CodeXomics¶

The AI-native genome browser

Talk to your genome — AI agents drive the view and run the analysis.

简体中文入口 · 中文产品介绍页

CodeXomics is an AI-native genome browser — a cross-platform Electron workspace where conversational AI agents drive the visualization and run real biological analyses, with plugin development, benchmark testing, and Model Context Protocol (MCP) integration.

This site documents the current source, version 0.723.0 (v0.723 display). See GitHub Releases for available installers and the changelog for changes since the release tag.

Install And Start¶

For a source checkout, use Node.js 22.12 or newer in the 22.x line and npm 10 or newer.

git clone https://github.com/Scilence2022/CodeXomics.git
cd CodeXomics
npm install
npm start

Load a genome with File → Load File → Genome File. To use the ChatBox, open Settings → Model Providers (⌘, / Ctrl+,), save a provider, and select a default model. Getting Started

Genome Visualization¶

• Browse FASTA and GenBank genomes with annotations, variants, SAM/BAM alignments, and WIG/BigWig tracks. Supported inputs
• Queue sequence edits and export a separate GenBank file. Sequence editing

AI-Assisted Analysis¶

• Ask the ChatBox to navigate, search, design primers, run BLAST, or simulate restriction digest and gel electrophoresis. User Guide
• Track Deep Gene Research in the ChatBox and review evidence-backed annotation ChangeSets in the Review Center. Deep Gene Research
• Run automatic benchmarks in production-parity or oracle-assisted mode. Benchmark Methods

Extensibility¶

• Build plugins with the VS Code-inspired extension host and Plugin API 2.0.0.
• Expose plugin functions to AI tool calling.
• Serve and test marketplace plugins through packages/marketplace-server/.

MCP Integration¶

• Start Electron with the authenticated MCP listener to give clients access to genome windows. Use tools mode for direct calls or agent mode to delegate natural-language prompts to the ChatBox. MCP Server Guide

Screenshots¶

Genome browser¶

Feature track, GC content and skew, multi-track WIG data, the gene details sidebar, and the protein/sequence view.

Read alignment and references¶

Coverage and base-resolution sequencing-read tracks alongside gene references and operons in the side panel.

Base-level read pileup over a selected gene:

Protein structures¶

AlphaFold structure lookup and an interactive 3D protein viewer, driven from the AI ChatBox.

Primer design¶

Designed primers rendered directly on the sequence view.

Documentation Map¶

Repository Links¶

• GitHub Repository
• Issues
• Discussions
• Releases