cloudgene.yaml

id: imputationserver2
name: Genotype Imputation
description: This is the new Michigan Imputation Server Pipeline using <a href="https://github.com/statgen/Minimac4">Minimac4</a>. Documentation can be found <a href="http://imputationserver.readthedocs.io/en/latest/">here</a>.<br><br>If your input data is <b>GRCh37/hg19</b> please ensure chromosomes are encoded without prefix  (e.g. <b>20</b>).<br>If your input data is <b>GRCh38hg38</b> please ensure chromosomes are encoded with prefix 'chr' (e.g. <b>chr20</b>).
version: 2.0.7
website: https://imputationserver.readthedocs.io
category: Application
submitButton: Start Imputation

workflow:
  steps:
    - name: Quality Control and Imputation
      type: nextflow
      script: main.nf
      # params without UI
      params:
        project: "${CLOUDGENE_JOB_NAME}"
        allele_frequency_population: "${population}"
        files: "${files}/*.vcf.gz"
        encryption:
          aes: ${aesEncryption}
        phasing:
          engine: ${phasing} 
        imputation:
          min_r2: ${r2Filter}        
          meta: ${meta}     
        user:
          email: "${CLOUDGENE_USER_EMAIL}"
          name: "${CLOUDGENE_USER_NAME}"
        service:
          name: "${CLOUDGENE_SERVICE_NAME}"
          contact: "${CLOUDGENE_CONTACT_NAME}"
          email: "${CLOUDGENE_CONTACT_EMAIL}"
          url: "${CLOUDGENE_SERVICE_URL}"
      groups:
        - id: validation
          label: "Input Validation"
        - id: qc
          label: "Quality Control"          
        - id: imputation
          label: "Phasing and Imputation"
        - id: summary
          label: "Summary"
      processes:
        - process: "INPUT_VALIDATION:INPUT_VALIDATION_VCF"
          view: status
          label: "Input Validation"
          group: "validation"
        - process: "QUALITY_CONTROL:QUALITY_CONTROL_VCF"
          view: status
          label: "Quality Control"
          group: "qc"
        - process: "QUALITY_CONTROL:QUALITY_CONTROL_REPORT"
          view: label
          label: "Quality Control Report"          
          group: "qc"
        - process: "PHASING:EAGLE"
          view: progressbar
          label: "Phasing with Eagle"
          group: "imputation"
        - process: "PHASING:BEAGLE"
          view: progressbar
          label: "Phasing with Beagle"
          group: "imputation"          
        - process: "IMPUTATION:MINIMAC4"
          view: progressbar
          label: "Imputation"
          group: "imputation"
        - process: "ENCRYPTION:COMPRESSION_ENCRYPTION_VCF"
          view: progressbar
          label: "Compression and Encryption"
          group: "summary"

  inputs:
    - id: refpanel
      description: Reference Panel (<a href="https://imputationserver.sph.umich.edu/start.html#!pages/refpanels" target="_blank">Details</a>)
      type: app_list
      category: RefPanel

    - id: files
      description: Input Files (<a href="http://www.1000genomes.org/wiki/Analysis/Variant%20Call%20Format/vcf-variant-call-format-version-41" target="_blank">VCF</a>)
      type: local_folder
      serialize: false

    - id: build
      description: Array Build
      type: list
      value: hg19
      values:
        hg19: GRCh37/hg19
        hg38: GRCh38/hg38
      details: Please note that the final SNP coordinates always match the reference build.

    - id: r2Filter
      description: rsq Filter
      type: list
      value: 0
      values:
        0: off
        0.001: 0.001
        0.1: 0.1
        0.2: 0.2
        0.3: 0.3
      serialize: false
      
    - id: phasing
      description: Phasing Engine
      type: list
      value: eagle
      values:
        eagle: Eagle v2.4 (phased output)
        beagle: Beagle 5.4 (HRC and 1KG only)
        no_phasing: No phasing
      serialize: false

    - id: population
      description: Allele Frequency Check
      type: list
      values:
        bind: refpanel
        property: populations
        category: RefPanel

    - id: mode
      description: Mode
      type: list
      value: imputation
      values:
        qc_only: Quality Control Only
        imputation: Quality Control & Imputation

    - id: aesEncryption
      description: AES 256 encryption
      details: Imputation Server encrypts all zip files by default. Please note that AES encryption does not work with standard unzip programs. Use 7z instead.
      type: checkbox
      value: false
      values:
        true: true
        false: false
      visible: true
      serialize: false

    - id: meta
      description: Generate Meta-imputation file
      type: checkbox
      value: false
      values:
        true: true
        false: false
      visible: true
      serialize: false

    - id: myseparator
      type: separator
      
    - id: password
      description: Password set by user.
      value:
      visible: false
      type: text

    - id: check1
      description: I will not attempt to re-identify or contact research participants.
      type: terms_checkbox

    - id: check2
      description: I will report any inadvertent data release, security breach or other data management incident of which I become aware.
      type: terms_checkbox

  outputs:
    - id: output
      description: Downloads
      type: local_folder
      download: true