE_filtering_plotting
  workflow_description: 'This workflow can only work on an experimental setup with
    exactly 2 conditions. It takes two collections of count tables as input and performs
    differential expression analysis. Additionally it filters for DE genes based on
    adjusted p-value  and log2 fold changes thresholds. It also generates informative
    plots.

    '
  ploidy: any
  parameters:
    Counts from changed condition:
      class: Collection
    Counts from reference condition:
      class: Collection
    Count files have header:
      class: boolean
    Gene Annotaton:
      class: File
    Adjusted p-value threshold:
      class: float
    log2 fold change threshold:
      class: float
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/rnaseq-pe/main/versions/v1.1'
  workflow_categories:
  - TRANSCRIPTOMICS
  workflow_name: RNA-seq for Paired-end fastqs
  workflow_description: 'This workflow takes as input a list of paired-end fastqs.
    Adapters and bad quality bases are removed with fastp. Reads are mapped with STAR
    with ENCODE parameters and genes are counted simultaneously as well as normalized
    coverage (per million mapped reads) on uniquely mapped reads. The counts are reprocessed
    to be similar to HTSeq-count output. Alternatively, featureCounts can be used
    to count the reads/fragments per gene. FPKM are computed with cufflinks and/or
    with StringTie. The unstranded normalized coverage is computed with bedtools.

    '
  ploidy: any
  parameters:
    Collection paired FASTQ files:
      class: Collection
    Forward adapter:
      class: text
    Reverse adapter:
      class: text
    Generate additional QC reports:
      class: boolean
    Reference genome:
      class: text
    GTF file of annotation:
      class: File
    Strandedness:
      class: text
    Use featureCounts for generating count tables:
      class: boolean
    Compute Cufflinks FPKM:
      class: boolean
    GTF with regions to exclude from FPKM normalization with Cufflinks:
      class: File
    Compute StringTie FPKM:
      class: boolean
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/rnaseq-sr/main/versions/v1.1'
  workflow_categories:
  - TRANSCRIPTOMICS
  workflow_name: RNA-seq for Single-read fastqs
  workflow_description: 'This workflow takes as input a list of single-end fastqs.
    Adapters and bad quality bases are removed with fastp. Reads are mapped with STAR
    with ENCODE parameters and genes are counted simultaneously as well as normalized
    coverage (per million mapped reads) on uniquely mapped reads. The counts are reprocessed
    to be similar to HTSeq-count output. Alternatively, featureCounts can be used
    to count the reads/fragments per gene. FPKM are computed with cufflinks and/or
    with StringTie. The unstranded normalized coverage is computed with bedtools.

    '
  ploidy: any
  parameters:
    Collection of FASTQ files:
      class: Collection
    Forward adapter:
      class: text
    Generate additional QC reports:
      class: boolean
    Reference genome:
      class: text
    GTF file of annotation:
      class: File
    Strandedness:
      class: text
    Use featureCounts for generating count tables:
      class: boolean
    Compute Cufflinks FPKM:
      class: boolean
    GTF with regions to exclude from FPKM normalization with Cufflinks:
      class: File
    Compute StringTie FPKM:
      class: boolean
  active: false
- trs_id: '#workflow/github.com/iwc-workflows/variation-reporting/main/versions/v0.1.1'
  workflow_categories:
  - VARIANT_CALLING
  workflow_name: Generic variation analysis reporting
  workflow_description: This workflow takes a VCF dataset of variants produced by
    any of the variant calling workflows in https://github.com/galaxyproject/iwc/tree/main/workflows/sars-cov-2-variant-calling
    and generates tabular lists of variants by Samples and by Variant, and an overview
    plot of variants and their allele-frequencies.
  ploidy: any
  parameters:
    Variation data to report:
      class: Collection
      ext:
      - vcf
      - vcf_bgzip
    AF Filter:
      class: float
    DP Filter:
      class: integer
    DP_ALT Filter:
      class: integer
  active: false