preamble:
   input_reference_genome: hg38/genomes/GRCh38.p14
   summary: GPF SFARI Annotation Pipeline 
   description: This is the pipeline used to annotate SFARI GPF instance resources  

annotators:

- effect_annotator:
    gene_models: hg38/gene_models/GENCODE/49/basic/PRI
    genome: hg38/genomes/GRCh38.p14

- normalize_allele_annotator:
    genome: hg38/genomes/GRCh38.p14

- allele_score:
    resource_id: hg38/scores/dbSNP
    input_annotatable: normalized_allele    
    
- allele_score:
    resource_id: hg38/variant_frequencies/gnomAD_4.1.0/exomes/ALL
    input_annotatable: normalized_allele
    attributes:
    - source: AF
      name: gnomad_v4_exomes_ALL_af
    - source: AF_percent
      name: gnomad_v4_exomes_ALL_af_percent

- allele_score:
    resource_id: hg38/variant_frequencies/gnomAD_4.1.0/genomes/ALL
    input_annotatable: normalized_allele
    attributes:
    - source: AF
      name: gnomad_v4_genomes_ALL_af
    - source: AF_percent
      name: gnomad_v4_genomes_ALL_af_percent

- allele_score:
    resource_id: hg38/scores/ClinVar_20251019
    input_annotatable: normalized_allele


- position_score: hg38/scores/phyloP100way
  attributes:
  - source: phyloP100way
    name: phylop100way

- position_score: hg38/scores/phyloP30way
  attributes:
  - source: phyloP30way
    name: phylop30way

- position_score: hg38/scores/phyloP20way
  attributes:
  - source: phyloP20way
    name: phylop20way

- position_score: hg38/scores/phyloP7way
  attributes:
  - source: phyloP7way
    name: phylop7way

- position_score: hg38/scores/phastCons100way
  attributes:
  - source: phastCons100way
    name: phastCons100way

- position_score: hg38/scores/phastCons30way
  attributes:
  - source: phastCons30way
    name: phastCons30way

- position_score: hg38/scores/phastCons20way
  attributes:
  - source: phastCons20way
    name: phastCons20way

- position_score: hg38/scores/phastCons7way
  attributes:
  - source: phastCons7way
    name: phastCons7way

- allele_score: hg38/scores/CADD_v1.7

- allele_score: hg38/scores/AlphaMissense

- liftover_annotator:
    chain: liftover/hg38_to_hg19
    source_genome: hg38/genomes/GRCh38.p14
    target_genome: hg19/genomes/GATK_ResourceBundle_5777_b37_phiX174
    attributes:
    - source: liftover_annotatable
      name: hg19_annotatable
      internal: true

- allele_score:
    resource_id: hg19/scores/MPC
    input_annotatable: hg19_annotatable
    

- effect_annotator:
    gene_models: hg38/gene_models/MANE/1.4
    genome: hg38/genomes/GRCh38.p14
    attributes:
    - name: worst_effect_MANE_1.4
      source: worst_effect 
    - name: effect_details_MANE_1.4
      source: effect_details 
    - name: gene_effects_MANE_1.4
      source: gene_effects 

- cnv_collection:
    resource_id: hg38/cnv_collections/Iossifov_Lab_SSC_AGRE_2021
    cnv_filter: >
        affected_status == "affected" and variant == "deletion"
    attributes:
    - name: number_of_deletions_in_SSC_affected
      source: count

- cnv_collection:
    resource_id: hg38/cnv_collections/Iossifov_Lab_SSC_AGRE_2021
    cnv_filter: >
        affected_status == "affected" and variant == "duplication"
    attributes:
    - name: number_of_duplications_in_SSC_affected
      source: count

- cnv_collection:
    resource_id: hg38/cnv_collections/SFARI_gene_CNV
    attributes:
    - name: in_a_SFARI_gene_CNV
      source: count