pubchem-database

Query PubChem by name, CID, or SMILES to retrieve compound properties and search results.

Updated Jan 15, 2026
One-click install
npx skills add https://github.com/KaiserWhoLearns/skillsbench --skill pubchem-database-kaiserwholearns
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pubchem-database
Source: https://github.com/KaiserWhoLearns/skillsbench/tree/main/tasks/find-topk-similiar-chemicals/environment/skills/pubchem-database
Command: npx skills add https://github.com/KaiserWhoLearns/skillsbench --skill pubchem-database-kaiserwholearns

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pubchempy, requests, and includes scripts (resource) and references (resource) components.

What problem does it solve?

PubChem data access and retrieval is essential for cheminformatics workflows but requires coding against the API. This Skill provides ready-made scripts to search compounds by name, CID, or SMILES, retrieve properties, and explore bioactivity data with rate-limited requests.

Core Features & Use Cases

  • Compound discovery & lookup: search by name, CID, SMILES, InChI, or molecular formula.
  • Property retrieval: fetch key identifiers and properties like MW, formula, canonical SMILES, XLogP, TPSA, and hydrogen-bond counts.
  • Search capabilities: perform similarity and substructure searches, plus batch queries for multiple compounds.
  • Bioactivity & annotations: access assay summaries and PUG-View sections for deeper insights, including drug information when available.
  • Use-case scenario: screen a list of candidate drugs for drug-likeness and gather comparative properties quickly.

Quick Start

Fetch properties for aspirin and display key identifiers and molecular weight.

Frequently Asked Questions about pubchem-database

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I retrieve compound properties from PubChem using SMILES or CID in batch?

Batch property retrieval from PubChem is performed by passing CIDs or SMILES to rate-limited API scripts that fetch molecular weight, XLogP, TPSA, and canonical SMILES, aggregating results for multiple compounds.

Can I perform similarity and substructure searches on PubChem compounds programmatically?

Similarity and substructure searches are supported by querying PubChem with SMILES or InChI strings to identify structurally related compounds and retrieve their bioactivity data and annotations.

How do I access PubChem bioactivity data and assay summaries for drug discovery workflows?

PubChem bioactivity data and assay summaries are accessed via PUG-View sections and API endpoints, allowing retrieval of drug information and annotation data for cheminformatics analysis.

Does PubChem batch processing handle rate-limiting and error handling for large compound lists?

Batch processing scripts implement rate-limiting and error handling to manage API requests across large compound lists, ensuring stable data aggregation when querying PubChem at scale.

What molecular identifiers and properties can I fetch from PubChem for cheminformatics workflows?

Cheminformatics workflows can fetch key identifiers and properties including molecular weight, formula, canonical SMILES, XLogP, TPSA, and hydrogen-bond counts by querying PubChem with name, CID, or InChI.

What is the best way to screen candidate drugs for drug-likeness using PubChem data?

Screening candidate drugs for drug-likeness involves batch querying PubChem to retrieve comparative properties like XLogP, TPSA, and molecular weight, enabling rapid evaluation of drug-likeness across a compound list.