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/P49278.json
  retrieved_at: '2026-10-18T23:39:26.844513+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/uniprotkb/A0ABQ8J715.json
  retrieved_at: '2026-10-18T23:39:27.012676+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/proteomes/UP000887458.json
  retrieved_at: '2026-10-18T23:39:27.168321+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/P49278?format=txt&versions=77
  retrieved_at: '2026-10-18T23:39:27.450507+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/P49278?format=txt&versions=90
  retrieved_at: '2026-10-18T23:39:27.834281+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/P49278?format=txt&versions=102
  retrieved_at: '2026-10-18T23:39:30.237738+00:00'
  uniprot_release: '2026_03'
observations:
  primary_accession: P49278
  alternative_accession: A0ABQ8J715
  sequence_identical: false
  primary_sequence_length: 146
  alternative_sequence_length: 146
  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:
  - 77
  - 90
  - 102
  sampled_versions_with_proteome_links:
  - 102
current_records:
- primaryAccession: P49278
  entryType: UniProtKB reviewed (Swiss-Prot)
  entryAudit:
    firstPublicDate: '1996-02-01'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '1996-02-01'
    entryVersion: 106
    sequenceVersion: 1
  genes:
  - geneName:
      value: DERP2
  organism:
    scientificName: Dermatophagoides pteronyssinus
    taxonId: 6956
  sequence:
    length: 146
    sha256: a86f72149d47c966294d42c05215980b0808f35209a50f278ae38a167d415f76
  uniProtKBCrossReferences: []
- primaryAccession: A0ABQ8J715
  entryType: UniProtKB unreviewed (TrEMBL)
  entryAudit:
    firstPublicDate: '2025-10-08'
    lastAnnotationUpdateDate: '2026-06-10'
    lastSequenceUpdateDate: '2025-10-08'
    entryVersion: 3
    sequenceVersion: 1
  genes:
  - geneName:
      evidences:
      - evidenceCode: ECO:0000313
        source: EMBL
        id: KAH9418379.1
      value: NPC2_5
    orfNames:
    - evidences:
      - evidenceCode: ECO:0000313
        source: EMBL
        id: KAH9418379.1
      value: DERP_010248
  organism:
    scientificName: Dermatophagoides pteronyssinus
    taxonId: 6956
  sequence:
    length: 146
    sha256: 8a3a2ef2aa342e83309154ab8077ea66c76213db2f3c631c6ee22ae0dbbfc931
  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: 77
  url: https://rest.uniprot.org/unisave/P49278?format=txt&versions=77
  entry_date: 14-OCT-2015, entry version 77.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 90
  url: https://rest.uniprot.org/unisave/P49278?format=txt&versions=90
  entry_date: 07-OCT-2020, entry version 90.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 102
  url: https://rest.uniprot.org/unisave/P49278?format=txt&versions=102
  entry_date: 27-NOV-2024, entry version 102.
  proteomes:
  - UP000515146
  reference_proteome_keyword: true
  record_text: ''
archived_sources:
- path: genes/DERPT/Derp2/Derp2-record-evidence.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/DERPT/Derp2/Derp2-record-evidence.yaml
  sha256: 883a8ca640e279692ac4480fd0a790f081c8e7b333ec9e2320ac7467a9a7cb66
  excerpts:
  - start_line: 26
    end_line: 38
    text: |2
        alternative_sequence_length: 146
        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:
        - 77
  - start_line: 1671
    end_line: 1676
    text: |
      - entry_version: 77
        url: https://rest.uniprot.org/unisave/P49278?format=txt&versions=77
        entry_date: 14-OCT-2015, entry version 77.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 1802
    end_line: 1807
    text: |
      - entry_version: 90
        url: https://rest.uniprot.org/unisave/P49278?format=txt&versions=90
        entry_date: 07-OCT-2020, entry version 90.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 1978
    end_line: 1984
    text: |
      - entry_version: 102
        url: https://rest.uniprot.org/unisave/P49278?format=txt&versions=102
        entry_date: 27-NOV-2024, entry version 102.
        proteomes:
        - UP000515146
        reference_proteome_keyword: true
        record_text: |
- path: genes/DERPT/Derp2/Derp2-bioinformatics/reference-counterparts/comparison.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/DERPT/Derp2/Derp2-bioinformatics/reference-counterparts/comparison.yaml
  sha256: f305f069c311dcc985766e9bf7c0db7d3faefd6fb6502d49d084af86b3e8cefb
  excerpts:
  - start_line: 25
    end_line: 29
    text: |2
        - -v
        - '1'
        target_sequence_count: 14675
        query_sha256: e0c151319cd5d3553b8b5a4c15601b873dc631dfbf75f01f638ff04120e9e17c
        targets_sha256: ca828b473340f0a27bc7c92cebf1e36990cd53a1f6ca120c9c19829f0943499d
  - start_line: 44
    end_line: 48
    text: |2
          sha256: ca828b473340f0a27bc7c92cebf1e36990cd53a1f6ca120c9c19829f0943499d
        detailed_alignment_limit: 10
      candidate_count: 6
      candidates:
      - accession: A0ABQ8J715
  - start_line: 52
    end_line: 64
    text: |2
        bit_score: 301.0
        global_score: 758.0
        query_length: 146
        target_length: 146
        alignment_columns: 146
        identities: 143
        mismatches: 3
        gap_columns: 0
        identity_percent: 97.9452
        query_coverage_percent: 100.0
        target_coverage_percent: 100.0
        substitutions:
        - query_position: 17
comparison:
  provenance:
    query_accession: P49278
    run_at: '2026-10-18T23:34:55.731211+00:00'
    biopython_version: '1.85'
    mmseqs_version: 18-8cc5c
    command:
    - mmseqs
    - easy-search
    - genes/DERPT/Derp2/Derp2-bioinformatics/reference-counterparts/query.fasta
    - .cache/orphan-curated/UP000887458.fasta
    - genes/DERPT/Derp2/Derp2-bioinformatics/reference-counterparts/search.tsv
    - genes/DERPT/Derp2/Derp2-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: e0c151319cd5d3553b8b5a4c15601b873dc631dfbf75f01f638ff04120e9e17c
    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: 6
  retained_alignment_count: 6
  candidates:
  - accession: A0ABQ8J715
    description: tr|A0ABQ8J715|A0ABQ8J715_DERPT Phosphatidylglycerol/phosphatidylinositol transfer protein
      OS=Dermatophagoides pteronyssinus OX=6956 GN=NPC2_5 PE=3 SV=1
    evalue: 8.336e-95
    bit_score: 301.0
    global_score: 758.0
    query_length: 146
    target_length: 146
    alignment_columns: 146
    identities: 143
    mismatches: 3
    gap_columns: 0
    identity_percent: 97.9452
    query_coverage_percent: 100.0
    target_coverage_percent: 100.0
  - accession: A0ABQ8JAK1
    description: tr|A0ABQ8JAK1|A0ABQ8JAK1_DERPT Phosphatidylglycerol/phosphatidylinositol transfer protein
      OS=Dermatophagoides pteronyssinus OX=6956 GN=NPC2_4 PE=3 SV=1
    evalue: 8.394e-34
    bit_score: 125.0
    global_score: 312.0
    query_length: 146
    target_length: 143
    alignment_columns: 147
    identities: 60
    mismatches: 82
    gap_columns: 5
    identity_percent: 40.8163
    query_coverage_percent: 97.2603
    target_coverage_percent: 99.3007
