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/A0A0A7HFE1.json
  retrieved_at: '2026-10-18T23:38:45.581822+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/uniprotkb/A0ACM8UA39.json
  retrieved_at: '2026-10-18T23:38:46.135908+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/proteomes/UP000232434.json
  retrieved_at: '2026-10-18T23:38:47.110957+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/A0A0A7HFE1?format=txt&versions=3
  retrieved_at: '2026-10-18T23:38:53.534996+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/A0A0A7HFE1?format=txt&versions=13
  retrieved_at: '2026-10-18T23:38:57.049455+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/A0A0A7HFE1?format=txt&versions=27
  retrieved_at: '2026-10-18T23:38:59.229583+00:00'
  uniprot_release: '2026_03'
observations:
  primary_accession: A0A0A7HFE1
  alternative_accession: A0ACM8UA39
  sequence_identical: false
  primary_sequence_length: 758
  alternative_sequence_length: 758
  shared_uniparc_id: null
  same_taxon: true
  reference_proteome: UP000232434
  proteome_is_reference: true
  proteome_taxon_matches: true
  primary_in_reference_proteome: false
  alternative_in_reference_proteome: true
  searched_reference_proteomes:
  - UP000232434
  primary_in_any_reference_proteome: false
  sampled_history_versions:
  - 3
  - 13
  - 27
  sampled_versions_with_proteome_links: []
current_records:
- primaryAccession: A0A0A7HFE1
  entryType: UniProtKB reviewed (Swiss-Prot)
  entryAudit:
    firstPublicDate: '2019-01-16'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '2015-03-04'
    entryVersion: 31
    sequenceVersion: 1
  genes:
  - geneName:
      evidences:
      - evidenceCode: ECO:0000303
        source: PubMed
        id: '25458845'
      value: cas10
    synonyms:
    - evidences:
      - evidenceCode: ECO:0000305
      value: csm1
  organism:
    scientificName: Streptococcus thermophilus
    taxonId: 1308
  sequence:
    length: 758
    sha256: 46f70cfc9087337c2ccd5b818fb4ecf5eb0033b52e50e4c1f6efa943f01950b5
  uniProtKBCrossReferences: []
- primaryAccession: A0ACM8UA39
  entryType: UniProtKB unreviewed (TrEMBL)
  entryAudit:
    firstPublicDate: '2026-09-02'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '2026-09-02'
    entryVersion: 1
    sequenceVersion: 1
  genes:
  - geneName:
      evidences:
      - evidenceCode: ECO:0000313
        source: EMBL
        id: AUF35823.1
      value: cas10
    orfNames:
    - evidences:
      - evidenceCode: ECO:0000313
        source: EMBL
        id: AUF35823.1
      value: CW339_04770
  organism:
    scientificName: Streptococcus thermophilus
    taxonId: 1308
  sequence:
    length: 758
    sha256: 99ae34307f07c5e6c1ded23adadfce81d6a38a639afba36b1f3e0674d6584698
  uniProtKBCrossReferences:
  - database: Proteomes
    id: UP000232434
    properties:
    - key: Component
      value: Chromosome
reference_proteomes:
- id: UP000232434
  proteomeType: Reference proteome
  taxonomy:
    scientificName: Streptococcus thermophilus
    taxonId: 1308
    mnemonic: STRTR
unisave_records:
- entry_version: 3
  url: https://rest.uniprot.org/unisave/A0A0A7HFE1?format=txt&versions=3
  entry_date: 09-DEC-2015, entry version 3.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 13
  url: https://rest.uniprot.org/unisave/A0A0A7HFE1?format=txt&versions=13
  entry_date: 07-OCT-2020, entry version 13.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 27
  url: https://rest.uniprot.org/unisave/A0A0A7HFE1?format=txt&versions=27
  entry_date: 27-NOV-2024, entry version 27.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
archived_sources:
- path: genes/STRTR/cas10/cas10-record-evidence.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/STRTR/cas10/cas10-record-evidence.yaml
  sha256: 035c532c8a1fe8311a7218d8fa18ccd28e99532c1da9e3d029d795fbfdc062db
  excerpts:
  - start_line: 26
    end_line: 38
    text: |2
        alternative_sequence_length: 758
        shared_uniparc_id: null
        same_taxon: true
        reference_proteome: UP000232434
        proteome_is_reference: true
        proteome_taxon_matches: true
        primary_in_reference_proteome: false
        alternative_in_reference_proteome: true
        searched_reference_proteomes:
        - UP000232434
        primary_in_any_reference_proteome: false
        sampled_history_versions:
        - 3
  - start_line: 1934
    end_line: 1939
    text: |
      - entry_version: 3
        url: https://rest.uniprot.org/unisave/A0A0A7HFE1?format=txt&versions=3
        entry_date: 09-DEC-2015, entry version 3.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 1989
    end_line: 1994
    text: |
      - entry_version: 13
        url: https://rest.uniprot.org/unisave/A0A0A7HFE1?format=txt&versions=13
        entry_date: 07-OCT-2020, entry version 13.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 2338
    end_line: 2343
    text: |
      - entry_version: 27
        url: https://rest.uniprot.org/unisave/A0A0A7HFE1?format=txt&versions=27
        entry_date: 27-NOV-2024, entry version 27.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
- path: genes/STRTR/cas10/cas10-bioinformatics/reference-counterparts/comparison.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/STRTR/cas10/cas10-bioinformatics/reference-counterparts/comparison.yaml
  sha256: 643dc6474fc81390a083f6bbfb87179bfb5e35da342c9363422f77f3a732ae31
  excerpts:
  - start_line: 25
    end_line: 29
    text: |2
        - -v
        - '1'
        target_sequence_count: 1657
        query_sha256: c83019316c80b199a92851865206d410eccab621c58fad19c84c0eee9be01f5e
        targets_sha256: 2ba0c960ff7acb33b8c94c91b1e5081c781e78154107e09e7bafda9de1dad85f
  - start_line: 44
    end_line: 48
    text: |2
          sha256: 2ba0c960ff7acb33b8c94c91b1e5081c781e78154107e09e7bafda9de1dad85f
        detailed_alignment_limit: 10
      candidate_count: 1
      candidates:
      - accession: A0ACM8UA39
  - start_line: 52
    end_line: 64
    text: |2
        bit_score: 1454.0
        global_score: 3721.5
        query_length: 758
        target_length: 758
        alignment_columns: 761
        identities: 720
        mismatches: 35
        gap_columns: 6
        identity_percent: 94.6124
        query_coverage_percent: 99.6042
        target_coverage_percent: 99.6042
        substitutions:
        - query_position: 62
comparison:
  provenance:
    query_accession: A0A0A7HFE1
    run_at: '2026-10-18T23:32:56.903396+00:00'
    biopython_version: '1.85'
    mmseqs_version: 18-8cc5c
    command:
    - mmseqs
    - easy-search
    - genes/STRTR/cas10/cas10-bioinformatics/reference-counterparts/query.fasta
    - .cache/orphan-curated/UP000232434.fasta
    - genes/STRTR/cas10/cas10-bioinformatics/reference-counterparts/search.tsv
    - genes/STRTR/cas10/cas10-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: 1657
    query_sha256: c83019316c80b199a92851865206d410eccab621c58fad19c84c0eee9be01f5e
    targets_sha256: 2ba0c960ff7acb33b8c94c91b1e5081c781e78154107e09e7bafda9de1dad85f
    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%3AUP000232434&format=fasta
      retrieved_at: '2026-10-18T23:32:24.964588+00:00'
      uniprot_release: '2026_03'
      sequence_count: 1657
      sha256: 2ba0c960ff7acb33b8c94c91b1e5081c781e78154107e09e7bafda9de1dad85f
    detailed_alignment_limit: 10
  candidate_count: 1
  retained_alignment_count: 1
  candidates:
  - accession: A0ACM8UA39
    description: tr|A0ACM8UA39|A0ACM8UA39_STRTR Type III-A CRISPR-associated protein Cas10/Csm1 OS=Streptococcus
      thermophilus OX=1308 GN=cas10 PE=4 SV=1
    evalue: 0.0
    bit_score: 1454.0
    global_score: 3721.5
    query_length: 758
    target_length: 758
    alignment_columns: 761
    identities: 720
    mismatches: 35
    gap_columns: 6
    identity_percent: 94.6124
    query_coverage_percent: 99.6042
    target_coverage_percent: 99.6042
