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/D2KBH9.json
  retrieved_at: '2026-10-18T23:38:54.200516+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/uniprotkb/A0A4U8UYW6.json
  retrieved_at: '2026-10-18T23:38:54.363195+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/proteomes/UP000298663.json
  retrieved_at: '2026-10-18T23:38:54.515643+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/D2KBH9?format=txt&versions=30
  retrieved_at: '2026-10-18T23:38:56.122532+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/D2KBH9?format=txt&versions=51
  retrieved_at: '2026-10-18T23:38:59.630552+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/D2KBH9?format=txt&versions=56
  retrieved_at: '2026-10-18T23:38:59.931601+00:00'
  uniprot_release: '2026_03'
observations:
  primary_accession: D2KBH9
  alternative_accession: A0A4U8UYW6
  sequence_identical: false
  primary_sequence_length: 418
  alternative_sequence_length: 418
  shared_uniparc_id: null
  same_taxon: true
  reference_proteome: UP000298663
  proteome_is_reference: true
  proteome_taxon_matches: true
  primary_in_reference_proteome: false
  alternative_in_reference_proteome: true
  searched_reference_proteomes:
  - UP000298663
  primary_in_any_reference_proteome: false
  sampled_history_versions:
  - 30
  - 51
  - 56
  sampled_versions_with_proteome_links: []
current_records:
- primaryAccession: D2KBH9
  entryType: UniProtKB reviewed (Swiss-Prot)
  entryAudit:
    firstPublicDate: '2017-11-22'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '2010-02-09'
    entryVersion: 58
    sequenceVersion: 1
  organism:
    scientificName: Steinernema carpocapsae
    taxonId: 34508
  sequence:
    length: 418
    sha256: 03b014a49e0b1a871635834ff111c35830524b5164bcff4be9a3aeb58152ec87
  uniProtKBCrossReferences: []
- primaryAccession: A0A4U8UYW6
  entryType: UniProtKB unreviewed (TrEMBL)
  entryAudit:
    firstPublicDate: '2019-07-31'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '2019-07-31'
    entryVersion: 18
    sequenceVersion: 1
  genes:
  - orfNames:
    - evidences:
      - evidenceCode: ECO:0000313
        source: EMBL
        id: TMS38119.1
      value: L596_004914
  organism:
    scientificName: Steinernema carpocapsae
    taxonId: 34508
  sequence:
    length: 418
    sha256: db22e4f3668a9dae6763186d3c707d4ac7799963c5c753f8d3e12bf66fe51c58
  uniProtKBCrossReferences:
  - database: Proteomes
    id: UP000298663
    properties:
    - key: Component
      value: Unassembled WGS sequence
reference_proteomes:
- id: UP000298663
  proteomeType: Reference proteome
  taxonomy:
    scientificName: Steinernema carpocapsae
    commonName: Entomopathogenic nematode
    taxonId: 34508
    mnemonic: STECR
unisave_records:
- entry_version: 30
  url: https://rest.uniprot.org/unisave/D2KBH9?format=txt&versions=30
  entry_date: 09-DEC-2015, entry version 30.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 51
  url: https://rest.uniprot.org/unisave/D2KBH9?format=txt&versions=51
  entry_date: 02-DEC-2020, entry version 51.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 56
  url: https://rest.uniprot.org/unisave/D2KBH9?format=txt&versions=56
  entry_date: 27-NOV-2024, entry version 56.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
archived_sources:
- path: genes/STECR/nas-8/nas-8-record-evidence.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/STECR/nas-8/nas-8-record-evidence.yaml
  sha256: 00222822dee4b8a32a97a6a1728264ccdfe4b7b504eccfcf81473e520a69d5b4
  excerpts:
  - start_line: 26
    end_line: 38
    text: |2
        alternative_sequence_length: 418
        shared_uniparc_id: null
        same_taxon: true
        reference_proteome: UP000298663
        proteome_is_reference: true
        proteome_taxon_matches: true
        primary_in_reference_proteome: false
        alternative_in_reference_proteome: true
        searched_reference_proteomes:
        - UP000298663
        primary_in_any_reference_proteome: false
        sampled_history_versions:
        - 30
  - start_line: 1496
    end_line: 1501
    text: |
      - entry_version: 30
        url: https://rest.uniprot.org/unisave/D2KBH9?format=txt&versions=30
        entry_date: 09-DEC-2015, entry version 30.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 1576
    end_line: 1581
    text: |
      - entry_version: 51
        url: https://rest.uniprot.org/unisave/D2KBH9?format=txt&versions=51
        entry_date: 02-DEC-2020, entry version 51.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 1710
    end_line: 1715
    text: |
      - entry_version: 56
        url: https://rest.uniprot.org/unisave/D2KBH9?format=txt&versions=56
        entry_date: 27-NOV-2024, entry version 56.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
- path: genes/STECR/nas-8/nas-8-bioinformatics/reference-counterparts/comparison.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/STECR/nas-8/nas-8-bioinformatics/reference-counterparts/comparison.yaml
  sha256: d26fd00618efed4be6da69693e1758a683062a547f13f7b751dcb948e7f07ea8
  excerpts:
  - start_line: 25
    end_line: 29
    text: |2
        - -v
        - '1'
        target_sequence_count: 35146
        query_sha256: 9a745fc7c7498ba612855f862695d349e9ab97ce3162c9255d66858eaccbd8d5
        targets_sha256: 8068d434445c35d5097e6fa7134463425af180d741383de96e953f7dd53e2f90
  - start_line: 44
    end_line: 48
    text: |2
          sha256: 8068d434445c35d5097e6fa7134463425af180d741383de96e953f7dd53e2f90
        detailed_alignment_limit: 10
      candidate_count: 44
      candidates:
      - accession: A0A4U8UYW6
  - start_line: 52
    end_line: 64
    text: |2
        bit_score: 865.0
        global_score: 2249.0
        query_length: 418
        target_length: 418
        alignment_columns: 418
        identities: 417
        mismatches: 1
        gap_columns: 0
        identity_percent: 99.7608
        query_coverage_percent: 100.0
        target_coverage_percent: 100.0
        substitutions:
        - query_position: 335
comparison:
  provenance:
    query_accession: D2KBH9
    run_at: '2026-10-18T23:33:29.831401+00:00'
    biopython_version: '1.85'
    mmseqs_version: 18-8cc5c
    command:
    - mmseqs
    - easy-search
    - genes/STECR/nas-8/nas-8-bioinformatics/reference-counterparts/query.fasta
    - .cache/orphan-curated/UP000298663.fasta
    - genes/STECR/nas-8/nas-8-bioinformatics/reference-counterparts/search.tsv
    - genes/STECR/nas-8/nas-8-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: 35146
    query_sha256: 9a745fc7c7498ba612855f862695d349e9ab97ce3162c9255d66858eaccbd8d5
    targets_sha256: 8068d434445c35d5097e6fa7134463425af180d741383de96e953f7dd53e2f90
    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%3AUP000298663&format=fasta
      retrieved_at: '2026-10-18T23:32:36.205085+00:00'
      uniprot_release: '2026_03'
      sequence_count: 35146
      sha256: 8068d434445c35d5097e6fa7134463425af180d741383de96e953f7dd53e2f90
    detailed_alignment_limit: 10
  candidate_count: 44
  retained_alignment_count: 10
  candidates:
  - accession: A0A4U8UYW6
    description: tr|A0A4U8UYW6|A0A4U8UYW6_STECR Metalloendopeptidase OS=Steinernema carpocapsae OX=34508
      GN=L596_004914 PE=4 SV=1
    evalue: 1.159e-284
    bit_score: 865.0
    global_score: 2249.0
    query_length: 418
    target_length: 418
    alignment_columns: 418
    identities: 417
    mismatches: 1
    gap_columns: 0
    identity_percent: 99.7608
    query_coverage_percent: 100.0
    target_coverage_percent: 100.0
  - accession: A0A4U5N1Z8
    description: tr|A0A4U5N1Z8|A0A4U5N1Z8_STECR Metalloendopeptidase OS=Steinernema carpocapsae OX=34508
      GN=L596_017540 PE=4 SV=1
    evalue: 2.059e-95
    bit_score: 318.0
    global_score: 827.5
    query_length: 418
    target_length: 366
    alignment_columns: 446
    identities: 177
    mismatches: 161
    gap_columns: 108
    identity_percent: 39.6861
    query_coverage_percent: 80.8612
    target_coverage_percent: 92.3497
