/gi-expression

name: gi-expression
description: Predict tissue / cell-type expression (log TPM + TPM) from a 9,198–500,000 bp TSS-centered DNA sequence (longer than one 9,198 bp window needs --tss-index) using the Genomic Intelligence G0 Expression model, via the hosted /v1/tasks/expression/predict
  API. The model is conditioned on a free-text cell-type / assay description.
license: MIT
metadata:
  openclaw:
    requires:
      bins:
      - python3
      env: null
      config: null
    always: false
    emoji: 🧪
    homepage: https://docs.genomicintelligence.ai
    os:
    - darwin
    - linux
    install:
    - kind: pip
      package: requests
      bins: null
    trigger_keywords:
    - expression prediction
    - predict expression
    - sequence to expression
    - TPM prediction
    - cell type expression
    - tissue expression
    - RNA-seq prediction
    - gi expression
    - G0 expression
    - genomic intelligence expression
  author: ClawBio + Genomic Intelligence
  demo_data:
  - path: example_data/expression_hbb_k562.fa
    description: HBB (β-globin) TSS-centered 9,198 bp window, reverse-complemented to gene-sense. K562 is the demo cell context — HBB is highly expressed in K562 erythroleukemia.
  dependencies:
    python: '>=3.10'
    packages:
    - requests>=2.31
  domain: genomics
  endpoints:
    cli: python skills/gi-expression/gi_expression.py --input {input_file} --output {output_dir}
  inputs:
  - name: input_file
    type: file
    format:
    - fa
    - fasta
    - fna
    description: Single-record FASTA, gene-sense (RC minus-strand genes). Either exactly 9,198 bp centered on the TSS, or 9,198–500,000 bp with --tss-index giving the 0-based TSS offset so the API cuts the window.
    required: false
  outputs:
  - name: report
    type: file
    format: md
    description: Markdown report — predicted log(TPM+1), TPM, model + timing.
  - name: result
    type: file
    format: json
    description: Full `{data, meta}` response.
  - name: reproducibility
    type: directory
    description: command.sh + environment.json.
  tags:
  - genomics
  - expression
  - RNA-seq
  - TPM
  - sequence-to-expression
  - dna-lm
  - gi-api
  version: 0.1.0

🧪 gi-expression

You are **gi-expression**, a ClawBio agent that calls the **Genomic Intelligence** sequence-to-expression model. Given a TSS-centered 9,198 bp window (or a longer locus plus `--tss-index`) and a cell-type description, it returns predicted expression (log TPM + TPM).

> ⚠️ **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](#authentication) below.

Trigger

**Fire this skill when the user says any of:**

• "predict expression for this gene / sequence"
• "what's the expression of this region in [cell type]?"
• "sequence-to-expression prediction"
• "TPM prediction", "log TPM prediction"
• "gi-expression", "G0 expression"

**Do NOT fire when:**

• The user has counts / RNA-seq output and wants differential expression → `rnaseq-de`
• The user wants tissue annotation / GTEx lookup → use external resources

Why This Exists

• **Without it**: Sequence-to-expression models (Enformer / Borzoi / G0 Expression) need GPU + private weights + careful 9-kbp windowing.
• **With it**: One CLI call → expression prediction conditioned on free-text cell-type description, in <1 s.
• **Why ClawBio**: Private weights, hosted. ClawBio's reproducibility bundle + chaining (`gi-promoter` → `gi-expression` → `rnaseq-de` interpretation).

API Backed

`POST https://api.genomicintelligence.ai/v1/tasks/expression/predict`. Omit `model` and the API resolves the default; `GET /v1/tasks/expression/models` is the current list.

> **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, gene-sense. Either exactly 9,198 bp TSS-centered, or 9,198–500,000 bp with `--tss-index`. Anything else is rejected locally before the request is sent. 2. **Build options**: `{"description": "assay term name is polyA plus RNA-seq. biosample summary is Homo sapiens K562."}` by default; override via `--description "..."`. 3. **POST** to `/v1/tasks/expression/predict`, which is its own operation with its own request schema — each of the six tasks has one, so there is no shared predict body. 4. **Render**: `report.md` (headline log TPM plus the scored window the API actually used) + `result.json` + `reproducibility/`.

CLI Reference

# Demo — HBB in K562
python skills/gi-expression/gi_expression.py --demo --output /tmp/gi-expression-demo

# Custom cell-type description
python skills/gi-expression/gi_expression.py \
  --input my_tss_window.fa \
  --description "assay term name is polyA plus RNA-seq. biosample summary is Homo sapiens liver." \
  --output report_dir

# Whole locus — the API cuts the 9,198 bp window around --tss-index
# (0-based offset into the sequence, counted after whitespace is stripped)
python skills/gi-expression/gi_expression.py \
  --input my_locus_50kb.fa --tss-index 24000 \
  --output report_dir

# Via ClawBio runner
python clawbio.py run gi-expression --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 rai