Render a KEGG pathway as ASCII text optimized for LLM consumption.

Two styles available:

• 'chain': Linear reaction flow text showing substrate->enzyme->product chains. Robust and compact. Best for understanding reaction sequences.

• 'grid': 2D spatial layout using KGML coordinates. Shows the pathway topology with box-and-arrow rendering. Best for seeing spatial relationships.

Args: pathway_id: KEGG pathway ID (e.g. 'hsa00010' for human glycolysis). Must be organism-specific; reference pathways (map*) have limited KGML. style: 'chain' (default, linear text) or 'grid' (2D spatial layout). max_width: Maximum line width in characters (40-200, default 100). max_height: Grid mode only: maximum height in lines (20-80, default 40).

Search KEGG BRITE functional hierarchy databases.

Args: query: Hierarchy name (e.g. 'KEGG pathway', 'transporter', 'ribosome'). max_results: Maximum number of results to return (capped at 100).

Get the structure of a KEGG BRITE functional hierarchy.

BRITE entries are large A/B/C/D trees, not flat-file entries, so the result is a bounded summary: the level line counts, the leaf column names, and the labels of the top two levels.

Args: brite_id: KEGG BRITE hierarchy ID. Any form KEGG hands out works — 'br:ko00001' (canonical), 'ko00001' / 'br08303' (as listed by list_databases), or the bare '00001' / '08303' returned by search_brite. detail_level: 'summary' (default) or 'full' (adds raw_content, the raw hierarchy text — TRUNCATED, since the largest hierarchies are several megabytes).

Search KEGG compounds by name or chemical property.

Args: query: Search term (compound name, formula, or mass). search_type: 'name' (default), 'formula', 'exact_mass', 'mol_weight', or 'nop'. max_results: Maximum number of results to return (capped at 100).

Get detailed information for a KEGG compound entry.

Args: compound_id: KEGG compound ID (e.g. 'C00002' for ATP, 'C00031' for D-Glucose). detail_level: 'summary' (default, compact) or 'full' (complete flat-file parse).

Get all reactions involving a KEGG compound.

Args: compound_id: KEGG compound ID (e.g. 'C00002').

Fetch multiple KEGG entries in bulk (max 50 IDs).

Automatically chunks requests into groups of 10 to respect KEGG's API limit.

Args: entry_ids: List of KEGG entry IDs (e.g. ['C00002', 'C00031', 'C00033']). Can mix databases. Max 50 entries.

Convert KEGG IDs to/from external database identifiers.

Converts within one kind only, KEGG side <-> outside side: genes (organism code 'hsa' or T-number 'T01001') <-> ncbi-geneid / ncbi-proteinid / uniprot; chemistry (compound / drug / glycan) <-> pubchem / chebi. Cross-kind pairs such as compound<->uniprot are rejected by KEGG, and 'kegg' is not a database conv accepts.

Args: source_db: Source database — 'hsa', 'T01001', 'ncbi-geneid', 'ncbi-proteinid', 'uniprot', 'compound', 'drug', 'glycan', 'pubchem' or 'chebi'. target_db: Target database, from the same list and the opposite side of the pair (e.g. source_db='hsa' + target_db='uniprot', or source_db='chebi' + target_db='compound'). entry_ids: Optional list of specific IDs to convert. Bare ids are prefixed with source_db automatically ('1956' -> 'hsa:1956'). KEGG accepts at most 10 per request; only the first 10 are sent. If None, converts the full source database (large: hsa <-> ncbi-geneid is ~700 KB).

Find related entries in another KEGG database for a given entry.

Args: entry_id: Source KEGG entry ID (e.g. 'hsa:1956', 'C00002', 'K00844'). target_db: Target database (e.g. 'pathway', 'disease', 'drug', 'ko', 'compound', 'reaction', 'module', 'genes').

Get release information and statistics for a KEGG database.

Args: database: Database name (e.g. 'kegg', 'pathway', 'compound', 'drug', 'genome').

List organisms available in KEGG with their 3-4 letter codes and names.

KEGG has ~12,000 organisms, so the full list is large. Pass query to filter by organism code or name (e.g. 'Bacillus', 'hsa') instead of paging through everything.

Args: query: Case-insensitive substring filter on the organism code or name. Empty (the default) returns the first max_results organisms. max_results: Maximum number of organisms to return (capped at 100).

Search KEGG diseases by name or keyword.

Args: query: Disease name (e.g. 'diabetes', 'cancer', 'Alzheimer'). max_results: Maximum number of results to return (capped at 100).

Get detailed information for a KEGG disease entry.

Args: disease_id: KEGG disease ID (e.g. 'H00004' for colorectal cancer). detail_level: 'summary' (default, compact) or 'full' (complete flat-file parse).

Search KEGG drugs by name, formula, or molecular weight.

Args: query: Drug name, formula, or mass value. search_type: 'name' (default), 'formula', 'exact_mass', or 'mol_weight'. max_results: Maximum number of results to return (capped at 100).

Get detailed information for a KEGG drug entry.

Args: drug_id: KEGG drug ID (e.g. 'D00001' for aspirin, 'D00564' for ibuprofen). detail_level: 'summary' (default, compact) or 'full' (complete flat-file parse).

Get drug-drug interactions for one or more KEGG drugs.

Args: drug_ids: Single drug ID (e.g. 'D00001') or multiple IDs joined with '+' (e.g. 'D00001+D00564'). Max 10 entries.

Search KEGG enzymes by EC number or name.

Args: query: EC number (e.g. '1.1.1.1') or enzyme name (e.g. 'kinase', 'oxidase'). max_results: Maximum number of results to return (capped at 100).

Get detailed information for a KEGG enzyme (EC number).

Args: enzyme_id: EC number (e.g. '1.1.1.1') or prefixed ID (e.g. 'ec:1.1.1.1'). detail_level: 'summary' (default, compact) or 'full' (complete flat-file parse).

Search for genes in a KEGG organism database.

Args: query: Search term (gene name, symbol, or description). organism_code: KEGG organism code (e.g. 'hsa' human, 'mmu' mouse, 'eco' E. coli). max_results: Maximum number of results to return (capped at 100).

Get detailed information for a KEGG gene entry.

Args: gene_id: KEGG gene ID in format 'organism:gene' (e.g. 'hsa:1956' for EGFR). detail_level: 'summary' (default, compact) or 'full' (complete parse with linked orthologs, pathways, xrefs, and references). include_sequence: If True and detail_level='full', fetches amino acid and nucleotide sequences.

Get KO (KEGG Orthology) entries and cross-organism orthologs for a gene.

Args: gene_id: KEGG gene ID (e.g. 'hsa:1956').

Search KEGG glycan database by keyword or composition.

Args: query: Glycan name or composition (e.g. 'GlcNAc', 'Man5', 'sialic acid'). max_results: Maximum number of results to return (capped at 100).

Get detailed information for a KEGG glycan entry.

Args: glycan_id: KEGG glycan ID (e.g. 'G00001'). detail_level: 'summary' (default, compact) or 'full' (complete flat-file parse).

Search KEGG modules by keyword.

Args: query: Module name or pathway block (e.g. 'glycolysis', 'TCA cycle'). max_results: Maximum number of results to return (capped at 100).

Get detailed information for a KEGG module.

Args: module_id: KEGG module ID (e.g. 'M00001' for glycolysis core module). detail_level: 'summary' (default, compact) or 'full' (complete flat-file parse).

Search KEGG Orthology (KO) entries by keyword.

Args: query: Gene function (e.g. 'hexokinase', 'ribosomal protein', 'cytochrome'). max_results: Maximum number of results to return (capped at 100).

Get detailed information for a KEGG Orthology (KO) entry.

Args: ko_id: KEGG KO identifier (e.g. 'K00844' for hexokinase). detail_level: 'summary' (default, compact) or 'full' (complete flat-file parse).

Search KEGG pathways by keyword.

Args: query: Search term (e.g. 'glycolysis', 'TCA', 'insulin signaling'). organism_code: 3-4 letter organism code (e.g. 'hsa' for human, 'mmu' for mouse). Use 'map' for reference pathways. max_results: Maximum number of results to return (capped at 100).

Get detailed information for a KEGG pathway.

Args: pathway_id: KEGG pathway ID (e.g. 'hsa00010', 'map00010'). detail_level: 'summary' (default, compact) or 'full' (complete flat-file parse with all linked genes, compounds, reactions, references, and xrefs).

Get all genes associated with a KEGG pathway.

Args: pathway_id: KEGG pathway ID (e.g. 'hsa00010'). Use organism-specific IDs (e.g. 'pae00350' for P. aeruginosa) — reference pathways ('map*') are not supported by the KEGG gene link API.

Get all compounds (metabolites) associated with a KEGG pathway.

Args: pathway_id: KEGG pathway ID (e.g. 'map00010').

Get all reactions in a KEGG pathway.

Args: pathway_id: KEGG pathway ID (e.g. 'hsa00010').

Search KEGG reactions by keyword.

Args: query: Search term (reaction name or description). max_results: Maximum number of results to return (capped at 100).

Get detailed information for a KEGG reaction.

Args: reaction_id: KEGG reaction ID (e.g. 'R00756' for glucose phosphorylation). detail_level: 'summary' (default, compact) or 'full' (complete flat-file parse).