TogoMCP

schema_info: title: Protein Data Bank (PDB) description: | 3D structural data for proteins, nucleic acids, and complexes from X-ray, NMR, and cryo-EM with 204K+ entries. Contains experimental methods, resolution, R-factors, sequences, and cross-references to UniProt, EMDB, GenBank. Supports structure quality assessment, experimental method analysis, and biological function studies. endpoint: https://rdfportal.org/backend/pdb/sparql base_uri: http://rdf.wwpdb.org/pdb/ graphs: - http://rdfportal.org/dataset/pdbj version: mie_version: "1.3" mie_created: "2025-01-10" data_version: "Current" update_frequency: "Weekly" license: data_license: "Public Domain" license_url: https://www.wwpdb.org access: rate_limiting: "Reasonable use" max_query_timeout: "60s" backend: "Virtuoso" shape_expressions: | PREFIX pdbx: <http://rdf.wwpdb.org/schema/pdbx-v50.owl#> PREFIX xsd: <http://www.w3.org/2001/XMLSchema#> PREFIX dct: <http://purl.org/dc/terms/> <Datablock> { a [ pdbx:datablock ] ; pdbx:has_entryCategory @<EntryCategory> ; pdbx:has_entityCategory @<EntityCategory> * ; pdbx:has_entity_polyCategory @<EntityPolyCategory> * ; pdbx:has_exptlCategory @<ExptlCategory> + ; pdbx:has_refineCategory @<RefineCategory> * ; pdbx:has_struct_refCategory @<StructRefCategory> * ; pdbx:has_database_2Category @<Database2Category> * ; pdbx:has_citationCategory @<CitationCategory> * ; pdbx:has_structCategory @<StructCategory> ; pdbx:has_struct_keywordsCategory @<StructKeywordsCategory> * ; pdbx:has_cellCategory @<CellCategory> * ; pdbx:has_symmetryCategory @<SymmetryCategory> * ; pdbx:has_softwareCategory @<SoftwareCategory> * ; pdbx:has_pdbx_struct_assemblyCategory @<AssemblyCategory> * ; pdbx:has_struct_asymCategory @<StructAsymCategory> * ; pdbx:has_audit_authorCategory @<AuditAuthorCategory> * } <Entry> { a [ pdbx:entry ] ; pdbx:entry.id xsd:string ; pdbx:of_datablock IRI } <Entity> { a [ pdbx:entity ] ; pdbx:entity.id xsd:string ; pdbx:entity.type [ "polymer" "non-polymer" "water" "macrolide" "branched" ] ; pdbx:entity.pdbx_description xsd:string ? ; pdbx:entity.formula_weight xsd:decimal ? ; pdbx:entity.pdbx_number_of_molecules xsd:integer ? ; pdbx:entity.src_method xsd:string ? ; pdbx:referenced_by_entity_poly IRI * ; pdbx:referenced_by_struct_ref IRI * ; pdbx:referenced_by_struct_asym IRI * ; pdbx:of_datablock IRI } <EntityPoly> { a [ pdbx:entity_poly ] ; pdbx:entity_poly.entity_id xsd:string ; pdbx:entity_poly.type xsd:string ; # polypeptide(L), polyribonucleotide, polydeoxyribonucleotide pdbx:entity_poly.pdbx_seq_one_letter_code xsd:string ? ; pdbx:entity_poly.pdbx_seq_one_letter_code_can xsd:string ? ; pdbx:entity_poly.pdbx_strand_id xsd:string ? ; pdbx:reference_to_entity IRI ; pdbx:of_datablock IRI } <Refine> { a [ pdbx:refine ] ; pdbx:refine.entry_id xsd:string ; pdbx:refine.pdbx_refine_id xsd:string ; pdbx:refine.ls_d_res_high xsd:decimal ? ; pdbx:refine.ls_d_res_low xsd:decimal ? ; pdbx:refine.ls_R_factor_R_work xsd:decimal ? ; pdbx:refine.ls_R_factor_R_free xsd:decimal ? ; pdbx:refine.ls_number_reflns_obs xsd:integer ? ; pdbx:refine.ls_percent_reflns_obs xsd:decimal ? ; pdbx:reference_to_entry IRI ; pdbx:of_datablock IRI } <Exptl> { a [ pdbx:exptl ] ; pdbx:exptl.entry_id xsd:string ; pdbx:exptl.method xsd:string ; # X-RAY DIFFRACTION, ELECTRON MICROSCOPY, SOLUTION NMR pdbx:exptl.crystals_number xsd:integer ? ; pdbx:reference_to_entry IRI ; pdbx:of_datablock IRI } <StructRef> { a [ pdbx:struct_ref ] ; pdbx:struct_ref.id xsd:string ; pdbx:struct_ref.db_name xsd:string ; # UNP, GB, EMBL, REF pdbx:struct_ref.db_code xsd:string ? ; pdbx:struct_ref.pdbx_db_accession xsd:string ? ; pdbx:struct_ref.entity_id xsd:string ? ; pdbx:reference_to_entity IRI * ; pdbx:of_datablock IRI } <Database2> { a [ pdbx:database_2 ] ; pdbx:database_2.database_id xsd:string ; # PDB, WWPDB, EMDB, BMRB pdbx:database_2.database_code xsd:string ; pdbx:of_datablock IRI } <Citation> { a [ pdbx:citation ] ; pdbx:citation.id xsd:string ; pdbx:citation.title xsd:string ? ; pdbx:citation.journal_abbrev xsd:string ? ; pdbx:citation.journal_volume xsd:string ? ; pdbx:citation.page_first xsd:string ? ; pdbx:citation.page_last xsd:string ? ; pdbx:citation.year xsd:integer ? ; pdbx:citation.pdbx_database_id_PubMed xsd:string ? ; pdbx:citation.pdbx_database_id_DOI xsd:string ? ; pdbx:link_to_doi IRI ? ; pdbx:link_to_pubmed IRI ? ; dct:references IRI * ; pdbx:referenced_by_citation_author IRI * ; pdbx:of_datablock IRI } <Struct> { a [ pdbx:struct ] ; pdbx:struct.entry_id xsd:string ; pdbx:struct.title xsd:string ? ; pdbx:struct.pdbx_descriptor xsd:string ? ; pdbx:struct.pdbx_model_details xsd:string ? ; pdbx:reference_to_entry IRI ; pdbx:of_datablock IRI } <StructKeywords> { a [ pdbx:struct_keywords ] ; pdbx:struct_keywords.entry_id xsd:string ; pdbx:struct_keywords.pdbx_keywords xsd:string ? ; pdbx:struct_keywords.text xsd:string ? ; pdbx:reference_to_entry IRI ; pdbx:of_datablock IRI } <Cell> { a [ pdbx:cell ] ; pdbx:cell.entry_id xsd:string ; pdbx:cell.length_a xsd:decimal ? ; pdbx:cell.length_b xsd:decimal ? ; pdbx:cell.length_c xsd:decimal ? ; pdbx:cell.angle_alpha xsd:decimal ? ; pdbx:cell.angle_beta xsd:decimal ? ; pdbx:cell.angle_gamma xsd:decimal ? ; pdbx:cell.Z_PDB xsd:integer ? ; pdbx:reference_to_entry IRI ; pdbx:of_datablock IRI } <Symmetry> { a [ pdbx:symmetry ] ; pdbx:symmetry.entry_id xsd:string ; pdbx:symmetry.space_group_name_H-M xsd:string ? ; pdbx:symmetry.Int_Tables_number xsd:integer ? ; pdbx:reference_to_entry IRI ; pdbx:of_datablock IRI } <Software> { a [ pdbx:software ] ; pdbx:software.name xsd:string ? ; pdbx:software.version xsd:string ? ; pdbx:software.classification xsd:string ? ; # data collection, refinement, data reduction, data scaling pdbx:software.pdbx_ordinal xsd:integer ? ; pdbx:of_datablock IRI } <StructAssembly> { a [ pdbx:pdbx_struct_assembly ] ; pdbx:pdbx_struct_assembly.id xsd:string ; pdbx:pdbx_struct_assembly.details xsd:string ? ; pdbx:pdbx_struct_assembly.oligomeric_count xsd:integer ? ; pdbx:pdbx_struct_assembly.oligomeric_details xsd:string ? ; pdbx:referenced_by_pdbx_struct_assembly_gen IRI * ; pdbx:of_datablock IRI } <StructAsym> { a [ pdbx:struct_asym ] ; pdbx:struct_asym.id xsd:string ; pdbx:struct_asym.entity_id xsd:string ? ; pdbx:struct_asym.pdbx_blank_PDB_chainid_flag [ "Y" "N" ] ? ; pdbx:reference_to_entity IRI ? ; pdbx:of_datablock IRI } sample_rdf_entries: - title: "High-Resolution Protein (3NIR)" description: "Ultra-high resolution structure with refinement statistics." rdf: | @prefix pdbx: <http://rdf.wwpdb.org/schema/pdbx-v50.owl#> . @prefix xsd: <http://www.w3.org/2001/XMLSchema#> . pdb:3NIR a pdbx:datablock ; pdbx:has_refineCategory pdb:3NIR/refineCategory . pdb:3NIR/refine/3NIR,X-RAY_DIFFRACTION a pdbx:refine ; pdbx:refine.ls_d_res_high "0.48"^^xsd:decimal ; pdbx:refine.ls_R_factor_R_work "0.127"^^xsd:decimal . - title: "DNA Structure (100D)" description: "Dickerson dodecamer with sequence." rdf: | @prefix pdbx: <http://rdf.wwpdb.org/schema/pdbx-v50.owl#> . pdb:100D/entity/1 a pdbx:entity ; pdbx:entity.id "1" ; pdbx:entity.type "polymer" ; pdbx:entity.pdbx_description "DNA/RNA (5'-R(*CP*)-D(*CP*GP*GP*CP*GP*CP*CP*GP*)-R(*G)-3')" . - title: "Protein with UniProt (16PK)" description: "Protein with UniProt cross-reference." rdf: | @prefix pdbx: <http://rdf.wwpdb.org/schema/pdbx-v50.owl#> . pdb:16PK/struct_ref/1 a pdbx:struct_ref ; pdbx:struct_ref.db_name "UNP" ; pdbx:struct_ref.pdbx_db_accession "P07378" . - title: "Cryo-EM Structure (8A2Z)" description: "EM structure with EMDB reference." rdf: | @prefix pdbx: <http://rdf.wwpdb.org/schema/pdbx-v50.owl#> . pdb:8A2Z/database_2/1 a pdbx:database_2 ; pdbx:database_2.database_id "EMDB" ; pdbx:database_2.database_code "EMD-15109" . pdb:8A2Z/exptl/1 a pdbx:exptl ; pdbx:exptl.method "ELECTRON MICROSCOPY" . - title: "RNA Structure (300D)" description: "Hammerhead ribozyme with sequence." rdf: | @prefix pdbx: <http://rdf.wwpdb.org/schema/pdbx-v50.owl#> . pdb:300D/entity_poly/1 a pdbx:entity_poly ; pdbx:entity_poly.type "polyribonucleotide" ; pdbx:entity_poly.pdbx_seq_one_letter_code "GUGGUCUGAUGAGGCC" . sparql_query_examples: - title: "Search by Keywords" description: "Find structures by classification keywords with biological annotations" question: "Find kinase structures" complexity: basic sparql: | PREFIX pdbx: <http://rdf.wwpdb.org/schema/pdbx-v50.owl#> SELECT ?entry_id ?title ?keywords FROM <http://rdfportal.org/dataset/pdbj> WHERE { ?entry a pdbx:datablock . BIND(STRAFTER(str(?entry), "http://rdf.wwpdb.org/pdb/") AS ?entry_id) ?entry pdbx:has_structCategory/pdbx:has_struct ?struct ; pdbx:has_struct_keywordsCategory/pdbx:has_struct_keywords ?kw . ?struct pdbx:struct.title ?title . ?kw pdbx:struct_keywords.pdbx_keywords ?keywords . FILTER(CONTAINS(LCASE(?keywords), "kinase")) } LIMIT 20 - title: "Software Usage Statistics" description: "Analyze software tools used in structure determination" question: "What software is most used for refinement?" complexity: basic sparql: | PREFIX pdbx: <http://rdf.wwpdb.org/schema/pdbx-v50.owl#> SELECT ?software_name ?classification (COUNT(?entry) as ?usage_count) FROM <http://rdfportal.org/dataset/pdbj> WHERE { ?entry pdbx:has_softwareCategory/pdbx:has_software ?sw . ?sw pdbx:software.name ?software_name ; pdbx:software.classification ?classification . FILTER(?classification = "refinement") } GROUP BY ?software_name ?classification ORDER BY DESC(?usage_count) LIMIT 15 - title: "Crystallographic Parameters" description: "Find X-ray structures with unit cell and symmetry information" question: "What are the cell parameters for small unit cells?" complexity: intermediate sparql: | PREFIX pdbx: <http://rdf.wwpdb.org/schema/pdbx-v50.owl#> PREFIX xsd: <http://www.w3.org/2001/XMLSchema#> SELECT ?entry_id ?a ?b ?c ?space_group FROM <http://rdfportal.org/dataset/pdbj> WHERE { ?entry a pdbx:datablock . BIND(STRAFTER(str(?entry), "http://rdf.wwpdb.org/pdb/") AS ?entry_id) ?entry pdbx:has_cellCategory/pdbx:has_cell ?cell ; pdbx:has_symmetryCategory/pdbx:has_symmetry ?sym ; pdbx:has_exptlCategory/pdbx:has_exptl/pdbx:exptl.method "X-RAY DIFFRACTION" . ?cell pdbx:cell.length_a ?a ; pdbx:cell.length_b ?b ; pdbx:cell.length_c ?c . ?sym pdbx:symmetry.space_group_name_H-M ?space_group . FILTER(xsd:decimal(?a) > 20 && xsd:decimal(?a) < 50) } LIMIT 20 - title: "Biological Assemblies" description: "Find quaternary structures with oligomeric state annotations" question: "Which structures form tetramers?" complexity: intermediate sparql: | PREFIX pdbx: <http://rdf.wwpdb.org/schema/pdbx-v50.owl#> SELECT ?entry_id ?assembly_id ?oligomeric_count ?oligomeric_details FROM <http://rdfportal.org/dataset/pdbj> WHERE { ?entry a pdbx:datablock . BIND(STRAFTER(str(?entry), "http://rdf.wwpdb.org/pdb/") AS ?entry_id) ?entry pdbx:has_pdbx_struct_assemblyCategory/pdbx:has_pdbx_struct_assembly ?assembly . ?assembly pdbx:pdbx_struct_assembly.id ?assembly_id ; pdbx:pdbx_struct_assembly.oligomeric_count ?oligomeric_count ; pdbx:pdbx_struct_assembly.oligomeric_details ?oligomeric_details . FILTER(CONTAINS(?oligomeric_details, "tetrameric")) } LIMIT 20 - title: "Search Publications" description: "Find structures by publication title keywords with citation metadata" question: "Find CRISPR-related structures with publications" complexity: intermediate sparql: | PREFIX pdbx: <http://rdf.wwpdb.org/schema/pdbx-v50.owl#> SELECT ?entry_id ?title ?year ?journal ?doi FROM <http://rdfportal.org/dataset/pdbj> WHERE { ?entry a pdbx:datablock . BIND(STRAFTER(str(?entry), "http://rdf.wwpdb.org/pdb/") AS ?entry_id) ?entry pdbx:has_citationCategory/pdbx:has_citation ?citation . ?citation pdbx:citation.title ?title ; pdbx:citation.year ?year ; pdbx:citation.journal_abbrev ?journal . OPTIONAL { ?citation pdbx:citation.pdbx_database_id_DOI ?doi } FILTER(CONTAINS(LCASE(?title), "crispr")) } LIMIT 20 - title: "Comprehensive Structure Analysis" description: "Multi-category query combining experimental, quality, and metadata" question: "What are high-quality recent kinase structures?" complexity: advanced sparql: | PREFIX pdbx: <http://rdf.wwpdb.org/schema/pdbx-v50.owl#> PREFIX xsd: <http://www.w3.org/2001/XMLSchema#> SELECT ?entry_id ?title ?resolution ?r_work ?year ?keywords FROM <http://rdfportal.org/dataset/pdbj> WHERE { ?entry a pdbx:datablock . BIND(STRAFTER(str(?entry), "http://rdf.wwpdb.org/pdb/") AS ?entry_id) ?entry pdbx:has_structCategory/pdbx:has_struct ?struct ; pdbx:has_struct_keywordsCategory/pdbx:has_struct_keywords ?kw ; pdbx:has_refineCategory/pdbx:has_refine ?refine ; pdbx:has_citationCategory/pdbx:has_citation ?citation . ?struct pdbx:struct.title ?title . ?kw pdbx:struct_keywords.pdbx_keywords ?keywords . ?refine pdbx:refine.ls_d_res_high ?resolution ; pdbx:refine.ls_R_factor_R_work ?r_work . ?citation pdbx:citation.year ?year . FILTER(CONTAINS(LCASE(?keywords), "kinase")) FILTER(xsd:decimal(?resolution) < 2.0) FILTER(xsd:integer(?year) >= 2020) } ORDER BY xsd:decimal(?resolution) LIMIT 20 - title: "Software Pipeline Analysis" description: "Trace complete data processing workflow through software categories" question: "What software pipelines are used together?" complexity: advanced sparql: | PREFIX pdbx: <http://rdf.wwpdb.org/schema/pdbx-v50.owl#> SELECT ?entry_id (GROUP_CONCAT(DISTINCT ?collection; separator=", ") as ?collection_sw) (GROUP_CONCAT(DISTINCT ?reduction; separator=", ") as ?reduction_sw) (GROUP_CONCAT(DISTINCT ?refinement; separator=", ") as ?refinement_sw) FROM <http://rdfportal.org/dataset/pdbj> WHERE { ?entry a pdbx:datablock . BIND(STRAFTER(str(?entry), "http://rdf.wwpdb.org/pdb/") AS ?entry_id) ?entry pdbx:has_softwareCategory/pdbx:has_software ?sw1, ?sw2, ?sw3 . ?sw1 pdbx:software.name ?collection ; pdbx:software.classification "data collection" . ?sw2 pdbx:software.name ?reduction ; pdbx:software.classification "data reduction" . ?sw3 pdbx:software.name ?refinement ; pdbx:software.classification "refinement" . } GROUP BY ?entry_id LIMIT 20 cross_references: - pattern: pdbx:struct_ref description: | Sequence database cross-references with db_name and pdbx_db_accession. databases: Protein: - UNP (UniProt): 352K refs, ~172% - PIR: 131 Nucleotide: - GB (GenBank): 5.9K - EMBL: 84 - REF (RefSeq): 49 sparql: | PREFIX pdbx: <http://rdf.wwpdb.org/schema/pdbx-v50.owl#> SELECT ?entry_id ?db_name ?db_accession FROM <http://rdfportal.org/dataset/pdbj> WHERE { ?entry a pdbx:datablock . BIND(STRAFTER(str(?entry), "http://rdf.wwpdb.org/pdb/") AS ?entry_id) ?entry pdbx:has_struct_refCategory/pdbx:has_struct_ref ?ref . ?ref pdbx:struct_ref.db_name ?db_name ; pdbx:struct_ref.pdbx_db_accession ?db_accession . } LIMIT 30 - pattern: pdbx:database_2 description: | External database links for WWPDB partners, EMDB, BMRB. databases: WWPDB: - PDB: 100% - WWPDB: 100% - RCSB: ~41% - PDBE: ~8% Structure: - EMDB: ~7% - BMRB: ~3% - NDB: ~2% sparql: | PREFIX pdbx: <http://rdf.wwpdb.org/schema/pdbx-v50.owl#> SELECT ?entry_id ?db_id ?db_code FROM <http://rdfportal.org/dataset/pdbj> WHERE { ?entry a pdbx:datablock . BIND(STRAFTER(str(?entry), "http://rdf.wwpdb.org/pdb/") AS ?entry_id) ?entry pdbx:has_database_2Category/pdbx:has_database_2 ?db . ?db pdbx:database_2.database_id ?db_id ; pdbx:database_2.database_code ?db_code . } LIMIT 30 - pattern: pdbx:citation description: | Publication references with DOI and PubMed identifiers. databases: Publications: - DOI: ~75% - PubMed: ~73% sparql: | PREFIX pdbx: <http://rdf.wwpdb.org/schema/pdbx-v50.owl#> SELECT ?entry_id ?doi ?pubmed FROM <http://rdfportal.org/dataset/pdbj> WHERE { ?entry a pdbx:datablock . BIND(STRAFTER(str(?entry), "http://rdf.wwpdb.org/pdb/") AS ?entry_id) ?entry pdbx:has_citationCategory/pdbx:has_citation ?citation . OPTIONAL { ?citation pdbx:citation.pdbx_database_id_DOI ?doi } OPTIONAL { ?citation pdbx:citation.pdbx_database_id_PubMed ?pubmed } FILTER(BOUND(?doi) || BOUND(?pubmed)) } LIMIT 20 architectural_notes: schema_design: - PDBx/mmCIF ontology with Category-Item design pattern - Datablock root with has_*Category properties linking to specialized categories - Each category contains has_* properties linking to individual items - Categories include entity, entity_poly, exptl, refine, struct_ref, database_2, citation, struct, cell, symmetry, software, pdbx_struct_assembly, struct_asym - Strong separation between structural data, experiments, refinement, cross-references, metadata - Bidirectional references (e.g., reference_to_entry, referenced_by_*) performance: - 204K+ entries with 900K+ entities require optimization - Use xsd:decimal() for resolution/R-factor numeric comparisons - Use CONTAINS/bif:contains for keyword/title searches - Filter by pdbx:datablock type to get entry-level data - Multi-join queries across categories need entry_id filtering early - Category traversal (has_*Category/has_*) efficient for targeted queries data_integration: - UniProt for protein sequences (352K refs, ~172% per entry) - EMDB for cryo-EM density maps (~7%) - GenBank/EMBL/RefSeq for nucleotide sequences - DOI/PubMed for publications (~75%/73%) - link_to_doi and link_to_pubmed for direct external links - dct:references for identifier-based references data_quality: - Resolution and R-factors indicate X-ray structure quality - Multiple UniProt refs per entry common (one per chain) - NMR structures lack resolution data - EM structures may lack R-factors - Cell and symmetry data only for crystallographic methods - Software metadata varies by deposition date data_statistics: total_entries: 204594 experimental_methods: xray: "~85%" em: "~7%" nmr: "~7%" coverage: uniprot: "~172%" emdb: "~7%" doi: "~75%" pubmed: "~73%" resolution: ">85%" cell_data: "~85%" symmetry: "~85%" software: "~90%" keywords: "~95%" assemblies: "~90%" cardinality: avg_uniprot_refs: 1.72 avg_entities: 4.4 avg_assemblies: 1.2 avg_software_entries: 3.5 cross_reference_counts: uniprot: 352114 genbank: 5874 emdb: 13974 doi: 186683 pubmed: 181261 software_usage: top_refinement: PHENIX (72K), REFMAC (70K) top_phasing: PHASER (62K) top_reduction: XDS (51K), HKL-2000 (40K) performance: - "Resolution queries: efficient with numeric filters" - "Cross-reference by db_name: works well" - "Keyword searches: use CONTAINS on keywords field" - "Category traversal: 2-3 property path steps optimal" - "Recommend LIMIT 20-100" anti_patterns: - title: "Missing Numeric Conversion" problem: "Resolution comparisons fail without casting" wrong_sparql: | PREFIX pdbx: <http://rdf.wwpdb.org/schema/pdbx-v50.owl#> SELECT ?resolution WHERE { ?refine pdbx:refine.ls_d_res_high ?resolution . FILTER(?resolution < 1.0) } correct_sparql: | PREFIX pdbx: <http://rdf.wwpdb.org/schema/pdbx-v50.owl#> PREFIX xsd: <http://www.w3.org/2001/XMLSchema#> SELECT ?resolution WHERE { ?refine pdbx:refine.ls_d_res_high ?resolution . FILTER(xsd:decimal(?resolution) > 0 && xsd:decimal(?resolution) < 1.0) } explanation: "Always use xsd:decimal() for numeric comparisons" - title: "Inefficient Keyword Search" problem: "Not using indexed keyword fields" wrong_sparql: | PREFIX pdbx: <http://rdf.wwpdb.org/schema/pdbx-v50.owl#> SELECT ?entry_id ?title WHERE { ?entry pdbx:has_structCategory/pdbx:has_struct ?struct . ?struct pdbx:struct.title ?title . FILTER(CONTAINS(LCASE(?title), "kinase")) } correct_sparql: | PREFIX pdbx: <http://rdf.wwpdb.org/schema/pdbx-v50.owl#> SELECT ?entry_id ?keywords FROM <http://rdfportal.org/dataset/pdbj> WHERE { ?entry a pdbx:datablock . BIND(STRAFTER(str(?entry), "http://rdf.wwpdb.org/pdb/") AS ?entry_id) ?entry pdbx:has_struct_keywordsCategory/pdbx:has_struct_keywords ?kw . ?kw pdbx:struct_keywords.pdbx_keywords ?keywords . FILTER(CONTAINS(LCASE(?keywords), "kinase")) } LIMIT 20 explanation: "Use struct_keywords for faster searches" - title: "Missing Entry Filter" problem: "Not filtering by datablock returns non-entries" wrong_sparql: | SELECT ?entry WHERE { ?entry pdbx:has_refineCategory ?refine . } correct_sparql: | PREFIX pdbx: <http://rdf.wwpdb.org/schema/pdbx-v50.owl#> SELECT ?entry_id FROM <http://rdfportal.org/dataset/pdbj> WHERE { ?entry a pdbx:datablock . BIND(STRAFTER(str(?entry), "http://rdf.wwpdb.org/pdb/") AS ?entry_id) ?entry pdbx:has_refineCategory ?refine . } explanation: "Filter by pdbx:datablock and extract entry_id" common_errors: - error: "Type conversion errors" causes: - "Comparing resolution strings without xsd:decimal()" - "Missing numeric filters" solutions: - "Always use xsd:decimal() for resolution/R-factors" - "Filter out invalid values (< 0 or > 100)" example_fix: | # Wrong: FILTER(?resolution < 1.0) # Right: FILTER(xsd:decimal(?resolution) > 0 && xsd:decimal(?resolution) < 1.0) - error: "Missing optional data" causes: - "NMR structures lack resolution" - "Not using OPTIONAL for cross-references" - "Software metadata not always complete" solutions: - "Use OPTIONAL for resolution, R-factors" - "Filter by experimental method if requiring resolution" - "Use OPTIONAL for software, citations, assemblies" - error: "Query timeout" causes: - "Using CONTAINS on long text fields" - "Not limiting results" - "Missing FROM clause" - "Complex multi-category joins without filters" solutions: - "Add LIMIT 20-100" - "Include FROM clause" - "Use keyword fields instead of titles" - "Filter by entry_id early in multi-joins"