syntax = "proto3";

package varfish.v1.strucvars.clinvar;

// Enum for storing the variation type from ClinVar.
enum VariationType {
  // Unspecified.
  VARIATION_TYPE_UNSPECIFIED = 0;
  // Complex.
  VARIATION_TYPE_COMPLEX = 1;
  // Microsatellite.
  VARIATION_TYPE_MICROSATELLITE = 2;
  // Duplication.
  VARIATION_TYPE_DUP = 3;
  // Deletion.
  VARIATION_TYPE_DEL = 4;
  // Break-end.
  VARIATION_TYPE_BND = 5;
  // Copy number variation.
  VARIATION_TYPE_CNV = 6;
  // Inversion.
  VARIATION_TYPE_INV = 7;
  // Insertion.
  VARIATION_TYPE_INS = 8;
}

// Pathogenicity from ClinVar.
enum Pathogenicity {
  // Unspecified.
  PATHOGENICITY_UNSPECIFIED = 0;
  // Benign.
  PATHOGENICITY_BENIGN = 1;
  // Likely benign.
  PATHOGENICITY_LIKELY_BENIGN = 2;
  // Uncertain significance.
  PATHOGENICITY_UNCERTAIN = 3;
  // Likely pathogenic.
  PATHOGENICITY_LIKELY_PATHOGENIC = 4;
  // Pathogenic.
  PATHOGENICITY_PATHOGENIC = 5;
}

// One record in ClinVar representing a structural variant.
message SvRecord {
  // The chromosome number.
  int32 chrom_no = 1;
  // The 1-based start position.
  int32 start = 2;
  // The 1-based stop position.
  int32 stop = 3;
  // The variation type.
  VariationType variation_type = 4;
  // The pathogenicity.
  Pathogenicity pathogenicity = 5;
  // The RCV ID.
  uint32 rcv = 6;
  // The VCV ID.
  uint32 vcv = 7;
}

// ClinVar structural variant database.
message SvDatabase {
  // The records.
  repeated SvRecord records = 1;
}