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/P41067.json retrieved_at: '2026-10-18T23:39:23.405052+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/proteomes/UP000000625.json retrieved_at: '2026-10-18T23:39:23.555071+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/unisave/P41067?format=txt&versions=71 retrieved_at: '2026-10-18T23:39:24.321957+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/unisave/P41067?format=txt&versions=85 retrieved_at: '2026-10-18T23:39:27.816670+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/unisave/P41067?format=txt&versions=97 retrieved_at: '2026-10-18T23:39:30.227189+00:00' uniprot_release: '2026_03' observations: primary_accession: P41067 alternative_accession: null sequence_identical: null primary_sequence_length: 475 alternative_sequence_length: null shared_uniparc_id: null same_taxon: null reference_proteome: UP000000625 proteome_is_reference: true proteome_taxon_matches: true primary_in_reference_proteome: false alternative_in_reference_proteome: null searched_reference_proteomes: - UP000000625 primary_in_any_reference_proteome: false sampled_history_versions: - 71 - 85 - 97 sampled_versions_with_proteome_links: [] current_records: - primaryAccession: P41067 entryType: UniProtKB reviewed (Swiss-Prot) entryAudit: firstPublicDate: '1995-02-01' lastAnnotationUpdateDate: '2026-01-28' lastSequenceUpdateDate: '1995-02-01' entryVersion: 101 sequenceVersion: 1 genes: - geneName: value: traB orderedLocusNames: - value: ECOK12F078 geneLocations: - value: F geneEncodingType: Plasmid - value: IncFII ColB2 geneEncodingType: Plasmid organism: scientificName: Escherichia coli (strain K12) taxonId: 83333 sequence: length: 475 sha256: 1ac6a5af992ff639147b3c84539258c9b96a1efaf42324eb308c4de4d9dd4e40 uniProtKBCrossReferences: [] reference_proteomes: - id: UP000000625 proteomeType: Reference proteome taxonomy: scientificName: Escherichia coli (strain K12) taxonId: 83333 mnemonic: ECOLI unisave_records: - entry_version: 71 url: https://rest.uniprot.org/unisave/P41067?format=txt&versions=71 entry_date: 16-SEP-2015, entry version 71. proteomes: [] reference_proteome_keyword: false record_text: '' - entry_version: 85 url: https://rest.uniprot.org/unisave/P41067?format=txt&versions=85 entry_date: 12-AUG-2020, entry version 85. proteomes: [] reference_proteome_keyword: false record_text: '' - entry_version: 97 url: https://rest.uniprot.org/unisave/P41067?format=txt&versions=97 entry_date: 27-NOV-2024, entry version 97. proteomes: [] reference_proteome_keyword: false record_text: '' archived_sources: - path: genes/ECOLI/traB/traB-record-evidence.yaml url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/ECOLI/traB/traB-record-evidence.yaml sha256: 5a359f38720bbabfffe135673ef7d7670fa5208febfff51322e56b50ec54bf2f excerpts: - start_line: 31 end_line: 35 text: |2 searched_reference_proteomes: - UP000000625 primary_in_any_reference_proteome: false sampled_history_versions: - 71 - start_line: 156 end_line: 162 text: |2 geneLocations: - value: F geneEncodingType: Plasmid - value: IncFII ColB2 geneEncodingType: Plasmid keywords: - id: KW-0184 - start_line: 498 end_line: 503 text: | - entry_version: 71 url: https://rest.uniprot.org/unisave/P41067?format=txt&versions=71 entry_date: 16-SEP-2015, entry version 71. proteomes: [] reference_proteome_keyword: false record_text: | - start_line: 604 end_line: 609 text: | - entry_version: 85 url: https://rest.uniprot.org/unisave/P41067?format=txt&versions=85 entry_date: 12-AUG-2020, entry version 85. proteomes: [] reference_proteome_keyword: false record_text: | - start_line: 698 end_line: 703 text: | - entry_version: 97 url: https://rest.uniprot.org/unisave/P41067?format=txt&versions=97 entry_date: 27-NOV-2024, entry version 97. proteomes: [] reference_proteome_keyword: false record_text: | - path: genes/ECOLI/traB/traB-bioinformatics/reference-counterparts/comparison.yaml url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/ECOLI/traB/traB-bioinformatics/reference-counterparts/comparison.yaml sha256: e65eec8765c612fc1d41303e830afbef743aaacedef8b370ca1fd8747c14a269 excerpts: - start_line: 25 end_line: 29 text: |2 - -v - '1' target_sequence_count: 4403 query_sha256: a5dba90b3f21e4c610cee95c180e9d128f61db573fb357267718dd050bcdc26b targets_sha256: a8052a607a98d2444c9d5dd685bd1370150df8c5570c3116811544bbf3d093a2 - start_line: 44 end_line: 47 text: |2 sha256: a8052a607a98d2444c9d5dd685bd1370150df8c5570c3116811544bbf3d093a2 detailed_alignment_limit: 10 candidate_count: 0 candidates: [] comparison: provenance: query_accession: P41067 run_at: '2026-10-18T23:34:45.953377+00:00' biopython_version: '1.85' mmseqs_version: 18-8cc5c command: - mmseqs - easy-search - genes/ECOLI/traB/traB-bioinformatics/reference-counterparts/query.fasta - .cache/orphan-curated/UP000000625.fasta - genes/ECOLI/traB/traB-bioinformatics/reference-counterparts/search.tsv - genes/ECOLI/traB/traB-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: 4403 query_sha256: a5dba90b3f21e4c610cee95c180e9d128f61db573fb357267718dd050bcdc26b targets_sha256: a8052a607a98d2444c9d5dd685bd1370150df8c5570c3116811544bbf3d093a2 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%3AUP000000625&format=fasta retrieved_at: '2026-10-18T23:32:09.369626+00:00' uniprot_release: '2026_03' sequence_count: 4403 sha256: a8052a607a98d2444c9d5dd685bd1370150df8c5570c3116811544bbf3d093a2 detailed_alignment_limit: 10 candidate_count: 0 retained_alignment_count: 0 candidates: []