Resolve a molecule
to its exact identity.
A chemical name is ambiguous; a structure is not. pubchem_compound turns a name into an exact identity — CID, molecular formula, weight, canonical SMILES and InChIKey — pinned to PubChem. An agent works with the real molecule, not a plausible-looking string a model wrote.
What the instrument does
PubChem (NCBI) is the largest open chemistry database — compounds with computed and curated properties: formula, molecular weight, SMILES, InChIKey, XLogP and more, each under a stable CID.
On the console, pubchem_compound resolves a name to its record and pubchem_compound_by_cid fetches one by CID — the canonical identity every downstream chemistry step keys on.
Tools this powers on the console
pubchem_compound · pubchem_compound_by_cid
Research use only. Service names belong to their owners; no partnership or endorsement is implied.
How Perslis integrates PubChem
SMILES strings are exactly where a language model's confidence outruns its correctness — a plausible-looking structure can be subtly wrong. PubChem replaces generation with resolution: ask for aspirin and the console returns CID 2244 with the real InChIKey, not a string a model assembled. The identity is looked up, never invented.
That verified identity is the key for the chemistry bench: the same compound resolves into ChEMBL for measured bioactivity and into KEGG and Reactome for the pathways it acts on — one molecule, correctly identified, across four databases.
Ask
One question at the console — no per-service query language, no tab-hopping.
Route
Lois calls this instrument alongside the others and gathers what returns.
Pin
Every field keeps its source: database, accession, URL. A result that cannot name its source is refused by construction.
Admit
The PEEL gate decides what enters the lab record. Reported values stay verbatim; unsupported claims stay out.
A real, source-pinned result
Pulled live from the service and pinned to its identifier — the same contract every answer on the console is held to.
| CID | 2244 |
|---|---|
| Molecular formula | C9H8O4 |
| Molecular weight | 180.16 |
| IUPAC name | 2-acetyloxybenzoic acid |
| Canonical SMILES | CC(=O)OC1=CC=CC=C1C(=O)O |
| InChIKey | BSYNRYMUTXBXSQ-UHFFFAOYSA-N |
Source: pubchem · CID 2244 · retrieved 2026-09-18
Why route PubChem through one console
Exact identity, callable
An agent gets a real CID, SMILES and InChIKey — no hand-written structure to be subtly wrong.
The key for chemistry
The same compound resolves into ChEMBL, KEGG and Reactome — one molecule across four databases.
Looked up, never invented
Structure is resolved from PubChem, so a SMILES on the console is the real one, pinned to CID.
Instruments PubChem talks to
Identity is the start of a chemistry question. PubChem hands off to bioactivity and pathways.
