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/P18004.json
  retrieved_at: '2026-10-18T23:39:16.162029+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/proteomes/UP000000625.json
  retrieved_at: '2026-10-18T23:39:16.324483+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/P18004?format=txt&versions=89
  retrieved_at: '2026-10-18T23:39:18.536993+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/P18004?format=txt&versions=105
  retrieved_at: '2026-10-18T23:39:20.739615+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/P18004?format=txt&versions=119
  retrieved_at: '2026-10-18T23:39:22.641589+00:00'
  uniprot_release: '2026_03'
observations:
  primary_accession: P18004
  alternative_accession: null
  sequence_identical: null
  primary_sequence_length: 875
  alternative_sequence_length: null
  shared_uniparc_id: null
  same_taxon: null
  reference_proteome: UP000000625
  proteome_is_reference: true
  proteome_taxon_matches: true
  primary_in_reference_proteome: false
  alternative_in_reference_proteome: null
  searched_reference_proteomes:
  - UP000000625
  primary_in_any_reference_proteome: false
  sampled_history_versions:
  - 89
  - 105
  - 119
  sampled_versions_with_proteome_links: []
current_records:
- primaryAccession: P18004
  entryType: UniProtKB reviewed (Swiss-Prot)
  entryAudit:
    firstPublicDate: '1990-11-01'
    lastAnnotationUpdateDate: '2026-01-28'
    lastSequenceUpdateDate: '1990-11-01'
    entryVersion: 122
    sequenceVersion: 1
  genes:
  - geneName:
      value: traC
    orderedLocusNames:
    - value: ECOK12F084
  geneLocations:
  - value: F
    geneEncodingType: Plasmid
  organism:
    scientificName: Escherichia coli (strain K12)
    taxonId: 83333
  sequence:
    length: 875
    sha256: 52af2ea5d366461b7d8e62ce3482a51c772b2d2da750a5b4483db4858d5854b9
  uniProtKBCrossReferences: []
reference_proteomes:
- id: UP000000625
  proteomeType: Reference proteome
  taxonomy:
    scientificName: Escherichia coli (strain K12)
    taxonId: 83333
    mnemonic: ECOLI
unisave_records:
- entry_version: 89
  url: https://rest.uniprot.org/unisave/P18004?format=txt&versions=89
  entry_date: 11-NOV-2015, entry version 89.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 105
  url: https://rest.uniprot.org/unisave/P18004?format=txt&versions=105
  entry_date: 02-DEC-2020, entry version 105.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 119
  url: https://rest.uniprot.org/unisave/P18004?format=txt&versions=119
  entry_date: 27-NOV-2024, entry version 119.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
archived_sources:
- path: genes/ECOLI/traC/traC-record-evidence.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/ECOLI/traC/traC-record-evidence.yaml
  sha256: 497b69edc0f29a144071c1bb10afbcf96733ad32a38d3a38daee5561aa2c4db2
  excerpts:
  - start_line: 31
    end_line: 35
    text: |2
        searched_reference_proteomes:
        - UP000000625
        primary_in_any_reference_proteome: false
        sampled_history_versions:
        - 89
  - start_line: 107
    end_line: 111
    text: |2
        geneLocations:
        - value: F
          geneEncodingType: Plasmid
        keywords:
        - id: KW-0997
  - start_line: 551
    end_line: 556
    text: |
      - entry_version: 89
        url: https://rest.uniprot.org/unisave/P18004?format=txt&versions=89
        entry_date: 11-NOV-2015, entry version 89.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 656
    end_line: 661
    text: |
      - entry_version: 105
        url: https://rest.uniprot.org/unisave/P18004?format=txt&versions=105
        entry_date: 02-DEC-2020, entry version 105.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 760
    end_line: 765
    text: |
      - entry_version: 119
        url: https://rest.uniprot.org/unisave/P18004?format=txt&versions=119
        entry_date: 27-NOV-2024, entry version 119.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
- path: genes/ECOLI/traC/traC-bioinformatics/reference-counterparts/comparison.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/ECOLI/traC/traC-bioinformatics/reference-counterparts/comparison.yaml
  sha256: 91ec35ad479316506eb37b5e655a5a74868d0c4516b190652254864fcacccd05
  excerpts:
  - start_line: 25
    end_line: 29
    text: |2
        - -v
        - '1'
        target_sequence_count: 4403
        query_sha256: 0f25bd322c6fcd63c8f98077170f9dd5c89e158645d10eac77f0d7f798d90809
        targets_sha256: a8052a607a98d2444c9d5dd685bd1370150df8c5570c3116811544bbf3d093a2
  - start_line: 44
    end_line: 47
    text: |2
          sha256: a8052a607a98d2444c9d5dd685bd1370150df8c5570c3116811544bbf3d093a2
        detailed_alignment_limit: 10
      candidate_count: 0
      candidates: []
comparison:
  provenance:
    query_accession: P18004
    run_at: '2026-10-18T23:34:40.829081+00:00'
    biopython_version: '1.85'
    mmseqs_version: 18-8cc5c
    command:
    - mmseqs
    - easy-search
    - genes/ECOLI/traC/traC-bioinformatics/reference-counterparts/query.fasta
    - .cache/orphan-curated/UP000000625.fasta
    - genes/ECOLI/traC/traC-bioinformatics/reference-counterparts/search.tsv
    - genes/ECOLI/traC/traC-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: 4403
    query_sha256: 0f25bd322c6fcd63c8f98077170f9dd5c89e158645d10eac77f0d7f798d90809
    targets_sha256: a8052a607a98d2444c9d5dd685bd1370150df8c5570c3116811544bbf3d093a2
    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%3AUP000000625&format=fasta
      retrieved_at: '2026-10-18T23:32:09.369626+00:00'
      uniprot_release: '2026_03'
      sequence_count: 4403
      sha256: a8052a607a98d2444c9d5dd685bd1370150df8c5570c3116811544bbf3d093a2
    detailed_alignment_limit: 10
  candidate_count: 0
  retained_alignment_count: 0
  candidates: []