PubChem Compound Lookup & Normalizer
Pricing
Pay per usage
PubChem Compound Lookup & Normalizer
Search and retrieve chemical compound data from PubChem (NIH). Returns normalized chemical properties (formula, MW, LogP, SMILES), categorized synonyms, and identifiers (CAS, UNII, InChIKey). No API key required - free open data from the US NIH.
Pricing
Pay per usage
Rating
0.0
(0)
Developer
Chris Wakefield
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
2 days ago
Last modified
Categories
Share

PubChem Compound Lookup & Normalizer
Search and retrieve chemical compound data from PubChem — the world's largest free chemical database, maintained by the US National Institutes of Health (NIH). Returns normalized chemical properties, categorized synonyms, and standard identifiers.
No API key required — free and open data from the NIH.
Why This Actor?
PubChem returns raw, complex data (atom-level structures, mixed-case names, catalog IDs). This Actor:
- Cleans — strips dosage info, suffixes, catalog numbers from names
- Normalizes — maps brand names (Ozempic → Semaglutide, Advil → Ibuprofen, Keytruda → Pembrolizumab) to generic names
- Categorizes — separates meaningful drug names from identifiers (CAS, UNII, ChEBI) and internal codes
- Standardizes — consistent camelCase property keys (molecularFormula, logP, smiles, etc.)
- Identifies — flags known drugs vs obscure compounds
Input Parameters
| Parameter | Type | Default | Description |
|---|---|---|---|
compoundNames | string[] | Aspirin, Ibuprofen, Paracetamol | One or more compound names or brand names to look up |
maxResults | integer | 5 | Maximum compounds returned per search query |
includeSynonyms | boolean | true | Include full synonym lists (names, identifiers, codes) |
includeProperties | select | standard | Property level: basic, standard, or all |
normalizeNames | boolean | true | Normalize brand→generic names and standardize formatting |
Example Input
{"compoundNames": ["Ozempic", "Keytruda", "Aspirin"],"maxResults": 3,"includeSynonyms": true,"includeProperties": "standard","normalizeNames": true}
Example Output (Dataset Record)
{"cid": 2244,"query": "Aspirin","properties": {"molecularFormula": "C9H8O4","molecularWeight": "180.16","smiles": "CC(=O)OC1=CC=CC=C1C(=O)O","inchikey": "BSYNRYMUTXBXSQ-UHFFFAOYSA-N","iupacName": "2-acetyloxybenzoic acid","logP": 1.2,"hBondDonors": 1,"hBondAcceptors": 4,"rotatableBonds": 3,"heavyAtomCount": 13},"normalizedName": "Aspirin","isKnownDrug": true,"synonyms": {"names": ["aspirin", "ACETYLSALICYLIC ACID", "2-Acetoxybenzoic acid", ...],"identifiers": ["50-78-2", "UNII-R16CO5Y76E", "CHEBI:15365", "DB00945"],"codes": ["NSC27223", "NCGC00015067-01", ...]}}
Use Cases
- Pharmaceutical R&D — drug property lookup and validation
- Drug Discovery — compound property screening
- Chemical Informatics — bulk compound data for ML/AI models
- Healthcare Analytics — drug identification and classification
- Regulatory Compliance — substance identification across global databases
- Education & Research — chemistry reference data for students and researchers
- Drug Repurposing — find compounds with similar properties to known drugs
Data Source
PubChem — an open chemistry database at the National Institutes of Health (NIH). Free, no API key required. Contains over 118 million compound substances with detailed chemical properties, synonyms, and 3D conformers.
License: PubChem data is available under the NIH/NLM license — free for commercial and non-commercial use.
Normalization Features
- 200+ brand→generic mappings (Ozempic→Semaglutide, Keytruda→Pembrolizumab, etc.)
- Dosage/suffix stripping (removes "mg", "tablet", "ER", "extended release", etc.)
- Identifier categorization (separates drug names from CAS, UNII, ChEBI, DrugBank codes)
- Abbreviation expansion (GLP-1→GLP-1 Receptor Agonist, SSRI→Selective Serotonin Reuptake Inhibitor)
- Known drug flagging — automatically marks compounds that match our drug database