mammalian_orphan.yaml

  # Scoring file suitable for any species with intron sizes similar to mammals
requirements:
  expression: [(combined_cds_fraction.ncrna or combined_cds_fraction.coding) and ((exon_num.multi and (cdna_length.multi or combined_cds_length.multi) and max_intron_length and min_intron_length and proportion_verified_introns_inlocus), or, (exon_num.mono and (combined_cds_length.mono or cdna_length.mono)))]
  parameters:
    combined_cds_fraction.ncrna: {operator: eq, value: 0}
    combined_cds_fraction.coding: {operator: gt, value: 0.20}
    cdna_length.mono: {operator: gt, value: 100}
    cdna_length.multi: {operator: ge, value: 100}
    combined_cds_length.mono: {operator: gt, value: 100}
    combined_cds_length.multi: {operator: gt, value: 100}
    exon_num.mono: {operator: eq, value: 1}
    exon_num.multi: {operator: gt, value: 1}
    max_intron_length: {operator: le, value: 1000000}
    min_intron_length: {operator: ge, value: 5}
    proportion_verified_introns_inlocus: {operator: gt, value: 0}
as_requirements:
  expression: [cdna_length and three_utr_length and five_utr_length and utr_length and suspicious_splicing]
  parameters:
    cdna_length: {operator: ge, value: 100}
    utr_length: {operator: le, value: 3500}
    five_utr_length: {operator: le, value: 3500}
    three_utr_length: {operator: le, value: 3500}
    suspicious_splicing: {operator: ne, value: true}
    max_intron_length: {operator: le, value: 200000}
not_fragmentary:
 expression: [((exon_num.multi and (cdna_length.multi or combined_cds_length.multi)), or, (exon_num.mono and combined_cds_length.mono))]
 parameters:
   is_complete: {operator: eq, value: true}
   exon_num.multi: {operator: gt, value: 1}
   cdna_length.multi: {operator: ge, value: 100}
   combined_cds_length.multi: {operator: gt, value: 100}
   exon_num.mono: {operator: eq, value: 1}
   combined_cds_length.mono: {operator: gt, value: 100}
scoring:
  blast_score: {rescaling: max}
  cdna_length: {rescaling: max}
  cds_not_maximal: {rescaling: min}
  cds_not_maximal_fraction: {rescaling: min}
  exon_num: {
    rescaling: max,
    filter: {
    operator: ge,
    value: 0}
  }
  five_utr_length:
    filter: {operator: le, value: 3500}
    rescaling: target
    value: 400
  five_utr_num:
    filter: {operator: lt, value: 4}
    rescaling: target
    value: 2
  end_distance_from_junction:
    filter: {operator: lt, value: 55}
    rescaling: min
  highest_cds_exon_number: {rescaling: max}
  intron_fraction: {rescaling: max}
  is_complete: {rescaling: target, value: true}
  number_internal_orfs: {rescaling: target, value: 1}
  non_verified_introns_num: {rescaling: min}
  proportion_verified_introns_inlocus: {rescaling: max}
  retained_fraction: {rescaling: min}
  retained_intron_num: {rescaling: min}
  selected_cds_fraction: {rescaling: target, value: 0.7}
  selected_cds_intron_fraction: {rescaling: max}
  selected_cds_length: {rescaling: max}
  selected_cds_num: {rescaling: max}
  three_utr_length:
    filter: {operator: le, value: 3500}
    rescaling: target
    value: 800
  three_utr_num:
    filter: {operator: lt, value: 3}
    rescaling: target
    value: 1
  combined_cds_locus_fraction: {rescaling: max}