Skip to content

Repository files navigation

logo

Build macOS DMG Build Windows installer Build Linux AppImage

InterAGt: An interactive interface for predicting genetic variant effects using AlphaGenome

About

InterAGt provides an intuitive way to visualize and interpret the functional impact of genetic variants using AlphaGenome, Google DeepMind's state-of-the-art model for predicting regulatory effects from DNA sequences.

Supported input formats:

  • HGVS notation (e.g., NC_000001.11:g.169549811C>T)
  • SNP IDs (rsIDs) (e.g., rs1234567)
  • Genomic coordinates (e.g., chr1:169549811:C:T)

AlphaGenome analyzes sequences up to 1 million base pairs and predicts 11 types of genomic tracks (e.g., gene expression, chromatin accessibility, splicing) across thousands of tissue and cell-type contexts.

By inputting a variant, researchers can:

  • Compare reference vs. alternative allele tracks for any variant
  • Analyze impacts on RNA-seq, ATAC, ChIP-seq, splicing, and more
  • Select from ontology-annotated tissues/cell types (e.g., UBERON:0002048 for lung)
  • No coding required: Access cutting-edge predictions through a user-friendly interface

References

  • Žiga Avsec, Natasha Latysheva, Jun Cheng, et al. Advancing regulatory variant effect prediction with AlphaGenome. Nature, 649(8099):1206–1218, 2026. DOI:10.1038/s41586-025-10014-0

For more details, see the AlphaGenome Documentation

Quick start

Windows

  • Download latest Windows release here
  • Double click InterAGt-Setup.exe
  • Follow the steps and click Install
  • Click Finish with Launch InterAGt ticked on
  • Windows Defender Firewall may warn and block app components, click Allow access
  • InterAGT will now run, next time you can start it directly via shortcut or install folder.

macOS

  • Download latest macOS release
    • If you have an M1 or better, download the arm64 version
    • If you have an older Intel based Mac, download the x86_64 version
  • Double click to open InterAGt-arm64.dmg (or InterAGt-x86_64.dmg)
  • In the popup window, drag InterAGT.app into Applications
  • Find InterAGt.app in Applications and double click to open
  • You will probably get the following warning:
InterAGt.app” Not Opened  
Apple could not verify “InterAGt.app” is free of malware that may harm your Mac or compromise your privacy.
  • Click Done
  • Go to your System Settings and then to Privacy & Security
  • Scroll down to where it says InterAGt.app was blocked to protect your Mac, click Open Anyway and again Open Anyway in the popup
  • Use your admin password or Touch ID to continue
  • InterAGT will now run, next time you can start it from Applications directly.

Linux (Ubuntu)

  • Download latest Ubuntu Linux release
    • If you have an x86_64 processor, download the x86_64 version
    • For arm processors, download the arm64 version
  • Double click to open the InterAGt-x86_64.AppImage (or InterAGt-aarch64.AppImage)
  • Note that you might need to add execution permission for the AppImage. This is done either by Properties -> Permissions -> Allow executing file as program or using the commandline:(sudo) chmod + x InterAGt-x86_64.AppImage (or InterAGt-aarch64.AppImage)
  • InterAGT will now run.

Full setup & installation instructions

Option 1: Pre-built Binaries

The easiest way to get started is to use one of the pre-compiled executables. No Python, Bun, or additional dependencies are required.

Pre-compiled binaries for Windows, macOS (arm64 and Intel), and Linux (x86_64 and arm64) are built by GitHub Actions and published two ways:

  • Releases: each published GitHub Release has InterAGt-Setup.exe, InterAGt-arm64.dmg, InterAGt-x86_64.dmg, InterAGt-x86_64.AppImage, and InterAGt-aarch64.AppImage attached — this is the recommended download location.
  • Manual builds: any workflow can also be triggered on demand from the Actions tab (Run workflow), producing artifacts downloadable from that run for 90 days without needing a release.

After downloading:

Extract the archive (macOS: mount the DMG; Windows: run the installer; Linux: chmod +x InterAGt-*.AppImage and run it). Launch the executable and the app will open in its own window (backed by http://localhost:8000).

Linux notes:

  • The AppImage is self-contained — it bundles Qt WebEngine, so no system WebKit/GTK packages are needed.
  • The x86_64 build requires glibc 2.35+ (Ubuntu 22.04+, Debian 12+, RHEL 9+). The arm64 build requires glibc 2.39+ (Ubuntu 24.04+, Debian 13+), because Qt publishes no older arm64 wheels.
  • If the AppImage fails to start with a FUSE error, either install libfuse2 or run it as ./InterAGt-x86_64.AppImage --appimage-extract-and-run.

Option 2: Run Directly (Recommended for Development)

Prerequisites:

  • Python 3.12+
  • Bun (for frontend development)

Run in production mode:

python app_launcher.py

Run in preview mode (serves the last built frontend on its own port, no rebuild needed):

python app_launcher.py --dev

Both open a native app window (via pywebview), backed by:

  • Production: http://localhost:8000
  • Preview: Frontend at http://localhost:4173, Backend at http://localhost:8000

For live frontend reload (HMR) while editing, run the frontend and backend dev servers directly instead:

cd frontend && bun run dev       # http://localhost:5173, hot reload
.venv/bin/uvicorn backend.main:app --reload   # http://localhost:8000

Option 3: Install via PyInstaller (Standalone Executable)

Prerequisites:

  • Python 3.12+
  • PyInstaller: pip install pyinstaller

macOS:

./packaging/build_mac.sh

Produces dist/InterAGt.app (and dist/InterAGt/ unbundled).

Windows:

.\packaging\build_win.ps1

Produces dist\InterAGt\InterAGt.exe.

Linux:

pip install "pywebview[qt]"   # Linux has no OS-provided webview; Qt supplies one
./packaging/build_linux.sh

Produces dist/InterAGt/InterAGt.

To wrap the build into an installer (dist/InterAGt.dmg on macOS via hdiutil, dist\InterAGt-Setup.exe on Windows via Inno Setup 6, dist/InterAGt.AppImage on Linux via appimagetool, downloaded automatically):

./packaging/package_mac.sh       # macOS
.\packaging\package_win.ps1      # Windows
./packaging/package_linux.sh     # Linux

These builds are unsigned — macOS Gatekeeper / Windows SmartScreen will warn on first launch.


Option 4: Manual Setup

For manual setup:

# Clone the repository
git clone https://github.com/molgenis/interAGt
cd interAGt

# Install dependencies
pip install --upgrade pip
pip install -r backend/requirements.txt

# Build frontend
cd frontend
bun install
bun run build

# Run the app
cd ..
python app_launcher.py

About

Interactive application for visualization of AlphaGenome variant effect predictions.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Used by

Contributors

Languages