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/A2AXI2.json retrieved_at: '2026-10-18T23:38:45.560565+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/proteomes/UP000814367.json retrieved_at: '2026-10-18T23:38:46.057064+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/unisave/A2AXI2?format=txt&versions=43 retrieved_at: '2026-10-18T23:38:49.121692+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/unisave/A2AXI2?format=txt&versions=58 retrieved_at: '2026-10-18T23:38:51.328775+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/unisave/A2AXI2?format=txt&versions=68 retrieved_at: '2026-10-18T23:38:53.421328+00:00' uniprot_release: '2026_03' observations: primary_accession: A2AXI2 alternative_accession: null sequence_identical: null primary_sequence_length: 349 alternative_sequence_length: null shared_uniparc_id: null same_taxon: null reference_proteome: UP000814367 proteome_is_reference: true proteome_taxon_matches: true primary_in_reference_proteome: false alternative_in_reference_proteome: null searched_reference_proteomes: - UP000814367 primary_in_any_reference_proteome: false sampled_history_versions: - 43 - 58 - 68 sampled_versions_with_proteome_links: [] current_records: - primaryAccession: A2AXI2 entryType: UniProtKB reviewed (Swiss-Prot) entryAudit: firstPublicDate: '2008-09-02' lastAnnotationUpdateDate: '2026-09-02' lastSequenceUpdateDate: '2007-02-20' entryVersion: 72 sequenceVersion: 1 genes: - geneName: evidences: - evidenceCode: ECO:0000255 source: HAMAP-Rule id: MF_01873 value: cfr geneLocations: - value: pSCFS6 geneEncodingType: Plasmid organism: scientificName: Staphylococcus warneri taxonId: 1292 sequence: length: 349 sha256: fba800392d6140b7063fa3d85ed4c4eb231d04baab250b9e435ceada4abf75f1 uniProtKBCrossReferences: [] reference_proteomes: - id: UP000814367 proteomeType: Reference proteome taxonomy: scientificName: Staphylococcus warneri taxonId: 1292 mnemonic: STAWA unisave_records: - entry_version: 43 url: https://rest.uniprot.org/unisave/A2AXI2?format=txt&versions=43 entry_date: 11-NOV-2015, entry version 43. proteomes: [] reference_proteome_keyword: false record_text: '' - entry_version: 58 url: https://rest.uniprot.org/unisave/A2AXI2?format=txt&versions=58 entry_date: 02-DEC-2020, entry version 58. proteomes: [] reference_proteome_keyword: false record_text: '' - entry_version: 68 url: https://rest.uniprot.org/unisave/A2AXI2?format=txt&versions=68 entry_date: 27-NOV-2024, entry version 68. proteomes: [] reference_proteome_keyword: false record_text: '' archived_sources: - path: genes/STAWA/cfr/cfr-record-evidence.yaml url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/STAWA/cfr/cfr-record-evidence.yaml sha256: 52d93afba3022d897ff281b6ba9ff9226b06e82ae159c695edf4ad3b2e1fbedd excerpts: - start_line: 31 end_line: 35 text: |2 searched_reference_proteomes: - UP000814367 primary_in_any_reference_proteome: false sampled_history_versions: - 43 - start_line: 381 end_line: 385 text: |2 geneLocations: - value: pSCFS6 geneEncodingType: Plasmid keywords: - id: KW-0004 - start_line: 818 end_line: 823 text: | - entry_version: 43 url: https://rest.uniprot.org/unisave/A2AXI2?format=txt&versions=43 entry_date: 11-NOV-2015, entry version 43. proteomes: [] reference_proteome_keyword: false record_text: | - start_line: 929 end_line: 934 text: | - entry_version: 58 url: https://rest.uniprot.org/unisave/A2AXI2?format=txt&versions=58 entry_date: 02-DEC-2020, entry version 58. proteomes: [] reference_proteome_keyword: false record_text: | - start_line: 1061 end_line: 1066 text: | - entry_version: 68 url: https://rest.uniprot.org/unisave/A2AXI2?format=txt&versions=68 entry_date: 27-NOV-2024, entry version 68. proteomes: [] reference_proteome_keyword: false record_text: | - path: genes/STAWA/cfr/cfr-bioinformatics/reference-counterparts/comparison.yaml url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/STAWA/cfr/cfr-bioinformatics/reference-counterparts/comparison.yaml sha256: b47fece670b83381163697f4c6cdcb81a319d6d8e77266d8ebd369dc7432c675 excerpts: - start_line: 25 end_line: 29 text: |2 - -v - '1' target_sequence_count: 2456 query_sha256: f67f68f499e70573a72677f5b4a525ad78fbfa4003ca9114ead0580632640efa targets_sha256: d03ae441139ca48fa353b554aa62346c4863126c30b8cc1ed167cc72b5d9ff38 - start_line: 44 end_line: 48 text: |2 sha256: d03ae441139ca48fa353b554aa62346c4863126c30b8cc1ed167cc72b5d9ff38 detailed_alignment_limit: 10 candidate_count: 1 candidates: - accession: A0A2T4Q1F7 comparison: provenance: query_accession: A2AXI2 run_at: '2026-10-18T23:33:00.865631+00:00' biopython_version: '1.85' mmseqs_version: 18-8cc5c command: - mmseqs - easy-search - genes/STAWA/cfr/cfr-bioinformatics/reference-counterparts/query.fasta - .cache/orphan-curated/UP000814367.fasta - genes/STAWA/cfr/cfr-bioinformatics/reference-counterparts/search.tsv - genes/STAWA/cfr/cfr-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: 2456 query_sha256: f67f68f499e70573a72677f5b4a525ad78fbfa4003ca9114ead0580632640efa targets_sha256: d03ae441139ca48fa353b554aa62346c4863126c30b8cc1ed167cc72b5d9ff38 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%3AUP000814367&format=fasta retrieved_at: '2026-10-18T23:32:36.591485+00:00' uniprot_release: '2026_03' sequence_count: 2456 sha256: d03ae441139ca48fa353b554aa62346c4863126c30b8cc1ed167cc72b5d9ff38 detailed_alignment_limit: 10 candidate_count: 1 retained_alignment_count: 1 candidates: - accession: A0A2T4Q1F7 description: tr|A0A2T4Q1F7|A0A2T4Q1F7_STAWA Probable dual-specificity RNA methyltransferase RlmN OS=Staphylococcus warneri OX=1292 GN=rlmN PE=3 SV=1 evalue: 3.518e-57 bit_score: 200.0 global_score: 500.0 query_length: 349 target_length: 364 alignment_columns: 374 identities: 126 mismatches: 213 gap_columns: 35 identity_percent: 33.6898 query_coverage_percent: 97.1347 target_coverage_percent: 93.1319