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/Q04720.json retrieved_at: '2026-10-18T23:39:31.065832+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/proteomes/UP000000427.json retrieved_at: '2026-10-18T23:39:31.226018+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/proteomes/UP000000594.json retrieved_at: '2026-10-18T23:39:32.102634+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/unisave/Q04720?format=txt&versions=65 retrieved_at: '2026-10-18T23:39:37.940404+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/unisave/Q04720?format=txt&versions=75 retrieved_at: '2026-10-18T23:39:40.229489+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/unisave/Q04720?format=txt&versions=84 retrieved_at: '2026-10-18T23:39:41.824910+00:00' uniprot_release: '2026_03' observations: primary_accession: Q04720 alternative_accession: null sequence_identical: null primary_sequence_length: 287 alternative_sequence_length: null shared_uniparc_id: null same_taxon: null reference_proteome: UP000000427 proteome_is_reference: true proteome_taxon_matches: true primary_in_reference_proteome: false alternative_in_reference_proteome: null searched_reference_proteomes: - UP000000427 - UP000000594 primary_in_any_reference_proteome: false sampled_history_versions: - 65 - 75 - 84 sampled_versions_with_proteome_links: [] current_records: - primaryAccession: Q04720 entryType: UniProtKB reviewed (Swiss-Prot) entryAudit: firstPublicDate: '1995-02-01' lastAnnotationUpdateDate: '2026-09-02' lastSequenceUpdateDate: '1995-02-01' entryVersion: 87 sequenceVersion: 1 genes: - geneName: value: ermJ organism: scientificName: Bacillus anthracis taxonId: 1392 sequence: length: 287 sha256: c7c9f1743cbaed70f3494c26e5aeb5059db7f5cf03af1f7bc8fa621e9013a132 uniProtKBCrossReferences: [] reference_proteomes: - id: UP000000427 proteomeType: Reference proteome taxonomy: scientificName: Bacillus anthracis commonName: anthrax bacterium taxonId: 1392 mnemonic: BACAN - id: UP000000594 proteomeType: Reference proteome taxonomy: scientificName: Bacillus anthracis commonName: anthrax bacterium taxonId: 1392 mnemonic: BACAN unisave_records: - entry_version: 65 url: https://rest.uniprot.org/unisave/Q04720?format=txt&versions=65 entry_date: 07-JAN-2015, entry version 65. proteomes: [] reference_proteome_keyword: false record_text: '' - entry_version: 75 url: https://rest.uniprot.org/unisave/Q04720?format=txt&versions=75 entry_date: 11-DEC-2019, entry version 75. proteomes: [] reference_proteome_keyword: false record_text: '' - entry_version: 84 url: https://rest.uniprot.org/unisave/Q04720?format=txt&versions=84 entry_date: 02-OCT-2024, entry version 84. proteomes: [] reference_proteome_keyword: false record_text: '' archived_sources: - path: genes/BACAN/ermJ/ermJ-record-evidence.yaml url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/BACAN/ermJ/ermJ-record-evidence.yaml sha256: 21022072fedc728f2dc54dc78d9d511f6fa569333c74af082d7d60c4095f62b3 excerpts: - start_line: 35 end_line: 39 text: |2 - UP000000427 - UP000000594 primary_in_any_reference_proteome: false sampled_history_versions: - 65 - start_line: 777 end_line: 782 text: | - entry_version: 65 url: https://rest.uniprot.org/unisave/Q04720?format=txt&versions=65 entry_date: 07-JAN-2015, entry version 65. proteomes: [] reference_proteome_keyword: false record_text: | - start_line: 860 end_line: 865 text: | - entry_version: 75 url: https://rest.uniprot.org/unisave/Q04720?format=txt&versions=75 entry_date: 11-DEC-2019, entry version 75. proteomes: [] reference_proteome_keyword: false record_text: | - start_line: 947 end_line: 952 text: | - entry_version: 84 url: https://rest.uniprot.org/unisave/Q04720?format=txt&versions=84 entry_date: 02-OCT-2024, entry version 84. proteomes: [] reference_proteome_keyword: false record_text: | - path: genes/BACAN/ermJ/ermJ-bioinformatics/reference-counterparts/comparison.yaml url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/BACAN/ermJ/ermJ-bioinformatics/reference-counterparts/comparison.yaml sha256: 7f84e75c77b98c84a7cb82137165a3a29b4c982623f6d7dadb4199ee8dec2ef5 excerpts: - start_line: 25 end_line: 29 text: |2 - -v - '1' target_sequence_count: 10161 query_sha256: f9ddfeaf401eaaa269282904979d26b0d8b4e171d6440388d4100004eed34ee7 targets_sha256: 21362af1760620e4b73e9445b5e48cae2a48db7a06df6d9cc7c8a997c7ae8528 - start_line: 55 end_line: 59 text: |2 - UP000000594 detailed_alignment_limit: 10 candidate_count: 1 candidates: - accession: Q81W00 comparison: provenance: query_accession: Q04720 run_at: '2026-10-18T23:34:59.296276+00:00' biopython_version: '1.85' mmseqs_version: 18-8cc5c command: - mmseqs - easy-search - genes/BACAN/ermJ/ermJ-bioinformatics/reference-counterparts/query.fasta - .cache/orphan-curated/UP000000427__UP000000594.fasta - genes/BACAN/ermJ/ermJ-bioinformatics/reference-counterparts/search.tsv - genes/BACAN/ermJ/ermJ-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: 10161 query_sha256: f9ddfeaf401eaaa269282904979d26b0d8b4e171d6440388d4100004eed34ee7 targets_sha256: 21362af1760620e4b73e9445b5e48cae2a48db7a06df6d9cc7c8a997c7ae8528 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: sources: - url: https://rest.uniprot.org/uniprotkb/stream?query=proteome%3AUP000000427&format=fasta retrieved_at: '2026-10-18T23:32:09.308747+00:00' uniprot_release: '2026_03' sequence_count: 5334 sha256: bddf5f49c8bf53d663c98f077b1c0336da1dfbdf545bca7f50e65ad16a2b6b84 - url: https://rest.uniprot.org/uniprotkb/stream?query=proteome%3AUP000000594&format=fasta retrieved_at: '2026-10-18T23:32:11.198470+00:00' uniprot_release: '2026_03' sequence_count: 5493 sha256: 4e8a3bbd223c31dd1cf08e7d4b50e4b8291b4ee94c34a1ec4246ecfc2fe73006 sequence_count: 10161 sha256: 21362af1760620e4b73e9445b5e48cae2a48db7a06df6d9cc7c8a997c7ae8528 proteomes: - UP000000427 - UP000000594 detailed_alignment_limit: 10 candidate_count: 1 retained_alignment_count: 1 candidates: - accession: Q81W00 description: sp|Q81W00|RSMA_BACAN Ribosomal RNA small subunit methyltransferase A OS=Bacillus anthracis OX=1392 GN=rsmA PE=3 SV=1 evalue: 7.003e-23 bit_score: 98.0 global_score: 229.0 query_length: 287 target_length: 292 alignment_columns: 315 identities: 86 mismatches: 178 gap_columns: 51 identity_percent: 27.3016 query_coverage_percent: 91.9861 target_coverage_percent: 90.411