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/P08176.json retrieved_at: '2026-10-18T23:39:05.265351+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/uniprotkb/A0ABQ8JGY3.json retrieved_at: '2026-10-18T23:39:06.137412+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/proteomes/UP000887458.json retrieved_at: '2026-10-18T23:39:06.282401+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/unisave/P08176?format=txt&versions=114 retrieved_at: '2026-10-18T23:39:08.742662+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/unisave/P08176?format=txt&versions=131 retrieved_at: '2026-10-18T23:39:14.726667+00:00' uniprot_release: '2026_03' - url: https://rest.uniprot.org/unisave/P08176?format=txt&versions=142 retrieved_at: '2026-10-18T23:39:16.930110+00:00' uniprot_release: '2026_03' observations: primary_accession: P08176 alternative_accession: A0ABQ8JGY3 sequence_identical: false primary_sequence_length: 320 alternative_sequence_length: 837 shared_uniparc_id: null same_taxon: true reference_proteome: UP000887458 proteome_is_reference: true proteome_taxon_matches: true primary_in_reference_proteome: false alternative_in_reference_proteome: true searched_reference_proteomes: - UP000887458 primary_in_any_reference_proteome: false sampled_history_versions: - 114 - 131 - 142 sampled_versions_with_proteome_links: - 142 current_records: - primaryAccession: P08176 entryType: UniProtKB reviewed (Swiss-Prot) entryAudit: firstPublicDate: '1988-08-01' lastAnnotationUpdateDate: '2026-09-02' lastSequenceUpdateDate: '1995-02-01' entryVersion: 146 sequenceVersion: 2 genes: - geneName: value: DERP1 organism: scientificName: Dermatophagoides pteronyssinus taxonId: 6956 sequence: length: 320 sha256: e02aa7e516b9ed92e60732c1f9a36175881869e9d7188aeec23b497c5f1cf9f6 uniProtKBCrossReferences: [] - primaryAccession: A0ABQ8JGY3 entryType: UniProtKB unreviewed (TrEMBL) entryAudit: firstPublicDate: '2025-10-08' lastAnnotationUpdateDate: '2026-09-02' lastSequenceUpdateDate: '2025-10-08' entryVersion: 4 sequenceVersion: 1 genes: - geneName: evidences: - evidenceCode: ECO:0000313 source: EMBL id: KAH9421866.1 value: MCM2_2 orfNames: - evidences: - evidenceCode: ECO:0000313 source: EMBL id: KAH9421866.1 value: DERP_002156 organism: scientificName: Dermatophagoides pteronyssinus taxonId: 6956 sequence: length: 837 sha256: 4f4a418c2cb13f0d87066f5e190050b41b41e003ab2d1ba022391563211c4ce1 uniProtKBCrossReferences: - database: Proteomes id: UP000887458 properties: - key: Component value: Unassembled WGS sequence reference_proteomes: - id: UP000887458 proteomeType: Reference proteome taxonomy: scientificName: Dermatophagoides pteronyssinus commonName: European house dust mite taxonId: 6956 mnemonic: DERPT unisave_records: - entry_version: 114 url: https://rest.uniprot.org/unisave/P08176?format=txt&versions=114 entry_date: 14-OCT-2015, entry version 114. proteomes: [] reference_proteome_keyword: false record_text: | CC -!- SIMILARITY: Belongs to the peptidase C1 family. CC {ECO:0000255|PROSITE-ProRule:PRU10088, ECO:0000255|PROSITE- CC ProRule:PRU10089, ECO:0000255|PROSITE-ProRule:PRU10090}. - entry_version: 131 url: https://rest.uniprot.org/unisave/P08176?format=txt&versions=131 entry_date: 07-OCT-2020, entry version 131. proteomes: [] reference_proteome_keyword: false record_text: | CC -!- SIMILARITY: Belongs to the peptidase C1 family. {ECO:0000255|PROSITE- CC ProRule:PRU10088, ECO:0000255|PROSITE-ProRule:PRU10089, CC ECO:0000255|PROSITE-ProRule:PRU10090}. - entry_version: 142 url: https://rest.uniprot.org/unisave/P08176?format=txt&versions=142 entry_date: 29-MAY-2024, entry version 142. proteomes: - UP000515146 reference_proteome_keyword: true record_text: | CC -!- SIMILARITY: Belongs to the peptidase C1 family. {ECO:0000255|PROSITE- CC ProRule:PRU10088, ECO:0000255|PROSITE-ProRule:PRU10089, CC ECO:0000255|PROSITE-ProRule:PRU10090}. archived_sources: - path: genes/DERPT/Derp1/Derp1-record-evidence.yaml url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/DERPT/Derp1/Derp1-record-evidence.yaml sha256: a7dc049c40b6a2f682cb65c525ac40de114eb6eb56d03b196baa7e6d0bd5b778 excerpts: - start_line: 26 end_line: 38 text: |2 alternative_sequence_length: 837 shared_uniparc_id: null same_taxon: true reference_proteome: UP000887458 proteome_is_reference: true proteome_taxon_matches: true primary_in_reference_proteome: false alternative_in_reference_proteome: true searched_reference_proteomes: - UP000887458 primary_in_any_reference_proteome: false sampled_history_versions: - 114 - start_line: 150 end_line: 154 text: |2 source: PROSITE-ProRule id: PRU10090 value: Belongs to the peptidase C1 family commentType: SIMILARITY - commentType: SEQUENCE CAUTION - start_line: 1470 end_line: 1474 text: |2 source: EMBL id: KAH9421866.1 value: MCM2_2 orfNames: - evidences: - start_line: 1486 end_line: 1490 text: |2 source: PROSITE-ProRule id: PRU10088 value: Belongs to the peptidase C1 family commentType: SIMILARITY - texts: - start_line: 2216 end_line: 2221 text: | - entry_version: 114 url: https://rest.uniprot.org/unisave/P08176?format=txt&versions=114 entry_date: 14-OCT-2015, entry version 114. proteomes: [] reference_proteome_keyword: false record_text: | - start_line: 2323 end_line: 2327 text: |2 CC conjunctivitis. Binds to IgE in 80% of patients with house dust CC allergy. CC -!- SIMILARITY: Belongs to the peptidase C1 family. CC {ECO:0000255|PROSITE-ProRule:PRU10088, ECO:0000255|PROSITE- CC ProRule:PRU10089, ECO:0000255|PROSITE-ProRule:PRU10090}. - start_line: 2433 end_line: 2438 text: | - entry_version: 131 url: https://rest.uniprot.org/unisave/P08176?format=txt&versions=131 entry_date: 07-OCT-2020, entry version 131. proteomes: [] reference_proteome_keyword: false record_text: | - start_line: 2535 end_line: 2539 text: |2 CC allergy are bronchial asthma, allergic rhinitis and conjunctivitis. CC Binds to IgE in 80% of patients with house dust allergy. CC -!- SIMILARITY: Belongs to the peptidase C1 family. {ECO:0000255|PROSITE- CC ProRule:PRU10088, ECO:0000255|PROSITE-ProRule:PRU10089, CC ECO:0000255|PROSITE-ProRule:PRU10090}. - start_line: 2693 end_line: 2699 text: | - entry_version: 142 url: https://rest.uniprot.org/unisave/P08176?format=txt&versions=142 entry_date: 29-MAY-2024, entry version 142. proteomes: - UP000515146 reference_proteome_keyword: true record_text: | - start_line: 2796 end_line: 2800 text: |2 CC allergy are bronchial asthma, allergic rhinitis and conjunctivitis. CC Binds to IgE in 80% of patients with house dust allergy. CC -!- SIMILARITY: Belongs to the peptidase C1 family. {ECO:0000255|PROSITE- CC ProRule:PRU10088, ECO:0000255|PROSITE-ProRule:PRU10089, CC ECO:0000255|PROSITE-ProRule:PRU10090}. - path: genes/DERPT/Derp1/Derp1-bioinformatics/reference-counterparts/comparison.yaml url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/DERPT/Derp1/Derp1-bioinformatics/reference-counterparts/comparison.yaml sha256: e5da4c3c88a6d149865b08c5a71cc5d98513ada35c7f74fd39c533e205ec7b45 excerpts: - start_line: 25 end_line: 29 text: |2 - -v - '1' target_sequence_count: 14675 query_sha256: 57f132084fbc8b7d7820a68f3f59e4e1eda032c741306643712e43f846b88a04 targets_sha256: ca828b473340f0a27bc7c92cebf1e36990cd53a1f6ca120c9c19829f0943499d - start_line: 44 end_line: 48 text: |2 sha256: ca828b473340f0a27bc7c92cebf1e36990cd53a1f6ca120c9c19829f0943499d detailed_alignment_limit: 10 candidate_count: 22 candidates: - accession: A0ABQ8JGY3 - start_line: 52 end_line: 64 text: |2 bit_score: 610.0 global_score: 1316.0 query_length: 320 target_length: 837 alignment_columns: 837 identities: 300 mismatches: 20 gap_columns: 517 identity_percent: 35.8423 query_coverage_percent: 100.0 target_coverage_percent: 38.2318 substitutions: - query_position: 2 comparison: provenance: query_accession: P08176 run_at: '2026-10-18T23:34:28.857216+00:00' biopython_version: '1.85' mmseqs_version: 18-8cc5c command: - mmseqs - easy-search - genes/DERPT/Derp1/Derp1-bioinformatics/reference-counterparts/query.fasta - .cache/orphan-curated/UP000887458.fasta - genes/DERPT/Derp1/Derp1-bioinformatics/reference-counterparts/search.tsv - genes/DERPT/Derp1/Derp1-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: 14675 query_sha256: 57f132084fbc8b7d7820a68f3f59e4e1eda032c741306643712e43f846b88a04 targets_sha256: ca828b473340f0a27bc7c92cebf1e36990cd53a1f6ca120c9c19829f0943499d 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%3AUP000887458&format=fasta retrieved_at: '2026-10-18T23:32:43.489103+00:00' uniprot_release: '2026_03' sequence_count: 14675 sha256: ca828b473340f0a27bc7c92cebf1e36990cd53a1f6ca120c9c19829f0943499d detailed_alignment_limit: 10 candidate_count: 22 retained_alignment_count: 10 candidates: - accession: A0ABQ8JGY3 description: tr|A0ABQ8JGY3|A0ABQ8JGY3_DERPT MCM DNA helicase complex subunit OS=Dermatophagoides pteronyssinus OX=6956 GN=MCM2_2 PE=3 SV=1 evalue: 2.441e-198 bit_score: 610.0 global_score: 1316.0 query_length: 320 target_length: 837 alignment_columns: 837 identities: 300 mismatches: 20 gap_columns: 517 identity_percent: 35.8423 query_coverage_percent: 100.0 target_coverage_percent: 38.2318 - accession: A0ABQ8J3M6 description: tr|A0ABQ8J3M6|A0ABQ8J3M6_DERPT Uncharacterized protein OS=Dermatophagoides pteronyssinus OX=6956 GN=DERP_015275 PE=3 SV=1 evalue: 5.727e-117 bit_score: 375.0 global_score: 906.0 query_length: 320 target_length: 578 alignment_columns: 578 identities: 203 mismatches: 117 gap_columns: 258 identity_percent: 35.1211 query_coverage_percent: 100.0 target_coverage_percent: 55.3633