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/P09130.json retrieved_at: '2026-10-18T23:39:07.144780+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/proteomes/UP000000625.json retrieved_at: '2026-10-18T23:39:07.303665+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/unisave/P09130?format=txt&versions=110 retrieved_at: '2026-10-18T23:39:09.046800+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/unisave/P09130?format=txt&versions=128 retrieved_at: '2026-10-18T23:39:11.252226+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/unisave/P09130?format=txt&versions=141 retrieved_at: '2026-10-18T23:39:11.644103+00:00' uniprot_release: '2026_03' observations: primary_accession: P09130 alternative_accession: null sequence_identical: null primary_sequence_length: 717 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: - 110 - 128 - 141 sampled_versions_with_proteome_links: [] current_records: - primaryAccession: P09130 entryType: UniProtKB reviewed (Swiss-Prot) entryAudit: firstPublicDate: '1989-07-01' lastAnnotationUpdateDate: '2026-09-02' lastSequenceUpdateDate: '2005-05-10' entryVersion: 146 sequenceVersion: 4 genes: - geneName: value: traD orderedLocusNames: - value: ECOK12F102 geneLocations: - value: F geneEncodingType: Plasmid - value: p1658/97 geneEncodingType: Plasmid organism: scientificName: Escherichia coli (strain K12) taxonId: 83333 sequence: length: 717 sha256: 9e1d814623bcc5f60ee3bd7fceaab807321b68b792043f5eac3d0280c5824c7d uniProtKBCrossReferences: [] reference_proteomes: - id: UP000000625 proteomeType: Reference proteome taxonomy: scientificName: Escherichia coli (strain K12) taxonId: 83333 mnemonic: ECOLI unisave_records: - entry_version: 110 url: https://rest.uniprot.org/unisave/P09130?format=txt&versions=110 entry_date: 11-NOV-2015, entry version 110. proteomes: [] reference_proteome_keyword: false record_text: '' - entry_version: 128 url: https://rest.uniprot.org/unisave/P09130?format=txt&versions=128 entry_date: 02-DEC-2020, entry version 128. proteomes: [] reference_proteome_keyword: false record_text: '' - entry_version: 141 url: https://rest.uniprot.org/unisave/P09130?format=txt&versions=141 entry_date: 27-NOV-2024, entry version 141. proteomes: [] reference_proteome_keyword: false record_text: '' archived_sources: - path: genes/ECOLI/traD/traD-record-evidence.yaml url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/ECOLI/traD/traD-record-evidence.yaml sha256: e83fa4c39d5a70ffcd9cc473f63512909c8bdf6565948a15499fab38147737e4 excerpts: - start_line: 31 end_line: 35 text: |2 searched_reference_proteomes: - UP000000625 primary_in_any_reference_proteome: false sampled_history_versions: - 110 - start_line: 427 end_line: 433 text: |2 geneLocations: - value: F geneEncodingType: Plasmid - value: p1658/97 geneEncodingType: Plasmid keywords: - id: KW-0002 - start_line: 1238 end_line: 1243 text: | - entry_version: 110 url: https://rest.uniprot.org/unisave/P09130?format=txt&versions=110 entry_date: 11-NOV-2015, entry version 110. proteomes: [] reference_proteome_keyword: false record_text: | - start_line: 1514 end_line: 1519 text: | - entry_version: 128 url: https://rest.uniprot.org/unisave/P09130?format=txt&versions=128 entry_date: 02-DEC-2020, entry version 128. proteomes: [] reference_proteome_keyword: false record_text: | - start_line: 1795 end_line: 1800 text: | - entry_version: 141 url: https://rest.uniprot.org/unisave/P09130?format=txt&versions=141 entry_date: 27-NOV-2024, entry version 141. proteomes: [] reference_proteome_keyword: false record_text: | - path: genes/ECOLI/traD/traD-bioinformatics/reference-counterparts/comparison.yaml url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/ECOLI/traD/traD-bioinformatics/reference-counterparts/comparison.yaml sha256: 50b6f189f3a9b28c5fcd286732a7b094a10bf3889d4b6c9b8b27719ba5b06384 excerpts: - start_line: 25 end_line: 29 text: |2 - -v - '1' target_sequence_count: 4403 query_sha256: ea17c135f38913e06f1e77814990ab6f7efd200a4c0f4c8a7c9d7b77259ce46f 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: P09130 run_at: '2026-10-18T23:34:30.680073+00:00' biopython_version: '1.85' mmseqs_version: 18-8cc5c command: - mmseqs - easy-search - genes/ECOLI/traD/traD-bioinformatics/reference-counterparts/query.fasta - .cache/orphan-curated/UP000000625.fasta - genes/ECOLI/traD/traD-bioinformatics/reference-counterparts/search.tsv - genes/ECOLI/traD/traD-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: ea17c135f38913e06f1e77814990ab6f7efd200a4c0f4c8a7c9d7b77259ce46f 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: []