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/P13664.json
  retrieved_at: '2026-10-18T23:39:12.477618+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/uniprotkb/A0A7J6K396.json
  retrieved_at: '2026-10-18T23:39:12.639822+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/proteomes/UP000557509.json
  retrieved_at: '2026-10-18T23:39:12.790359+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/P13664?format=txt&versions=84
  retrieved_at: '2026-10-18T23:39:13.320902+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/P13664?format=txt&versions=97
  retrieved_at: '2026-10-18T23:39:14.639191+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/P13664?format=txt&versions=102
  retrieved_at: '2026-10-18T23:39:14.834468+00:00'
  uniprot_release: '2026_03'
observations:
  primary_accession: P13664
  alternative_accession: A0A7J6K396
  sequence_identical: true
  primary_sequence_length: 336
  alternative_sequence_length: 336
  shared_uniparc_id: UPI000013100B
  same_taxon: true
  reference_proteome: UP000557509
  proteome_is_reference: true
  proteome_taxon_matches: true
  primary_in_reference_proteome: false
  alternative_in_reference_proteome: true
  searched_reference_proteomes:
  - UP000557509
  primary_in_any_reference_proteome: false
  sampled_history_versions:
  - 84
  - 97
  - 102
  sampled_versions_with_proteome_links: []
current_records:
- primaryAccession: P13664
  entryType: UniProtKB reviewed (Swiss-Prot)
  entryAudit:
    firstPublicDate: '1990-01-01'
    lastAnnotationUpdateDate: '2026-06-10'
    lastSequenceUpdateDate: '1990-01-01'
    entryVersion: 104
    sequenceVersion: 1
  genes:
  - geneName:
      evidences:
      - evidenceCode: ECO:0000303
        source: PubMed
        id: '12091874'
      - evidenceCode: ECO:0000303
        source: PubMed
        id: '15151144'
      - evidenceCode: ECO:0000303
        source: PubMed
        id: '16242717'
      - evidenceCode: ECO:0000303
        source: PubMed
        id: '29351065'
      - evidenceCode: ECO:0000303
        source: PubMed
        id: '31165984'
      - evidenceCode: ECO:0000303
        source: PubMed
        id: '38157925'
      - evidenceCode: ECO:0000303
        source: PubMed
        id: '40607979'
      value: SAG1
  organism:
    scientificName: Toxoplasma gondii
    taxonId: 5811
  sequence:
    length: 336
    sha256: 82d6f098be9ab913e26e1c8771f4736a72cb7911ac3ff6def0e44dd291efaeb1
  uniProtKBCrossReferences: []
- primaryAccession: A0A7J6K396
  entryType: UniProtKB unreviewed (TrEMBL)
  entryAudit:
    firstPublicDate: '2026-06-10'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '2026-06-10'
    entryVersion: 2
    sequenceVersion: 1
  genes:
  - orfNames:
    - evidences:
      - evidenceCode: ECO:0000313
        source: EMBL
        id: KAF4641933.1
      value: TGRH88_077450
  organism:
    scientificName: Toxoplasma gondii
    taxonId: 5811
  sequence:
    length: 336
    sha256: 82d6f098be9ab913e26e1c8771f4736a72cb7911ac3ff6def0e44dd291efaeb1
  uniProtKBCrossReferences:
  - database: Proteomes
    id: UP000557509
    properties:
    - key: Component
      value: Unassembled WGS sequence
reference_proteomes:
- id: UP000557509
  proteomeType: Reference proteome
  taxonomy:
    scientificName: Toxoplasma gondii
    taxonId: 5811
    mnemonic: TOXGO
unisave_records:
- entry_version: 84
  url: https://rest.uniprot.org/unisave/P13664?format=txt&versions=84
  entry_date: 09-DEC-2015, entry version 84.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 97
  url: https://rest.uniprot.org/unisave/P13664?format=txt&versions=97
  entry_date: 02-DEC-2020, entry version 97.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 102
  url: https://rest.uniprot.org/unisave/P13664?format=txt&versions=102
  entry_date: 22-FEB-2023, entry version 102.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
archived_sources:
- path: genes/TOXGO/SAG1/SAG1-record-evidence.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/TOXGO/SAG1/SAG1-record-evidence.yaml
  sha256: dd56a2540c047e14df5b9137eb96c25df74c37e4c4e770af6a52d24e8939c222
  excerpts:
  - start_line: 26
    end_line: 38
    text: |2
        alternative_sequence_length: 336
        shared_uniparc_id: UPI000013100B
        same_taxon: true
        reference_proteome: UP000557509
        proteome_is_reference: true
        proteome_taxon_matches: true
        primary_in_reference_proteome: false
        alternative_in_reference_proteome: true
        searched_reference_proteomes:
        - UP000557509
        primary_in_any_reference_proteome: false
        sampled_history_versions:
        - 84
  - start_line: 1777
    end_line: 1782
    text: |
      - entry_version: 84
        url: https://rest.uniprot.org/unisave/P13664?format=txt&versions=84
        entry_date: 09-DEC-2015, entry version 84.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 1884
    end_line: 1889
    text: |
      - entry_version: 97
        url: https://rest.uniprot.org/unisave/P13664?format=txt&versions=97
        entry_date: 02-DEC-2020, entry version 97.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 2023
    end_line: 2028
    text: |
      - entry_version: 102
        url: https://rest.uniprot.org/unisave/P13664?format=txt&versions=102
        entry_date: 22-FEB-2023, entry version 102.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
- path: genes/TOXGO/SAG1/SAG1-bioinformatics/reference-counterparts/comparison.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/TOXGO/SAG1/SAG1-bioinformatics/reference-counterparts/comparison.yaml
  sha256: 4a55d3221ed21b3db2a46861abae401a457400ababdeac553278d583951d8818
  excerpts:
  - start_line: 25
    end_line: 29
    text: |2
        - -v
        - '1'
        target_sequence_count: 8261
        query_sha256: df73bcdb206197ab062c83ea24c5bdd73a5267c5d3ef81ba7262b66df1a33fd2
        targets_sha256: 0080c5b84a3f6730563119178ec2df3d6efabb97766b2a73c55387d36c2695a9
  - start_line: 44
    end_line: 48
    text: |2
          sha256: 0080c5b84a3f6730563119178ec2df3d6efabb97766b2a73c55387d36c2695a9
        detailed_alignment_limit: 10
      candidate_count: 37
      candidates:
      - accession: A0A7J6K396
  - start_line: 52
    end_line: 64
    text: |2
        bit_score: 669.0
        global_score: 1740.0
        query_length: 336
        target_length: 336
        alignment_columns: 336
        identities: 336
        mismatches: 0
        gap_columns: 0
        identity_percent: 100.0
        query_coverage_percent: 100.0
        target_coverage_percent: 100.0
        substitutions: []
      - accession: A0A7J6K383
comparison:
  provenance:
    query_accession: P13664
    run_at: '2026-10-18T23:34:36.912149+00:00'
    biopython_version: '1.85'
    mmseqs_version: 18-8cc5c
    command:
    - mmseqs
    - easy-search
    - genes/TOXGO/SAG1/SAG1-bioinformatics/reference-counterparts/query.fasta
    - .cache/orphan-curated/UP000557509.fasta
    - genes/TOXGO/SAG1/SAG1-bioinformatics/reference-counterparts/search.tsv
    - genes/TOXGO/SAG1/SAG1-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: 8261
    query_sha256: df73bcdb206197ab062c83ea24c5bdd73a5267c5d3ef81ba7262b66df1a33fd2
    targets_sha256: 0080c5b84a3f6730563119178ec2df3d6efabb97766b2a73c55387d36c2695a9
    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%3AUP000557509&format=fasta
      retrieved_at: '2026-10-18T23:32:33.673857+00:00'
      uniprot_release: '2026_03'
      sequence_count: 8261
      sha256: 0080c5b84a3f6730563119178ec2df3d6efabb97766b2a73c55387d36c2695a9
    detailed_alignment_limit: 10
  candidate_count: 37
  retained_alignment_count: 10
  candidates:
  - accession: A0A7J6K396
    description: tr|A0A7J6K396|A0A7J6K396_TOXGO SAG-related sequence SRS29B OS=Toxoplasma gondii OX=5811
      GN=TGRH88_077450 PE=4 SV=1
    evalue: 1.136e-218
    bit_score: 669.0
    global_score: 1740.0
    query_length: 336
    target_length: 336
    alignment_columns: 336
    identities: 336
    mismatches: 0
    gap_columns: 0
    identity_percent: 100.0
    query_coverage_percent: 100.0
    target_coverage_percent: 100.0
  - accession: A0A7J6K383
    description: tr|A0A7J6K383|A0A7J6K383_TOXGO SAG-related sequence SRS29C OS=Toxoplasma gondii OX=5811
      GN=TGRH88_077470 PE=4 SV=1
    evalue: 4.082e-29
    bit_score: 119.0
    global_score: 317.5
    query_length: 336
    target_length: 372
    alignment_columns: 391
    identities: 103
    mismatches: 214
    gap_columns: 74
    identity_percent: 26.3427
    query_coverage_percent: 94.3452
    target_coverage_percent: 85.2151