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/P15802.json
  retrieved_at: '2026-10-18T23:39:15.290892+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/uniprotkb/A0ABQ8WFJ5.json
  retrieved_at: '2026-10-18T23:39:15.452928+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/proteomes/UP001220256.json
  retrieved_at: '2026-10-18T23:39:15.605691+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/P15802?format=txt&versions=79
  retrieved_at: '2026-10-18T23:39:18.600816+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/P15802?format=txt&versions=87
  retrieved_at: '2026-10-18T23:39:20.848842+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/P15802?format=txt&versions=97
  retrieved_at: '2026-10-18T23:39:22.641312+00:00'
  uniprot_release: '2026_03'
observations:
  primary_accession: P15802
  alternative_accession: A0ABQ8WFJ5
  sequence_identical: false
  primary_sequence_length: 357
  alternative_sequence_length: 357
  shared_uniparc_id: null
  same_taxon: true
  reference_proteome: UP001220256
  proteome_is_reference: true
  proteome_taxon_matches: true
  primary_in_reference_proteome: false
  alternative_in_reference_proteome: true
  searched_reference_proteomes:
  - UP001220256
  primary_in_any_reference_proteome: false
  sampled_history_versions:
  - 79
  - 87
  - 97
  sampled_versions_with_proteome_links: []
current_records:
- primaryAccession: P15802
  entryType: UniProtKB reviewed (Swiss-Prot)
  entryAudit:
    firstPublicDate: '1990-04-01'
    lastAnnotationUpdateDate: '2025-02-05'
    lastSequenceUpdateDate: '1990-04-01'
    entryVersion: 98
    sequenceVersion: 1
  genes:
  - geneName:
      evidences:
      - evidenceCode: ECO:0000303
        source: PubMed
        id: '2555269'
      value: aatA
    synonyms:
    - evidences:
      - evidenceCode: ECO:0000303
        source: PubMed
        id: '2120195'
      value: penDE
  organism:
    scientificName: Penicillium chrysogenum
    taxonId: 5076
  sequence:
    length: 357
    sha256: 44daaf90bbb325ed90ca539f058846eab0695689df4f193bd8b3704acdf1ebda
  uniProtKBCrossReferences: []
- primaryAccession: A0ABQ8WFJ5
  entryType: UniProtKB unreviewed (TrEMBL)
  entryAudit:
    firstPublicDate: '2025-10-08'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '2025-10-08'
    entryVersion: 4
    sequenceVersion: 1
  genes:
  - orfNames:
    - evidences:
      - evidenceCode: ECO:0000313
        source: EMBL
        id: KAJ5268731.1
      value: N7505_004489
  organism:
    scientificName: Penicillium chrysogenum
    taxonId: 5076
  sequence:
    length: 357
    sha256: 45f85959870be7442beaa9bce11328c373d82774cdd82efef44b1827dc306143
  uniProtKBCrossReferences:
  - database: Proteomes
    id: UP001220256
    properties:
    - key: Component
      value: Unassembled WGS sequence
reference_proteomes:
- id: UP001220256
  proteomeType: Reference proteome
  taxonomy:
    scientificName: Penicillium chrysogenum
    synonyms:
    - Penicillium notatum
    taxonId: 5076
    mnemonic: PENCH
unisave_records:
- entry_version: 79
  url: https://rest.uniprot.org/unisave/P15802?format=txt&versions=79
  entry_date: 11-NOV-2015, entry version 79.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 87
  url: https://rest.uniprot.org/unisave/P15802?format=txt&versions=87
  entry_date: 12-AUG-2020, entry version 87.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 97
  url: https://rest.uniprot.org/unisave/P15802?format=txt&versions=97
  entry_date: 27-NOV-2024, entry version 97.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
archived_sources:
- path: genes/PENCH/aatA/aatA-record-evidence.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/PENCH/aatA/aatA-record-evidence.yaml
  sha256: 74799211280199e306ee23fcca3c60ebc562d5c5369aec7719e8fc8c02bfcda9
  excerpts:
  - start_line: 26
    end_line: 38
    text: |2
        alternative_sequence_length: 357
        shared_uniparc_id: null
        same_taxon: true
        reference_proteome: UP001220256
        proteome_is_reference: true
        proteome_taxon_matches: true
        primary_in_reference_proteome: false
        alternative_in_reference_proteome: true
        searched_reference_proteomes:
        - UP001220256
        primary_in_any_reference_proteome: false
        sampled_history_versions:
        - 79
  - start_line: 1815
    end_line: 1820
    text: |
      - entry_version: 79
        url: https://rest.uniprot.org/unisave/P15802?format=txt&versions=79
        entry_date: 11-NOV-2015, entry version 79.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 1970
    end_line: 1975
    text: |
      - entry_version: 87
        url: https://rest.uniprot.org/unisave/P15802?format=txt&versions=87
        entry_date: 12-AUG-2020, entry version 87.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 2159
    end_line: 2164
    text: |
      - entry_version: 97
        url: https://rest.uniprot.org/unisave/P15802?format=txt&versions=97
        entry_date: 27-NOV-2024, entry version 97.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
- path: genes/PENCH/aatA/aatA-bioinformatics/reference-counterparts/comparison.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/PENCH/aatA/aatA-bioinformatics/reference-counterparts/comparison.yaml
  sha256: 42b3882bffbf5861f9f26075ad50ac5ed1566e1321a0d38d9e7ddec0d340035d
  excerpts:
  - start_line: 25
    end_line: 29
    text: |2
        - -v
        - '1'
        target_sequence_count: 12232
        query_sha256: 18f748ae752ec0b3731fbaf6970acb4b1dbc3b6cd004f69053d0b1473329b3d5
        targets_sha256: 12df947d88b56c2c158e6faf5dbe55afbd8bf8ec26ee9ec4aa096e8ac59ff786
  - start_line: 44
    end_line: 48
    text: |2
          sha256: 12df947d88b56c2c158e6faf5dbe55afbd8bf8ec26ee9ec4aa096e8ac59ff786
        detailed_alignment_limit: 10
      candidate_count: 2
      candidates:
      - accession: A0ABQ8WFJ5
  - start_line: 52
    end_line: 64
    text: |2
        bit_score: 735.0
        global_score: 1856.0
        query_length: 357
        target_length: 357
        alignment_columns: 357
        identities: 355
        mismatches: 2
        gap_columns: 0
        identity_percent: 99.4398
        query_coverage_percent: 100.0
        target_coverage_percent: 100.0
        substitutions:
        - query_position: 16
comparison:
  provenance:
    query_accession: P15802
    run_at: '2026-10-18T23:34:39.289623+00:00'
    biopython_version: '1.85'
    mmseqs_version: 18-8cc5c
    command:
    - mmseqs
    - easy-search
    - genes/PENCH/aatA/aatA-bioinformatics/reference-counterparts/query.fasta
    - .cache/orphan-curated/UP001220256.fasta
    - genes/PENCH/aatA/aatA-bioinformatics/reference-counterparts/search.tsv
    - genes/PENCH/aatA/aatA-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: 12232
    query_sha256: 18f748ae752ec0b3731fbaf6970acb4b1dbc3b6cd004f69053d0b1473329b3d5
    targets_sha256: 12df947d88b56c2c158e6faf5dbe55afbd8bf8ec26ee9ec4aa096e8ac59ff786
    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%3AUP001220256&format=fasta
      retrieved_at: '2026-10-18T23:32:48.692886+00:00'
      uniprot_release: '2026_03'
      sequence_count: 12232
      sha256: 12df947d88b56c2c158e6faf5dbe55afbd8bf8ec26ee9ec4aa096e8ac59ff786
    detailed_alignment_limit: 10
  candidate_count: 2
  retained_alignment_count: 2
  candidates:
  - accession: A0ABQ8WFJ5
    description: tr|A0ABQ8WFJ5|A0ABQ8WFJ5_PENCH Isopenicillin-N N-acyltransferase OS=Penicillium chrysogenum
      OX=5076 GN=N7505_004489 PE=3 SV=1
    evalue: 3.545e-241
    bit_score: 735.0
    global_score: 1856.0
    query_length: 357
    target_length: 357
    alignment_columns: 357
    identities: 355
    mismatches: 2
    gap_columns: 0
    identity_percent: 99.4398
    query_coverage_percent: 100.0
    target_coverage_percent: 100.0
  - accession: A0ABQ8WYG4
    description: tr|A0ABQ8WYG4|A0ABQ8WYG4_PENCH beta-glucosidase OS=Penicillium chrysogenum OX=5076 GN=N7505_001999
      PE=3 SV=1
    evalue: 1.415e-47
    bit_score: 175.0
    global_score: 183.5
    query_length: 357
    target_length: 852
    alignment_columns: 867
    identities: 134
    mismatches: 208
    gap_columns: 525
    identity_percent: 15.4556
    query_coverage_percent: 95.7983
    target_coverage_percent: 40.1408