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/Q54FI4.json
  retrieved_at: '2026-10-18T23:39:35.626001+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/proteomes/UP000002195.json
  retrieved_at: '2026-10-18T23:39:36.347995+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/Q54FI4?format=txt&versions=56
  retrieved_at: '2026-10-18T23:39:38.836978+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/Q54FI4?format=txt&versions=74
  retrieved_at: '2026-10-18T23:39:40.647705+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/Q54FI4?format=txt&versions=90
  retrieved_at: '2026-10-18T23:39:41.253290+00:00'
  uniprot_release: '2026_03'
observations:
  primary_accession: Q54FI4
  alternative_accession: null
  sequence_identical: null
  primary_sequence_length: 603
  alternative_sequence_length: null
  shared_uniparc_id: null
  same_taxon: null
  reference_proteome: UP000002195
  proteome_is_reference: true
  proteome_taxon_matches: true
  primary_in_reference_proteome: false
  alternative_in_reference_proteome: null
  searched_reference_proteomes:
  - UP000002195
  primary_in_any_reference_proteome: false
  sampled_history_versions:
  - 56
  - 74
  - 90
  sampled_versions_with_proteome_links:
  - 56
  - 74
current_records:
- primaryAccession: Q54FI4
  entryType: UniProtKB reviewed (Swiss-Prot)
  entryAudit:
    firstPublicDate: '2020-10-07'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '2005-05-24'
    entryVersion: 94
    sequenceVersion: 1
  genes:
  - geneName:
      evidences:
      - evidenceCode: ECO:0000303
        source: PubMed
        id: '20231486'
      value: ChlA
    orfNames:
    - evidences:
      - evidenceCode: ECO:0000312
        source: EMBL
        id: EAL62046.1
      value: DDB0189108
  organism:
    scientificName: Dictyostelium discoideum
    taxonId: 44689
  sequence:
    length: 603
    sha256: 3d90159757d6644dccd87b3ab6cfcef0f73ec4ec919675ccb8d77929299120f1
  uniProtKBCrossReferences: []
reference_proteomes:
- id: UP000002195
  proteomeType: Reference proteome
  taxonomy:
    scientificName: Dictyostelium discoideum
    commonName: Social amoeba
    taxonId: 44689
    mnemonic: DICDI
unisave_records:
- entry_version: 56
  url: https://rest.uniprot.org/unisave/Q54FI4?format=txt&versions=56
  entry_date: 11-NOV-2015, entry version 56.
  proteomes:
  - UP000002195
  reference_proteome_keyword: true
  record_text: ''
- entry_version: 74
  url: https://rest.uniprot.org/unisave/Q54FI4?format=txt&versions=74
  entry_date: 02-DEC-2020, entry version 74.
  proteomes:
  - UP000002195
  reference_proteome_keyword: true
  record_text: ''
- entry_version: 90
  url: https://rest.uniprot.org/unisave/Q54FI4?format=txt&versions=90
  entry_date: 27-NOV-2024, entry version 90.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
archived_sources:
- path: genes/DICDI/chlA/chlA-record-evidence.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/DICDI/chlA/chlA-record-evidence.yaml
  sha256: b91da8114cfa04b05360bd4fca1421e5de409029e4cb0c393717a2430432e263
  excerpts:
  - start_line: 31
    end_line: 35
    text: |2
        searched_reference_proteomes:
        - UP000002195
        primary_in_any_reference_proteome: false
        sampled_history_versions:
        - 56
  - start_line: 1071
    end_line: 1077
    text: |
      - entry_version: 56
        url: https://rest.uniprot.org/unisave/Q54FI4?format=txt&versions=56
        entry_date: 11-NOV-2015, entry version 56.
        proteomes:
        - UP000002195
        reference_proteome_keyword: true
        record_text: |
  - start_line: 1161
    end_line: 1167
    text: |
      - entry_version: 74
        url: https://rest.uniprot.org/unisave/Q54FI4?format=txt&versions=74
        entry_date: 02-DEC-2020, entry version 74.
        proteomes:
        - UP000002195
        reference_proteome_keyword: true
        record_text: |
  - start_line: 1322
    end_line: 1327
    text: |
      - entry_version: 90
        url: https://rest.uniprot.org/unisave/Q54FI4?format=txt&versions=90
        entry_date: 27-NOV-2024, entry version 90.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
- path: genes/DICDI/chlA/chlA-bioinformatics/reference-counterparts/comparison.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/DICDI/chlA/chlA-bioinformatics/reference-counterparts/comparison.yaml
  sha256: 39fcb0c7d38c87340cbd6037e08d5b6e48a00e680c421f7c7ce6b7b3e588552d
  excerpts:
  - start_line: 25
    end_line: 29
    text: |2
        - -v
        - '1'
        target_sequence_count: 12726
        query_sha256: 0e2ac590038c9e009b966154728be8ea6e2084897f5340c5b5897faa3c96e87c
        targets_sha256: 02b7a40aeb9fdc7aa5297208c79b8ff7cc54219e9caa34e42d38c2b7bae3a5ef
  - start_line: 44
    end_line: 47
    text: |2
          sha256: 02b7a40aeb9fdc7aa5297208c79b8ff7cc54219e9caa34e42d38c2b7bae3a5ef
        detailed_alignment_limit: 10
      candidate_count: 0
      candidates: []
comparison:
  provenance:
    query_accession: Q54FI4
    run_at: '2026-10-18T23:35:02.728707+00:00'
    biopython_version: '1.85'
    mmseqs_version: 18-8cc5c
    command:
    - mmseqs
    - easy-search
    - genes/DICDI/chlA/chlA-bioinformatics/reference-counterparts/query.fasta
    - .cache/orphan-curated/UP000002195.fasta
    - genes/DICDI/chlA/chlA-bioinformatics/reference-counterparts/search.tsv
    - genes/DICDI/chlA/chlA-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: 12726
    query_sha256: 0e2ac590038c9e009b966154728be8ea6e2084897f5340c5b5897faa3c96e87c
    targets_sha256: 02b7a40aeb9fdc7aa5297208c79b8ff7cc54219e9caa34e42d38c2b7bae3a5ef
    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%3AUP000002195&format=fasta
      retrieved_at: '2026-10-18T23:32:12.991548+00:00'
      uniprot_release: '2026_03'
      sequence_count: 12726
      sha256: 02b7a40aeb9fdc7aa5297208c79b8ff7cc54219e9caa34e42d38c2b7bae3a5ef
    detailed_alignment_limit: 10
  candidate_count: 0
  retained_alignment_count: 0
  candidates: []