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/P16579.json retrieved_at: '2026-10-18T23:26:04.329968+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/uniprotkb/B9HQY4.json retrieved_at: '2026-10-18T23:26:05.102429+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/proteomes/UP000006729.json retrieved_at: '2026-10-18T23:26:06.016504+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/unisave/P16579?format=txt&versions=109 retrieved_at: '2026-10-18T23:26:07.147667+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/unisave/P16579?format=txt&versions=128 retrieved_at: '2026-10-18T23:26:08.237844+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/unisave/P16579?format=txt&versions=138 retrieved_at: '2026-10-18T23:26:10.729853+00:00' uniprot_release: '2026_03' - url: https://www.ebi.ac.uk/ena/browser/api/embl/U01661 retrieved_at: '2026-10-18T23:26:11.363281+00:00' uniprot_release: null observations: primary_accession: P16579 alternative_accession: B9HQY4 sequence_identical: false primary_sequence_length: 340 alternative_sequence_length: 333 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: - 109 - 128 - 138 sampled_versions_with_proteome_links: [] current_records: - primaryAccession: P16579 entryType: UniProtKB reviewed (Swiss-Prot) entryAudit: firstPublicDate: '1990-08-01' lastAnnotationUpdateDate: '2026-09-02' lastSequenceUpdateDate: '1996-10-01' entryVersion: 143 sequenceVersion: 2 genes: - geneName: value: WIN6 organism: scientificName: Populus trichocarpa taxonId: 3694 sequence: length: 340 sha256: 31f84c50a1f7c7130bc67bb7a1d806869eb4da0eaa786345dc0c78536b39dab6 uniProtKBCrossReferences: [] - primaryAccession: B9HQY4 entryType: UniProtKB unreviewed (TrEMBL) entryAudit: firstPublicDate: '2009-03-24' lastAnnotationUpdateDate: '2026-09-02' lastSequenceUpdateDate: '2026-01-28' entryVersion: 65 sequenceVersion: 3 genes: - orfNames: - evidences: - evidenceCode: ECO:0000313 source: EMBL id: PNT21336.2 value: POPTR_009G141800v4 organism: scientificName: Populus trichocarpa taxonId: 3694 sequence: length: 333 sha256: 25419cccfe23ae90869e8d1bf2b6ff6548e9a93d479ec9adb5f44757358964ca uniProtKBCrossReferences: - database: Proteomes id: UP000006729 properties: - key: Component value: Chromosome 9 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: 109 url: https://rest.uniprot.org/unisave/P16579?format=txt&versions=109 entry_date: 11-NOV-2015, entry version 109. proteomes: [] reference_proteome_keyword: false record_text: '' - entry_version: 128 url: https://rest.uniprot.org/unisave/P16579?format=txt&versions=128 entry_date: 07-OCT-2020, entry version 128. proteomes: [] reference_proteome_keyword: false record_text: '' - entry_version: 138 url: https://rest.uniprot.org/unisave/P16579?format=txt&versions=138 entry_date: 27-NOV-2024, entry version 138. proteomes: [] reference_proteome_keyword: false record_text: '' archived_sources: - path: genes/POPTR/WIN6/WIN6-record-evidence.yaml url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/POPTR/WIN6/WIN6-record-evidence.yaml sha256: 6faca8b3764100871ff2cf2eead0ffc5a137bb36bd775634a59865f076885086 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: - 109 - 128 - 138 sampled_versions_with_proteome_links: [] current_records: - entryType: UniProtKB reviewed (Swiss-Prot) - start_line: 2254 end_line: 2259 text: |2 FH FT source 1..1635 FT /organism="Populus trichocarpa x Populus deltoides" FT /strain="H11-11" FT /mol_type="genomic DNA" FT /dev_stage="juvenile" - path: genes/POPTR/WIN6/WIN6-bioinformatics/reference-counterparts/comparison.yaml url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/POPTR/WIN6/WIN6-bioinformatics/reference-counterparts/comparison.yaml sha256: 1c47fe1442d92b26966ad0409b8ae9b5d557fbec77046ddc6b30e9e063408436 excerpts: - start_line: 49 end_line: 61 text: |2 bit_score: 689.0 global_score: 1788.0 query_length: 340 target_length: 333 alignment_columns: 340 identities: 317 mismatches: 16 gap_columns: 7 identity_percent: 93.2353 query_coverage_percent: 97.9412 target_coverage_percent: 100.0 substitutions: - query_position: 6 comparison: provenance: query_accession: P16579 run_at: '2026-10-18T23:25:27.648247+00:00' biopython_version: '1.85' mmseqs_version: 18-8cc5c command: - mmseqs - easy-search - genes/POPTR/WIN6/WIN6-bioinformatics/reference-counterparts/query.fasta - .cache/orphan-curated/UP000006729.fasta - genes/POPTR/WIN6/WIN6-bioinformatics/reference-counterparts/search.tsv - genes/POPTR/WIN6/WIN6-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: 94dd6fe48241c4a509656fc85f201d0955c845a7212926b982574ca1c53a1a08 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: 33 retained_alignment_count: 33 candidates: - accession: B9HQY4 description: tr|B9HQY4|B9HQY4_POPTR chitinase OS=Populus trichocarpa OX=3694 GN=POPTR_009G141800v4 PE=3 SV=3 evalue: 1.397e-224 bit_score: 689.0 global_score: 1788.0 query_length: 340 target_length: 333 alignment_columns: 340 identities: 317 mismatches: 16 gap_columns: 7 identity_percent: 93.2353 query_coverage_percent: 97.9412 target_coverage_percent: 100.0 - accession: B9HQZ1 description: tr|B9HQZ1|B9HQZ1_POPTR chitinase OS=Populus trichocarpa OX=3694 GN=POPTR_009G141800 PE=3 SV=1 evalue: 2.827e-215 bit_score: 662.0 global_score: 1711.5 query_length: 340 target_length: 334 alignment_columns: 342 identities: 306 mismatches: 26 gap_columns: 10 identity_percent: 89.4737 query_coverage_percent: 97.6471 target_coverage_percent: 99.4012