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/P22643.json
  retrieved_at: '2026-10-18T23:39:21.849479+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/proteomes/UP001161920.json
  retrieved_at: '2026-10-18T23:39:21.998732+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/proteomes/UP001603991.json
  retrieved_at: '2026-10-18T23:39:22.149025+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/P22643?format=txt&versions=97
  retrieved_at: '2026-10-18T23:39:22.431616+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/P22643?format=txt&versions=110
  retrieved_at: '2026-10-18T23:39:26.653694+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/P22643?format=txt&versions=122
  retrieved_at: '2026-10-18T23:39:33.125919+00:00'
  uniprot_release: '2026_03'
observations:
  primary_accession: P22643
  alternative_accession: null
  sequence_identical: null
  primary_sequence_length: 310
  alternative_sequence_length: null
  shared_uniparc_id: null
  same_taxon: null
  reference_proteome: UP001161920
  proteome_is_reference: true
  proteome_taxon_matches: true
  primary_in_reference_proteome: false
  alternative_in_reference_proteome: null
  searched_reference_proteomes:
  - UP001161920
  - UP001603991
  primary_in_any_reference_proteome: false
  sampled_history_versions:
  - 97
  - 110
  - 122
  sampled_versions_with_proteome_links: []
current_records:
- primaryAccession: P22643
  entryType: UniProtKB reviewed (Swiss-Prot)
  entryAudit:
    firstPublicDate: '1991-08-01'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '1995-02-01'
    entryVersion: 127
    sequenceVersion: 2
  genes:
  - geneName:
      value: dhlA
  organism:
    scientificName: Xanthobacter autotrophicus
    taxonId: 280
  sequence:
    length: 310
    sha256: 7c3388a577fe60ea11c4f16a48c345a295fbdba41a8a8a525d9d97a8f1b4f68b
  uniProtKBCrossReferences: []
reference_proteomes:
- id: UP001161920
  proteomeType: Reference proteome
  taxonomy:
    scientificName: Xanthobacter autotrophicus
    taxonId: 280
    mnemonic: XANAU
- id: UP001603991
  proteomeType: Reference proteome
  taxonomy:
    scientificName: Xanthobacter autotrophicus
    taxonId: 280
    mnemonic: XANAU
unisave_records:
- entry_version: 97
  url: https://rest.uniprot.org/unisave/P22643?format=txt&versions=97
  entry_date: 14-OCT-2015, entry version 97.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 110
  url: https://rest.uniprot.org/unisave/P22643?format=txt&versions=110
  entry_date: 02-DEC-2020, entry version 110.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 122
  url: https://rest.uniprot.org/unisave/P22643?format=txt&versions=122
  entry_date: 27-NOV-2024, entry version 122.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
archived_sources:
- path: genes/XANAU/dhlA/dhlA-record-evidence.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/XANAU/dhlA/dhlA-record-evidence.yaml
  sha256: 313837b10ab1ba3c67e90eee2aa63452edd67daf95dd9db0660674b0c86fd42a
  excerpts:
  - start_line: 35
    end_line: 39
    text: |2
        - UP001161920
        - UP001603991
        primary_in_any_reference_proteome: false
        sampled_history_versions:
        - 97
  - start_line: 1601
    end_line: 1606
    text: |
      - entry_version: 97
        url: https://rest.uniprot.org/unisave/P22643?format=txt&versions=97
        entry_date: 14-OCT-2015, entry version 97.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 1824
    end_line: 1829
    text: |
      - entry_version: 110
        url: https://rest.uniprot.org/unisave/P22643?format=txt&versions=110
        entry_date: 02-DEC-2020, entry version 110.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 2091
    end_line: 2096
    text: |
      - entry_version: 122
        url: https://rest.uniprot.org/unisave/P22643?format=txt&versions=122
        entry_date: 27-NOV-2024, entry version 122.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
- path: genes/XANAU/dhlA/dhlA-bioinformatics/reference-counterparts/comparison.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/XANAU/dhlA/dhlA-bioinformatics/reference-counterparts/comparison.yaml
  sha256: 4bd248799a9148abb2b1dbf123eb44531b051fec05a2c8444c0fb4d013168a9f
  excerpts:
  - start_line: 25
    end_line: 29
    text: |2
        - -v
        - '1'
        target_sequence_count: 9703
        query_sha256: 0be7f6873e597886f3b46fc5743f1730f8b123a5f0fdd1d80591922802856eb2
        targets_sha256: 077766436b1474bc465d0cc25baa18c37a20fd74918e9ba3aac85830cd4a6a0a
  - start_line: 55
    end_line: 59
    text: |2
          - UP001603991
        detailed_alignment_limit: 10
      candidate_count: 9
      candidates:
      - accession: A0ACG3ZSA9
comparison:
  provenance:
    query_accession: P22643
    run_at: '2026-10-18T23:34:44.357402+00:00'
    biopython_version: '1.85'
    mmseqs_version: 18-8cc5c
    command:
    - mmseqs
    - easy-search
    - genes/XANAU/dhlA/dhlA-bioinformatics/reference-counterparts/query.fasta
    - .cache/orphan-curated/UP001161920__UP001603991.fasta
    - genes/XANAU/dhlA/dhlA-bioinformatics/reference-counterparts/search.tsv
    - genes/XANAU/dhlA/dhlA-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: 9703
    query_sha256: 0be7f6873e597886f3b46fc5743f1730f8b123a5f0fdd1d80591922802856eb2
    targets_sha256: 077766436b1474bc465d0cc25baa18c37a20fd74918e9ba3aac85830cd4a6a0a
    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:
      sources:
      - url: https://rest.uniprot.org/uniprotkb/stream?query=proteome%3AUP001161920&format=fasta
        retrieved_at: '2026-10-18T23:32:41.911171+00:00'
        uniprot_release: '2026_03'
        sequence_count: 4758
        sha256: 3e0824cfe4b05e24b57068c39be155305321a1920a6db1e42f468ed8294bc635
      - url: https://rest.uniprot.org/uniprotkb/stream?query=proteome%3AUP001603991&format=fasta
        retrieved_at: '2026-10-18T23:32:49.253374+00:00'
        uniprot_release: '2026_03'
        sequence_count: 4945
        sha256: abf27c9f3610ea968d00c813d465864fa3d6bc975d774105b0a1e3de4f5154e8
      sequence_count: 9703
      sha256: 077766436b1474bc465d0cc25baa18c37a20fd74918e9ba3aac85830cd4a6a0a
      proteomes:
      - UP001161920
      - UP001603991
    detailed_alignment_limit: 10
  candidate_count: 9
  retained_alignment_count: 9
  candidates:
  - accession: A0ACG3ZSA9
    description: tr|A0ACG3ZSA9|A0ACG3ZSA9_XANAU Alpha/beta hydrolase OS=Xanthobacter autotrophicus OX=280
      GN=V5F46_05145 PE=4 SV=1
    evalue: 5.14e-16
    bit_score: 78.0
    global_score: 191.0
    query_length: 310
    target_length: 309
    alignment_columns: 359
    identities: 90
    mismatches: 170
    gap_columns: 99
    identity_percent: 25.0696
    query_coverage_percent: 83.871
    target_coverage_percent: 84.1424
  - accession: A0ACG2KQT6
    description: tr|A0ACG2KQT6|A0ACG2KQT6_XANAU AB hydrolase-1 domain-containing protein (Fragment) OS=Xanthobacter
      autotrophicus OX=280 GN=K9U40_23710 PE=4 SV=1
    evalue: 3.015e-34
    bit_score: 133.0
    global_score: 181.0
    query_length: 310
    target_length: 152
    alignment_columns: 349
    identities: 61
    mismatches: 52
    gap_columns: 236
    identity_percent: 17.4785
    query_coverage_percent: 36.4516
    target_coverage_percent: 74.3421
