UniBind TF Binding Sites (Claude Skill)
Query UniBind for experimentally validated, ChIP-seq-derived transcription-factor binding sites and download their coordinates for local analysis.
| Type | Claude Skill |
| Supplier | Google DeepMind |
| Availability | GA |
| Pricing | Free / OSS skill (Apache-2.0 code, CC-BY-4.0 docs); UniBind API is public, no key |
| Capabilities | Read-only — Claude runs the skill’s Python locally (uv run) against the UniBind REST API |
| Verified | degraded · 2026-07-29 — dir resolves; prior-run fix of a stale scienceskillscommon copy line stands |
| Security | cleared · 2026-07-29 — provenance matches google-deepmind, Apache-2.0, maintained, keyless public API, no OSV advisories |
How to install
The google-deepmind/science-skills collection follows the Agent Skills SKILL.md spec. The repo’s primary npx skills add path targets Gemini/Antigravity; for Claude the followable path is a manual copy of the skill directory.
- Claude Code / Claude Desktop — clone and copy the skill into your skills directory:
git clone https://github.com/google-deepmind/science-skills cp -r science-skills/skills/unibind_database ~/.claude/skills/ cp -r science-skills/skills/uv ~/.claude/skills/(The
SKILL.mdrequires the bundleduvskill for its setup — copy it too.) - Prerequisite — the skill runs its Python helpers via
uv run; installuvfirst if absent:curl -LsSf https://astral.sh/uv/install.sh | sh.jqis recommended for parsing large JSON responses. Python deps install into an isolated environment on first run.
What it does
Wraps the UniBind REST API — a curated repository of direct TF–DNA interactions across 9 species, integrating ChIP-seq peaks with JASPAR profiles via the DAMO framework:
- List species, collections, cell lines, and transcription factors
- Filter/retrieve datasets by organism, TF name, cell line, or data source
- Download binding-site coordinates in BED or FASTA
- Retrieve dataset metadata
It is for dataset discovery and bulk coordinate download, not for querying specific intervals, genes, or motif models.
Primary use cases: retrieving validated TF binding-site sets, downstream peak/enrichment analysis, building TF-regulation datasets.
Notes
Claude Science: This resource is offered inside Anthropic’s Claude Science via the Regulation featured connector. Its inclusion there is an independent signal of quality and trustworthiness for life-science research.
No API key required, but users must review the UniBind terms at unibind.uio.no before use. Complements the catalogued JASPAR skill (jaspar-database.md), which provides the motif models UniBind integrates. The npx skills add google-deepmind/science-skills/ command documented upstream is oriented at Gemini/Antigravity (it writes to ~/.gemini/config/skills/); for Claude, the manual copy into ~/.claude/skills/ shown above is the equivalent path.
Sources
Installed this tool?
Share feedback — install path, OS, errors, workarounds. The form opens with this tool pre-selected and a link back to this page.