drug-db-pubchem

Retrieve PubChem compound identifiers and metadata via PUG-REST queries.

144|21|Updated Jan 8, 2026
One-click install
npx skills add https://github.com/learningmatter-mit/AtomisticSkills --skill drug-db-pubchem
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: drug-db-pubchem
Source: https://github.com/learningmatter-mit/AtomisticSkills/tree/main/.agents/skills/drug-db-pubchem
Command: npx skills add https://github.com/learningmatter-mit/AtomisticSkills --skill drug-db-pubchem

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill removes manual lookups by automating PubChem Compound queries to retrieve standardized identifiers, computed properties, and optional structure files for downstream drug-discovery or cheminformatics workflows.

Core Features & Use Cases

  • Multi-modal compound search: Find PubChem CIDs by name, SMILES, InChI, InChIKey, CID, or molecular formula.
  • Property retrieval for automation: Pull key computed properties (e.g., molecular weight, XLogP, TPSA, HBD/HBA, rotatable bonds, canonical/isomeric SMILES, InChI/InChIKey, IUPAC name) in a reproducible JSON output.
  • Optional enrichment: Retrieve a limited set of synonyms and optionally download 2D/3D SDF structures with 3D-to-2D fallback when available.
  • Rate-limited, retry-aware querying: Uses adaptive rate limiting and exponential backoff to handle PubChem throttling (503) safely for batch/agent use.

Quick Start

Query PubChem for aspirin by name (exact match) and write the results to a JSON file: python .agents/skills/drug-db-pubchem/scripts/query_pubchem.py --name "aspirin" --name_type complete --max_results 5 --outdir research/pubchem/aspirin --output aspirin.json

Frequently Asked Questions about drug-db-pubchem

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

FAQPage Schema
How do I retrieve PubChem compound data in bulk for cheminformatics workflows?

To retrieve PubChem compound data in bulk, you can automate PUG-REST queries by compound name, SMILES, InChI, or CID to fetch standardized identifiers and computed properties. The process outputs structured JSON artifacts suitable for reproducible downstream processing.

Can I download 2D and 3D SDF structures from PubChem using SMILES or InChIKey?

Yes, you can download 2D and 3D SDF structures from PubChem using SMILES or InChIKey. The query process optionally enriches outputs by retrieving SDF structures and includes a 3D-to-2D fallback mechanism when 3D structures are unavailable.

What computed properties can I pull from PubChem for drug discovery automation?

For drug discovery automation, you can pull computed properties including molecular weight, XLogP, TPSA, HBD/HBA, rotatable bonds, canonical SMILES, InChI, InChIKey, and IUPAC name. These are extracted into a reproducible JSON output for downstream analysis.

How do I handle PubChem PUG-REST throttling and 503 errors during batch compound lookups?

To handle PubChem PUG-REST throttling and 503 errors during batch compound lookups, implement adaptive rate limiting with exponential backoff and retry logic. This ensures safe, automated batch querying without exceeding server limits.

Does PubChem compound search support molecular formula and synonym enrichment?

Yes, PubChem compound search supports molecular formula queries and synonym enrichment. You can look up compounds by molecular formula and optionally enrich the structured JSON output with a limited set of associated synonyms.