AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

Genomic Intelligence — DNA Sequence Models

Give it a gene symbol, genomic region, or FASTA and it calls hosted DNA language models to predict promoters, splice sites, enhancer activity, chromatin state, expression, and gene annotations.

Data & AnalyticsIntermediate★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

  • Calls Genomic Intelligence's hosted transformer DNA language models for six tasks: promoter regions, splice donor/acceptor sites, enhancer activity (developmental + housekeeping), chromatin state across hundreds of tracks, sequence-to-expression as log(TPM+1), and de-novo gene/transcript annotation.
  • No local GPU or model weights: use plain REST (api.genomicintelligence.ai/v1, needs a gi_ bearer key) or the hosted MCP server (mcp.genomicintelligence.ai/mcp, keyless public demo quota).
  • On MCP hosts, sequences are passed as sequence_ref handles so long DNA never bloats the conversation context.
  • Encodes the hard rules: ≤500,000 bp per task, expression requires exactly 9,198 bp centred on the TSS plus a cell-type description, annotation is submit-and-poll async, and models should be discovered via list_models rather than hardcoded. Includes a 400/401/413/422/429 error playbook.

Who it's for

  • Regulatory-genomics researchers, grad students, and bioinformatics engineers.
  • Anyone who wants sequence-model predictions without standing up a deep-learning stack.
  • Teams wiring genomics inference into Claude via MCP.

Example uses

  1. "Find promoters around TP53" → fetch the Ensembl region, run predict_promoter, print the summary.
  2. "Predict HBB expression in K562 cells" → build the TSS-centred 9,198 bp window automatically and call expression with description="K562 cells".
  3. "Which genes are in chr11:5,225,000-5,235,000 and how are they expressed?" → fetch_region, then the composite find_genes_and_predict_expression.

Research and development use only — not for clinical or diagnostic decisions.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/genomic-intelligence/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the skills/genomic-intelligence folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/genomic-intelligence/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/genomic-intelligence ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal (on Windows, use WSL or Git Bash).
  2. Clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Copy the skill into Claude's skills folder: mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/genomic-intelligence ~/.claude/skills/
  4. Make sure you have Python 3.10+ and the HTTP client: pip install requests python-dotenv
  5. For the REST path, export your key: export GI_API_KEY="gi_yourkeyhere" (request one at contact@genomicintelligence.ai). Skip this if you only want the keyless MCP demo.
  6. For the MCP path, add the MCP server https://mcp.genomicintelligence.ai/mcp (Streamable HTTP) in your Claude MCP configuration.
  7. Restart Claude Code and try: "Predict promoters for TP53." For a keyless smoke test, ask it to use load_demo_sequence(name=...).
View source on GitHub ↗License: MIT