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/Q9GF35.json
  retrieved_at: '2026-10-18T23:39:46.574534+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/uniprotkb/A0A1U9RZH7.json
  retrieved_at: '2026-10-18T23:39:46.751571+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/proteomes/UP000836841.json
  retrieved_at: '2026-10-18T23:39:46.902891+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/Q9GF35?format=txt&versions=46
  retrieved_at: '2026-10-18T23:39:47.131936+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/Q9GF35?format=txt&versions=51
  retrieved_at: '2026-10-18T23:39:51.241558+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/Q9GF35?format=txt&versions=53
  retrieved_at: '2026-10-18T23:39:53.327636+00:00'
  uniprot_release: '2026_03'
observations:
  primary_accession: Q9GF35
  alternative_accession: A0A1U9RZH7
  sequence_identical: false
  primary_sequence_length: 504
  alternative_sequence_length: 503
  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:
  - 46
  - 51
  - 53
  sampled_versions_with_proteome_links: []
current_records:
- primaryAccession: Q9GF35
  entryType: UniProtKB reviewed (Swiss-Prot)
  entryAudit:
    firstPublicDate: '2003-01-17'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '2001-03-01'
    entryVersion: 54
    sequenceVersion: 1
  genes:
  - geneName:
      evidences:
      - evidenceCode: ECO:0000255
        source: HAMAP-Rule
        id: MF_01390
      value: matK
  geneLocations:
  - geneEncodingType: Chloroplast
  organism:
    scientificName: Thlaspi arvense
    taxonId: 13288
  sequence:
    length: 504
    sha256: d6afe907213db230efc335b84401b2480dc8d704520b5a10120a20ae6b02a670
  uniProtKBCrossReferences: []
- primaryAccession: A0A1U9RZH7
  entryType: UniProtKB unreviewed (TrEMBL)
  entryAudit:
    firstPublicDate: '2017-06-07'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '2017-06-07'
    entryVersion: 17
    sequenceVersion: 1
  genes:
  - geneName:
      evidences:
      - evidenceCode: ECO:0000256
        source: HAMAP-Rule
        id: MF_01390
      - evidenceCode: ECO:0000313
        source: EMBL
        id: AQV10439.1
      value: matK
  organism:
    scientificName: Thlaspi arvense
    taxonId: 13288
  sequence:
    length: 503
    sha256: 6b31bfaf411317186a9692ecbead6858715ab14da7ed31a3eec13155340d66c6
  uniProtKBCrossReferences:
  - database: Proteomes
    id: UP000836841
    properties:
    - key: Component
      value: Chloroplast
reference_proteomes:
- id: UP000836841
  proteomeType: Reference proteome
  taxonomy:
    scientificName: Thlaspi arvense
    commonName: Field penny-cress
    taxonId: 13288
    mnemonic: THLAR
unisave_records:
- entry_version: 46
  url: https://rest.uniprot.org/unisave/Q9GF35?format=txt&versions=46
  entry_date: 07-JAN-2015, entry version 46.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 51
  url: https://rest.uniprot.org/unisave/Q9GF35?format=txt&versions=51
  entry_date: 11-DEC-2019, entry version 51.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 53
  url: https://rest.uniprot.org/unisave/Q9GF35?format=txt&versions=53
  entry_date: 22-FEB-2023, entry version 53.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
archived_sources:
- path: genes/THLAR/matK/matK-record-evidence.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/THLAR/matK/matK-record-evidence.yaml
  sha256: 82bb83f44e9f29d1a8041d987ad27be3ff59192d26e258348cbdd8aaedfbbe5b
  excerpts:
  - start_line: 26
    end_line: 38
    text: |2
        alternative_sequence_length: 503
        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:
        - 46
  - start_line: 871
    end_line: 876
    text: |
      - entry_version: 46
        url: https://rest.uniprot.org/unisave/Q9GF35?format=txt&versions=46
        entry_date: 07-JAN-2015, entry version 46.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 936
    end_line: 941
    text: |
      - entry_version: 51
        url: https://rest.uniprot.org/unisave/Q9GF35?format=txt&versions=51
        entry_date: 11-DEC-2019, entry version 51.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 1002
    end_line: 1007
    text: |
      - entry_version: 53
        url: https://rest.uniprot.org/unisave/Q9GF35?format=txt&versions=53
        entry_date: 22-FEB-2023, entry version 53.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
- path: genes/THLAR/matK/matK-bioinformatics/reference-counterparts/comparison.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/THLAR/matK/matK-bioinformatics/reference-counterparts/comparison.yaml
  sha256: 6abb4e32b588385b5cd89bbfe265191872dc390816a3c0e188c2801ed547bfec
  excerpts:
  - start_line: 25
    end_line: 29
    text: |2
        - -v
        - '1'
        target_sequence_count: 26379
        query_sha256: 8554b22bd9b055bef2e6aa96608bfa2c74ccdcb6ce7c3c41fb523b0759d0d8e0
        targets_sha256: 910a65b4aade115c4580367fef21e13622f7c9124925c8eb53c942c103d735d2
  - start_line: 44
    end_line: 48
    text: |2
          sha256: 910a65b4aade115c4580367fef21e13622f7c9124925c8eb53c942c103d735d2
        detailed_alignment_limit: 10
      candidate_count: 6
      candidates:
      - accession: A0A1U9RZH7
  - start_line: 51
    end_line: 63
    text: |2
        bit_score: 1014.0
        global_score: 2584.0
        query_length: 504
        target_length: 503
        alignment_columns: 504
        identities: 495
        mismatches: 8
        gap_columns: 1
        identity_percent: 98.2143
        query_coverage_percent: 99.8016
        target_coverage_percent: 100.0
        substitutions:
        - query_position: 2
comparison:
  provenance:
    query_accession: Q9GF35
    run_at: '2026-10-18T23:35:59.788523+00:00'
    biopython_version: '1.85'
    mmseqs_version: 18-8cc5c
    command:
    - mmseqs
    - easy-search
    - genes/THLAR/matK/matK-bioinformatics/reference-counterparts/query.fasta
    - .cache/orphan-curated/UP000836841.fasta
    - genes/THLAR/matK/matK-bioinformatics/reference-counterparts/search.tsv
    - genes/THLAR/matK/matK-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: 8554b22bd9b055bef2e6aa96608bfa2c74ccdcb6ce7c3c41fb523b0759d0d8e0
    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: 6
  retained_alignment_count: 6
  candidates:
  - accession: A0A1U9RZH7
    description: tr|A0A1U9RZH7|A0A1U9RZH7_THLAR Maturase K OS=Thlaspi arvense OX=13288 GN=matK PE=3 SV=1
    evalue: 0.0
    bit_score: 1014.0
    global_score: 2584.0
    query_length: 504
    target_length: 503
    alignment_columns: 504
    identities: 495
    mismatches: 8
    gap_columns: 1
    identity_percent: 98.2143
    query_coverage_percent: 99.8016
    target_coverage_percent: 100.0
  - accession: A0AAU9S9N0
    description: tr|A0AAU9S9N0|A0AAU9S9N0_THLAR Maturase K (Fragment) OS=Thlaspi arvense OX=13288 GN=TAV2_LOCUS15039
      PE=3 SV=1
    evalue: 1.792e-199
    bit_score: 624.0
    global_score: 1576.0
    query_length: 504
    target_length: 339
    alignment_columns: 504
    identities: 328
    mismatches: 11
    gap_columns: 165
    identity_percent: 65.0794
    query_coverage_percent: 67.2619
    target_coverage_percent: 100.0