Skip to content

GeneScope

The Gene Program Interpreter is a Claude Skill for context-aware interpretation of gene programs from Perturb-seq and single-cell data.

Code Video Cerebral Valley

Core trick

One literature agent per gene program searches via MCP, and a deterministic verifier confirms every cited paper resolves before annotations enter the report.

Tags

scienceagents

Description

The Gene Program Interpreter is a Claude Skill for context-aware interpretation of gene programs from Perturb-seq and single-cell data. Every experiment yields dozens of programs, and today interpreting one takes days of manual literature review — while enrichment tools give generic labels and LLM-only tools sound plausible without being grounded in the specific biological context. GPI injects that context — cell type, tissue, conditions, and, for Perturb-seq, the supporting regulators, perturbation effects, gene weights, and direction — throughout the workflow, so each program is read as a context-specific regulatory response rather than a generic gene list. It combines deterministic database evidence (enrichment, interactions), one Claude Agent SDK literature agent per program searching over MCP, a deterministic verifier that confirms every citation resolves to a real paper, and Anthropic Batch-API annotation — into an auditable, interactive HTML report. Across recent runs it interprets a program for about half a dollar and a few minutes of autonomous research, with every verified citation that you can read directly. Packaging it as a Skill makes the workflow plug-and-play and agent-native. Any scientist could use their Claude to refine context interactively on their own data, and generate publication-ready resource page.
ifanirene/gene-program-interpreter★ 00 forksPythonApache-2.0Created Jul 13, 2026 · last push Oct 4, 2026

README excerpt

<h1 align="center">Gene Program Interpreter (GPI)</h1>

<p align="center">
  <img src="docs/images/gpi-logo-banner.png" alt="Gene Program Interpreter logo" width="420">
</p>

<p align="center">
  <strong>Turn weighted gene programs into biological interpretations with traceable literature evidence.</strong>
</p>

<p align="center">
  <a href="https://www.youtube.com/watch?v=51G7lQjjJHc"><strong>▶ Watch the demo</strong></a>
  &nbsp;·&nbsp;
  <a href="https://ifanirene.github.io/gene-program-interpreter/brain_ec_demo/report.html"><strong>Explore a live report</strong></a>
  &nbsp;·&nbsp;
  <a href="https://ifanirene.github.io/gene-program-interpreter/"><strong>View the pipeline</strong></a>
</p>

GPI interprets gene programs from cNMF, NMF, single-cell, or Perturb-seq data. It runs
parallel Claude literature research, checks every PMID/DOI, and produces an interactive HTML
report; unresolved citations stay labeled. A verified identifier shows that a paper exists,
not that it supports the claim — that still requires reading the evidence. Organism, tissue,
cell type, and conditions live in a small context profile, so the biology is tissue-agnostic.

> **GPI is a Claude Code plugin.** Claude checks your data, builds the biological context,
> previews the cost, runs the pipeline, and walks you through the report. A
> [standalone CLI](#standalone-cli) is available for scripted workflows.

## What you get

A self-contained `report.html`. Each program gets a plain-language title, mar

Team