Gi Annotation

📜 gi-annotation

You are gi-annotation, a ClawBio agent that calls the Genomic Intelligence DNA annotation pipeline. Given a genomic region, it predicts gene boundaries → intervals → transcripts, all from sequence alone (no external annotation database).

⚠️ Remote inference — opt-in required. Unlike most ClawBio skills, this skill uploads your FASTA sequence to the hosted Genomic Intelligence API at https://api.genomicintelligence.ai. The same models also run interactively at https://genomicintelligence.ai. Do not submit identifiable patient data without an appropriate data-use agreement. Key setup: see Authentication below.

Trigger

Fire this skill when the user says any of:

• "annotate this DNA sequence"
• "predict genes / transcripts in this region"
• "what genes are encoded here?" (from sequence, not coordinates)
• "de novo gene prediction"
• "gi-annotation"

Do NOT fire when:

• The user has a VCF and wants variant consequences → variant-annotation (VEP)
• The user wants known gene records by coordinate → external NCBI / Ensembl lookup

Why This Exists

• Without it: Running AUGUSTUS / Helixer locally requires species models + dependency setup.
• With it: One CLI call → predicted transcript structures, in ~20 s for ~20 kbp.
• Why ClawBio: Hosted private weights (ModernBERT-based) plus ClawBio's reproducibility bundle and progress streaming for long jobs.

API Backed

POST https://api.genomicintelligence.ai/v1/tasks/annotation/predict with Prefer: respond-async. The API accepts either delivery mode on every task; this skill always submits async because the pipeline is long-running. The pipeline streams progress through GET /v1/tasks/jobs/{job_id} (typically: load → gene-boundaries → gene-intervals → transcripts).

Contract note. The Genomic Intelligence API publishes one operation per task, each with its own request schema: per-task minLength/maxLength on sequence, and a typed, closed options object (an unknown option key is a 422 validation_failed, not a silent ignore). The bounds quoted in this file are the published ones, but the authority is always the served schema: GET https://api.genomicintelligence.ai/v1/openapi.json.

Workflow

1. Parse: single-record FASTA.
2. Submit async: POST /v1/tasks/annotation/predict with Prefer: respond-async → 202 + job_id.
3. Poll: stream progress (percent, message) until terminal.
4. Render: report.md (transcripts table) + result.json (full response) + reproducibility/.

CLI Reference

# Demo — bundled TP53 region (~20 s)
python skills/gi-annotation/gi_annotation.py --demo --output /tmp/gi-annotation-demo

# Your own FASTA
python skills/gi-annotation/gi_annotation.py --input my_region.fa --output report_dir

# Via ClawBio runner
python clawbio.py run gi-annotation --demo

Authentication

The skill requires a Genomic Intelligence partner key in GI_API_KEY. Resolution order:

1. --api-key <value> CLI flag (explicit override).
2. GI_API_KEY environment variable.
3. Otherwise: the skill raises a RuntimeError pointing here.

Quick start — ClawBio hackathon key

A shared hackathon-tier key ships in .env.example at the repo root (opt-in only). Caps are per-key and are not published as a fixed number — read RateLimit-Limit / RateLimit-Remaining on any /v1/tasks/ response for the live allowance. The runner keeps them for you: they are in result.json under rate_limit, and a 429 names them on the error line. From wherever the ClawBio files live on your machine:

# Repo root (git clone) — or ~/.claude/plugins/cache/clawbio/clawbio/<version>/ for plugin installs
cp .env.example .env
set -a && source .env && set +a

Production / heavier use

Request an individual key at contact@genomicintelligence.ai, then:

export GI_API_KEY=gi_yourkeyhere