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-0.2.7.tar.gz (83.6 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-0.2.7-py3-none-any.whl (83.6 MB view details)

Uploaded Python 3

File details

Details for the file napari_bruce-0.2.7.tar.gz.

File metadata

  • Download URL: napari_bruce-0.2.7.tar.gz
  • Upload date:
  • Size: 83.6 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.12

File hashes

Hashes for napari_bruce-0.2.7.tar.gz
Algorithm Hash digest
SHA256 42f281611178fd9e006ae2427ded6169b28f7df9510c8966e5797de908d12d1e
MD5 cea04c6e1a10d065b339a8b93304ae01
BLAKE2b-256 85cee8d294153bc7637a0a1e8defe75e8e74ff49650e39642e600ec24a38dc62

See more details on using hashes here.

File details

Details for the file napari_bruce-0.2.7-py3-none-any.whl.

File metadata

  • Download URL: napari_bruce-0.2.7-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-0.2.7-py3-none-any.whl
Algorithm Hash digest
SHA256 3516bf8ea49a4a317d6cb84dc8fb9208c974f5d840659330db76d427f95c23e1
MD5 2262b1f933ca81f37e476723bf79d141
BLAKE2b-256 f27f45926687e1426765064c2c7b40266fbef905200971bcac3f4f2198522b17

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