Skip to main content

A napari plugin for drawing PALM RoboSoftware elements using StarDist segmentation

Project description

🦇 Bruce

A napari plugin for creating PALMRobo elements using StarDist segmentation


Description

Bruce is a napari plugin for automated detection of cells of interest in PALM RoboSoftware images, enabling fast laser capture microdissection on the PALM MicroBeam system.

Key features:

  • Load 2-channel images and metadata from .zvi files produced by PALMRobo 4.9
  • Perform StarDist-based cell segmentation (default or user-defined models)
  • Allow manual editing of ROIs / elements in napari
  • Perform ROI overlap analysis between 2 channels
  • Export element list as .txt file compatible with PALMRobo 4.9

System requirements

  • Conda / Mamba (recommended)
  • Java (OpenJDK) – required for Bio-Formats .zvi → OME-TIFF conversion
  • GPU (optional) – for accelerated StarDist inference

Installation

Bruce requires a platform-specific Conda environment due to differences in native dependencies and GPU support. Predefined environment files are provided in the env/ directory:

| Platform                | Environment file                     |
|-------------------------|--------------------------------------|
| Windows (native)        | `env/bruce-env_windows_native.yml`   |
| macOS (Apple Silicon)   | `env/bruce-env_macos_arm.yml`        |

Open a terminal and run:

# Create the conda environment (replace <ENV_FILE> with the appropriate .yml file)
mamba env create -f <ENV_FILE>

# Activate the environment
mamba activate bruce-env

# Install Bruce from PyPI
pip install napari-bruce

# Launch Bruce via the command line
bruce

# Or launch Bruce directly from napari
napari --with napari-bruce

# Show help
bruce -h

Configuration

Bruce stores its configuration in a user-specific JSON file.

Available commands:

# Show config file path
bruce --show-config-path

# Open config in default editor
bruce --edit-config

# Reset config to defaults
bruce --reset-config

GPU support & StarDist models

Bruce runs StarDist predictions on the GPU when visible to TensorFlow, and supports user-defined StarDist models.

Available commands:

# Check whether GPU(s) are visible to TensorFlow
bruce --gpu-status

# List available StarDist models
bruce --list-models

# Add a user-defined StarDist model located at <MODEL_DIR>
bruce --add-model <MODEL_DIR>

Image annotation for model training

Bruce comes with a dedicated GUI to annotate 2-channel images produced by PALMRobo 4.9.

Available commands:

# Construct an image set from 2-channel .zvi files located at <IN_DIR> and save to <OUT_DIR>/imgs.pkl
bruce --zvi-to-dict <IN_DIR> <OUT_DIR>

# Open the annotation GUI to label the image set at <IN_DIR>/imgs.pkl and save image/mask pairs to <OUT_DIR>/imgs_annotated.pkl
bruce --annotate <IN_DIR> <OUT_DIR>

Example images

Example .zvi files are provided in the example_images/ directory for testing and demonstration purposes. They are not installed with the napari-bruce Python package.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

napari_bruce-0.2.5.tar.gz (83.5 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

napari_bruce-0.2.5-py3-none-any.whl (83.6 MB view details)

Uploaded Python 3

File details

Details for the file napari_bruce-0.2.5.tar.gz.

File metadata

  • Download URL: napari_bruce-0.2.5.tar.gz
  • Upload date:
  • Size: 83.5 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.12

File hashes

Hashes for napari_bruce-0.2.5.tar.gz
Algorithm Hash digest
SHA256 112a7ffb0034b4bba2e91d87f28534c610ac93f20205534161025c0964600b6f
MD5 5d671a9c6d7c42b355740df270a13e0b
BLAKE2b-256 19667b5247dbf74c6c16320f5f19ff2d50048fa8233da3baa8e82f038c03e5e1

See more details on using hashes here.

File details

Details for the file napari_bruce-0.2.5-py3-none-any.whl.

File metadata

  • Download URL: napari_bruce-0.2.5-py3-none-any.whl
  • Upload date:
  • Size: 83.6 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.12

File hashes

Hashes for napari_bruce-0.2.5-py3-none-any.whl
Algorithm Hash digest
SHA256 9000e41a7d9556f4932d104d5167c497743181b822e37a80748ee1a28a5923a2
MD5 9294830f3de66f193a146f91269a3a2b
BLAKE2b-256 a0267fa289842f10fc424c7f058cb679c14673a0af749425e0cec969d27aa3c0

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page