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/P34105.json retrieved_at: '2026-10-18T23:26:04.273138+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/uniprotkb/B9ILT5.json retrieved_at: '2026-10-18T23:26:05.066411+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/proteomes/UP000006729.json retrieved_at: '2026-10-18T23:26:06.021762+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/unisave/P34105?format=txt&versions=101 retrieved_at: '2026-10-18T23:26:09.321767+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/unisave/P34105?format=txt&versions=118 retrieved_at: '2026-10-18T23:26:13.418527+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/unisave/P34105?format=txt&versions=132 retrieved_at: '2026-10-18T23:26:15.641512+00:00' uniprot_release: '2026_03' - url: https://www.ebi.ac.uk/ena/browser/api/embl/X56233 retrieved_at: '2026-10-18T23:26:16.279386+00:00' uniprot_release: null observations: primary_accession: P34105 alternative_accession: B9ILT5 sequence_identical: false primary_sequence_length: 591 alternative_sequence_length: 591 shared_uniparc_id: null same_taxon: true reference_proteome: UP000006729 proteome_is_reference: true proteome_taxon_matches: true primary_in_reference_proteome: false alternative_in_reference_proteome: true sampled_history_versions: - 101 - 118 - 132 sampled_versions_with_proteome_links: [] current_records: - primaryAccession: P34105 entryType: UniProtKB reviewed (Swiss-Prot) entryAudit: firstPublicDate: '1994-02-01' lastAnnotationUpdateDate: '2026-09-02' lastSequenceUpdateDate: '1996-02-01' entryVersion: 138 sequenceVersion: 3 organism: scientificName: Populus trichocarpa taxonId: 3694 sequence: length: 591 sha256: 4faad7a9dd5269f1c9fa5a6397768be44e5e313cc304ef02274e4ab9a8f1693e uniProtKBCrossReferences: [] - primaryAccession: B9ILT5 entryType: UniProtKB unreviewed (TrEMBL) entryAudit: firstPublicDate: '2009-03-24' lastAnnotationUpdateDate: '2026-09-02' lastSequenceUpdateDate: '2009-03-24' entryVersion: 103 sequenceVersion: 1 genes: - orfNames: - evidences: - evidenceCode: ECO:0000313 source: EMBL id: PNS93422.1 value: POPTR_018G086700 organism: scientificName: Populus trichocarpa taxonId: 3694 sequence: length: 591 sha256: a699ab5074b7ce106f2242a8d330a827403298637d48e903568fb276586076dc uniProtKBCrossReferences: - database: Gramene id: Potri.018G086700.1.v4.1 properties: - key: ProteinId value: Potri.018G086700.1.v4.1 - key: GeneId value: Potri.018G086700.v4.1 - database: Proteomes id: UP000006729 properties: - key: Component value: Chromosome 18 reference_proteomes: - id: UP000006729 proteomeType: Reference proteome taxonomy: scientificName: Populus trichocarpa commonName: Western balsam poplar synonyms: - Populus balsamifera subsp. trichocarpa taxonId: 3694 mnemonic: POPTR unisave_records: - entry_version: 101 url: https://rest.uniprot.org/unisave/P34105?format=txt&versions=101 entry_date: 09-DEC-2015, entry version 101. proteomes: [] reference_proteome_keyword: false record_text: '' - entry_version: 118 url: https://rest.uniprot.org/unisave/P34105?format=txt&versions=118 entry_date: 12-AUG-2020, entry version 118. proteomes: [] reference_proteome_keyword: false record_text: '' - entry_version: 132 url: https://rest.uniprot.org/unisave/P34105?format=txt&versions=132 entry_date: 27-NOV-2024, entry version 132. proteomes: [] reference_proteome_keyword: false record_text: '' archived_sources: - path: genes/POPTR/MAOX/MAOX-record-evidence.yaml url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/POPTR/MAOX/MAOX-record-evidence.yaml sha256: a24d8038726e0d497d4d51acd184dfa355dd26d912bdd48df556c3819b3f00ec excerpts: - start_line: 30 end_line: 43 text: |2 shared_uniparc_id: null same_taxon: true reference_proteome: UP000006729 proteome_is_reference: true proteome_taxon_matches: true primary_in_reference_proteome: false alternative_in_reference_proteome: true sampled_history_versions: - 101 - 118 - 132 sampled_versions_with_proteome_links: [] current_records: - entryType: UniProtKB reviewed (Swiss-Prot) - path: genes/POPTR/MAOX/MAOX-bioinformatics/reference-counterparts/comparison.yaml url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/POPTR/MAOX/MAOX-bioinformatics/reference-counterparts/comparison.yaml sha256: 8b0edaa5ff48e5a7ef9987287faa960a03c33ac030d4eb6790f313e8195d06c8 excerpts: - start_line: 49 end_line: 61 text: |2 bit_score: 1176.0 global_score: 2997.0 query_length: 591 target_length: 591 alignment_columns: 591 identities: 584 mismatches: 7 gap_columns: 0 identity_percent: 98.8156 query_coverage_percent: 100.0 target_coverage_percent: 100.0 substitutions: - query_position: 53 - path: genes/POPTR/MAOX/MAOX-origin-evidence.yaml url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/POPTR/MAOX/MAOX-origin-evidence.yaml sha256: e691ef0699bf9bc8b144143ef697a685b5dfcf5eeffd55c39119569eac49e807 excerpts: - start_line: 8 end_line: 10 text: | extraction_method: Downloaded institutional copy of primary article; extracted with pdftotext -layout and checked Table I. supporting_text: 'Organism: Populus deltoides x Populus trichocarpa, clone 064' comparison: provenance: query_accession: P34105 run_at: '2026-10-18T23:25:36.440522+00:00' biopython_version: '1.85' mmseqs_version: 18-8cc5c command: - mmseqs - easy-search - genes/POPTR/MAOX/MAOX-bioinformatics/reference-counterparts/query.fasta - .cache/orphan-curated/UP000006729.fasta - genes/POPTR/MAOX/MAOX-bioinformatics/reference-counterparts/search.tsv - genes/POPTR/MAOX/MAOX-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: 77340 query_sha256: 1cc0964e87998cd6f494b834b819ff8d7797593b29f471cdf71e1d3bc0797d74 targets_sha256: 988d46285688cd97f593b97011935be87d007e7844c778e1d5c30ba9839dc4c0 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%3AUP000006729&format=fasta retrieved_at: '2026-10-18T23:23:27.698811+00:00' uniprot_release: '2026_03' sequence_count: 77340 candidate_count: 19 retained_alignment_count: 19 candidates: - accession: B9ILT5 description: tr|B9ILT5|B9ILT5_POPTR Malic enzyme OS=Populus trichocarpa OX=3694 GN=POPTR_018G086700 PE=3 SV=1 evalue: 0.0 bit_score: 1176.0 global_score: 2997.0 query_length: 591 target_length: 591 alignment_columns: 591 identities: 584 mismatches: 7 gap_columns: 0 identity_percent: 98.8156 query_coverage_percent: 100.0 target_coverage_percent: 100.0 - accession: B9GGM4 description: tr|B9GGM4|B9GGM4_POPTR Malic enzyme OS=Populus trichocarpa OX=3694 GN=POPTR_001G189700 PE=3 SV=2 evalue: 0.0 bit_score: 1004.0 global_score: 2533.5 query_length: 591 target_length: 649 alignment_columns: 649 identities: 487 mismatches: 104 gap_columns: 58 identity_percent: 75.0385 query_coverage_percent: 100.0 target_coverage_percent: 91.0632