RCSB Protein Data Bank
data.rcsb.org
The US arm of the Worldwide Protein Data Bank: experimentally determined 3D structures of proteins, nucleic acids and their complexes, with their sequences, ligands, biological assemblies, interfaces, validation metrics and links out to UniProt, PubMed and DrugBank.
GET /v1/data/rcsbpdb/assembly1Request
A 4-character PDB ID (case-insensitive), or a computed structure model ID such as AF_AFP69905F1.
The assembly number within the entry; '1' is the first and usually the preferred assembly.
curl "https://api.fastcrw.com/v1/data/rcsbpdb/assembly?entry_id=4HHB&assembly_id=1" \ -H "Authorization: Bearer $FASTCRW_API_KEY"
2Response example
A sample shape. Press Run to see live data from RCSB Protein Data Bank.
{
"pdbx_struct_assembly": {
"details": "author_and_software_defined_assembly",
"id": "1",
"method_details": "PISA",
"oligomeric_count": 4,
"oligomeric_details": "tetrameric",
"rcsb_candidate_assembly": "Y",
"rcsb_details": "author_and_software_defined_assembly"
},
"pdbx_struct_assembly_gen": [
{
"assembly_id": "1",
"asym_id_list": [
"A",
"B",
"C",
"D",
"E",
"F",
"G",
"H",
"I",
"J",
"… 4 more items"
],
"oper_expression": "1",
"ordinal": 1
}
],
"pdbx_struct_oper_list": [
{
"id": "1",
"matrix_1_1": 1,
"matrix_1_2": 0,
"matrix_1_3": 0,
"matrix_2_1": 0,
"matrix_2_2": 1,
"matrix_2_3": 0,
"matrix_3_1": 0,
"matrix_3_2": 0,
"matrix_3_3": 1,
"name": "1_555",
"symmetry_operation": "x,y,z",
"type": "identity operation",
"vector_1": 0,
"vector_2": 0,
"vector_3": 0
}
],
"rcsb_assembly_container_identifiers": {
"assembly_id": "1",
"entry_id": "4HHB",
"interface_ids": [
"1",
"2",
"3",
"4",
"5"
],
"rcsb_id": "4HHB-1"
},
"rcsb_assembly_info": {
"assembly_id": "1",
"atom_count": 4779,
"branched_atom_count": 0,
"branched_entity_count": 0,
"branched_entity_instance_count": 0,
"deuterated_water_count": 0,
"entry_id": "4HHB",
"formula_weight": 64.74,
"hydrogen_atom_count": 0,
"modeled_polymer_monomer_count": 574,
"na_polymer_entity_types": "Other",
"nonpolymer_atom_count": 174,
"nonpolymer_entity_count": 2,
"nonpolymer_entity_instance_count": 6,
"num_heterologous_interface_entities": 2,
"num_heteromeric_interface_entities": 2,
"num_homomeric_interface_entities": 1,
"num_interface_entities": 3,
"num_interfaces": 5,
"num_isologous_interface_entities": 1,
"num_na_interface_entities": 0,
"num_prot_na_interface_entities": 0,
"num_protein_interface_entities": 3,
"polymer_atom_count": 4384,
"polymer_composition": "heteromeric protein",
"polymer_entity_count": 2,
"polymer_entity_count_DNA": 0,
"polymer_entity_count_RNA": 0,
"polymer_entity_count_nucleic_acid": 0,
"polymer_entity_count_nucleic_acid_hybrid": 0,
"polymer_entity_count_protein": 2,
"polymer_entity_instance_count": 4,
"polymer_entity_instance_count_DNA": 0,
"polymer_entity_instance_count_RNA": 0,
"polymer_entity_instance_count_nucleic_acid": 0,
"polymer_entity_instance_count_nucleic_acid_hybrid": 0,
"polymer_entity_instance_count_protein": 4,
"polymer_monomer_count": 574,
"selected_polymer_entity_types": "Protein (only)",
"solvent_atom_count": 221,
"solvent_entity_count": 1,
"solvent_entity_instance_count": 4,
"total_assembly_buried_surface_area": 3305.3493305341694,
"total_number_interface_residues": 174,
"unmodeled_polymer_monomer_count": 0
},
"rcsb_struct_symmetry": [
{
"kind": "Global Symmetry",
"oligomeric_state": "Hetero 4-mer",
"stoichiometry": [
"A2",
"B2"
],
"symbol": "C2",
"type": "Cyclic",
"rotation_axes": [
{
"end": [
14.768193984554415,
42.44938893146809,
37.112154610549396
],
"order": 2,
"start": [
5.714139716037695,
-15.600903402959595,
42.62663109321926
]
}
],
"clusters": [
{
"members": [
{
"asym_id": "A",
"pdbx_struct_oper_list_ids": [
"1"
]
},
{
"asym_id": "C",
"pdbx_struct_oper_list_ids": [
"1"
]
}
],
"avg_rmsd": 0.2969817166222886
},
{
"members": [
{
"asym_id": "B",
"pdbx_struct_oper_list_ids": [
"1"
]
},
{
"asym_id": "D",
"pdbx_struct_oper_list_ids": [
"1"
]
}
],
"avg_rmsd": 0.36369606336673194
}
]
},
{
"kind": "Pseudo Symmetry",
"oligomeric_state": "Homo 4-mer",
"stoichiometry": [
"A4"
],
"symbol": "D2",
"type": "Dihedral",
"rotation_axes": [
{
"end": [
5.075788587517716,
-19.703911411612587,
43.02087201622288
],
"order": 2,
"start": [
15.341211412482291,
46.105775382200825,
36.76012063083596
]
},
{
"end": [
45.757420727162895,
7.532719800969255,
38.564316013903756
],
"order": 2,
"start": [
-25.340420727162883,
18.86914416961898,
41.21667663315508
]
},
{
"end": [
8.504532064190151,
10.300733369275356,
6.610501752352555
],
"order": 2,
"start": [
11.912467935809858,
16.101130601312878,
73.17049089470629
]
}
],
"clusters": [
{
"members": [
{
"asym_id": "A",
"pdbx_struct_oper_list_ids": [
"1"
]
},
{
"asym_id": "D",
"pdbx_struct_oper_list_ids": [
"1"
]
},
{
"asym_id": "C",
"pdbx_struct_oper_list_ids": [
"1"
]
},
{
"asym_id": "B",
"pdbx_struct_oper_list_ids": [
"1"
]
}
],
"avg_rmsd": 1.2388222275683525
}
]
}
],
"rcsb_struct_symmetry_lineage": [
{
"depth": 0,
"id": "Global Symmetry",
"name": "Global Symmetry"
},
{
"depth": 0,
"id": "Pseudo Symmetry",
"name": "Pseudo Symmetry"
},
{
"depth": 2,
"id": "Pseudo Symmetry.Dihedral.D2",
"name": "D2"
},
{
"depth": 2,
"id": "Global Symmetry.Cyclic.C2",
"name": "C2"
},
{
"depth": 1,
"id": "Global Symmetry.Cyclic",
"name": "Cyclic"
},
{
"depth": 3,
"id": "Pseudo Symmetry.Dihedral.D2.Homo 4-mer",
"name": "Homo 4-mer"
},
{
"depth": 1,
"id": "Pseudo Symmetry.Dihedral",
"name": "Dihedral"
},
{
"depth": 3,
"id": "Global Symmetry.Cyclic.C2.Hetero 4-mer",
"name": "Hetero 4-mer"
}
],
"rcsb_id": "4HHB-1",
"rcsb_struct_symmetry_provenance_code": "biojava-7.2.4"
}Attribution: Source: RCSB Protein Data Bank (RCSB.org), data released under CC0 1.0. Structure data deposited by the original authors; please also cite the PDB entry and its primary citation.
Licence: CC0 1.0 Universal Public Domain Dedication. The RCSB PDB Usage Policies page states: "The wwPDB policy states that data files contained in the PDB archive are available under the CC0 1.0 Universal (CC0 1.0) Public Domain Dedication. All data provided by RCSB PDB programmatic APIs are available under the same license. All data are presented at RCSB.org without any warranties about the work; RCSB PDB disclaims liability for all uses of the work, to the fullest extent permitted by applicable law. Users of PDB data are encouraged to attribute the original authors of the PDB structure data where possible." Commercial use and redistribution are therefore both permitted. Attribution is encouraged, not required, and we credit RCSB PDB anyway. Note the separate terms RCSB applies to things we do not serve: Molecule of the Month illustrations are CC BY 4.0, and the articles and other site text are copyrighted.
Ask with this source
A prompt for your agent that names this source and how to call it through the crw MCP.
Biological assembly
Use RCSB Protein Data Bank (rcsbpdb) from fastCRW Pergamon, capability "Biological assembly" (assembly). You need the biologically relevant oligomer rather than the asymmetric unit as deposited. Example options: entry_id=4HHB, assembly_id=1. Use the crw MCP tools: crw_find_data to confirm the source and its options, then crw_get_data with provider "rcsbpdb" and capability "assembly". Tell me the credits used and cite the licence from the response. If the crw MCP tools are missing, install them with: npx -y crw-mcp install --api-key <your fastCRW API key>
Oligosaccharide chain instance
Use RCSB Protein Data Bank (rcsbpdb) from fastCRW Pergamon, capability "Oligosaccharide chain instance" (branched-entity-instance). You want to know where a specific glycan chain attaches to the protein in a given structure. Example options: entry_id=5FMB, asym_id=C. Use the crw MCP tools: crw_find_data to confirm the source and its options, then crw_get_data with provider "rcsbpdb" and capability "branched-entity-instance". Tell me the credits used and cite the licence from the response. If the crw MCP tools are missing, install them with: npx -y crw-mcp install --api-key <your fastCRW API key>
Chemical component (ligand) definition
Use RCSB Protein Data Bank (rcsbpdb) from fastCRW Pergamon, capability "Chemical component (ligand) definition" (chemical-component). You have a 1-5 character ligand code from a structure and want the chemistry behind it. Example options: comp_id=HEM. Use the crw MCP tools: crw_find_data to confirm the source and its options, then crw_get_data with provider "rcsbpdb" and capability "chemical-component". Tell me the credits used and cite the licence from the response. If the crw MCP tools are missing, install them with: npx -y crw-mcp install --api-key <your fastCRW API key>
All current chemical component IDs
Use RCSB Protein Data Bank (rcsbpdb) from fastCRW Pergamon, capability "All current chemical component IDs" (current-ccd-ids). You want the full vocabulary of ligand codes before resolving any of them. Use the crw MCP tools: crw_find_data to confirm the source and its options, then crw_get_data with provider "rcsbpdb" and capability "current-ccd-ids". Tell me the credits used and cite the licence from the response. If the crw MCP tools are missing, install them with: npx -y crw-mcp install --api-key <your fastCRW API key>