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/A9PCL4.json
  retrieved_at: '2026-10-18T23:26:04.381540+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/uniprotkb/B9ILP9.json
  retrieved_at: '2026-10-18T23:26:05.030196+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/proteomes/UP000006729.json
  retrieved_at: '2026-10-18T23:26:06.018590+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/A9PCL4?format=txt&versions=37
  retrieved_at: '2026-10-18T23:26:09.228402+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/A9PCL4?format=txt&versions=62
  retrieved_at: '2026-10-18T23:26:11.345164+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/A9PCL4?format=txt&versions=77
  retrieved_at: '2026-10-18T23:26:13.742570+00:00'
  uniprot_release: '2026_03'
- url: https://www.ebi.ac.uk/ena/browser/api/embl/EF146010
  retrieved_at: '2026-10-18T23:26:14.382031+00:00'
  uniprot_release: null
observations:
  primary_accession: A9PCL4
  alternative_accession: B9ILP9
  sequence_identical: false
  primary_sequence_length: 162
  alternative_sequence_length: 162
  shared_uniparc_id: null
  same_taxon: true
  reference_proteome: UP000006729
  proteome_is_reference: true
  proteome_taxon_matches: true
  primary_in_reference_proteome: false
  alternative_in_reference_proteome: true
  sampled_history_versions:
  - 37
  - 62
  - 77
  sampled_versions_with_proteome_links: []
current_records:
- primaryAccession: A9PCL4
  entryType: UniProtKB reviewed (Swiss-Prot)
  entryAudit:
    firstPublicDate: '2017-08-30'
    lastAnnotationUpdateDate: '2026-06-10'
    lastSequenceUpdateDate: '2008-02-05'
    entryVersion: 78
    sequenceVersion: 1
  organism:
    scientificName: Populus trichocarpa
    taxonId: 3694
  sequence:
    length: 162
    sha256: 166bac3fd1fc72f889db4f3ffec64c86feafb16f0699d28f614e78739ef242dd
  uniProtKBCrossReferences: []
- primaryAccession: B9ILP9
  entryType: UniProtKB unreviewed (TrEMBL)
  entryAudit:
    firstPublicDate: '2009-03-24'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '2009-03-24'
    entryVersion: 91
    sequenceVersion: 1
  genes:
  - orfNames:
    - evidences:
      - evidenceCode: ECO:0000313
        source: EMBL
        id: PNS93359.1
      value: POPTR_018G083500
  organism:
    scientificName: Populus trichocarpa
    taxonId: 3694
  sequence:
    length: 162
    sha256: 1b9c7c674a9cf732ef517986e1f6fdd166ae0353d0f5f903fad0008c2efbe86d
  uniProtKBCrossReferences:
  - database: Gramene
    id: Potri.018G083500.1.v4.1
    properties:
    - key: ProteinId
      value: Potri.018G083500.1.v4.1
    - key: GeneId
      value: Potri.018G083500.v4.1
  - database: Proteomes
    id: UP000006729
    properties:
    - key: Component
      value: Chromosome 18
reference_proteomes:
- id: UP000006729
  proteomeType: Reference proteome
  taxonomy:
    scientificName: Populus trichocarpa
    commonName: Western balsam poplar
    synonyms:
    - Populus balsamifera subsp. trichocarpa
    taxonId: 3694
    mnemonic: POPTR
unisave_records:
- entry_version: 37
  url: https://rest.uniprot.org/unisave/A9PCL4?format=txt&versions=37
  entry_date: 09-DEC-2015, entry version 37.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 62
  url: https://rest.uniprot.org/unisave/A9PCL4?format=txt&versions=62
  entry_date: 12-AUG-2020, entry version 62.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 77
  url: https://rest.uniprot.org/unisave/A9PCL4?format=txt&versions=77
  entry_date: 27-NOV-2024, entry version 77.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
archived_sources:
- path: genes/POPTR/PRX2/PRX2-record-evidence.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/POPTR/PRX2/PRX2-record-evidence.yaml
  sha256: 83603fde9482dfd90904ff9f578b3f56af03cff88461bed05fc43ebd3c6200a1
  excerpts:
  - start_line: 30
    end_line: 43
    text: |2
        shared_uniparc_id: null
        same_taxon: true
        reference_proteome: UP000006729
        proteome_is_reference: true
        proteome_taxon_matches: true
        primary_in_reference_proteome: false
        alternative_in_reference_proteome: true
        sampled_history_versions:
        - 37
        - 62
        - 77
        sampled_versions_with_proteome_links: []
      current_records:
      - entryType: UniProtKB reviewed (Swiss-Prot)
  - start_line: 2421
    end_line: 2425
    text: |2
          FT   source          1..693
          FT                   /organism="Populus trichocarpa"
          FT                   /cultivar="383-2499 (Nisqually-1)"
          FT                   /mol_type="mRNA"
          FT                   /sex="Female"
- path: genes/POPTR/PRX2/PRX2-bioinformatics/reference-counterparts/comparison.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/POPTR/PRX2/PRX2-bioinformatics/reference-counterparts/comparison.yaml
  sha256: c189c5dcdbb86580639491f4f6164760ac491a504ea1fc1f28da33a37fead8ca
  excerpts:
  - start_line: 50
    end_line: 62
    text: |2
        bit_score: 330.0
        global_score: 823.0
        query_length: 162
        target_length: 162
        alignment_columns: 162
        identities: 161
        mismatches: 1
        gap_columns: 0
        identity_percent: 99.3827
        query_coverage_percent: 100.0
        target_coverage_percent: 100.0
        substitutions:
        - query_position: 117
comparison:
  provenance:
    query_accession: A9PCL4
    run_at: '2026-10-18T23:25:23.324537+00:00'
    biopython_version: '1.85'
    mmseqs_version: 18-8cc5c
    command:
    - mmseqs
    - easy-search
    - genes/POPTR/PRX2/PRX2-bioinformatics/reference-counterparts/query.fasta
    - .cache/orphan-curated/UP000006729.fasta
    - genes/POPTR/PRX2/PRX2-bioinformatics/reference-counterparts/search.tsv
    - genes/POPTR/PRX2/PRX2-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: 77340
    query_sha256: 213b399cc2c62e4ce170006a24a265bd8529b590163c7c85cb4973ebcb05bb8e
    targets_sha256: 988d46285688cd97f593b97011935be87d007e7844c778e1d5c30ba9839dc4c0
    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%3AUP000006729&format=fasta
      retrieved_at: '2026-10-18T23:23:27.698811+00:00'
      uniprot_release: '2026_03'
      sequence_count: 77340
  candidate_count: 5
  retained_alignment_count: 5
  candidates:
  - accession: B9ILP9
    description: tr|B9ILP9|B9ILP9_POPTR Glutaredoxin-dependent peroxiredoxin OS=Populus trichocarpa OX=3694
      GN=POPTR_018G083500 PE=3 SV=1
    evalue: 9.356e-104
    bit_score: 330.0
    global_score: 823.0
    query_length: 162
    target_length: 162
    alignment_columns: 162
    identities: 161
    mismatches: 1
    gap_columns: 0
    identity_percent: 99.3827
    query_coverage_percent: 100.0
    target_coverage_percent: 100.0
  - accession: A0A2K2CCD0
    description: tr|A0A2K2CCD0|A0A2K2CCD0_POPTR Glutaredoxin-dependent peroxiredoxin OS=Populus trichocarpa
      OX=3694 GN=POPTR_001G423500 PE=3 SV=1
    evalue: 1.823e-100
    bit_score: 320.0
    global_score: 799.0
    query_length: 162
    target_length: 162
    alignment_columns: 162
    identities: 155
    mismatches: 7
    gap_columns: 0
    identity_percent: 95.679
    query_coverage_percent: 100.0
    target_coverage_percent: 100.0
