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/G1FNI6.json
  retrieved_at: '2026-10-18T23:39:00.051037+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/uniprotkb/A0AAU9R9U8.json
  retrieved_at: '2026-10-18T23:39:00.222776+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/proteomes/UP000836841.json
  retrieved_at: '2026-10-18T23:39:00.373697+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/G1FNI6?format=txt&versions=12
  retrieved_at: '2026-10-18T23:39:01.728437+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/G1FNI6?format=txt&versions=25
  retrieved_at: '2026-10-18T23:39:03.137310+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/G1FNI6?format=txt&versions=36
  retrieved_at: '2026-10-18T23:39:04.347917+00:00'
  uniprot_release: '2026_03'
observations:
  primary_accession: G1FNI6
  alternative_accession: A0AAU9R9U8
  sequence_identical: false
  primary_sequence_length: 348
  alternative_sequence_length: 340
  shared_uniparc_id: null
  same_taxon: true
  reference_proteome: UP000836841
  proteome_is_reference: true
  proteome_taxon_matches: true
  primary_in_reference_proteome: false
  alternative_in_reference_proteome: true
  searched_reference_proteomes:
  - UP000836841
  primary_in_any_reference_proteome: false
  sampled_history_versions:
  - 12
  - 25
  - 36
  sampled_versions_with_proteome_links: []
current_records:
- primaryAccession: G1FNI6
  entryType: UniProtKB reviewed (Swiss-Prot)
  entryAudit:
    firstPublicDate: '2023-09-13'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '2011-10-19'
    entryVersion: 40
    sequenceVersion: 1
  genes:
  - geneName:
      evidences:
      - evidenceCode: ECO:0000303
        source: PubMed
        id: '21783213'
      value: TFP
  organism:
    scientificName: Thlaspi arvense
    taxonId: 13288
  sequence:
    length: 348
    sha256: f22c0c7eb7f46d999a3f69277deffece43d4f9e416a66515a504483c02ae2362
  uniProtKBCrossReferences: []
- primaryAccession: A0AAU9R9U8
  entryType: UniProtKB unreviewed (TrEMBL)
  entryAudit:
    firstPublicDate: '2024-11-27'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '2024-11-27'
    entryVersion: 7
    sequenceVersion: 1
  genes:
  - orfNames:
    - evidences:
      - evidenceCode: ECO:0000313
        source: EMBL
        id: CAH2036628.1
      value: TAV2_LOCUS671
  organism:
    scientificName: Thlaspi arvense
    taxonId: 13288
  sequence:
    length: 340
    sha256: dbbdab52ed4aa3b65bc4f532026d5b384801841d1114e108832865e63e554ccd
  uniProtKBCrossReferences:
  - database: Proteomes
    id: UP000836841
    properties:
    - key: Component
      value: Chromosome 1
reference_proteomes:
- id: UP000836841
  proteomeType: Reference proteome
  taxonomy:
    scientificName: Thlaspi arvense
    commonName: Field penny-cress
    taxonId: 13288
    mnemonic: THLAR
unisave_records:
- entry_version: 12
  url: https://rest.uniprot.org/unisave/G1FNI6?format=txt&versions=12
  entry_date: 11-NOV-2015, entry version 12.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 25
  url: https://rest.uniprot.org/unisave/G1FNI6?format=txt&versions=25
  entry_date: 11-DEC-2019, entry version 25.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 36
  url: https://rest.uniprot.org/unisave/G1FNI6?format=txt&versions=36
  entry_date: 27-NOV-2024, entry version 36.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
archived_sources:
- path: genes/THLAR/TFP/TFP-record-evidence.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/THLAR/TFP/TFP-record-evidence.yaml
  sha256: e82472fc4db3289426d53a237797d0c93225d64b8f6831e86a73a78ebf6e069d
  excerpts:
  - start_line: 26
    end_line: 38
    text: |2
        alternative_sequence_length: 340
        shared_uniparc_id: null
        same_taxon: true
        reference_proteome: UP000836841
        proteome_is_reference: true
        proteome_taxon_matches: true
        primary_in_reference_proteome: false
        alternative_in_reference_proteome: true
        searched_reference_proteomes:
        - UP000836841
        primary_in_any_reference_proteome: false
        sampled_history_versions:
        - 12
  - start_line: 2622
    end_line: 2627
    text: |
      - entry_version: 12
        url: https://rest.uniprot.org/unisave/G1FNI6?format=txt&versions=12
        entry_date: 11-NOV-2015, entry version 12.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 2682
    end_line: 2687
    text: |
      - entry_version: 25
        url: https://rest.uniprot.org/unisave/G1FNI6?format=txt&versions=25
        entry_date: 11-DEC-2019, entry version 25.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 2743
    end_line: 2748
    text: |
      - entry_version: 36
        url: https://rest.uniprot.org/unisave/G1FNI6?format=txt&versions=36
        entry_date: 27-NOV-2024, entry version 36.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
- path: genes/THLAR/TFP/TFP-bioinformatics/reference-counterparts/comparison.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/THLAR/TFP/TFP-bioinformatics/reference-counterparts/comparison.yaml
  sha256: dc46c88aa86d7dfb57e5d46cc01fb0607cec2ec922c1b3da211ba452ecbfa2f8
  excerpts:
  - start_line: 25
    end_line: 29
    text: |2
        - -v
        - '1'
        target_sequence_count: 26379
        query_sha256: 601cb0d9eccfe8ea711a11723cd43455a0b79741b2b015cd1909f0cce0301343
        targets_sha256: 910a65b4aade115c4580367fef21e13622f7c9124925c8eb53c942c103d735d2
  - start_line: 44
    end_line: 48
    text: |2
          sha256: 910a65b4aade115c4580367fef21e13622f7c9124925c8eb53c942c103d735d2
        detailed_alignment_limit: 10
      candidate_count: 28
      candidates:
      - accession: A0AAU9R9U8
  - start_line: 52
    end_line: 64
    text: |2
        bit_score: 731.0
        global_score: 1819.5
        query_length: 348
        target_length: 340
        alignment_columns: 348
        identities: 338
        mismatches: 2
        gap_columns: 8
        identity_percent: 97.1264
        query_coverage_percent: 97.7011
        target_coverage_percent: 100.0
        substitutions:
        - query_position: 10
comparison:
  provenance:
    query_accession: G1FNI6
    run_at: '2026-10-18T23:34:20.959503+00:00'
    biopython_version: '1.85'
    mmseqs_version: 18-8cc5c
    command:
    - mmseqs
    - easy-search
    - genes/THLAR/TFP/TFP-bioinformatics/reference-counterparts/query.fasta
    - .cache/orphan-curated/UP000836841.fasta
    - genes/THLAR/TFP/TFP-bioinformatics/reference-counterparts/search.tsv
    - genes/THLAR/TFP/TFP-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: 26379
    query_sha256: 601cb0d9eccfe8ea711a11723cd43455a0b79741b2b015cd1909f0cce0301343
    targets_sha256: 910a65b4aade115c4580367fef21e13622f7c9124925c8eb53c942c103d735d2
    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%3AUP000836841&format=fasta
      retrieved_at: '2026-10-18T23:32:46.697751+00:00'
      uniprot_release: '2026_03'
      sequence_count: 26379
      sha256: 910a65b4aade115c4580367fef21e13622f7c9124925c8eb53c942c103d735d2
    detailed_alignment_limit: 10
  candidate_count: 28
  retained_alignment_count: 10
  candidates:
  - accession: A0AAU9R9U8
    description: tr|A0AAU9R9U8|A0AAU9R9U8_THLAR Epithiospecifier protein OS=Thlaspi arvense OX=13288 GN=TAV2_LOCUS671
      PE=4 SV=1
    evalue: 1.037e-239
    bit_score: 731.0
    global_score: 1819.5
    query_length: 348
    target_length: 340
    alignment_columns: 348
    identities: 338
    mismatches: 2
    gap_columns: 8
    identity_percent: 97.1264
    query_coverage_percent: 97.7011
    target_coverage_percent: 100.0
  - accession: A0AAU9RD64
    description: tr|A0AAU9RD64|A0AAU9RD64_THLAR Epithiospecifier protein OS=Thlaspi arvense OX=13288 GN=TAV2_LOCUS676
      PE=4 SV=1
    evalue: 3.578e-203
    bit_score: 626.0
    global_score: 1564.0
    query_length: 348
    target_length: 348
    alignment_columns: 349
    identities: 292
    mismatches: 55
    gap_columns: 2
    identity_percent: 83.6676
    query_coverage_percent: 99.7126
    target_coverage_percent: 99.7126