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/Q07341.json retrieved_at: '2026-10-18T23:39:33.956762+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/uniprotkb/A0A1D7XAJ1.json retrieved_at: '2026-10-18T23:39:34.124132+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/proteomes/UP000322283.json retrieved_at: '2026-10-18T23:39:34.285939+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/unisave/Q07341?format=txt&versions=76 retrieved_at: '2026-10-18T23:39:34.643088+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/unisave/Q07341?format=txt&versions=92 retrieved_at: '2026-10-18T23:39:37.036811+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/unisave/Q07341?format=txt&versions=105 retrieved_at: '2026-10-18T23:39:39.445736+00:00' uniprot_release: '2026_03' observations: primary_accession: Q07341 alternative_accession: A0A1D7XAJ1 sequence_identical: true primary_sequence_length: 323 alternative_sequence_length: 323 shared_uniparc_id: UPI000016EBA3 same_taxon: true reference_proteome: UP000322283 proteome_is_reference: true proteome_taxon_matches: true primary_in_reference_proteome: false alternative_in_reference_proteome: true searched_reference_proteomes: - UP000322283 primary_in_any_reference_proteome: false sampled_history_versions: - 76 - 92 - 105 sampled_versions_with_proteome_links: [] current_records: - primaryAccession: Q07341 entryType: UniProtKB reviewed (Swiss-Prot) entryAudit: firstPublicDate: '1995-02-01' lastAnnotationUpdateDate: '2026-09-02' lastSequenceUpdateDate: '2007-01-23' entryVersion: 111 sequenceVersion: 2 genes: - geneName: value: acsD organism: scientificName: Neomoorella thermoacetica taxonId: 1525 sequence: length: 323 sha256: e0c3efbeefaa05d2ff50e0405fa32ec5b62199b7a010de6de6700eb1090f2842 uniProtKBCrossReferences: [] - primaryAccession: A0A1D7XAJ1 entryType: UniProtKB unreviewed (TrEMBL) entryAudit: firstPublicDate: '2017-01-18' lastAnnotationUpdateDate: '2026-09-02' lastSequenceUpdateDate: '2017-01-18' entryVersion: 41 sequenceVersion: 1 genes: - geneName: evidences: - evidenceCode: ECO:0000313 source: EMBL id: TYL14326.1 value: acsD orfNames: - evidences: - evidenceCode: ECO:0000313 source: EMBL id: TYL14326.1 value: MTAT_05570 organism: scientificName: Neomoorella thermoacetica taxonId: 1525 sequence: length: 323 sha256: e0c3efbeefaa05d2ff50e0405fa32ec5b62199b7a010de6de6700eb1090f2842 uniProtKBCrossReferences: - database: Proteomes id: UP000322283 properties: - key: Component value: Unassembled WGS sequence reference_proteomes: - id: UP000322283 proteomeType: Reference proteome taxonomy: scientificName: Neomoorella thermoacetica synonyms: - Clostridium thermoaceticum taxonId: 1525 mnemonic: NEOTH unisave_records: - entry_version: 76 url: https://rest.uniprot.org/unisave/Q07341?format=txt&versions=76 entry_date: 11-NOV-2015, entry version 76. proteomes: [] reference_proteome_keyword: false record_text: '' - entry_version: 92 url: https://rest.uniprot.org/unisave/Q07341?format=txt&versions=92 entry_date: 12-AUG-2020, entry version 92. proteomes: [] reference_proteome_keyword: false record_text: '' - entry_version: 105 url: https://rest.uniprot.org/unisave/Q07341?format=txt&versions=105 entry_date: 27-NOV-2024, entry version 105. proteomes: [] reference_proteome_keyword: false record_text: '' archived_sources: - path: genes/MOOTH/acsD/acsD-record-evidence.yaml url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/MOOTH/acsD/acsD-record-evidence.yaml sha256: a08b8e782710f30d8fdc10f00f0ce6eaa8aced920b50366e472f9ce4a929e587 excerpts: - start_line: 26 end_line: 38 text: |2 alternative_sequence_length: 323 shared_uniparc_id: UPI000016EBA3 same_taxon: true reference_proteome: UP000322283 proteome_is_reference: true proteome_taxon_matches: true primary_in_reference_proteome: false alternative_in_reference_proteome: true searched_reference_proteomes: - UP000322283 primary_in_any_reference_proteome: false sampled_history_versions: - 76 - start_line: 1315 end_line: 1320 text: | - entry_version: 76 url: https://rest.uniprot.org/unisave/Q07341?format=txt&versions=76 entry_date: 11-NOV-2015, entry version 76. proteomes: [] reference_proteome_keyword: false record_text: | - start_line: 1454 end_line: 1459 text: | - entry_version: 92 url: https://rest.uniprot.org/unisave/Q07341?format=txt&versions=92 entry_date: 12-AUG-2020, entry version 92. proteomes: [] reference_proteome_keyword: false record_text: | - start_line: 1635 end_line: 1640 text: | - entry_version: 105 url: https://rest.uniprot.org/unisave/Q07341?format=txt&versions=105 entry_date: 27-NOV-2024, entry version 105. proteomes: [] reference_proteome_keyword: false record_text: | - path: genes/MOOTH/acsD/acsD-bioinformatics/reference-counterparts/comparison.yaml url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/MOOTH/acsD/acsD-bioinformatics/reference-counterparts/comparison.yaml sha256: a5afeb65cf5cdebf6cfb3e600ccb3db4cb7555f5cc3d2f6ff490dd239f0a046a excerpts: - start_line: 25 end_line: 29 text: |2 - -v - '1' target_sequence_count: 2959 query_sha256: f412c17a54e1e45a60432edea2a7bbbf2e27f26248ee1cf7a1fc136262be7ec7 targets_sha256: 1a6357a5ce3e79cec2362f765f19923824fe54e468155cc6a9bc13b6d10a903a - start_line: 44 end_line: 48 text: |2 sha256: 1a6357a5ce3e79cec2362f765f19923824fe54e468155cc6a9bc13b6d10a903a detailed_alignment_limit: 10 candidate_count: 1 candidates: - accession: A0A1D7XAJ1 - start_line: 52 end_line: 63 text: |2 bit_score: 662.0 global_score: 1675.0 query_length: 323 target_length: 323 alignment_columns: 323 identities: 323 mismatches: 0 gap_columns: 0 identity_percent: 100.0 query_coverage_percent: 100.0 target_coverage_percent: 100.0 substitutions: [] comparison: provenance: query_accession: Q07341 run_at: '2026-10-18T23:35:00.731622+00:00' biopython_version: '1.85' mmseqs_version: 18-8cc5c command: - mmseqs - easy-search - genes/MOOTH/acsD/acsD-bioinformatics/reference-counterparts/query.fasta - .cache/orphan-curated/UP000322283.fasta - genes/MOOTH/acsD/acsD-bioinformatics/reference-counterparts/search.tsv - genes/MOOTH/acsD/acsD-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: 2959 query_sha256: f412c17a54e1e45a60432edea2a7bbbf2e27f26248ee1cf7a1fc136262be7ec7 targets_sha256: 1a6357a5ce3e79cec2362f765f19923824fe54e468155cc6a9bc13b6d10a903a 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%3AUP000322283&format=fasta retrieved_at: '2026-10-18T23:32:32.166208+00:00' uniprot_release: '2026_03' sequence_count: 2959 sha256: 1a6357a5ce3e79cec2362f765f19923824fe54e468155cc6a9bc13b6d10a903a detailed_alignment_limit: 10 candidate_count: 1 retained_alignment_count: 1 candidates: - accession: A0A1D7XAJ1 description: tr|A0A1D7XAJ1|A0A1D7XAJ1_NEOTH Corrinoid/iron-sulfur protein small subunit OS=Neomoorella thermoacetica OX=1525 GN=acsD PE=4 SV=1 evalue: 3.159e-217 bit_score: 662.0 global_score: 1675.0 query_length: 323 target_length: 323 alignment_columns: 323 identities: 323 mismatches: 0 gap_columns: 0 identity_percent: 100.0 query_coverage_percent: 100.0 target_coverage_percent: 100.0