snapshot_type: uniprot_record_evidence_extract
archive:
  repository: https://github.com/ai4curation/uniprot-orphan-analysis
  commit: f6a331cb47f61256ad070bbaa75567094ef64e8a
extraction: Original source line ranges with two context lines; not complete records. Structured fields
  are selected from the same archived snapshots. Sequence values are replaced by lengths and SHA-256 digests.
sources:
- url: https://rest.uniprot.org/uniprotkb/P49264.json
  retrieved_at: '2026-10-18T23:39:23.442793+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/uniprotkb/A0AAU9RUE5.json
  retrieved_at: '2026-10-18T23:39:23.615224+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/proteomes/UP000836841.json
  retrieved_at: '2026-10-18T23:39:24.049920+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/P49264?format=txt&versions=68
  retrieved_at: '2026-10-18T23:39:30.627321+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/P49264?format=txt&versions=77
  retrieved_at: '2026-10-18T23:39:32.718935+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/P49264?format=txt&versions=86
  retrieved_at: '2026-10-18T23:39:34.837170+00:00'
  uniprot_release: '2026_03'
observations:
  primary_accession: P49264
  alternative_accession: A0AAU9RUE5
  sequence_identical: true
  primary_sequence_length: 496
  alternative_sequence_length: 496
  shared_uniparc_id: UPI0000126CE3
  same_taxon: true
  reference_proteome: UP000836841
  proteome_is_reference: true
  proteome_taxon_matches: true
  primary_in_reference_proteome: false
  alternative_in_reference_proteome: true
  searched_reference_proteomes:
  - UP000836841
  primary_in_any_reference_proteome: false
  sampled_history_versions:
  - 68
  - 77
  - 86
  sampled_versions_with_proteome_links: []
current_records:
- primaryAccession: P49264
  entryType: UniProtKB reviewed (Swiss-Prot)
  entryAudit:
    firstPublicDate: '1996-02-01'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '1996-02-01'
    entryVersion: 88
    sequenceVersion: 1
  genes:
  - geneName:
      value: CYP71B1
  organism:
    scientificName: Thlaspi arvense
    taxonId: 13288
  sequence:
    length: 496
    sha256: 24912ddd19d0ff681fe1fb8310ec8696b19d526d8e3e0cbb97853eabd63b16cb
  uniProtKBCrossReferences: []
- primaryAccession: A0AAU9RUE5
  entryType: UniProtKB unreviewed (TrEMBL)
  entryAudit:
    firstPublicDate: '2024-11-27'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '2024-11-27'
    entryVersion: 7
    sequenceVersion: 1
  genes:
  - orfNames:
    - evidences:
      - evidenceCode: ECO:0000313
        source: EMBL
        id: CAH2047965.1
      value: TAV2_LOCUS8036
  organism:
    scientificName: Thlaspi arvense
    taxonId: 13288
  sequence:
    length: 496
    sha256: 24912ddd19d0ff681fe1fb8310ec8696b19d526d8e3e0cbb97853eabd63b16cb
  uniProtKBCrossReferences:
  - database: Proteomes
    id: UP000836841
    properties:
    - key: Component
      value: Chromosome 2
reference_proteomes:
- id: UP000836841
  proteomeType: Reference proteome
  taxonomy:
    scientificName: Thlaspi arvense
    commonName: Field penny-cress
    taxonId: 13288
    mnemonic: THLAR
unisave_records:
- entry_version: 68
  url: https://rest.uniprot.org/unisave/P49264?format=txt&versions=68
  entry_date: 26-NOV-2014, entry version 68.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 77
  url: https://rest.uniprot.org/unisave/P49264?format=txt&versions=77
  entry_date: 07-OCT-2020, entry version 77.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 86
  url: https://rest.uniprot.org/unisave/P49264?format=txt&versions=86
  entry_date: 27-NOV-2024, entry version 86.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
archived_sources:
- path: genes/THLAR/CYP71B1/CYP71B1-record-evidence.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/THLAR/CYP71B1/CYP71B1-record-evidence.yaml
  sha256: cc67494c11f6f87152093bf697b7ab317e43f59d56b6ba9ed6499d9c21aaa568
  excerpts:
  - start_line: 26
    end_line: 38
    text: |2
        alternative_sequence_length: 496
        shared_uniparc_id: UPI0000126CE3
        same_taxon: true
        reference_proteome: UP000836841
        proteome_is_reference: true
        proteome_taxon_matches: true
        primary_in_reference_proteome: false
        alternative_in_reference_proteome: true
        searched_reference_proteomes:
        - UP000836841
        primary_in_any_reference_proteome: false
        sampled_history_versions:
        - 68
  - start_line: 992
    end_line: 997
    text: |
      - entry_version: 68
        url: https://rest.uniprot.org/unisave/P49264?format=txt&versions=68
        entry_date: 26-NOV-2014, entry version 68.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 1062
    end_line: 1067
    text: |
      - entry_version: 77
        url: https://rest.uniprot.org/unisave/P49264?format=txt&versions=77
        entry_date: 07-OCT-2020, entry version 77.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 1135
    end_line: 1140
    text: |
      - entry_version: 86
        url: https://rest.uniprot.org/unisave/P49264?format=txt&versions=86
        entry_date: 27-NOV-2024, entry version 86.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
- path: genes/THLAR/CYP71B1/CYP71B1-bioinformatics/reference-counterparts/comparison.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/THLAR/CYP71B1/CYP71B1-bioinformatics/reference-counterparts/comparison.yaml
  sha256: b87835d9668e0704284cc9a6a300fc267677e1babe74dfd8ab593ac1a28114ce
  excerpts:
  - start_line: 25
    end_line: 29
    text: |2
        - -v
        - '1'
        target_sequence_count: 26379
        query_sha256: 68aedbab4bbd884ee1a222a0a05daef11c0704cc25232868d5e0adc6232ad823
        targets_sha256: 910a65b4aade115c4580367fef21e13622f7c9124925c8eb53c942c103d735d2
  - start_line: 44
    end_line: 48
    text: |2
          sha256: 910a65b4aade115c4580367fef21e13622f7c9124925c8eb53c942c103d735d2
        detailed_alignment_limit: 10
      candidate_count: 214
      candidates:
      - accession: A0AAU9RUE5
  - start_line: 52
    end_line: 64
    text: |2
        bit_score: 999.0
        global_score: 2566.0
        query_length: 496
        target_length: 496
        alignment_columns: 496
        identities: 496
        mismatches: 0
        gap_columns: 0
        identity_percent: 100.0
        query_coverage_percent: 100.0
        target_coverage_percent: 100.0
        substitutions: []
      - accession: A0AAU9RKN2
comparison:
  provenance:
    query_accession: P49264
    run_at: '2026-10-18T23:34:49.490666+00:00'
    biopython_version: '1.85'
    mmseqs_version: 18-8cc5c
    command:
    - mmseqs
    - easy-search
    - genes/THLAR/CYP71B1/CYP71B1-bioinformatics/reference-counterparts/query.fasta
    - .cache/orphan-curated/UP000836841.fasta
    - genes/THLAR/CYP71B1/CYP71B1-bioinformatics/reference-counterparts/search.tsv
    - genes/THLAR/CYP71B1/CYP71B1-bioinformatics/reference-counterparts/tmp
    - --threads
    - '4'
    - -s
    - '7.5'
    - -e
    - 1e-5
    - --max-seqs
    - '1000'
    - --format-output
    - query,target,pident,alnlen,qstart,qend,qlen,tstart,tend,tlen,evalue,bits
    - --remove-tmp-files
    - '1'
    - -v
    - '1'
    target_sequence_count: 26379
    query_sha256: 68aedbab4bbd884ee1a222a0a05daef11c0704cc25232868d5e0adc6232ad823
    targets_sha256: 910a65b4aade115c4580367fef21e13622f7c9124925c8eb53c942c103d735d2
    global_alignment:
      mode: global
      matrix: BLOSUM62
      open_gap: -10
      extend_gap: -0.5
      terminal_gaps_penalized: true
    identity_denominator: All global alignment columns, including gaps
    coverage_denominator: Full query/target length; numerator is paired nongap residues
    limitation: MMseqs2 heuristic search; no guarantee of exhaustive retrieval or locus equivalence
    target_source:
      url: https://rest.uniprot.org/uniprotkb/stream?query=proteome%3AUP000836841&format=fasta
      retrieved_at: '2026-10-18T23:32:46.697751+00:00'
      uniprot_release: '2026_03'
      sequence_count: 26379
      sha256: 910a65b4aade115c4580367fef21e13622f7c9124925c8eb53c942c103d735d2
    detailed_alignment_limit: 10
  candidate_count: 214
  retained_alignment_count: 10
  candidates:
  - accession: A0AAU9RUE5
    description: tr|A0AAU9RUE5|A0AAU9RUE5_THLAR Cytochrome P450 OS=Thlaspi arvense OX=13288 GN=TAV2_LOCUS8036
      PE=3 SV=1
    evalue: 0.0
    bit_score: 999.0
    global_score: 2566.0
    query_length: 496
    target_length: 496
    alignment_columns: 496
    identities: 496
    mismatches: 0
    gap_columns: 0
    identity_percent: 100.0
    query_coverage_percent: 100.0
    target_coverage_percent: 100.0
  - accession: A0AAU9RKN2
    description: tr|A0AAU9RKN2|A0AAU9RKN2_THLAR Cytochrome P450 OS=Thlaspi arvense OX=13288 GN=TAV2_LOCUS5026
      PE=3 SV=1
    evalue: 6.859e-250
    bit_score: 769.0
    global_score: 1972.0
    query_length: 496
    target_length: 507
    alignment_columns: 507
    identities: 359
    mismatches: 137
    gap_columns: 11
    identity_percent: 70.8087
    query_coverage_percent: 100.0
    target_coverage_percent: 97.8304
