Pubchem Database logo

Pubchem Database

OrganizationPopular
google-deepmind
pubchem-database

Query PubChem, search by name/CID/SMILES, retrieve properties, similarity/substructure searches, bioactivity, for cheminformatics. Use when a user asks about a specific chemical, drug, or molecule.

Overview

Publishergoogle-deepmind
Repositoryscience-skills
Skill namepubchem-database
Stars
3.1K
Forks
349
Bundled files
4
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by google-deepmind on GitHub. Read the source before you install it.

Installation

Install the Pubchem Database AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/google-deepmind/science-skills.git /tmp/science-skills
mkdir -p .claude/skills
cp -r /tmp/science-skills/skills/pubchem_database .claude/skills/pubchem-database
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pubchem Database in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Pubchem Database on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Pubchem Database is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

PubChem Database

Prerequisites

  1. uv: Read the uv skill and follow its Setup instructions to ensure uv is installed and on PATH.
  2. User Notification: If .licenses/pubchem_database_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://pubchem.ncbi.nlm.nih.gov/docs/citation-guidelines and https://pubchem.ncbi.nlm.nih.gov/docs/pug-rest, then (2) create the file recording the notification text and timestamp.

Quick Start

PubChem queries are executed via a robust Python wrapper script to respect terms-of-service and handle complex JSON parsing. This script allows safe multi-agent use of APIs.

Example: Resolve a chemical name to its Compound ID (CID)

bash
uv run scripts/pubchem_api.py resolve --name "aspirin" --output result.json

Core Rules

  • Use the Wrapper: ALWAYS execute the provided helper scripts to query the database rather than accessing the database directly. The scripts automatically enforce the required rate limit gracefully.
  • Read the generated JSON output file, and process it with jq or code.
  • Verify Facts: ALWAYS verify information retrieved from memory with a database query if the user asks for a specific fact that can be checked in PubChem. Do not rely solely on internal knowledge.
  • Notification: If this skill is used, ensure this is mentioned in the output.

Core Capabilities

1. Compound Resolution (Name or InChI to Identifiers) Convert chemical/trade names or InChI strings into PubChem CIDs, SMILES, and InChIKeys.

bash
uv run scripts/pubchem_api.py resolve --name "ibuprofen" --output result.json
# OR
uv run scripts/pubchem_api.py resolve --inchi "InChI=1S/C3/c1-3-2/i1+1" --output result.json

2. Physical & Chemical Property Retrieval Fetch computed properties (e.g., MolecularWeight, XLogP, TPSA).

bash
uv run scripts/pubchem_api.py properties --cid 2244 --output result.json

3. Synonyms and Trade Names Find alternative names and brand names.

bash
uv run scripts/pubchem_api.py synonyms --cid 2244 --output result.json

Advanced Context

4. Safety and Hazard Information (GHS) Retrieve Global Harmonized System hazard statements and handling precautions (uses PUG-View).

bash
uv run scripts/pubchem_api.py safety --cid 2244 --output result.json

5. Drug and Medication Information Fetch FDA pharmacology data, mechanism of action, and therapeutic uses (uses PUG-View).

bash
uv run scripts/pubchem_api.py pharmacology --cid 2244 --output result.json

6. Custom Heading (PUG-View) Retrieve any specific heading from the PUG-View system (e.g., 'Geometry', 'Crystal Structures').

bash
uv run scripts/pubchem_api.py view --cid 3939 --heading "Crystal Structures" --output result.json

7. Image Generation Retrieve 2D chemical structure images. The script returns a Markdown-formatted image link.

bash
uv run scripts/pubchem_api.py image --cid 2244 --output result.json

Complex Search & Biology

8. Structure-Based Searching (Similarity & Substructure) Find molecules similar to a SMILES string or containing a specific substructure.

bash
uv run scripts/pubchem_api.py similarity --smiles "CC(=O)OC1=CC=CC=C1C(=O)O" --output result.json

and

bash
uv run scripts/pubchem_api.py substructure --smiles "C1=CC=CC=C1" --output result.json

9. BioAssay & Target Interactions Identify genes or proteins a chemical interacts with.

bash
uv run scripts/pubchem_api.py assays --cid 2244 --output result.json

Advanced Usage & Workflows

10. Cross-references (Xrefs) Fetch identifiers cross-referenced with a CID (e.g., PatentID, PubMedID).

bash
uv run scripts/pubchem_api.py xrefs --cid 2244 --type "PatentID" --output result.json

11. Property Range Search Find CIDs within a specific property range. Supported features include: molecular_weight, heavy_atom_count, xlogp, tpsa, h_bond_donor_count, h_bond_acceptor_count, rotatable_bond_count, exact_mass, monoisotopic_mass, and complexity.

bash
uv run scripts/pubchem_api.py range --feature molecular_weight --min 400.0 --max 400.05 --output result.json

12. Custom PUG-REST Query Execute a raw path against the PUG-REST API.

bash
uv run scripts/pubchem_api.py query --path "compound/cid/2244/xrefs/PatentID/JSON" --output result.json

Fallback Search Strategies

If direct resolution by name or formula fails (e.g., for complex compounds or specific ions):

  • Search for parent/neutral molecule: If searching for an ion or salt, try searching for the neutral parent compound.
  • Deconstruct complex formulas: If a complex formula returns no results, try searching for major components or ligands.
  • Use substructure or similarity search: If you have a SMILES string or can generate one for a component, use it to find related compounds.

Complex Queries and Multi-Step Tasks

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Pubchem Database AI skill do?

Query PubChem, search by name/CID/SMILES, retrieve properties, similarity/substructure searches, bioactivity, for cheminformatics. Use when a user asks about a specific chemical, drug, or molecule.

Why use Pubchem Database on TypingMind?

Because you install it once and use it with any model. Pubchem Database is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Pubchem Database in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/google-deepmind/science-skills/tree/main/skills/pubchem_database. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Pubchem Database?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Pubchem Database?

As many as you like. As long as a model supports skills, you can use Pubchem Database with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Pubchem Database AI skill free?

Yes. It is published on GitHub by google-deepmind under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇