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/Q00363.json
  retrieved_at: '2026-10-18T23:39:31.034480+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/uniprotkb/L7YE01.json
  retrieved_at: '2026-10-18T23:39:31.221110+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/proteomes/UP000756132.json
  retrieved_at: '2026-10-18T23:39:31.381379+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/Q00363?format=txt&versions=67
  retrieved_at: '2026-10-18T23:39:34.034502+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/Q00363?format=txt&versions=81
  retrieved_at: '2026-10-18T23:39:36.030914+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/Q00363?format=txt&versions=88
  retrieved_at: '2026-10-18T23:39:38.442088+00:00'
  uniprot_release: '2026_03'
observations:
  primary_accession: Q00363
  alternative_accession: L7YE01
  sequence_identical: true
  primary_sequence_length: 135
  alternative_sequence_length: 135
  shared_uniparc_id: UPI0000126679
  same_taxon: true
  reference_proteome: UP000756132
  proteome_is_reference: true
  proteome_taxon_matches: true
  primary_in_reference_proteome: false
  alternative_in_reference_proteome: true
  searched_reference_proteomes:
  - UP000756132
  primary_in_any_reference_proteome: false
  sampled_history_versions:
  - 67
  - 81
  - 88
  sampled_versions_with_proteome_links: []
current_records:
- primaryAccession: Q00363
  entryType: UniProtKB reviewed (Swiss-Prot)
  entryAudit:
    firstPublicDate: '1997-11-01'
    lastAnnotationUpdateDate: '2026-06-10'
    lastSequenceUpdateDate: '1996-11-01'
    entryVersion: 90
    sequenceVersion: 1
  genes:
  - geneName:
      value: AVR4
  organism:
    scientificName: Fulvia fulva
    taxonId: 5499
  sequence:
    length: 135
    sha256: 2b225f7233e1cff383a1e4bf8d569c845c434d12a06d965f5d641d176f7264f2
  uniProtKBCrossReferences: []
- primaryAccession: L7YE01
  entryType: UniProtKB unreviewed (TrEMBL)
  entryAudit:
    firstPublicDate: '2013-04-03'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '2013-04-03'
    entryVersion: 43
    sequenceVersion: 1
  genes:
  - orfNames:
    - evidences:
      - evidenceCode: ECO:0000313
        source: EMBL
        id: UJO19575.1
      value: CLAFUR5_10112
  organism:
    scientificName: Fulvia fulva
    taxonId: 5499
  sequence:
    length: 135
    sha256: 2b225f7233e1cff383a1e4bf8d569c845c434d12a06d965f5d641d176f7264f2
  uniProtKBCrossReferences:
  - database: Proteomes
    id: UP000756132
    properties:
    - key: Component
      value: Chromosome 7
reference_proteomes:
- id: UP000756132
  proteomeType: Reference proteome
  taxonomy:
    scientificName: Fulvia fulva
    commonName: Tomato leaf mold
    synonyms:
    - Passalora fulva
    taxonId: 5499
    mnemonic: FULFL
unisave_records:
- entry_version: 67
  url: https://rest.uniprot.org/unisave/Q00363?format=txt&versions=67
  entry_date: 09-DEC-2015, entry version 67.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 81
  url: https://rest.uniprot.org/unisave/Q00363?format=txt&versions=81
  entry_date: 02-DEC-2020, entry version 81.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 88
  url: https://rest.uniprot.org/unisave/Q00363?format=txt&versions=88
  entry_date: 27-MAR-2024, entry version 88.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
archived_sources:
- path: genes/FULFL/AVR4/AVR4-record-evidence.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/FULFL/AVR4/AVR4-record-evidence.yaml
  sha256: ad3e8cdaef907bf5f10a289c53bddd32dddcbe11a269e3a02dccd301b9926c01
  excerpts:
  - start_line: 26
    end_line: 38
    text: |2
        alternative_sequence_length: 135
        shared_uniparc_id: UPI0000126679
        same_taxon: true
        reference_proteome: UP000756132
        proteome_is_reference: true
        proteome_taxon_matches: true
        primary_in_reference_proteome: false
        alternative_in_reference_proteome: true
        searched_reference_proteomes:
        - UP000756132
        primary_in_any_reference_proteome: false
        sampled_history_versions:
        - 67
  - start_line: 1163
    end_line: 1168
    text: |
      - entry_version: 67
        url: https://rest.uniprot.org/unisave/Q00363?format=txt&versions=67
        entry_date: 09-DEC-2015, entry version 67.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 1231
    end_line: 1236
    text: |
      - entry_version: 81
        url: https://rest.uniprot.org/unisave/Q00363?format=txt&versions=81
        entry_date: 02-DEC-2020, entry version 81.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 1330
    end_line: 1335
    text: |
      - entry_version: 88
        url: https://rest.uniprot.org/unisave/Q00363?format=txt&versions=88
        entry_date: 27-MAR-2024, entry version 88.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
- path: genes/FULFL/AVR4/AVR4-bioinformatics/reference-counterparts/comparison.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/FULFL/AVR4/AVR4-bioinformatics/reference-counterparts/comparison.yaml
  sha256: 94cb1e5111c524c0240ee8d37139bc646553850a81a040af930b814537d8e4da
  excerpts:
  - start_line: 25
    end_line: 29
    text: |2
        - -v
        - '1'
        target_sequence_count: 14687
        query_sha256: b4bbff878b7ccc0c8be48587ad16f448aa495dd764b11c4c64ff63ba6d8b4aa6
        targets_sha256: 35d8b487261f72aa4516f53be905a25950fdf4e9fa291fc85ebfe488c2a62f48
  - start_line: 44
    end_line: 48
    text: |2
          sha256: 35d8b487261f72aa4516f53be905a25950fdf4e9fa291fc85ebfe488c2a62f48
        detailed_alignment_limit: 10
      candidate_count: 1
      candidates:
      - accession: L7YE01
  - start_line: 51
    end_line: 62
    text: |2
        bit_score: 295.0
        global_score: 771.0
        query_length: 135
        target_length: 135
        alignment_columns: 135
        identities: 135
        mismatches: 0
        gap_columns: 0
        identity_percent: 100.0
        query_coverage_percent: 100.0
        target_coverage_percent: 100.0
        substitutions: []
comparison:
  provenance:
    query_accession: Q00363
    run_at: '2026-10-18T23:34:57.627848+00:00'
    biopython_version: '1.85'
    mmseqs_version: 18-8cc5c
    command:
    - mmseqs
    - easy-search
    - genes/FULFL/AVR4/AVR4-bioinformatics/reference-counterparts/query.fasta
    - .cache/orphan-curated/UP000756132.fasta
    - genes/FULFL/AVR4/AVR4-bioinformatics/reference-counterparts/search.tsv
    - genes/FULFL/AVR4/AVR4-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: 14687
    query_sha256: b4bbff878b7ccc0c8be48587ad16f448aa495dd764b11c4c64ff63ba6d8b4aa6
    targets_sha256: 35d8b487261f72aa4516f53be905a25950fdf4e9fa291fc85ebfe488c2a62f48
    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%3AUP000756132&format=fasta
      retrieved_at: '2026-10-18T23:32:39.118552+00:00'
      uniprot_release: '2026_03'
      sequence_count: 14687
      sha256: 35d8b487261f72aa4516f53be905a25950fdf4e9fa291fc85ebfe488c2a62f48
    detailed_alignment_limit: 10
  candidate_count: 1
  retained_alignment_count: 1
  candidates:
  - accession: L7YE01
    description: tr|L7YE01|L7YE01_FULFL Avr4 OS=Fulvia fulva OX=5499 GN=CLAFUR5_10112 PE=4 SV=1
    evalue: 3.938e-93
    bit_score: 295.0
    global_score: 771.0
    query_length: 135
    target_length: 135
    alignment_columns: 135
    identities: 135
    mismatches: 0
    gap_columns: 0
    identity_percent: 100.0
    query_coverage_percent: 100.0
    target_coverage_percent: 100.0
