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/L7N6F8.json
  retrieved_at: '2026-10-18T23:39:01.107459+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/uniprotkb/A0ABQ8JBE4.json
  retrieved_at: '2026-10-18T23:39:01.283116+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/proteomes/UP000887458.json
  retrieved_at: '2026-10-18T23:39:02.156192+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/L7N6F8?format=txt&versions=10
  retrieved_at: '2026-10-18T23:39:03.229501+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/L7N6F8?format=txt&versions=26
  retrieved_at: '2026-10-18T23:39:04.439983+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/L7N6F8?format=txt&versions=33
  retrieved_at: '2026-10-18T23:39:05.745429+00:00'
  uniprot_release: '2026_03'
observations:
  primary_accession: L7N6F8
  alternative_accession: A0ABQ8JBE4
  sequence_identical: false
  primary_sequence_length: 90
  alternative_sequence_length: 91
  shared_uniparc_id: null
  same_taxon: true
  reference_proteome: UP000887458
  proteome_is_reference: true
  proteome_taxon_matches: true
  primary_in_reference_proteome: false
  alternative_in_reference_proteome: true
  searched_reference_proteomes:
  - UP000887458
  primary_in_any_reference_proteome: false
  sampled_history_versions:
  - 10
  - 26
  - 33
  sampled_versions_with_proteome_links:
  - 33
current_records:
- primaryAccession: L7N6F8
  entryType: UniProtKB reviewed (Swiss-Prot)
  entryAudit:
    firstPublicDate: '2019-01-16'
    lastAnnotationUpdateDate: '2026-06-10'
    lastSequenceUpdateDate: '2013-04-03'
    entryVersion: 38
    sequenceVersion: 1
  organism:
    scientificName: Dermatophagoides pteronyssinus
    taxonId: 6956
  sequence:
    length: 90
    sha256: db4296cb5c463df0b18317d1e9087687c71777e960e30b5ec65adba591c25638
  uniProtKBCrossReferences: []
- primaryAccession: A0ABQ8JBE4
  entryType: UniProtKB unreviewed (TrEMBL)
  entryAudit:
    firstPublicDate: '2025-10-08'
    lastAnnotationUpdateDate: '2026-06-10'
    lastSequenceUpdateDate: '2025-10-08'
    entryVersion: 3
    sequenceVersion: 1
  genes:
  - orfNames:
    - evidences:
      - evidenceCode: ECO:0000313
        source: EMBL
        id: KAH9419710.1
      value: DERP_001540
  organism:
    scientificName: Dermatophagoides pteronyssinus
    taxonId: 6956
  sequence:
    length: 91
    sha256: 756c4e6b728ce9e2080f5d16862288f99452dc7a601eb33e626122d765cf45ae
  uniProtKBCrossReferences:
  - database: Proteomes
    id: UP000887458
    properties:
    - key: Component
      value: Unassembled WGS sequence
reference_proteomes:
- id: UP000887458
  proteomeType: Reference proteome
  taxonomy:
    scientificName: Dermatophagoides pteronyssinus
    commonName: European house dust mite
    taxonId: 6956
    mnemonic: DERPT
unisave_records:
- entry_version: 10
  url: https://rest.uniprot.org/unisave/L7N6F8?format=txt&versions=10
  entry_date: 09-DEC-2015, entry version 10.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 26
  url: https://rest.uniprot.org/unisave/L7N6F8?format=txt&versions=26
  entry_date: 17-JUN-2020, entry version 26.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 33
  url: https://rest.uniprot.org/unisave/L7N6F8?format=txt&versions=33
  entry_date: 24-JUL-2024, entry version 33.
  proteomes:
  - UP000515146
  reference_proteome_keyword: true
  record_text: ''
archived_sources:
- path: genes/DERPT/Derp23/Derp23-record-evidence.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/DERPT/Derp23/Derp23-record-evidence.yaml
  sha256: eba617b1be904e24e94940078efcabebd66cb4b46ef43556220fe679f6980706
  excerpts:
  - start_line: 26
    end_line: 38
    text: |2
        alternative_sequence_length: 91
        shared_uniparc_id: null
        same_taxon: true
        reference_proteome: UP000887458
        proteome_is_reference: true
        proteome_taxon_matches: true
        primary_in_reference_proteome: false
        alternative_in_reference_proteome: true
        searched_reference_proteomes:
        - UP000887458
        primary_in_any_reference_proteome: false
        sampled_history_versions:
        - 10
  - start_line: 1207
    end_line: 1212
    text: |
      - entry_version: 10
        url: https://rest.uniprot.org/unisave/L7N6F8?format=txt&versions=10
        entry_date: 09-DEC-2015, entry version 10.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 1262
    end_line: 1267
    text: |
      - entry_version: 26
        url: https://rest.uniprot.org/unisave/L7N6F8?format=txt&versions=26
        entry_date: 17-JUN-2020, entry version 26.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 1387
    end_line: 1393
    text: |
      - entry_version: 33
        url: https://rest.uniprot.org/unisave/L7N6F8?format=txt&versions=33
        entry_date: 24-JUL-2024, entry version 33.
        proteomes:
        - UP000515146
        reference_proteome_keyword: true
        record_text: |
- path: genes/DERPT/Derp23/Derp23-bioinformatics/reference-counterparts/comparison.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/DERPT/Derp23/Derp23-bioinformatics/reference-counterparts/comparison.yaml
  sha256: 22f2143fcb52a3019720ae5f9aba5331a76f599d98d4ef3547928ed9ab98e34f
  excerpts:
  - start_line: 25
    end_line: 29
    text: |2
        - -v
        - '1'
        target_sequence_count: 14675
        query_sha256: 215a5f17909ff38375b0eb132de4628e838a9aab8608a90835d61b657b1b1344
        targets_sha256: ca828b473340f0a27bc7c92cebf1e36990cd53a1f6ca120c9c19829f0943499d
  - start_line: 44
    end_line: 48
    text: |2
          sha256: ca828b473340f0a27bc7c92cebf1e36990cd53a1f6ca120c9c19829f0943499d
        detailed_alignment_limit: 10
      candidate_count: 4
      candidates:
      - accession: A0ABQ8JBE4
  - start_line: 52
    end_line: 64
    text: |2
        bit_score: 149.0
        global_score: 379.0
        query_length: 90
        target_length: 91
        alignment_columns: 98
        identities: 74
        mismatches: 9
        gap_columns: 15
        identity_percent: 75.5102
        query_coverage_percent: 92.2222
        target_coverage_percent: 91.2088
        substitutions:
        - query_position: 26
comparison:
  provenance:
    query_accession: L7N6F8
    run_at: '2026-10-18T23:34:23.076084+00:00'
    biopython_version: '1.85'
    mmseqs_version: 18-8cc5c
    command:
    - mmseqs
    - easy-search
    - genes/DERPT/Derp23/Derp23-bioinformatics/reference-counterparts/query.fasta
    - .cache/orphan-curated/UP000887458.fasta
    - genes/DERPT/Derp23/Derp23-bioinformatics/reference-counterparts/search.tsv
    - genes/DERPT/Derp23/Derp23-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: 14675
    query_sha256: 215a5f17909ff38375b0eb132de4628e838a9aab8608a90835d61b657b1b1344
    targets_sha256: ca828b473340f0a27bc7c92cebf1e36990cd53a1f6ca120c9c19829f0943499d
    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%3AUP000887458&format=fasta
      retrieved_at: '2026-10-18T23:32:43.489103+00:00'
      uniprot_release: '2026_03'
      sequence_count: 14675
      sha256: ca828b473340f0a27bc7c92cebf1e36990cd53a1f6ca120c9c19829f0943499d
    detailed_alignment_limit: 10
  candidate_count: 4
  retained_alignment_count: 4
  candidates:
  - accession: A0ABQ8JBE4
    description: tr|A0ABQ8JBE4|A0ABQ8JBE4_DERPT Chitin-binding type-2 domain-containing protein OS=Dermatophagoides
      pteronyssinus OX=6956 GN=DERP_001540 PE=4 SV=1
    evalue: 3.793e-43
    bit_score: 149.0
    global_score: 379.0
    query_length: 90
    target_length: 91
    alignment_columns: 98
    identities: 74
    mismatches: 9
    gap_columns: 15
    identity_percent: 75.5102
    query_coverage_percent: 92.2222
    target_coverage_percent: 91.2088
  - accession: A0ABQ8JAT2
    description: tr|A0ABQ8JAT2|A0ABQ8JAT2_DERPT Chitin-binding domain type 2 OS=Dermatophagoides pteronyssinus
      OX=6956 GN=Cpap3-a1_1 PE=4 SV=1
    evalue: 1.695e-11
    bit_score: 58.0
    global_score: 50.5
    query_length: 90
    target_length: 324
    alignment_columns: 328
    identities: 41
    mismatches: 45
    gap_columns: 242
    identity_percent: 12.5
    query_coverage_percent: 95.5556
    target_coverage_percent: 26.5432
