general-chemical-literature

Retrieve PubMed and patent cross-references for a chemical compound via PubChem CID.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires urllib.request, urllib.error, urllib.parse, json, argparse, pathlib, time, http.client, and includes scripts (resource) and assets (resource) components.

What problem does it solve?

Identifies whether a specific chemical compound is already covered by recent peer-reviewed literature or existing patents to support molecule novelty checks.

Core Features & Use Cases

  • PubChem CID cross-reference retrieval: Pulls PubMed IDs and patent numbers associated with a compound via PubChem PUG-REST XRefs.
  • Actionable verification output: Prints direct PubMed and Google Patents links for quick human review of top results.
  • Safety cap for ubiquitous molecules: Limits the saved result arrays (default 1000) to prevent oversized outputs for high-hit compounds like Aspirin.
  • Use Case: When evaluating a generated candidate molecule, fetch associated publication and patent identifiers to quickly gauge whether similar compounds have already been described or claimed.

Quick Start

Provide a PubChem CID and ask the skill to fetch and save its associated PubMed and patent cross-references.

Frequently Asked Questions about general-chemical-literature

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

FAQPage Schema
How do I find PubMed and patent records for a chemical compound using its PubChem CID?▼

To find PubMed and patent records for a chemical compound, retrieve its PubChem CID and query the PubChem PUG-REST XRefs JSON. This extracts PubMedID and PatentID lists to support literature and intellectual property novelty checks for drug discovery.

Can I check the novelty of a drug discovery candidate against existing patents and literature?▼

Yes, you can check the novelty of a drug discovery candidate by pulling PubMed IDs and patent numbers associated with the compound via PubChem PUG-REST. This identifies whether the molecule is already covered by peer-reviewed literature or existing patents.

How do I retrieve PubChem cross-references for molecule screening without getting oversized data outputs?▼

To retrieve PubChem cross-references for molecule screening without oversized data outputs, apply a safety cap to limit saved result arrays. The default limit caps saved records at 1000 to prevent oversized outputs for high-hit compounds like Aspirin.

What is the best way to get direct verification links for PubMed and Google Patents during candidate triage?▼

The best way to get direct verification links for PubMed and Google Patents during candidate triage is to extract cross-references and print structured output. This generates actionable direct links for quick human review of top literature and patent results.

Does PubChem PUG-REST support retrieving both PubMed IDs and patent numbers in one query?▼

Yes, PubChem PUG-REST supports retrieving both PubMed IDs and patent numbers in one query by requesting XRefs JSON. It extracts both PubMedID and PatentID lists simultaneously for a target chemical compound to support materials screening workflows.

Why are patent and literature cross-references capped at 1000 results for ubiquitous molecules?▼

Patent and literature cross-references are capped at 1000 results for ubiquitous molecules to prevent oversized outputs. High-hit compounds generate massive result arrays during data retrieval, so limiting saved results ensures the output remains manageable for novelty checks.