{ "date": "2026-09-10", "scope": "All18 exact benchmark accessions without a PANTHER assignment in the current mapping snapshot. Gene-context bridges do not change exact-target assignment.", "cases": [ { "cohort": "ARGO50", "role": "prediction_target", "accession": "Q9L243", "species": "STRCO", "gene_symbol": "Q9L243", "gene_review": "genes/STRCO/Q9L243/Q9L243-ai-review.yaml", "cohort_source": "projects/PROTNLM_EVALUATION/argo_protnlm_50.csv", "uniprot_panther": "", "member_index_panther": "", "resolved_accession": "Q9L243", "families": "", "mapping_status": "NO_PANTHER_ASSIGNMENT", "assessment": "HAD_SAK_2-domain candidate; substrate unresolved", "reason": "Pfam PF18143 (HAD_SAK_2) supplies a domain-level relationship for this 171-residue Streptomyces protein. The current name 'Secreted protein' is explicitly ProtNLM-derived and does not independently validate secretion. Neither a specific 5-prime-nucleotidase reaction nor deoxyribonucleotide catabolism follows from the domain assignment.", "next": "Resolve full HAD-domain architecture and catalytic residues, compare the substrate-recognition region with experimentally characterized HAD_SAK_2 proteins, and test nucleotide versus non-nucleotide substrates.", "evolution": "Useful substrate-divergence candidate if a characterized HAD_SAK_2 clade can be established; not yet a defensible nucleotidase family.", "length": 171, "taxon_id": 100226, "current_record_url": "https://www.uniprot.org/uniprotkb/Q9L243/entry", "gene_identifiers": [], "domain_cross_references": [ { "database": "Pfam", "id": "PF18143", "properties": [ { "key": "EntryName", "value": "HAD_SAK_2" }, { "key": "MatchStatus", "value": "1" } ] } ], "features": [], "same_gene_alternative_records": [], "search_url": "https://rest.uniprot.org/uniprotkb/search?query=gene_exact%3ASCO2678+AND+organism_id%3A100226&format=json&size=100" }, { "cohort": "ARGO50", "role": "prediction_target", "accession": "S0EDH7", "species": "GIBF5", "gene_symbol": "S0EDH7", "gene_review": "genes/GIBF5/S0EDH7/S0EDH7-ai-review.yaml", "cohort_source": "projects/PROTNLM_EVALUATION/argo_protnlm_50.csv", "uniprot_panther": "", "member_index_panther": "", "resolved_accession": "S0EDH7", "families": "", "mapping_status": "NO_PANTHER_ASSIGNMENT", "assessment": "Kinase-like structural superfamily; catalytic class unresolved", "reason": "InterPro IPR011009 identifies a kinase-like structural superfamily in the 342-residue Fusarium protein, but no specific protein-kinase family or catalytic-site assignment is present. The recommended kinase-domain name is ProtNLM-derived. A structural fold relationship alone does not establish ATP binding or protein phosphorylation.", "next": "Recover a structure-supported alignment spanning the nucleotide-binding and catalytic regions, distinguish active protein kinases from other kinase-like proteins, and establish the target gene model.", "evolution": "Potential divergent kinase or kinase-like nonenzyme case, provided catalytic competence is tested rather than presumed from the name.", "length": 342, "taxon_id": 1279085, "current_record_url": "https://www.uniprot.org/uniprotkb/S0EDH7/entry", "gene_identifiers": [], "domain_cross_references": [ { "database": "InterPro", "id": "IPR011009", "properties": [ { "key": "EntryName", "value": "Kinase-like_dom_sf" } ] } ], "features": [], "same_gene_alternative_records": [], "search_url": "https://rest.uniprot.org/uniprotkb/search?query=gene_exact%3AFFUJ_06423+AND+organism_id%3A1279085&format=json&size=100" }, { "cohort": "ARGO50", "role": "prediction_target", "accession": "Q2U1U6", "species": "ASPOR", "gene_symbol": "Q2U1U6", "gene_review": "genes/ASPOR/Q2U1U6/Q2U1U6-ai-review.yaml", "cohort_source": "projects/PROTNLM_EVALUATION/argo_protnlm_50.csv", "uniprot_panther": "", "member_index_panther": "", "resolved_accession": "Q2U1U6", "families": "", "mapping_status": "NO_PANTHER_ASSIGNMENT", "assessment": "Short chondroitin-lyase-like structural match; enzyme unresolved", "reason": "The 134-residue Aspergillus sequence has only InterPro IPR008929, a chondroitin-lyase-like structural relationship. This does not establish a complete polysaccharide-degrading enzyme. Lyase chemistry and hydrolysis are different mechanisms, and neither is established by the short fold match.", "next": "Check transcript/gene-model completeness and whether the sequence covers a diagnostic catalytic domain; then compare the actual active-site architecture with characterized polysaccharide enzymes.", "evolution": "A useful fragment-versus-divergent-enzyme control, but too incomplete for confident substrate-family placement.", "length": 134, "taxon_id": 510516, "current_record_url": "https://www.uniprot.org/uniprotkb/Q2U1U6/entry", "gene_identifiers": [], "domain_cross_references": [ { "database": "InterPro", "id": "IPR008929", "properties": [ { "key": "EntryName", "value": "Chondroitin_lyas" } ] } ], "features": [], "same_gene_alternative_records": [], "search_url": "https://rest.uniprot.org/uniprotkb/search?query=gene_exact%3AAO090138000091+AND+organism_id%3A510516&format=json&size=100" }, { "cohort": "ARGO50", "role": "prediction_target", "accession": "A0A061AL94", "species": "CAEEL", "gene_symbol": "A0A061AL94", "gene_review": "genes/CAEEL/A0A061AL94/A0A061AL94-ai-review.yaml", "cohort_source": "projects/PROTNLM_EVALUATION/argo_protnlm_50.csv", "uniprot_panther": "", "member_index_panther": "", "resolved_accession": "A0A061AL94", "families": "", "mapping_status": "NO_PANTHER_ASSIGNMENT", "assessment": "Verified mcm-4 gene context; isolated MCM4 C-terminal sequence", "reason": "The target has the WormBase gene identifier WBGene00003156 and Pfam PF21128 (WHD_MCM4). The reviewed full-length record Q95XQ8 shares that gene identifier and maps to PTHR11630:SF66. Direct sequence comparison shows the entire 74-residue target is exactly Q95XQ8 residues 750\u2013823. This licenses MCM4 gene context, not ATPase/helicase activity, nuclear targeting or complex incorporation of the fragment itself.", "next": "Establish whether the short transcript produces a stable protein and whether its winged-helix region has independent interactions. Retain the short exact input when evaluating ProtNLM.", "evolution": "Strong domain-isolation control for propagation from full-length MCM4. The observed relationship is alternative gene-product structure, not evidence of evolutionary loss of helicase activity.", "length": 74, "taxon_id": 6239, "current_record_url": "https://www.uniprot.org/uniprotkb/A0A061AL94/entry", "gene_identifiers": [ [ "WormBase", "WBGene00003156" ] ], "domain_cross_references": [ { "database": "Pfam", "id": "PF21128", "properties": [ { "key": "EntryName", "value": "WHD_MCM4" }, { "key": "MatchStatus", "value": "1" } ] } ], "features": [], "same_gene_alternative_records": [ { "accession": "Q95XQ8", "length": 823, "shared_gene_identifiers": [ [ "WormBase", "WBGene00003156" ] ], "panther": [ "PTHR11630", "PTHR11630:SF66" ] } ], "search_url": "https://rest.uniprot.org/uniprotkb/search?query=gene_exact%3Amcm-4+AND+organism_id%3A6239&format=json&size=100" }, { "cohort": "ARGO50", "role": "prediction_target", "accession": "A2FPI7", "species": "TRIV3", "gene_symbol": "A2FPI7", "gene_review": "genes/TRIV3/A2FPI7/A2FPI7-ai-review.yaml", "cohort_source": "projects/PROTNLM_EVALUATION/argo_protnlm_50.csv", "uniprot_panther": "", "member_index_panther": "", "resolved_accession": "A2FPI7", "families": "", "mapping_status": "NO_PANTHER_ASSIGNMENT", "assessment": "KilA-N/APSES DNA-binding domain family", "reason": "Pfam PF04383 and InterPro IPR017880/IPR018004 identify a KilA-N/APSES helix-turn-helix module; the domain spans residues 19\u2013124 of a 129-residue protein. This is an informative domain-family assignment despite absent PANTHER coverage. It supports a broad DNA-binding inference without specifying a target sequence or regulatory program. The record lists two Trichomonas ORF identifiers, so locus provenance also needs attention.", "next": "Compare full KilA-N domains with characterized regulators and inspect genomic context for the two listed ORFs. Resolve DNA-recognition residues and regulatory partners before assigning a transcriptional role.", "evolution": "Interesting cross-lineage and mobile-element-associated DNA-binding module; investigate domain distribution without assuming horizontal transfer from domain presence alone.", "length": 129, "taxon_id": 412133, "current_record_url": "https://www.uniprot.org/uniprotkb/A2FPI7/entry", "gene_identifiers": [], "domain_cross_references": [ { "database": "InterPro", "id": "IPR018004", "properties": [ { "key": "EntryName", "value": "KilA/APSES_HTH" } ] }, { "database": "InterPro", "id": "IPR017880", "properties": [ { "key": "EntryName", "value": "KilA_N" } ] }, { "database": "Pfam", "id": "PF04383", "properties": [ { "key": "EntryName", "value": "KilA-N" }, { "key": "MatchStatus", "value": "1" } ] } ], "features": [ { "type": "Domain", "location": { "start": { "value": 19, "modifier": "EXACT" }, "end": { "value": 124, "modifier": "EXACT" } }, "description": "KilA-N", "evidences": [ { "evidenceCode": "ECO:0000259", "source": "PROSITE", "id": "PS51301" } ] } ], "same_gene_alternative_records": [], "search_url": "https://rest.uniprot.org/uniprotkb/search?query=gene_exact%3ATVAG_233530+AND+organism_id%3A412133&format=json&size=100" }, { "cohort": "HORSE40", "role": "prediction_target", "accession": "F7A4N8", "species": "HORSE", "gene_symbol": "CTDSP2", "gene_review": "genes/HORSE/CTDSP2/CTDSP2-ai-review.yaml", "cohort_source": "projects/PROTNLM_EVALUATION/mammal-benchmark/horse40.csv", "uniprot_panther": "", "member_index_panther": "", "resolved_accession": "F7A4N8", "families": "", "mapping_status": "NO_PANTHER_ASSIGNMENT", "assessment": "Short CTDSP2 gene model; canonical phosphatase context insufficient", "reason": "The horse record names CTDSP2 and carries ENSECAG00000018788.4, but its 174-residue sequence has no diagnostic phosphatase or kinase domain assignment. The existing reproducible human\u2013horse comparison reports a match to part of human CTDSP2 and loss/divergence across the catalytic region. The current horse gene search returned no longer same-gene record, so no verified horse canonical bridge is available.", "next": "Resolve the horse transcript and exon model against the genomic locus and an intact ortholog. A CTDSP2 gene-name assignment must not substitute for catalytic-domain evidence in the exact target.", "evolution": "Gene-model control for kinase-versus-phosphatase predictions; distinguish incomplete annotation from a real truncated isoform before interpreting functional divergence.", "length": 174, "taxon_id": 9796, "current_record_url": "https://www.uniprot.org/uniprotkb/F7A4N8/entry", "gene_identifiers": [ [ "Ensembl", "ENSECAG00000018788.4" ], [ "VGNC", "VGNC:16932" ] ], "domain_cross_references": [], "features": [ { "type": "Region", "location": { "start": { "value": 111, "modifier": "EXACT" }, "end": { "value": 135, "modifier": "EXACT" } }, "description": "Disordered", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "MobiDB-lite" } ] }, { "type": "Compositional bias", "location": { "start": { "value": 119, "modifier": "EXACT" }, "end": { "value": 135, "modifier": "EXACT" } }, "description": "Low complexity", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "MobiDB-lite" } ] } ], "same_gene_alternative_records": [], "search_url": "https://rest.uniprot.org/uniprotkb/search?query=gene_exact%3ACTDSP2+AND+organism_id%3A9796&format=json&size=100" }, { "cohort": "FLY41", "role": "prediction_target", "accession": "Q8IPG8", "species": "DROME", "gene_symbol": "CG31606", "gene_review": "genes/DROME/CG31606/CG31606-ai-review.yaml", "cohort_source": "projects/PROTNLM_EVALUATION/fly-benchmark/functional-cohort.csv", "uniprot_panther": "", "member_index_panther": "", "resolved_accession": "Q8IPG8", "families": "", "mapping_status": "NO_PANTHER_ASSIGNMENT", "assessment": "Unclassified secreted fly protein; apolipoprotein placement unsupported", "reason": "CG31606 has a SignalP-derived signal peptide at residues 1\u201318 and a soluble mature sequence, supporting secretion as an inference. No recognized family domain is assigned. The retained analytical report shows asymmetric structural similarity to a mammalian apolipoprotein donor; that partial match does not establish apolipoprotein orthology, lipid binding or lipid transport.", "next": "Find well-supported insect orthologs and test whether a full-length structural relationship survives signal-peptide removal and low-complexity controls. Ligand or lipid assays are needed for the proposed cargo function.", "evolution": "Interesting lineage-restricted secreted-protein case and a control for overinterpreting partial structure matches across distant taxa.", "length": 197, "taxon_id": 7227, "current_record_url": "https://www.uniprot.org/uniprotkb/Q8IPG8/entry", "gene_identifiers": [ [ "FlyBase", "FBgn0051606" ] ], "domain_cross_references": [], "features": [ { "type": "Signal", "location": { "start": { "value": 1, "modifier": "EXACT" }, "end": { "value": 18, "modifier": "EXACT" } }, "description": "", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "SignalP" } ] }, { "type": "Chain", "location": { "start": { "value": 19, "modifier": "EXACT" }, "end": { "value": 197, "modifier": "EXACT" } }, "description": "", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "SignalP" } ], "featureId": "PRO_5004308877" } ], "same_gene_alternative_records": [], "search_url": "https://rest.uniprot.org/uniprotkb/search?query=gene_exact%3ACG31606+AND+organism_id%3A7227&format=json&size=100" }, { "cohort": "FLY_LOCATION_KEYWORD", "role": "prediction_target", "accession": "A0A0B4LGP2", "species": "DROME", "gene_symbol": "CG45100", "gene_review": "", "cohort_source": "projects/PROTNLM_EVALUATION/fly-benchmark/location-keyword-tier.csv", "uniprot_panther": "", "member_index_panther": "", "resolved_accession": "A0A0B4LGP2", "families": "", "mapping_status": "NO_PANTHER_ASSIGNMENT", "assessment": "Hdac3 upstream-ORF microprotein; no deacetylase family inference", "reason": "The current UniProt gene name is Hdac3-5'utr, with aliases CG45100 and Dmel_Hdac3_uORF and FlyBase FBgn0266539. The protein is 38 residues and has a predicted transmembrane helix at 12\u201330. This is not the full-length histone deacetylase HDAC3; genomic association with its transcript must not transfer deacetylase activity to the microprotein.", "next": "Verify the uORF transcript/translation evidence and membrane insertion experimentally, then assess conservation of the small ORF independently from conservation of the downstream Hdac3 coding sequence.", "evolution": "High-interest de novo/uORF microprotein candidate. Conservation of the host gene is not conservation of the peptide.", "length": 38, "taxon_id": 7227, "current_record_url": "https://www.uniprot.org/uniprotkb/A0A0B4LGP2/entry", "gene_identifiers": [ [ "FlyBase", "FBgn0266539" ] ], "domain_cross_references": [], "features": [ { "type": "Transmembrane", "location": { "start": { "value": 12, "modifier": "EXACT" }, "end": { "value": 30, "modifier": "EXACT" } }, "description": "Helical", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "Phobius" } ] } ], "same_gene_alternative_records": [], "search_url": "https://rest.uniprot.org/uniprotkb/search?query=gene_exact%3ACG45100+AND+organism_id%3A7227&format=json&size=100" }, { "cohort": "FLY_LOCATION_KEYWORD", "role": "prediction_target", "accession": "M9NF85", "species": "DROME", "gene_symbol": "CG32086", "gene_review": "", "cohort_source": "projects/PROTNLM_EVALUATION/fly-benchmark/location-keyword-tier.csv", "uniprot_panther": "", "member_index_panther": "", "resolved_accession": "M9NF85", "families": "", "mapping_status": "NO_PANTHER_ASSIGNMENT", "assessment": "EFHB C-terminal EF-hand domain protein", "reason": "CG32086 has Pfam PF25325/InterPro IPR057428 and a domain assigned at residues 399\u2013469. Two additional records share FlyBase FBgn0052086, with lengths 491 and 245 residues, but none has a PANTHER assignment. This supplies an EFHB-related domain relationship without resolving calcium-binding stoichiometry, target pathway or equivalence of all isoforms.", "next": "Align the EF-hand liganding loops and complete N-terminal architecture across the three same-gene products and characterized EFHB relatives. Confirm whether each product retains a functional calcium-binding module.", "evolution": "Useful domain-retention and splice-product comparison for calcium sensing; ligand competence must be evaluated rather than inferred from an EF-hand label.", "length": 475, "taxon_id": 7227, "current_record_url": "https://www.uniprot.org/uniprotkb/M9NF85/entry", "gene_identifiers": [ [ "FlyBase", "FBgn0052086" ] ], "domain_cross_references": [ { "database": "InterPro", "id": "IPR057428", "properties": [ { "key": "EntryName", "value": "EFHB_EF-hand_C" } ] }, { "database": "Pfam", "id": "PF25325", "properties": [ { "key": "EntryName", "value": "EF-hand_EFHB_C" }, { "key": "MatchStatus", "value": "1" } ] } ], "features": [ { "type": "Domain", "location": { "start": { "value": 399, "modifier": "EXACT" }, "end": { "value": 469, "modifier": "EXACT" } }, "description": "EFHB C-terminal EF-hand", "evidences": [ { "evidenceCode": "ECO:0000259", "source": "Pfam", "id": "PF25325" } ] } ], "same_gene_alternative_records": [ { "accession": "Q8IQG0", "length": 491, "shared_gene_identifiers": [ [ "FlyBase", "FBgn0052086" ] ], "panther": [] }, { "accession": "Q8T4E3", "length": 245, "shared_gene_identifiers": [ [ "FlyBase", "FBgn0052086" ] ], "panther": [] } ], "search_url": "https://rest.uniprot.org/uniprotkb/search?query=gene_exact%3ACG32086+AND+organism_id%3A7227&format=json&size=100" }, { "cohort": "FLY_LOCATION_KEYWORD;FLY_NEXT20", "role": "prediction_target", "accession": "Q7KVQ7", "species": "DROME", "gene_symbol": "Tango5", "gene_review": "", "cohort_source": "projects/PROTNLM_EVALUATION/fly-benchmark/location-keyword-tier.csv", "uniprot_panther": "", "member_index_panther": "", "resolved_accession": "Q7KVQ7", "families": "", "mapping_status": "NO_PANTHER_ASSIGNMENT", "assessment": "VMP1-related membrane architecture without PANTHER coverage", "reason": "Tango5 has independently assigned KMS1 N-terminal and VMP1 C-terminal domains (PF28607/IPR063065 and PF27639/IPR059828) and multiple membrane helices. A second same-FlyBase-gene record Q9W2S1 is longer (530 versus 428 residues) and also lacks PANTHER. This domain architecture supports a VMP1-related comparison; the ARBA-derived scramblase reactions in the record are not independent confirmation of the target reaction.", "next": "Compare the two FlyBase-matched protein models with experimentally characterized VMP1 proteins, check missing sequence/topology, and trace lipid-scrambling evidence to reconstituted assays and its conserved structural determinants.", "evolution": "Strong membrane-lipid biology candidate: analyze family-specific architecture and paralog specialization while controlling for alternative input models.", "length": 428, "taxon_id": 7227, "current_record_url": "https://www.uniprot.org/uniprotkb/Q7KVQ7/entry", "gene_identifiers": [ [ "FlyBase", "FBgn0052675" ] ], "domain_cross_references": [ { "database": "InterPro", "id": "IPR063065", "properties": [ { "key": "EntryName", "value": "KMS1_N" } ] }, { "database": "InterPro", "id": "IPR059828", "properties": [ { "key": "EntryName", "value": "VMP1_C" } ] }, { "database": "Pfam", "id": "PF28607", "properties": [ { "key": "EntryName", "value": "KMS1_N" }, { "key": "MatchStatus", "value": "1" } ] }, { "database": "Pfam", "id": "PF27639", "properties": [ { "key": "EntryName", "value": "VMP1_C" }, { "key": "MatchStatus", "value": "1" } ] } ], "features": [ { "type": "Transmembrane", "location": { "start": { "value": 69, "modifier": "EXACT" }, "end": { "value": 86, "modifier": "EXACT" } }, "description": "Helical", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "Phobius" } ] }, { "type": "Transmembrane", "location": { "start": { "value": 106, "modifier": "EXACT" }, "end": { "value": 131, "modifier": "EXACT" } }, "description": "Helical", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "Phobius" } ] }, { "type": "Transmembrane", "location": { "start": { "value": 246, "modifier": "EXACT" }, "end": { "value": 262, "modifier": "EXACT" } }, "description": "Helical", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "Phobius" } ] }, { "type": "Transmembrane", "location": { "start": { "value": 368, "modifier": "EXACT" }, "end": { "value": 389, "modifier": "EXACT" } }, "description": "Helical", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "Phobius" } ] }, { "type": "Domain", "location": { "start": { "value": 20, "modifier": "EXACT" }, "end": { "value": 117, "modifier": "EXACT" } }, "description": "KMS1 N-terminal", "evidences": [ { "evidenceCode": "ECO:0000259", "source": "Pfam", "id": "PF28607" } ] }, { "type": "Domain", "location": { "start": { "value": 368, "modifier": "EXACT" }, "end": { "value": 399, "modifier": "EXACT" } }, "description": "Vacuole membrane protein 1 C-terminal helical", "evidences": [ { "evidenceCode": "ECO:0000259", "source": "Pfam", "id": "PF27639" } ] }, { "type": "Region", "location": { "start": { "value": 1, "modifier": "EXACT" }, "end": { "value": 30, "modifier": "EXACT" } }, "description": "Disordered", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "MobiDB-lite" } ] }, { "type": "Region", "location": { "start": { "value": 399, "modifier": "EXACT" }, "end": { "value": 428, "modifier": "EXACT" } }, "description": "Disordered", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "MobiDB-lite" } ] }, { "type": "Compositional bias", "location": { "start": { "value": 1, "modifier": "EXACT" }, "end": { "value": 10, "modifier": "EXACT" } }, "description": "Polar residues", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "MobiDB-lite" } ] }, { "type": "Compositional bias", "location": { "start": { "value": 21, "modifier": "EXACT" }, "end": { "value": 30, "modifier": "EXACT" } }, "description": "Basic and acidic residues", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "MobiDB-lite" } ] }, { "type": "Compositional bias", "location": { "start": { "value": 405, "modifier": "EXACT" }, "end": { "value": 416, "modifier": "EXACT" } }, "description": "Polar residues", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "MobiDB-lite" } ] }, { "type": "Compositional bias", "location": { "start": { "value": 419, "modifier": "EXACT" }, "end": { "value": 428, "modifier": "EXACT" } }, "description": "Basic residues", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "MobiDB-lite" } ] } ], "same_gene_alternative_records": [ { "accession": "Q9W2S1", "length": 530, "shared_gene_identifiers": [ [ "FlyBase", "FBgn0052675" ] ], "panther": [] } ], "search_url": "https://rest.uniprot.org/uniprotkb/search?query=gene_exact%3ATango5+AND+organism_id%3A7227&format=json&size=100" }, { "cohort": "FLY_LOCATION_KEYWORD", "role": "prediction_target", "accession": "Q8MZA7", "species": "DROME", "gene_symbol": "CG13494", "gene_review": "", "cohort_source": "projects/PROTNLM_EVALUATION/fly-benchmark/location-keyword-tier.csv", "uniprot_panther": "", "member_index_panther": "", "resolved_accession": "Q8MZA7", "families": "", "mapping_status": "NO_PANTHER_ASSIGNMENT", "assessment": "Small membrane protein CG13494; family unresolved", "reason": "The 120-residue target carries a predicted helix at residues 37\u201361 and no recognized InterPro/Pfam family. Another 120-residue record Q7KVM4 shares FlyBase FBgn0034671 but likewise has no PANTHER match. Membrane insertion does not establish a transport pore, receptor or particular organelle.", "next": "Compare same-gene records and conserved fly orthologs, assess topology and signal-anchor orientation, and seek interaction/localization evidence before assigning a specific membrane function.", "evolution": "Useful small membrane-protein conservation case; distinguish genuine lineage restriction from weak profile sensitivity for short proteins.", "length": 120, "taxon_id": 7227, "current_record_url": "https://www.uniprot.org/uniprotkb/Q8MZA7/entry", "gene_identifiers": [ [ "FlyBase", "FBgn0034671" ] ], "domain_cross_references": [], "features": [ { "type": "Transmembrane", "location": { "start": { "value": 37, "modifier": "EXACT" }, "end": { "value": 61, "modifier": "EXACT" } }, "description": "Helical", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "Phobius" } ] } ], "same_gene_alternative_records": [], "search_url": "https://rest.uniprot.org/uniprotkb/search?query=gene_exact%3ACG13494+AND+organism_id%3A7227&format=json&size=100" }, { "cohort": "FLY_LOCATION_KEYWORD", "role": "prediction_target", "accession": "Q9VN74", "species": "DROME", "gene_symbol": "CG14662", "gene_review": "", "cohort_source": "projects/PROTNLM_EVALUATION/fly-benchmark/location-keyword-tier.csv", "uniprot_panther": "", "member_index_panther": "", "resolved_accession": "Q9VN74", "families": "", "mapping_status": "NO_PANTHER_ASSIGNMENT", "assessment": "LRR-related membrane protein CG14662; receptor mechanism unresolved", "reason": "The 550-residue target carries InterPro IPR032675 (LRR structural superfamily) and predicted helices at residues 29\u201350 and 421\u2013447. Q8T4D5 is a same-FlyBase-gene 550-residue record with no PANTHER match. LRR-mediated interaction is a reasonable architectural hypothesis, but ligand identity, receptor function and signaling mechanism are not established.", "next": "Resolve whether the N-terminal hydrophobic segment is a signal peptide or retained membrane helix, compare extracellular LRR organization with insect homologs, and investigate binding partners.", "evolution": "Interesting LRR architecture and receptor/scaffold diversification case; avoid assigning a named receptor family solely from repeats.", "length": 550, "taxon_id": 7227, "current_record_url": "https://www.uniprot.org/uniprotkb/Q9VN74/entry", "gene_identifiers": [ [ "FlyBase", "FBgn0037291" ] ], "domain_cross_references": [ { "database": "InterPro", "id": "IPR032675", "properties": [ { "key": "EntryName", "value": "LRR_dom_sf" } ] } ], "features": [ { "type": "Transmembrane", "location": { "start": { "value": 29, "modifier": "EXACT" }, "end": { "value": 50, "modifier": "EXACT" } }, "description": "Helical", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "Phobius" } ] }, { "type": "Transmembrane", "location": { "start": { "value": 421, "modifier": "EXACT" }, "end": { "value": 447, "modifier": "EXACT" } }, "description": "Helical", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "Phobius" } ] }, { "type": "Region", "location": { "start": { "value": 296, "modifier": "EXACT" }, "end": { "value": 332, "modifier": "EXACT" } }, "description": "Disordered", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "MobiDB-lite" } ] }, { "type": "Region", "location": { "start": { "value": 505, "modifier": "EXACT" }, "end": { "value": 527, "modifier": "EXACT" } }, "description": "Disordered", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "MobiDB-lite" } ] }, { "type": "Compositional bias", "location": { "start": { "value": 300, "modifier": "EXACT" }, "end": { "value": 332, "modifier": "EXACT" } }, "description": "Low complexity", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "MobiDB-lite" } ] } ], "same_gene_alternative_records": [ { "accession": "Q8T4D5", "length": 550, "shared_gene_identifiers": [ [ "FlyBase", "FBgn0037291" ] ], "panther": [] } ], "search_url": "https://rest.uniprot.org/uniprotkb/search?query=gene_exact%3ACG14662+AND+organism_id%3A7227&format=json&size=100" }, { "cohort": "POMBE_REMAINING8", "role": "prediction_target", "accession": "C6Y4C2", "species": "SCHPO", "gene_symbol": "spo2", "gene_review": "", "cohort_source": "projects/PROTNLM_EVALUATION/pombe-benchmark/remaining/cohort.csv", "uniprot_panther": "", "member_index_panther": "", "resolved_accession": "C6Y4C2", "families": "", "mapping_status": "NO_PANTHER_ASSIGNMENT", "assessment": "Spo2 is a short VPS13 C-terminal-derived protein at a distinct annotated locus", "reason": "Reviewed UniProt evidence places Spo2 in meiotic spindle-pole-body modification and forespore-membrane initiation. Its record states that its sequence is identical to the C-terminus of Vps13b. Direct comparison confirms all 133 residues equal Vps1302 O42926 residues 2999\u20133131. However, PomBase assigns distinct loci: spo2 SPBC16C6.14 and vps1302 SPBC16C6.02c. O42926 has PTHR16166:SF93, but this is a domain-relationship lead, not a same-gene canonical bridge and not proof of full VPS13 lipid-transfer activity in Spo2.", "next": "Inspect the overlapping genomic and transcript models, translation initiation, and primary Spo2 constructs to distinguish a separately expressed C-terminal product from gene-model overlap or misassigned products. Examine whether the terminal module mediates the experimentally observed Spo13/Spo15 interactions.", "evolution": "Highest-priority nontrivial case here: potential reuse of a VPS13 terminal module for sporulation. Do not infer duplication, evolutionary truncation or misannotation until locus and protein-expression evidence resolves the origin.", "length": 133, "taxon_id": 284812, "current_record_url": "https://www.uniprot.org/uniprotkb/C6Y4C2/entry", "gene_identifiers": [ [ "PomBase", "SPBC16C6.14" ] ], "domain_cross_references": [], "features": [ { "type": "Chain", "location": { "start": { "value": 1, "modifier": "EXACT" }, "end": { "value": 133, "modifier": "EXACT" } }, "description": "Sporulation-specific protein 2", "featureId": "PRO_0000389117" } ], "same_gene_alternative_records": [], "search_url": "https://rest.uniprot.org/uniprotkb/search?query=gene_exact%3Aspo2+AND+organism_id%3A284812&format=json&size=100" }, { "cohort": "NEUROSPORA20", "role": "prediction_target", "accession": "Q7S3T0", "species": "NEUCR", "gene_symbol": "NCU04937", "gene_review": "genes/NEUCR/NCU04937/NCU04937-ai-review.yaml", "cohort_source": "projects/PROTNLM_EVALUATION/neurospora-benchmark/review-cohort.csv", "uniprot_panther": "", "member_index_panther": "", "resolved_accession": "Q7S3T0", "families": "", "mapping_status": "NO_PANTHER_ASSIGNMENT", "assessment": "Short coiled-coil protein; DNA-binding family unresolved", "reason": "NCU04937 is 114 residues, with N-terminal disorder and a predicted coiled coil at 52\u2013104. No diagnostic DNA-binding domain or protein family is assigned. A weak human THAP11 prediction donor does not establish a THAP DNA-binding fold, particularly where low-complexity and coiled-coil sequence can drive similarity.", "next": "Use composition-aware searches and structure comparisons to distinguish a conserved interaction helix from a genuine DNA-binding module. Seek fungal orthologs and direct localization/binding evidence.", "evolution": "A useful false-homology control for coiled-coil and low-complexity proteins; the current evidence does not justify a THAP family.", "length": 114, "taxon_id": 367110, "current_record_url": "https://www.uniprot.org/uniprotkb/Q7S3T0/entry", "gene_identifiers": [], "domain_cross_references": [], "features": [ { "type": "Region", "location": { "start": { "value": 1, "modifier": "EXACT" }, "end": { "value": 25, "modifier": "EXACT" } }, "description": "Disordered", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "MobiDB-lite" } ] }, { "type": "Coiled coil", "location": { "start": { "value": 52, "modifier": "EXACT" }, "end": { "value": 104, "modifier": "EXACT" } }, "description": "", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "Coils" } ] } ], "same_gene_alternative_records": [], "search_url": "https://rest.uniprot.org/uniprotkb/search?query=gene_exact%3ANCU04937+AND+organism_id%3A367110&format=json&size=100" }, { "cohort": "NEUROSPORA20", "role": "prediction_target", "accession": "V5ILC0", "species": "NEUCR", "gene_symbol": "NCU12035", "gene_review": "genes/NEUCR/NCU12035/NCU12035-ai-review.yaml", "cohort_source": "projects/PROTNLM_EVALUATION/neurospora-benchmark/review-cohort.csv", "uniprot_panther": "", "member_index_panther": "", "resolved_accession": "V5ILC0", "families": "", "mapping_status": "NO_PANTHER_ASSIGNMENT", "assessment": "GNAT-domain acetyltransferase candidate; substrate unresolved", "reason": "NCU12035 has an N-acetyltransferase domain spanning 3\u2013184 of its 232 residues, with Pfam PF00583 and InterPro IPR000182/IPR016181. This provides a broad GNAT-fold assignment. It does not distinguish protein/histone, small-molecule or other acceptors and does not establish nuclear localization.", "next": "Compare the GNAT substrate-recognition regions and genomic context with experimentally characterized fungal enzymes. Verify acetyl-CoA utilization and acceptor specificity before assigning a narrow reaction or a chromatin function.", "evolution": "Good metabolic diversification candidate if a substrate-specific clade can be established; broad GNAT membership is too heterogeneous for a family-wide substrate prediction.", "length": 232, "taxon_id": 367110, "current_record_url": "https://www.uniprot.org/uniprotkb/V5ILC0/entry", "gene_identifiers": [], "domain_cross_references": [ { "database": "InterPro", "id": "IPR016181", "properties": [ { "key": "EntryName", "value": "Acyl_CoA_acyltransferase" } ] }, { "database": "InterPro", "id": "IPR000182", "properties": [ { "key": "EntryName", "value": "GNAT_dom" } ] }, { "database": "Pfam", "id": "PF00583", "properties": [ { "key": "EntryName", "value": "Acetyltransf_1" }, { "key": "MatchStatus", "value": "1" } ] } ], "features": [ { "type": "Domain", "location": { "start": { "value": 3, "modifier": "EXACT" }, "end": { "value": 184, "modifier": "EXACT" } }, "description": "N-acetyltransferase", "evidences": [ { "evidenceCode": "ECO:0000259", "source": "PROSITE", "id": "PS51186" } ] } ], "same_gene_alternative_records": [], "search_url": "https://rest.uniprot.org/uniprotkb/search?query=gene_exact%3ANCU12035+AND+organism_id%3A367110&format=json&size=100" }, { "cohort": "MOD_EVOLUTION20", "role": "prediction_target", "accession": "F8WDQ9", "species": "human", "gene_symbol": "UBE2F", "gene_review": "", "cohort_source": "projects/PROTNLM_EVALUATION/mod-evolution-benchmark/cohort.csv", "uniprot_panther": "", "member_index_panther": "", "resolved_accession": "F8WDQ9", "families": "", "mapping_status": "NO_PANTHER_ASSIGNMENT", "assessment": "Verified UBE2F gene context; truncated alternative UBC product", "reason": "The 101-residue target and reviewed UBE2F Q969M7 share HGNC:12480 and ENSG00000184182.20. Q969M7 maps to PTHR24067 and is an experimentally supported NEDD8 E2, not a generic ubiquitin-only conjugase. The target shares the first 94 residues with the 185-residue canonical protein, followed by a distinct short tail; it therefore lacks the intact canonical UBC domain. The canonical active-site feature is at residue 116, outside the retained common prefix. A record caution also flags missing conserved residues. Canonical catalytic activity must not be transferred to this exact alternative product.", "next": "Validate the alternative transcript, translation and folding, and determine whether the short UBC fragment has any regulatory interaction or is an incomplete/nonproductive product. Retain NEDD8-versus-ubiquitin specificity in the full-length comparison.", "evolution": "Excellent isoform/truncation and modifier-specificity control. Do not describe an alternatively encoded short product as an evolved pseudoenzyme without independent evidence.", "length": 101, "taxon_id": 9606, "current_record_url": "https://www.uniprot.org/uniprotkb/F8WDQ9/entry", "gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "domain_cross_references": [ { "database": "InterPro", "id": "IPR000608", "properties": [ { "key": "EntryName", "value": "UBC" } ] }, { "database": "InterPro", "id": "IPR016135", "properties": [ { "key": "EntryName", "value": "UBQ-conjugating_enzyme/RWD" } ] } ], "features": [ { "type": "Domain", "location": { "start": { "value": 32, "modifier": "EXACT" }, "end": { "value": 101, "modifier": "EXACT" } }, "description": "UBC core", "evidences": [ { "evidenceCode": "ECO:0000259", "source": "PROSITE", "id": "PS50127" } ] }, { "type": "Region", "location": { "start": { "value": 1, "modifier": "EXACT" }, "end": { "value": 29, "modifier": "EXACT" } }, "description": "Disordered", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "MobiDB-lite" } ] } ], "same_gene_alternative_records": [ { "accession": "Q969M7", "length": 185, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [ "PTHR24067" ] }, { "accession": "A0ACI8QAH6", "length": 195, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [ "PTHR24068" ] }, { "accession": "A0ACI8QUE3", "length": 200, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [ "PTHR24067" ] }, { "accession": "A0ACI8UHS8", "length": 196, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [ "PTHR24068" ] }, { "accession": "C9JSK8", "length": 153, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [ "PTHR24068" ] }, { "accession": "A0ACI8TFK9", "length": 184, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [ "PTHR24067" ] }, { "accession": "A0ACI8TG35", "length": 184, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [ "PTHR24067" ] }, { "accession": "A0ACI8TGR8", "length": 193, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [ "PTHR24067" ] }, { "accession": "C9IZ93", "length": 163, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [ "PTHR24068" ] }, { "accession": "C9J9P8", "length": 171, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [ "PTHR24067" ] }, { "accession": "C9JF62", "length": 139, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [ "PTHR24068" ] }, { "accession": "C9JFD2", "length": 142, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [ "PTHR24068" ] }, { "accession": "A0ACI8TGZ7", "length": 152, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [ "PTHR24068" ] }, { "accession": "F8WD80", "length": 123, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [ "PTHR24068" ] }, { "accession": "F8WB39", "length": 86, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [] }, { "accession": "F8WFB7", "length": 48, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [] }, { "accession": "A0ACI8QAF5", "length": 132, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [] }, { "accession": "G5E9R6", "length": 63, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [] }, { "accession": "A0ACI8R090", "length": 199, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [] }, { "accession": "A0ACI8TGR7", "length": 142, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [] }, { "accession": "A0ACI8TH99", "length": 109, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [] }, { "accession": "A0ACI8UHL8", "length": 111, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [] }, { "accession": "F8WCT3", "length": 78, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [] }, { "accession": "H3BSR4", "length": 131, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [] }, { "accession": "A0ACI8QCD0", "length": 100, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [] }, { "accession": "A0ACI8S899", "length": 143, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [] }, { "accession": "A0ACI8TGB1", "length": 99, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [] }, { "accession": "A0ACI8TH55", "length": 121, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [] }, { "accession": "F2Z363", "length": 47, "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "panther": [] } ], "search_url": "https://rest.uniprot.org/uniprotkb/search?query=gene_exact%3AUBE2F+AND+organism_id%3A9606&format=json&size=100" }, { "cohort": "MOD_EVOLUTION20", "role": "prediction_target", "accession": "A0A140LHW5", "species": "mouse", "gene_symbol": "Spcs2", "gene_review": "", "cohort_source": "projects/PROTNLM_EVALUATION/mod-evolution-benchmark/cohort.csv", "uniprot_panther": "", "member_index_panther": "", "resolved_accession": "A0A140LHW5", "families": "", "mapping_status": "NO_PANTHER_ASSIGNMENT", "assessment": "Verified Spcs2 gene context; short product lacks canonical membrane architecture", "reason": "The 74-residue target and reviewed Spcs2 Q9CYN2 share MGI:1913874 and ENSMUSG00000035227.8. Q9CYN2 is 226 residues and maps to PTHR13085:SF0. The first 66 residues match exactly, followed by a distinct target tail; the canonical membrane helices at 87\u2013107 and 112\u2013132 are outside this shared region. The target is annotated as disordered throughout. SPCS2 is an accessory signal-peptidase-complex subunit, so even the intact canonical protein should not be conflated with the catalytic SEC11 subunit.", "next": "Check the short transcript/protein's expression and interactions; distinguish absent membrane incorporation from any retained N-terminal binding function. Use full-length SPCS2 only as same-gene family context.", "evolution": "Strong short-isoform versus complex-subunit function control; distinguish accessory-subunit participation from protease catalysis.", "length": 74, "taxon_id": 10090, "current_record_url": "https://www.uniprot.org/uniprotkb/A0A140LHW5/entry", "gene_identifiers": [ [ "Ensembl", "ENSMUSG00000035227.8" ], [ "MGI", "MGI:1913874" ] ], "domain_cross_references": [], "features": [ { "type": "Region", "location": { "start": { "value": 1, "modifier": "EXACT" }, "end": { "value": 74, "modifier": "EXACT" } }, "description": "Disordered", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "MobiDB-lite" } ] }, { "type": "Compositional bias", "location": { "start": { "value": 9, "modifier": "EXACT" }, "end": { "value": 25, "modifier": "EXACT" } }, "description": "Gly residues", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "MobiDB-lite" } ] }, { "type": "Compositional bias", "location": { "start": { "value": 35, "modifier": "EXACT" }, "end": { "value": 52, "modifier": "EXACT" } }, "description": "Basic and acidic residues", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "MobiDB-lite" } ] }, { "type": "Compositional bias", "location": { "start": { "value": 65, "modifier": "EXACT" }, "end": { "value": 74, "modifier": "EXACT" } }, "description": "Basic residues", "evidences": [ { "evidenceCode": "ECO:0000256", "source": "SAM", "id": "MobiDB-lite" } ] } ], "same_gene_alternative_records": [ { "accession": "Q9CYN2", "length": 226, "shared_gene_identifiers": [ [ "Ensembl", "ENSMUSG00000035227.8" ], [ "MGI", "MGI:1913874" ] ], "panther": [ "PTHR13085", "PTHR13085:SF0" ] }, { "accession": "A0A140LJG6", "length": 123, "shared_gene_identifiers": [ [ "Ensembl", "ENSMUSG00000035227.8" ], [ "MGI", "MGI:1913874" ] ], "panther": [ "PTHR13085", "PTHR13085:SF0" ] }, { "accession": "A0A140LHG8", "length": 260, "shared_gene_identifiers": [ [ "Ensembl", "ENSMUSG00000035227.8" ], [ "MGI", "MGI:1913874" ] ], "panther": [ "PTHR13085", "PTHR13085:SF0" ] }, { "accession": "A0A140LIK0", "length": 177, "shared_gene_identifiers": [ [ "Ensembl", "ENSMUSG00000035227.8" ], [ "MGI", "MGI:1913874" ] ], "panther": [ "PTHR13085", "PTHR13085:SF0" ] }, { "accession": "A0A140LHR3", "length": 190, "shared_gene_identifiers": [ [ "Ensembl", "ENSMUSG00000035227.8" ], [ "MGI", "MGI:1913874" ] ], "panther": [ "PTHR13085", "PTHR13085:SF0" ] }, { "accession": "A0A140LJ01", "length": 252, "shared_gene_identifiers": [ [ "Ensembl", "ENSMUSG00000035227.8" ], [ "MGI", "MGI:1913874" ] ], "panther": [ "PTHR13085", "PTHR13085:SF0" ] } ], "search_url": "https://rest.uniprot.org/uniprotkb/search?query=gene_exact%3ASpcs2+AND+organism_id%3A10090&format=json&size=100" }, { "cohort": "MOD_EVOLUTION20", "role": "prediction_target", "accession": "Q18287", "species": "worm", "gene_symbol": "C28G1.2", "gene_review": "", "cohort_source": "projects/PROTNLM_EVALUATION/mod-evolution-benchmark/cohort.csv", "uniprot_panther": "", "member_index_panther": "", "resolved_accession": "Q18287", "families": "", "mapping_status": "NO_PANTHER_ASSIGNMENT", "assessment": "Serpin-fold protein; inhibitory mechanism unresolved", "reason": "The worm protein has Pfam PF00079 and three serpin-domain/superfamily assignments, but its 265-residue sequence has only a local serpin-domain feature at residues 96\u2013199. The same-gene search recovered no alternative canonical record. Serpin folds occur in inhibitory and noninhibitory proteins, and domain membership does not establish a protease target or a functional reactive-center-loop mechanism.", "next": "Establish whether the complete serpin fold and reactive-center-loop insertion machinery are present; compare structure and loop sequence against characterized inhibitory and noninhibitory serpins, then test protease trapping rather than simple binding.", "evolution": "High-interest inhibitory-versus-noninhibitory serpin comparison once fold completeness and reactive-center-loop architecture are resolved; avoid equating missing PANTHER coverage with pseudoenzyme status.", "length": 265, "taxon_id": 6239, "current_record_url": "https://www.uniprot.org/uniprotkb/Q18287/entry", "gene_identifiers": [ [ "WormBase", "WBGene00016187" ] ], "domain_cross_references": [ { "database": "InterPro", "id": "IPR023796", "properties": [ { "key": "EntryName", "value": "Serpin_dom" } ] }, { "database": "InterPro", "id": "IPR036186", "properties": [ { "key": "EntryName", "value": "Serpin_sf" } ] }, { "database": "InterPro", "id": "IPR042185", "properties": [ { "key": "EntryName", "value": "Serpin_sf_2" } ] }, { "database": "Pfam", "id": "PF00079", "properties": [ { "key": "EntryName", "value": "Serpin" }, { "key": "MatchStatus", "value": "1" } ] } ], "features": [ { "type": "Domain", "location": { "start": { "value": 96, "modifier": "EXACT" }, "end": { "value": 199, "modifier": "EXACT" } }, "description": "Serpin", "evidences": [ { "evidenceCode": "ECO:0000259", "source": "Pfam", "id": "PF00079" } ] } ], "same_gene_alternative_records": [], "search_url": "https://rest.uniprot.org/uniprotkb/search?query=gene_exact%3AC28G1.2+AND+organism_id%3A6239&format=json&size=100" } ], "verified_same_gene_bridges": [ { "target_accession": "A0A061AL94", "context_accession": "Q95XQ8", "context_record_status": "UniProtKB reviewed (Swiss-Prot)", "relationship": "SAME_GENE_CONTEXT_ONLY", "shared_gene_identifiers": [ [ "WormBase", "WBGene00003156" ] ], "target_length": 74, "context_length": 823, "context_panther": [ "PTHR11630", "PTHR11630:SF66" ], "exact_target_substring_start_1based": 750, "exact_target_substring_end_1based": 823, "common_prefix_length": 1, "target_sequence_sha256": "c1ad54ea50c0f3952f13f061f246aacb7b93e308e4712051a962b3c96f7ae343", "context_sequence_sha256": "8ade9863a2ac9e99ad5a539ffd9e334f0d82d5ddc22b4b707928305b5c1c459d", "source_url": "https://rest.uniprot.org/uniprotkb/search?query=gene_exact%3Amcm-4+AND+organism_id%3A6239&format=json&size=100" }, { "target_accession": "F8WDQ9", "context_accession": "Q969M7", "context_record_status": "UniProtKB reviewed (Swiss-Prot)", "relationship": "SAME_GENE_CONTEXT_ONLY", "shared_gene_identifiers": [ [ "Ensembl", "ENSG00000184182.20" ], [ "HGNC", "HGNC:12480" ] ], "target_length": 101, "context_length": 185, "context_panther": [ "PTHR24067" ], "exact_target_substring_start_1based": null, "exact_target_substring_end_1based": null, "common_prefix_length": 94, "target_sequence_sha256": "e3e20778779813044a00ce64a9a3aec318e11c8c158bed2e930a5d7c965b059e", "context_sequence_sha256": "bd8916d5b386090347733404bbf48b413a0b237b851f1b05a6ee2d3902d23137", "source_url": "https://rest.uniprot.org/uniprotkb/search?query=gene_exact%3AUBE2F+AND+organism_id%3A9606&format=json&size=100" }, { "target_accession": "A0A140LHW5", "context_accession": "Q9CYN2", "context_record_status": "UniProtKB reviewed (Swiss-Prot)", "relationship": "SAME_GENE_CONTEXT_ONLY", "shared_gene_identifiers": [ [ "Ensembl", "ENSMUSG00000035227.8" ], [ "MGI", "MGI:1913874" ] ], "target_length": 74, "context_length": 226, "context_panther": [ "PTHR13085", "PTHR13085:SF0" ], "exact_target_substring_start_1based": null, "exact_target_substring_end_1based": null, "common_prefix_length": 66, "target_sequence_sha256": "8cb489c165a420f39729a5bbaba3523309ad64349ef898657621ed55c7f54535", "context_sequence_sha256": "cccd32db169077bd534e31d2189d4d6db663dc4838bb781d823e76282c4f21e3", "source_url": "https://rest.uniprot.org/uniprotkb/search?query=gene_exact%3ASpcs2+AND+organism_id%3A10090&format=json&size=100" } ], "distinct_locus_sequence_relationships": [ { "target_accession": "C6Y4C2", "context_accession": "O42926", "relationship": "EXACT_C_TERMINAL_SEQUENCE_DIFFERENT_GENE_IDS", "target_gene_identifiers": [ [ "PomBase", "SPBC16C6.14" ] ], "context_gene_identifiers": [ [ "PomBase", "SPBC16C6.02c" ] ], "exact_target_substring_start_1based": 2999, "exact_target_substring_end_1based": 3131, "context_panther": [ "PTHR16166:SF93", "PTHR16166" ], "target_sequence_sha256": "5477bd5cdf10f64be21b168561ccc4609e51638f8b6b020b9a44e3ffff5cd352", "context_sequence_sha256": "019246d743d95b72df92ccfa8a048508c2b62b4a1288e86f8d77e5f15f2e9b34" } ], "sources": { "original_records": "uniprot-records.jsonl.gz", "record_overrides": "uniprot-retries.jsonl.gz", "additional_searches_and_publications": "unmapped-sources.jsonl.gz", "additional_sources_sha256": "ec941280c998954628e95d3e45edfbdb9ffe14643951a4f130a66ba36ff4cdcd" }, "limitations": [ "Current UniProt sequences are compared; equivalence to every prediction-time input sequence has not been established here.", "Gene-name searches are bounded queries, not exhaustive protein-family searches.", "No new PANTHER assignment is made to an exact target without a source assignment.", "No evolutionary duplication, catalytic-loss event or gene-model error is asserted from a short product alone." ], "validation": { "sequence_and_gene_checks": "PASS", "ruff": "PASS", "local_html_links_checked": 24, "missing_local_html_links": [], "history_record": "history/projects/PROTNLM_EVALUATION/2026-09-10T182418Z-codex-74b164.yaml", "history_validation": "PASS" } }