public_recipes.yml

recipes:
- name: dbSNP (v1.0.0)
  description: Adds dbSNP rs_ids using the variant - supports both GRCh37 and GRCh38
  template_type: recipe
  is_public: 'True'
  version: 1.0.0
  annotator_params:
    annotator: parallel
  fields:
    data_type: string
    title: rs_id
    is_list: true
    expression: |
      dataset_field_values(
              'solvebio:public:/dbSNP/2.0.0-b151/Variants-{}'.format(get(record, 'genomic_coordinates.build')),
              field='row_id',
              entities=[('variant', record.variant)])
      if get(record, 'variant') else None
    name: rs_id
- name: Genes for genomic region (v1.0.0)
  description: Returns all the genes within a genomic region - supports both GRCh37
    and GRCh38
  template_type: recipe
  is_public: 'True'
  version: 1.0.0
  annotator_params:
    annotator: parallel
  fields:
    data_type: string
    entity_type: gene
    title: gene
    is_list: true
    expression: |
      dataset_field_values(
             'solvebio:public:/GENCODE/3.0.0-29/GENCODE-{}'.format(get(record, 'genomic_coordinates.build')),
             'gene_symbol',
              entities=[('genomic_region',record.genomic_coordinates)],
              filters=[('info.gene_type','protein_coding'),('feature','gene')],
              limit=20000)
      if get(record,'genomic_coordinates') else None
    name: gene
- name: gnomAD Allele Frequency (v1.0.0)
  description: Gets the population allele frequency from gnomAD v2.1.1 - supports
    both GRCh37 and GRCh38 builds
  template_type: recipe
  is_public: 'True'
  version: 1.0.0
  annotator_params:
    annotator: parallel
  fields:
    data_type: float
    title: gnomad_af
    is_list: true
    expression: |
      dataset_field_values('solvebio:public:/gnomAD/2.1.1/Exomes-{}'.format(record.variant.split('-')[0]), field='af',
      entities=[('variant',record.variant)])
      if get(record,'variant') else None
    name: gnomad_af
- name: Protein Change (v1.0.0)
  description: Gets the protein change from the variant field
  template_type: recipe
  is_public: 'True'
  version: 1.0.0
  annotator_params:
    annotator: parallel
  fields:
    data_type: string
    title: protein_change
    expression: |
      get(translate_variant(record.variant),'protein_change')
      if record.variant else None
    name: protein_change
- name: Gene (v1.0.0)
  description: Gets the gene symbol from the variant field
  template_type: recipe
  is_public: 'True'
  version: 1.0.0
  annotator_params:
    annotator: parallel
  fields:
    data_type: string
    title: gene
    expression: |
      get(translate_variant(record.variant),'gene')
      if record.variant else None
    name: gene
- name: cDNA Change (v1.0.0)
  description: Gets the cDNA change from the variant field
  template_type: recipe
  is_public: 'True'
  version: 1.0.0
  annotator_params:
    annotator: parallel
  fields:
    data_type: string
    title: cdna_change
    expression: |
      get(translate_variant(record.variant),'cdna_change')
      if record.variant else None
    name: cdna_change
- name: ClinVar clinical significance (GRCh38)
  description: Annotate this variant with the current ClinVar clinical significance.
    Requires valid GRCh38 variant field.
  template_type: recipe
  is_public: 'True'
  version: 1.0.0
  annotator_params:
    annotator: parallel
  fields:
    data_type: string
    title: Clinvar
    ordering: 8
    is_list: true
    expression: |-
      dataset_field_values(
          'solvebio:public:/ClinVar/5.0.0-20190805/Variants-GRCH38',
          field='clinical_significance',
          entities=[('variant', record.variant)],
          limit=1
      )  if get(record, 'variant') else None
    name: clinvar
- name: Crossmap (GRCh37 -> GRCh38)
  description: Use crossmap to convert GRCh37 coordinates to GRCh38 coordinates.
  template_type: recipe
  is_public: 'True'
  version: 1.0.0
  annotator_params:
    annotator: parallel
  fields:
    title: variant
    expression: |-
      crossmap(record.variant, 'GRCH38')  if get(record, 'variant') else None
    name: variant
    data_type: string
    entity_type: variant
- name: Crossmap (GRCh38 -> GRCh37)
  description: Use crossmap to convert GRCh38 coordinates to GRCh37 coordinates.
  template_type: recipe
  is_public: 'True'
  version: 1.0.0
  annotator_params:
    annotator: parallel
  fields:
    title: variant
    expression: |-
      crossmap(record.variant, 'GRCH37')  if get(record, 'variant') else None
    name: variant
    data_type: string
    entity_type: variant
- name: Nucleotide change
  description: Returns the ref sequence and the alt sequence separated by >. Requires
    valid variant.
  template_type: recipe
  is_public: 'True'
  version: 1.0.0
  annotator_params:
    annotator: parallel
  fields:
    description: Returns the ref sequence and the alt sequence separated by >.
    data_type: string
    title: Nucleotide change
    expression: |-
      '>'.join([genomic_sequence('-'.join(record.variant.split('-')[:4])), record.variant.split('-')[4]])  if get(record, 'variant') else None
    name: nucleotide_change
- name: Nucleotide context
  description: Returns the neighboring reference sequence for a given variant (1 position
    on each side). For example, a SNV will return the trinucleotide context. Requires
    valid variant.
  template_type: recipe
  is_public: 'True'
  version: 1.0.0
  annotator_params:
    annotator: parallel
  fields:
    description: The neighboring reference sequence for a given variant (1 position
      on each side). For example, a SNV will return the trinucleotide context.
    data_type: string
    title: Nucleotide context
    expression: |-
      genomic_sequence('-'.join([record.variant.split('-')[0], record.variant.split('-')[1], str(int(record.variant.split('-')[2])-1), str(int(record.variant.split('-')[3])+1)]))  if get(record, 'variant') else None
    name: nucleotide_context
- name: 'TCGA cancers count (GRCh37) '
  description: TCGA cancer types with at least one occurrence of this variant. Requires
    valid variant field. GRCh37 variants only.
  template_type: recipe
  is_public: 'True'
  version: 1.0.0
  annotator_params:
    annotator: parallel
  fields:
    description: TCGA cancers that have at last one occurrence of this variant
    data_type: string
    title: TCGA cancers
    ordering: 12
    is_list: true
    expression: |-
      [facet.get('term') for facet in dataset_field_top_terms(
          'solvebio:public:/TCGA/2.0.0-2018-mc3-v0.2.8/SomaticMutations-GRCh37',
          field='disease',
          entities=[('variant', record.variant)],
          limit=100
      )] if get(record, 'variant') else None
    name: tcga_cancers
- name: Split by comma
  description: Split a comma-delimited string into a list of values. Requires field
    named PMIDs with multiple comma separated PubMed IDs.
  template_type: recipe
  is_public: 'True'
  version: 1.0.0
  annotator_params:
    annotator: parallel
  fields:
    data_type: string
    title: PubMed ID
    ordering: 10
    entity_type: literature
    is_list: true
    expression: |-
      record.PMIDs.split(', ')  if get(record, 'PMIDs') else None
    name: pubmed_id
- name: "Prevalence in TCGA (gene)\t"
  description: Prevalence of mutations in this gene in TCGA. Requires valid gene field.
  template_type: recipe
  is_public: 'True'
  version: 1.0.0
  annotator_params:
    annotator: parallel
  fields:
    data_type: double
    title: Prevalence
    ordering: 12
    expression: |-
      prevalence(
          'solvebio:public:/TCGA/2.0.0-2018-mc3-v0.2.8/SomaticMutations-GRCh37',
          entity=['gene',record.gene],
          sample_field='sample_barcode'
      )  if get(record, 'gene') else None
    name: prevalence
- name: Predict variant effect (variant)
  description: Predicts effect of this variant in sequence ontology terms with veppy.
    Requires valid variant field.
  template_type: recipe
  is_public: 'True'
  version: 1.0.0
  annotator_params:
    annotator: parallel
  fields:
    data_type: string
    title: Effects
    ordering: 9
    expression: |-
      predict_variant_effects(record.variant)[0].get('so_term') if get(record, 'variant') else None
    name: effects
- name: ClinVar clinical significance (GRCh37)
  description: Annotate this variant with the current ClinVar clinical significance.
    Requires valid GRCh37 variant field.
  template_type: recipe
  is_public: 'True'
  version: 1.0.0
  annotator_params:
    annotator: parallel
  fields:
    data_type: string
    title: Clinvar
    ordering: 8
    is_list: true
    expression: |-
      dataset_field_values(
          'solvebio:public:/ClinVar/5.0.0-20190805/Variants-GRCH37',
          field='clinical_significance',
          entities=[('variant', record.variant)],
          limit=1
      ) if get(record, 'variant') else None
    name: clinvar
- name: Current user
  description: Save the current user
  template_type: recipe
  is_public: 'True'
  version: 1.0.0
  annotator_params:
    annotator: parallel
  fields:
    data_type: object
    title: Last updated by
    ordering: 1
    expression: |-
      user()
    name: last_updated_by
- name: Diseases (gene)
  description: Diseases associated with this gene from NHGRI's Clinical Genomic Database.
    Requires valid gene field.
  template_type: recipe
  is_public: 'True'
  version: 1.0.0
  annotator_params:
    annotator: parallel
  fields:
    data_type: string
    title: Diseases
    ordering: 11
    is_list: true
    expression: |-
      dataset_field_values(
          'solvebio:public:/CGD/1.2.0-2017-06-19/CGD',
          field='condition',
          entities=[('gene', record.gene)],
          limit=1
      )  if get(record, 'gene') else None
    name: diseases
- name: 'ExAC allele frequency (GRCh37) '
  description: Find the allele frequency of this variant in all of ExAC. Requires
    valid variant field. GRCh37 only.
  template_type: recipe
  is_public: 'True'
  version: 1.0.0
  annotator_params:
    annotator: parallel
  fields:
    data_type: double
    title: Exac AF
    ordering: 7
    expression: |-
      dataset_field_values(
              'solvebio:public:/ExAC/2.1.0-r1/ExAC-GRCh37',
              field='af_adj',
              entities=[('variant', record.variant)],
              limit=1)  if get(record, 'variant') else None
    name: exac_af
- name: ExAC allele frequency (GRCh38)
  description: Find the allele frequency of this variant in all of ExAC. Requires
    valid variant field. GRCh38 only.
  template_type: recipe
  is_public: 'True'
  version: 1.0.0
  annotator_params:
    annotator: parallel
  fields:
    data_type: double
    title: Exac AF
    ordering: 7
    expression: |-
      dataset_field_values(
              'solvebio:public:/ExAC/2.1.0-r1/ExAC-GRCh38',
              field='af_adj',
              entities=[('variant', record.variant)],
              limit=1)  if get(record, 'variant') else None
    name: exac_af
- name: Gene synonyms (gene)
  description: Annotate each record with gene synonyms from HUGO. Requires valid gene
    field.
  template_type: recipe
  is_public: 'True'
  version: 1.0.0
  annotator_params:
    annotator: parallel
  fields:
    data_type: object
    title: HUGO
    ordering: 12
    expression: |-
      dataset_query(
          'solvebio:public:/HGNC/3.3.0-2020-10-29/HGNC',
          fields=['synonyms'],
          entities=[('gene', record.gene)],
          limit=1
      )  if get(record, 'gene') else None
    name: hugo
- name: Normalize variant (variant)
  description: Normalize existing variant (left shifted, minimal representation).
    Requires valid variant field.
  template_type: recipe
  is_public: 'True'
  version: 1.0.0
  annotator_params:
    annotator: parallel
  fields:
    data_type: string
    title: Normalized
    ordering: 2
    expression: |-
      normalize_variant(record.variant) if get(record, 'variant') else None
    name: variant_normalized
- name: Current time
  description: Creates a field with the current time
  template_type: recipe
  is_public: 'True'
  version: 1.0.0
  annotator_params:
    annotator: parallel
  fields:
    data_type: date
    title: Date Modified
    ordering: 3
    expression: |-
      now()
    name: date_modified
- name: 'Cancer beacons '
  description: 'Make a list of cancer-related datasets that each variant in this dataset
    is found in. Requires valid variant field.  '
  template_type: recipe
  is_public: 'True'
  version: 1.0.0
  annotator_params:
    annotator: parallel
  fields:
    data_type: string
    title: Cancer Beacons
    ordering: 5
    is_list: true
    expression: |-
      [ds.split('/')[1] for ds in [
              'solvebio:public:/3DHotSpots/1.0.0-2017-01/SignificantResidues-GRCh37',
              'solvebio:public:/ICGC/3.0.0-23/SimpleSomaticMutation-GRCh37',
              'solvebio:public:/CIViC/2.0.1-2016-12-28/Variants-GRCh37',
              'solvebio:public:/CancerHotspots/1.0.0-2016-08-08/Variants-GRCh37',
              'solvebio:public:/COSMIC/1.1.0-COSMIC71/SomaticMutationsCoding-GRCh37'
          ] if bool(
              dataset_count(ds, entities=[
      ("variant", crossmap(entity_ids('variant', record.variant)[0], 'GRCH37'))
              ])
          )
      ]  if get(record, 'variant') else None
    name: cancer_beacons
- name: Map variant entity (GRCh38)
  description: Use SolveBio's entity mapping engine to find the matching variant for
    a field named alteration containing HGVS, rs ID, or gene and amino acid change.
    This will return a GRCh38 variant.
  template_type: recipe
  is_public: 'True'
  version: 1.0.0
  annotator_params:
    annotator: parallel
  fields:
    data_type: string
    title: Variant
    ordering: 2
    entity_type: variant
    expression: |-
      entity_ids('variant', record.alteration) if get(record, 'alteration') else None
    name: variant