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/Q6RHR6.json
  retrieved_at: '2026-10-18T23:39:39.271079+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/uniprotkb/G7IN96.json
  retrieved_at: '2026-10-18T23:39:39.455928+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/proteomes/UP000002051.json
  retrieved_at: '2026-10-18T23:39:39.624444+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/Q6RHR6?format=txt&versions=56
  retrieved_at: '2026-10-18T23:39:44.049088+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/Q6RHR6?format=txt&versions=83
  retrieved_at: '2026-10-18T23:39:45.953376+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/Q6RHR6?format=txt&versions=95
  retrieved_at: '2026-10-18T23:39:47.849888+00:00'
  uniprot_release: '2026_03'
observations:
  primary_accession: Q6RHR6
  alternative_accession: G7IN96
  sequence_identical: true
  primary_sequence_length: 882
  alternative_sequence_length: 882
  shared_uniparc_id: UPI000025397A
  same_taxon: true
  reference_proteome: UP000002051
  proteome_is_reference: true
  proteome_taxon_matches: true
  primary_in_reference_proteome: false
  alternative_in_reference_proteome: true
  searched_reference_proteomes:
  - UP000002051
  primary_in_any_reference_proteome: false
  sampled_history_versions:
  - 56
  - 83
  - 95
  sampled_versions_with_proteome_links: []
current_records:
- primaryAccession: Q6RHR6
  entryType: UniProtKB reviewed (Swiss-Prot)
  entryAudit:
    firstPublicDate: '2005-03-29'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '2004-07-05'
    entryVersion: 101
    sequenceVersion: 1
  genes:
  - geneName:
      evidences:
      - evidenceCode: ECO:0000303
        source: PubMed
        id: '14963334'
      value: DMI1
  organism:
    scientificName: Medicago truncatula
    taxonId: 3880
  sequence:
    length: 882
    sha256: 1de59376114780103aba9935dfab4ccf51067c01c0028d861df30b91a17388cd
  uniProtKBCrossReferences:
  - database: Gramene
    id: rna7068
    properties:
    - key: ProteinId
      value: RHN71463.1
    - key: GeneId
      value: gene7068
- primaryAccession: G7IN96
  entryType: UniProtKB unreviewed (TrEMBL)
  entryAudit:
    firstPublicDate: '2012-01-25'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '2012-01-25'
    entryVersion: 76
    sequenceVersion: 1
  genes:
  - orderedLocusNames:
    - evidences:
      - evidenceCode: ECO:0000313
        source: EMBL
        id: AES63182.1
      value: MTR_2g005870
  organism:
    scientificName: Medicago truncatula
    taxonId: 3880
  sequence:
    length: 882
    sha256: 1de59376114780103aba9935dfab4ccf51067c01c0028d861df30b91a17388cd
  uniProtKBCrossReferences:
  - database: Gramene
    id: rna7068
    properties:
    - key: ProteinId
      value: RHN71463.1
    - key: GeneId
      value: gene7068
  - database: Proteomes
    id: UP000002051
    properties:
    - key: Component
      value: Unassembled WGS sequence
reference_proteomes:
- id: UP000002051
  proteomeType: Reference proteome
  taxonomy:
    scientificName: Medicago truncatula
    commonName: Barrel medic
    synonyms:
    - Medicago tribuloides
    taxonId: 3880
    mnemonic: MEDTR
unisave_records:
- entry_version: 56
  url: https://rest.uniprot.org/unisave/Q6RHR6?format=txt&versions=56
  entry_date: 09-DEC-2015, entry version 56.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 83
  url: https://rest.uniprot.org/unisave/Q6RHR6?format=txt&versions=83
  entry_date: 07-OCT-2020, entry version 83.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 95
  url: https://rest.uniprot.org/unisave/Q6RHR6?format=txt&versions=95
  entry_date: 27-NOV-2024, entry version 95.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
archived_sources:
- path: genes/MEDTR/DMI1/DMI1-record-evidence.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/MEDTR/DMI1/DMI1-record-evidence.yaml
  sha256: 1ee84ff79a820dc0f9c79236a5220328b908555df7be401214ce94095a5043a1
  excerpts:
  - start_line: 26
    end_line: 38
    text: |2
        alternative_sequence_length: 882
        shared_uniparc_id: UPI000025397A
        same_taxon: true
        reference_proteome: UP000002051
        proteome_is_reference: true
        proteome_taxon_matches: true
        primary_in_reference_proteome: false
        alternative_in_reference_proteome: true
        searched_reference_proteomes:
        - UP000002051
        primary_in_any_reference_proteome: false
        sampled_history_versions:
        - 56
  - start_line: 2485
    end_line: 2490
    text: |
      - entry_version: 56
        url: https://rest.uniprot.org/unisave/Q6RHR6?format=txt&versions=56
        entry_date: 09-DEC-2015, entry version 56.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 2611
    end_line: 2616
    text: |
      - entry_version: 83
        url: https://rest.uniprot.org/unisave/Q6RHR6?format=txt&versions=83
        entry_date: 07-OCT-2020, entry version 83.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 2765
    end_line: 2770
    text: |
      - entry_version: 95
        url: https://rest.uniprot.org/unisave/Q6RHR6?format=txt&versions=95
        entry_date: 27-NOV-2024, entry version 95.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
- path: genes/MEDTR/DMI1/DMI1-bioinformatics/reference-counterparts/comparison.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/MEDTR/DMI1/DMI1-bioinformatics/reference-counterparts/comparison.yaml
  sha256: d42a9906da3abf09d7699b3b04ef2ae757cce7d9bc55086c670f5820cf864da2
  excerpts:
  - start_line: 25
    end_line: 29
    text: |2
        - -v
        - '1'
        target_sequence_count: 57093
        query_sha256: 71803a261f8f17d6206327bf008024a9b3a87f7204f5bf8556dfef44302b7317
        targets_sha256: 8ac430216530f98d6200d71bbba8c620be70841df3903a137559bd1a0fe4b8be
  - start_line: 44
    end_line: 48
    text: |2
          sha256: 8ac430216530f98d6200d71bbba8c620be70841df3903a137559bd1a0fe4b8be
        detailed_alignment_limit: 10
      candidate_count: 13
      candidates:
      - accession: G7IN96
  - start_line: 52
    end_line: 64
    text: |2
        bit_score: 1731.0
        global_score: 4495.0
        query_length: 882
        target_length: 882
        alignment_columns: 882
        identities: 882
        mismatches: 0
        gap_columns: 0
        identity_percent: 100.0
        query_coverage_percent: 100.0
        target_coverage_percent: 100.0
        substitutions: []
      - accession: A0A072VE48
comparison:
  provenance:
    query_accession: Q6RHR6
    run_at: '2026-10-18T23:35:05.836540+00:00'
    biopython_version: '1.85'
    mmseqs_version: 18-8cc5c
    command:
    - mmseqs
    - easy-search
    - genes/MEDTR/DMI1/DMI1-bioinformatics/reference-counterparts/query.fasta
    - .cache/orphan-curated/UP000002051.fasta
    - genes/MEDTR/DMI1/DMI1-bioinformatics/reference-counterparts/search.tsv
    - genes/MEDTR/DMI1/DMI1-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: 57093
    query_sha256: 71803a261f8f17d6206327bf008024a9b3a87f7204f5bf8556dfef44302b7317
    targets_sha256: 8ac430216530f98d6200d71bbba8c620be70841df3903a137559bd1a0fe4b8be
    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%3AUP000002051&format=fasta
      retrieved_at: '2026-10-18T23:32:19.876686+00:00'
      uniprot_release: '2026_03'
      sequence_count: 57093
      sha256: 8ac430216530f98d6200d71bbba8c620be70841df3903a137559bd1a0fe4b8be
    detailed_alignment_limit: 10
  candidate_count: 13
  retained_alignment_count: 10
  candidates:
  - accession: G7IN96
    description: tr|G7IN96|G7IN96_MEDTR Ion channel pollux-like protein OS=Medicago truncatula OX=3880
      GN=MTR_2g005870 PE=3 SV=1
    evalue: 0.0
    bit_score: 1731.0
    global_score: 4495.0
    query_length: 882
    target_length: 882
    alignment_columns: 882
    identities: 882
    mismatches: 0
    gap_columns: 0
    identity_percent: 100.0
    query_coverage_percent: 100.0
    target_coverage_percent: 100.0
  - accession: A0A072VE48
    description: tr|A0A072VE48|A0A072VE48_MEDTR Ion channel pollux-like protein OS=Medicago truncatula
      OX=3880 GN=MTR_2g005870 PE=3 SV=1
    evalue: 0.0
    bit_score: 1364.0
    global_score: 3461.0
    query_length: 882
    target_length: 705
    alignment_columns: 882
    identities: 694
    mismatches: 11
    gap_columns: 177
    identity_percent: 78.6848
    query_coverage_percent: 79.932
    target_coverage_percent: 100.0
