Pdbe Search Tools#

Configuration File: pdbe_search_tools.json Tool Type: Local Tools Count: 3

This page contains all tools defined in the pdbe_search_tools.json configuration file.

Available Tools#

PDBeSearch_get_compound (Type: PDBeSearchTool)#

Get PDB ligand/compound information by compound ID from PDBe. Returns chemical name, formula, mol…

PDBeSearch_get_compound tool specification

Tool Information:

  • Name: PDBeSearch_get_compound

  • Type: PDBeSearchTool

  • Description: Get PDB ligand/compound information by compound ID from PDBe. Returns chemical name, formula, molecular weight, InChI, InChI key, SMILES, and systematic names. Useful for looking up small molecules that co-crystallize with proteins. Example: ‘ATP’ returns adenosine-5’-triphosphate (C10H16N5O13P3, MW 507.18); ‘HEM’ returns protoporphyrin IX containing iron.

Parameters:

  • compound_id (string) (required) PDB ligand/compound 3-letter code. Examples: ‘ATP’ (adenosine triphosphate), ‘HEM’ (heme), ‘NAG’ (N-acetyl-D-glucosamine), ‘FAD’ (flavin adenine dinucleotide).

Example Usage:

query = {
    "name": "PDBeSearch_get_compound",
    "arguments": {
        "compound_id": "example_value"
    }
}
result = tu.run(query)

PDBeSearch_search_by_organism (Type: PDBeSearchTool)#

Search PDBe Solr records filtered by organism, optionally combined with a keyword. Results are of…

PDBeSearch_search_by_organism tool specification

Tool Information:

  • Name: PDBeSearch_search_by_organism

  • Type: PDBeSearchTool

  • Description: Search PDBe Solr records filtered by organism, optionally combined with a keyword. Results are offset-paginated: pass metadata.next_start as start while metadata.has_more is true. PDBe’s total_found is an entity-level Solr count, so one PDB entry can occur in multiple records.

Parameters:

  • organism (string) (required) Scientific name of organism. Examples: ‘Homo sapiens’, ‘Escherichia coli’, ‘Mus musculus’, ‘Saccharomyces cerevisiae’.

  • query ([‘string’, ‘null’]) (optional) Optional keyword query to combine with organism filter. Examples: ‘kinase’, ‘receptor’. Default searches all structures for the organism.

  • limit ([‘integer’, ‘null’]) (optional) PDBe Solr records per page (1-10000, default 10), matching the verified upstream capability. Invalid values return an error rather than being silently clamped.

  • start (integer) (optional) Zero-based PDBe Solr record offset (default 0).

Example Usage:

query = {
    "name": "PDBeSearch_search_by_organism",
    "arguments": {
        "organism": "example_value"
    }
}
result = tu.run(query)

PDBeSearch_search_structures (Type: PDBeSearchTool)#

Search PDB structures through PDBe’s Solr search interface by keyword, protein name, or gene name…

PDBeSearch_search_structures tool specification

Tool Information:

  • Name: PDBeSearch_search_structures

  • Type: PDBeSearchTool

  • Description: Search PDB structures through PDBe’s Solr search interface by keyword, protein name, or gene name. Returns PDB IDs, titles, resolution, experimental methods, deposition dates, and organisms, sorted by relevance by default (best text match first, resolution as tie-breaker; sort_by=’resolution’ gives best-resolved first). PDBe’s index is entity-level, so one PDB entry can occur in many Solr documents: this tool deduplicates by pdb_id and applies offset after deduplication. Metadata distinguishes entity-level total_found from unique results, exposes next_offset, and reports whether max_rows_scanned prevented the requested unique page from being filled. Complements RCSB PDB tools with powerful full-text search. Example: searching ‘insulin’ returns 400+ structures; ‘BRCA1’ returns 148 structures including BRCT domains.

Parameters:

  • query (string) (required) Search query - protein name, gene name, or keyword. Supports Solr syntax. Examples: ‘insulin’, ‘BRCA1’, ‘kinase AND human’, ‘TP53’.

  • limit ([‘integer’, ‘null’]) (optional) Unique PDB entries per page (1-1000, default 10). Invalid values return an error rather than being silently clamped.

  • sort_by (string) (optional) Result ordering: ‘relevance’ (default) puts the best text match first with resolution as the tie-breaker; ‘resolution’ lists the best-resolved structures first, even if they only mention the query.

  • offset (integer) (optional) Zero-based offset after deduplication by pdb_id. Continue with metadata.next_offset while has_more is true.

  • max_rows_scanned (integer) (optional) Optional entity-level Solr scan budget used to fill the requested unique-PDB page. The dynamic default scales with offset+limit. If metadata.scan_limit_reached is true, increase this value and rerun the same offset.

Example Usage:

query = {
    "name": "PDBeSearch_search_structures",
    "arguments": {
        "query": "example_value"
    }
}
result = tu.run(query)