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/Q8L4H4.json
  retrieved_at: '2026-10-18T23:39:40.253936+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/uniprotkb/A9YWR7.json
  retrieved_at: '2026-10-18T23:39:40.431119+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/proteomes/UP000002051.json
  retrieved_at: '2026-10-18T23:39:40.582784+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/Q8L4H4?format=txt&versions=79
  retrieved_at: '2026-10-18T23:39:42.433582+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/Q8L4H4?format=txt&versions=105
  retrieved_at: '2026-10-18T23:39:43.338690+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/Q8L4H4?format=txt&versions=119
  retrieved_at: '2026-10-18T23:39:45.750625+00:00'
  uniprot_release: '2026_03'
observations:
  primary_accession: Q8L4H4
  alternative_accession: A9YWR7
  sequence_identical: true
  primary_sequence_length: 925
  alternative_sequence_length: 925
  shared_uniparc_id: UPI00000A0BAD
  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:
  - 79
  - 105
  - 119
  sampled_versions_with_proteome_links: []
current_records:
- primaryAccession: Q8L4H4
  entryType: UniProtKB reviewed (Swiss-Prot)
  entryAudit:
    firstPublicDate: '2005-07-19'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '2005-07-19'
    entryVersion: 124
    sequenceVersion: 2
  genes:
  - geneName:
      value: NORK
    synonyms:
    - value: DMI2
    - value: SYMRK
  organism:
    scientificName: Medicago truncatula
    taxonId: 3880
  sequence:
    length: 925
    sha256: 0219f3f658fda80d96b813f9baeef6e21445118a17e4cf23fadec453873afae2
  uniProtKBCrossReferences:
  - database: Gramene
    id: rna29973
    properties:
    - key: ProteinId
      value: RHN54876.1
    - key: GeneId
      value: gene29973
- primaryAccession: A9YWR7
  entryType: UniProtKB unreviewed (TrEMBL)
  entryAudit:
    firstPublicDate: '2008-02-05'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '2008-02-05'
    entryVersion: 110
    sequenceVersion: 1
  genes:
  - orderedLocusNames:
    - evidences:
      - evidenceCode: ECO:0000313
        source: EMBL
        id: AES95909.2
      value: MTR_5g030920
  organism:
    scientificName: Medicago truncatula
    taxonId: 3880
  sequence:
    length: 925
    sha256: 0219f3f658fda80d96b813f9baeef6e21445118a17e4cf23fadec453873afae2
  uniProtKBCrossReferences:
  - database: Gramene
    id: rna29973
    properties:
    - key: ProteinId
      value: RHN54876.1
    - key: GeneId
      value: gene29973
  - database: Proteomes
    id: UP000002051
    properties:
    - key: Component
      value: Chromosome 5
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: 79
  url: https://rest.uniprot.org/unisave/Q8L4H4?format=txt&versions=79
  entry_date: 11-NOV-2015, entry version 79.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 105
  url: https://rest.uniprot.org/unisave/Q8L4H4?format=txt&versions=105
  entry_date: 07-OCT-2020, entry version 105.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 119
  url: https://rest.uniprot.org/unisave/Q8L4H4?format=txt&versions=119
  entry_date: 27-NOV-2024, entry version 119.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
archived_sources:
- path: genes/MEDTR/NORK/NORK-record-evidence.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/MEDTR/NORK/NORK-record-evidence.yaml
  sha256: 3219655756b6c96c335fcdf486cf13b159844526b2075bfe5da2edad08fbce5f
  excerpts:
  - start_line: 26
    end_line: 38
    text: |2
        alternative_sequence_length: 925
        shared_uniparc_id: UPI00000A0BAD
        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:
        - 79
  - start_line: 2243
    end_line: 2248
    text: |
      - entry_version: 79
        url: https://rest.uniprot.org/unisave/Q8L4H4?format=txt&versions=79
        entry_date: 11-NOV-2015, entry version 79.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 2389
    end_line: 2394
    text: |
      - entry_version: 105
        url: https://rest.uniprot.org/unisave/Q8L4H4?format=txt&versions=105
        entry_date: 07-OCT-2020, entry version 105.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 2582
    end_line: 2587
    text: |
      - entry_version: 119
        url: https://rest.uniprot.org/unisave/Q8L4H4?format=txt&versions=119
        entry_date: 27-NOV-2024, entry version 119.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
- path: genes/MEDTR/NORK/NORK-bioinformatics/reference-counterparts/comparison.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/MEDTR/NORK/NORK-bioinformatics/reference-counterparts/comparison.yaml
  sha256: 577cb162326c669b8a6901de0accdf53bcbe85142caf6e2dd311e35165ecc1f7
  excerpts:
  - start_line: 25
    end_line: 29
    text: |2
        - -v
        - '1'
        target_sequence_count: 57093
        query_sha256: 0e8325c1f24a520de7ce0a6d431ce40b2744d30b2d79c3c3410335d3c6f8d619
        targets_sha256: 8ac430216530f98d6200d71bbba8c620be70841df3903a137559bd1a0fe4b8be
  - start_line: 44
    end_line: 48
    text: |2
          sha256: 8ac430216530f98d6200d71bbba8c620be70841df3903a137559bd1a0fe4b8be
        detailed_alignment_limit: 10
      candidate_count: 1000
      candidates:
      - accession: A9YWR7
  - start_line: 52
    end_line: 64
    text: |2
        bit_score: 1875.0
        global_score: 4791.0
        query_length: 925
        target_length: 925
        alignment_columns: 925
        identities: 925
        mismatches: 0
        gap_columns: 0
        identity_percent: 100.0
        query_coverage_percent: 100.0
        target_coverage_percent: 100.0
        substitutions: []
      - accession: G7KGF4
comparison:
  provenance:
    query_accession: Q8L4H4
    run_at: '2026-10-18T23:35:20.892538+00:00'
    biopython_version: '1.85'
    mmseqs_version: 18-8cc5c
    command:
    - mmseqs
    - easy-search
    - genes/MEDTR/NORK/NORK-bioinformatics/reference-counterparts/query.fasta
    - .cache/orphan-curated/UP000002051.fasta
    - genes/MEDTR/NORK/NORK-bioinformatics/reference-counterparts/search.tsv
    - genes/MEDTR/NORK/NORK-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: 0e8325c1f24a520de7ce0a6d431ce40b2744d30b2d79c3c3410335d3c6f8d619
    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: 1000
  retained_alignment_count: 10
  candidates:
  - accession: A9YWR7
    description: tr|A9YWR7|A9YWR7_MEDTR Serine/threonine-protein OS=Medicago truncatula OX=3880 GN=MTR_5g030920
      PE=3 SV=1
    evalue: 0.0
    bit_score: 1875.0
    global_score: 4791.0
    query_length: 925
    target_length: 925
    alignment_columns: 925
    identities: 925
    mismatches: 0
    gap_columns: 0
    identity_percent: 100.0
    query_coverage_percent: 100.0
    target_coverage_percent: 100.0
  - accession: G7KGF4
    description: tr|G7KGF4|G7KGF4_MEDTR Serine/threonine-protein OS=Medicago truncatula OX=3880 GN=MTR_5g030920
      PE=3 SV=2
    evalue: 0.0
    bit_score: 1815.0
    global_score: 4651.0
    query_length: 925
    target_length: 902
    alignment_columns: 925
    identities: 902
    mismatches: 0
    gap_columns: 23
    identity_percent: 97.5135
    query_coverage_percent: 97.5135
    target_coverage_percent: 100.0