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/P0DH90.json
  retrieved_at: '2026-10-18T23:39:10.200866+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/uniprotkb/Q67Z93.json
  retrieved_at: '2026-10-18T23:39:10.371017+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/proteomes/UP000006548.json
  retrieved_at: '2026-10-18T23:39:10.547422+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/P0DH90?format=txt&versions=21
  retrieved_at: '2026-10-18T23:39:14.952171+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/P0DH90?format=txt&versions=36
  retrieved_at: '2026-10-18T23:39:19.035771+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/P0DH90?format=txt&versions=43
  retrieved_at: '2026-10-18T23:39:21.047351+00:00'
  uniprot_release: '2026_03'
observations:
  primary_accession: P0DH90
  alternative_accession: Q67Z93
  sequence_identical: false
  primary_sequence_length: 609
  alternative_sequence_length: 314
  shared_uniparc_id: null
  same_taxon: true
  reference_proteome: UP000006548
  proteome_is_reference: true
  proteome_taxon_matches: true
  primary_in_reference_proteome: false
  alternative_in_reference_proteome: true
  searched_reference_proteomes:
  - UP000006548
  primary_in_any_reference_proteome: false
  sampled_history_versions:
  - 21
  - 36
  - 43
  sampled_versions_with_proteome_links: []
current_records:
- primaryAccession: P0DH90
  entryType: UniProtKB reviewed (Swiss-Prot)
  entryAudit:
    firstPublicDate: '2012-01-25'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '2012-01-25'
    entryVersion: 47
    sequenceVersion: 1
  genes:
  - geneName:
      evidences:
      - evidenceCode: ECO:0000303
        source: PubMed
        id: '11030654'
      value: FRI
  organism:
    scientificName: Arabidopsis thaliana
    taxonId: 3702
  sequence:
    length: 609
    sha256: 02207bc378d4704ff55c29a1fc506fe6ed29ba4efed3babfdac1a5fcc5128b59
  uniProtKBCrossReferences: []
- primaryAccession: Q67Z93
  entryType: UniProtKB reviewed (Swiss-Prot)
  entryAudit:
    firstPublicDate: '2012-01-25'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '2004-10-11'
    entryVersion: 91
    sequenceVersion: 1
  genes:
  - geneName:
      value: FRI
    orderedLocusNames:
    - value: At4g00650
    orfNames:
    - value: F6N23.25
  organism:
    scientificName: Arabidopsis thaliana
    taxonId: 3702
  sequence:
    length: 314
    sha256: f85f4e82f61c76962bbfdf6eb1c6e08dd2018f3fc7f728bf18231cd4618fce05
  uniProtKBCrossReferences:
  - database: Proteomes
    id: UP000006548
    properties:
    - key: Component
      value: Chromosome 4
reference_proteomes:
- id: UP000006548
  proteomeType: Reference proteome
  taxonomy:
    scientificName: Arabidopsis thaliana
    commonName: Mouse-ear cress
    taxonId: 3702
    mnemonic: ARATH
unisave_records:
- entry_version: 21
  url: https://rest.uniprot.org/unisave/P0DH90?format=txt&versions=21
  entry_date: 11-NOV-2015, entry version 21.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 36
  url: https://rest.uniprot.org/unisave/P0DH90?format=txt&versions=36
  entry_date: 12-AUG-2020, entry version 36.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 43
  url: https://rest.uniprot.org/unisave/P0DH90?format=txt&versions=43
  entry_date: 24-JAN-2024, entry version 43.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
archived_sources:
- path: genes/ARATH/FRI/FRI-record-evidence.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/ARATH/FRI/FRI-record-evidence.yaml
  sha256: 5e6231606a3c307a1f3def17d037ab00158c99f3656abea79bf527eee87cb980
  excerpts:
  - start_line: 26
    end_line: 38
    text: |2
        alternative_sequence_length: 314
        shared_uniparc_id: null
        same_taxon: true
        reference_proteome: UP000006548
        proteome_is_reference: true
        proteome_taxon_matches: true
        primary_in_reference_proteome: false
        alternative_in_reference_proteome: true
        searched_reference_proteomes:
        - UP000006548
        primary_in_any_reference_proteome: false
        sampled_history_versions:
        - 21
  - start_line: 732
    end_line: 737
    text: |2
          - evidences:
            - evidenceCode: ECO:0000305
            value: In strain cv. Columbia, cv. Landsberg Erecta and cv. Wassilewskija, loss-of-function mutations lead
              to inactive FRI protein. A complete sequence for FRI can be found in strains cv. H51 (AC P0DH90)
          commentType: CAUTION
        - commentType: SEQUENCE CAUTION
  - start_line: 2374
    end_line: 2379
    text: |
      - entry_version: 21
        url: https://rest.uniprot.org/unisave/P0DH90?format=txt&versions=21
        entry_date: 11-NOV-2015, entry version 21.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 2523
    end_line: 2528
    text: |
      - entry_version: 36
        url: https://rest.uniprot.org/unisave/P0DH90?format=txt&versions=36
        entry_date: 12-AUG-2020, entry version 36.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 2679
    end_line: 2684
    text: |
      - entry_version: 43
        url: https://rest.uniprot.org/unisave/P0DH90?format=txt&versions=43
        entry_date: 24-JAN-2024, entry version 43.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
- path: genes/ARATH/FRI/FRI-bioinformatics/reference-counterparts/comparison.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/ARATH/FRI/FRI-bioinformatics/reference-counterparts/comparison.yaml
  sha256: 57ea491e9725013cb234ef7da00511c1bf4c3a94babc1a843573df79d802425b
  excerpts:
  - start_line: 25
    end_line: 29
    text: |2
        - -v
        - '1'
        target_sequence_count: 39272
        query_sha256: 21055e99868bf7466f775177ae53ccce69a31750be36b566704c3644478b2dd2
        targets_sha256: 63edb51070a0f51cfce737f0ea84b186f2b511a5b7820a694139a04b30607464
  - start_line: 44
    end_line: 48
    text: |2
          sha256: 63edb51070a0f51cfce737f0ea84b186f2b511a5b7820a694139a04b30607464
        detailed_alignment_limit: 10
      candidate_count: 6
      candidates:
      - accession: Q67Z93
  - start_line: 51
    end_line: 63
    text: |2
        bit_score: 606.0
        global_score: 1403.0
        query_length: 609
        target_length: 314
        alignment_columns: 609
        identities: 311
        mismatches: 3
        gap_columns: 295
        identity_percent: 51.0673
        query_coverage_percent: 51.5599
        target_coverage_percent: 100.0
        substitutions:
        - query_position: 146
comparison:
  provenance:
    query_accession: P0DH90
    run_at: '2026-10-18T23:34:34.799779+00:00'
    biopython_version: '1.85'
    mmseqs_version: 18-8cc5c
    command:
    - mmseqs
    - easy-search
    - genes/ARATH/FRI/FRI-bioinformatics/reference-counterparts/query.fasta
    - .cache/orphan-curated/UP000006548.fasta
    - genes/ARATH/FRI/FRI-bioinformatics/reference-counterparts/search.tsv
    - genes/ARATH/FRI/FRI-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: 39272
    query_sha256: 21055e99868bf7466f775177ae53ccce69a31750be36b566704c3644478b2dd2
    targets_sha256: 63edb51070a0f51cfce737f0ea84b186f2b511a5b7820a694139a04b30607464
    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%3AUP000006548&format=fasta
      retrieved_at: '2026-10-18T23:32:19.237076+00:00'
      uniprot_release: '2026_03'
      sequence_count: 39272
      sha256: 63edb51070a0f51cfce737f0ea84b186f2b511a5b7820a694139a04b30607464
    detailed_alignment_limit: 10
  candidate_count: 6
  retained_alignment_count: 6
  candidates:
  - accession: Q67Z93
    description: sp|Q67Z93|FRIG0_ARATH Inactive protein FRIGIDA OS=Arabidopsis thaliana OX=3702 GN=FRI
      PE=2 SV=1
    evalue: 2.223e-191
    bit_score: 606.0
    global_score: 1403.0
    query_length: 609
    target_length: 314
    alignment_columns: 609
    identities: 311
    mismatches: 3
    gap_columns: 295
    identity_percent: 51.0673
    query_coverage_percent: 51.5599
    target_coverage_percent: 100.0
  - accession: Q67ZB3
    description: sp|Q67ZB3|FRL3_ARATH FRIGIDA-like protein 3 OS=Arabidopsis thaliana OX=3702 GN=FRL3 PE=1
      SV=1
    evalue: 2.145e-24
    bit_score: 110.0
    global_score: 300.5
    query_length: 609
    target_length: 558
    alignment_columns: 684
    identities: 146
    mismatches: 337
    gap_columns: 201
    identity_percent: 21.345
    query_coverage_percent: 79.3103
    target_coverage_percent: 86.5591
