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/P06519.json
  retrieved_at: '2026-10-18T23:39:05.053689+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/uniprotkb/A0A1L7N7J0.json
  retrieved_at: '2026-10-18T23:39:05.217804+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/proteomes/UP000218731.json
  retrieved_at: '2026-10-18T23:39:05.366306+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/P06519?format=txt&versions=110
  retrieved_at: '2026-10-18T23:39:07.426071+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/P06519?format=txt&versions=124
  retrieved_at: '2026-10-18T23:39:08.323066+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/P06519?format=txt&versions=136
  retrieved_at: '2026-10-18T23:39:08.617931+00:00'
  uniprot_release: '2026_03'
observations:
  primary_accession: P06519
  alternative_accession: A0A1L7N7J0
  sequence_identical: false
  primary_sequence_length: 566
  alternative_sequence_length: 563
  shared_uniparc_id: null
  same_taxon: true
  reference_proteome: UP000218731
  proteome_is_reference: true
  proteome_taxon_matches: true
  primary_in_reference_proteome: false
  alternative_in_reference_proteome: true
  searched_reference_proteomes:
  - UP000218731
  primary_in_any_reference_proteome: false
  sampled_history_versions:
  - 110
  - 124
  - 136
  sampled_versions_with_proteome_links: []
current_records:
- primaryAccession: P06519
  entryType: UniProtKB reviewed (Swiss-Prot)
  entryAudit:
    firstPublicDate: '1988-01-01'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '1988-08-01'
    entryVersion: 141
    sequenceVersion: 1
  genes:
  - geneName:
      value: xylR
  geneLocations:
  - value: TOL pWW0
    geneEncodingType: Plasmid
  organism:
    scientificName: Pseudomonas putida
    taxonId: 303
  sequence:
    length: 566
    sha256: 9a1475b5aa7bfc18ca70e47c5cfacd087ed1688d0834b76137d981e3524e8405
  uniProtKBCrossReferences: []
- primaryAccession: A0A1L7N7J0
  entryType: UniProtKB unreviewed (TrEMBL)
  entryAudit:
    firstPublicDate: '2017-03-15'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '2017-03-15'
    entryVersion: 39
    sequenceVersion: 1
  genes:
  - orfNames:
    - evidences:
      - evidenceCode: ECO:0000313
        source: EMBL
        id: BAW21414.1
      value: KF715C_ch8410
  organism:
    scientificName: Pseudomonas putida
    taxonId: 303
  sequence:
    length: 563
    sha256: fe072ade1668f742c2502d9dd2459824fe4339d33753f0bf06fe2a21667830fc
  uniProtKBCrossReferences:
  - database: Proteomes
    id: UP000218731
    properties:
    - key: Component
      value: Chromosome 1
reference_proteomes:
- id: UP000218731
  proteomeType: Reference proteome
  taxonomy:
    scientificName: Pseudomonas putida
    synonyms:
    - Arthrobacter siderocapsulatus
    taxonId: 303
    mnemonic: PSEPU
unisave_records:
- entry_version: 110
  url: https://rest.uniprot.org/unisave/P06519?format=txt&versions=110
  entry_date: 24-JUN-2015, entry version 110.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 124
  url: https://rest.uniprot.org/unisave/P06519?format=txt&versions=124
  entry_date: 02-DEC-2020, entry version 124.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 136
  url: https://rest.uniprot.org/unisave/P06519?format=txt&versions=136
  entry_date: 27-NOV-2024, entry version 136.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
archived_sources:
- path: genes/PSEPK/xylR/xylR-record-evidence.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/PSEPK/xylR/xylR-record-evidence.yaml
  sha256: b62b99e4121e74541616f0d5729651057566343eaeb46dd2789c89a6677a55d1
  excerpts:
  - start_line: 26
    end_line: 38
    text: |2
        alternative_sequence_length: 563
        shared_uniparc_id: null
        same_taxon: true
        reference_proteome: UP000218731
        proteome_is_reference: true
        proteome_taxon_matches: true
        primary_in_reference_proteome: false
        alternative_in_reference_proteome: true
        searched_reference_proteomes:
        - UP000218731
        primary_in_any_reference_proteome: false
        sampled_history_versions:
        - 110
  - start_line: 170
    end_line: 174
    text: |2
        geneLocations:
        - value: TOL pWW0
          geneEncodingType: Plasmid
        keywords:
        - id: KW-0010
  - start_line: 1279
    end_line: 1284
    text: |
      - entry_version: 110
        url: https://rest.uniprot.org/unisave/P06519?format=txt&versions=110
        entry_date: 24-JUN-2015, entry version 110.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 1403
    end_line: 1408
    text: |
      - entry_version: 124
        url: https://rest.uniprot.org/unisave/P06519?format=txt&versions=124
        entry_date: 02-DEC-2020, entry version 124.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 1524
    end_line: 1529
    text: |
      - entry_version: 136
        url: https://rest.uniprot.org/unisave/P06519?format=txt&versions=136
        entry_date: 27-NOV-2024, entry version 136.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
- path: genes/PSEPK/xylR/xylR-bioinformatics/reference-counterparts/comparison.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/PSEPK/xylR/xylR-bioinformatics/reference-counterparts/comparison.yaml
  sha256: 75c121fff4e46190c4e65120d29512c6a322dd90918de5aefdade5dbd1956338
  excerpts:
  - start_line: 25
    end_line: 29
    text: |2
        - -v
        - '1'
        target_sequence_count: 6919
        query_sha256: 22bf1a24301db69118b50f530972b760651809a5f768673df2291103608b46e5
        targets_sha256: df9f4f76b6f2b00ff1d86732af293f625a39f8dedb68094238922047df2e8e50
  - start_line: 44
    end_line: 48
    text: |2
          sha256: df9f4f76b6f2b00ff1d86732af293f625a39f8dedb68094238922047df2e8e50
        detailed_alignment_limit: 10
      candidate_count: 24
      candidates:
      - accession: A0A1L7N7J0
  - start_line: 52
    end_line: 64
    text: |2
        bit_score: 786.0
        global_score: 1987.0
        query_length: 566
        target_length: 563
        alignment_columns: 570
        identities: 380
        mismatches: 179
        gap_columns: 11
        identity_percent: 66.6667
        query_coverage_percent: 98.7633
        target_coverage_percent: 99.2895
        substitutions:
        - query_position: 2
comparison:
  provenance:
    query_accession: P06519
    run_at: '2026-10-18T23:34:26.422638+00:00'
    biopython_version: '1.85'
    mmseqs_version: 18-8cc5c
    command:
    - mmseqs
    - easy-search
    - genes/PSEPK/xylR/xylR-bioinformatics/reference-counterparts/query.fasta
    - .cache/orphan-curated/UP000218731.fasta
    - genes/PSEPK/xylR/xylR-bioinformatics/reference-counterparts/search.tsv
    - genes/PSEPK/xylR/xylR-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: 6919
    query_sha256: 22bf1a24301db69118b50f530972b760651809a5f768673df2291103608b46e5
    targets_sha256: df9f4f76b6f2b00ff1d86732af293f625a39f8dedb68094238922047df2e8e50
    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%3AUP000218731&format=fasta
      retrieved_at: '2026-10-18T23:32:23.400652+00:00'
      uniprot_release: '2026_03'
      sequence_count: 6919
      sha256: df9f4f76b6f2b00ff1d86732af293f625a39f8dedb68094238922047df2e8e50
    detailed_alignment_limit: 10
  candidate_count: 24
  retained_alignment_count: 10
  candidates:
  - accession: A0A1L7N7J0
    description: tr|A0A1L7N7J0|A0A1L7N7J0_PSEPU Transcriptional activator of xyl-upper pathway operon
      OS=Pseudomonas putida OX=303 GN=KF715C_ch8410 PE=4 SV=1
    evalue: 5.682e-255
    bit_score: 786.0
    global_score: 1987.0
    query_length: 566
    target_length: 563
    alignment_columns: 570
    identities: 380
    mismatches: 179
    gap_columns: 11
    identity_percent: 66.6667
    query_coverage_percent: 98.7633
    target_coverage_percent: 99.2895
  - accession: A0A1L7N7S1
    description: tr|A0A1L7N7S1|A0A1L7N7S1_PSEPU Transcriptional regulator FhpR OS=Pseudomonas putida OX=303
      GN=KF715C_ch9450 PE=4 SV=1
    evalue: 1.359e-71
    bit_score: 252.0
    global_score: 638.5
    query_length: 566
    target_length: 518
    alignment_columns: 617
    identities: 199
    mismatches: 268
    gap_columns: 150
    identity_percent: 32.2528
    query_coverage_percent: 82.5088
    target_coverage_percent: 90.1544