Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/alleninstitute/deep-neurographs

A Python package that corrects split mistakes in a fragmented neuron segmentation using a graph neural network.

https://github.com/alleninstitute/deep-neurographs

Science Score: 36.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ✓
    Committers with academic emails
    1 of 4 committers (25.0%) from academic institutions
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (12.7%) to scientific vocabulary

Keywords from Contributors

interpretability standardization animal hack autograder report
Last synced: 10 months ago · JSON representation

Repository

A Python package that corrects split mistakes in a fragmented neuron segmentation using a graph neural network.

Basic Info
  • Host: GitHub
  • Owner: AllenInstitute
  • License: mit
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 13.5 MB
Statistics
  • Stars: 6
  • Watchers: 2
  • Forks: 0
  • Open Issues: 0
  • Releases: 3
Created about 3 years ago · Last pushed 11 months ago
Metadata Files
Readme License

README.md

GraphTrace

License Code Style semantic-release: angular Interrogate Coverage Python

GraphTrace is a Python library that automatically corrects split errors in fragmented neuron segmentations from whole-brain images. It takes SWC files as input and uses a graph-based neural network pipeline to propose, score, and merge candidate connections between neuron fragments. GraphTrace efficiently handles datasets with millions of fragments across whole-brain volumes, enabling high-throughput proofreading and reconstruction at scale.


Figure: GraphTrace reconnects fragmented neuron segments into coherent traces.

Overview

The neuron fragment split correction pipeline consists of three main steps:

a. Graph Construction: Reads neuron fragments stored as SWC files and loads them into a Networkx graph.

b. Proposal Generation: Generates potential connections between nearby fragments.

c. GNN-Based Inference: Predicts whether to accept or reject proposals based on the geometric and image-based features.


pipeline
Figure: Visualization of split correction pipeline, see Inference section for description of each step.

Inference

Step 1: Graph Construction

To do...

Step 2: Proposal Generation

To do...

Step 3: Proposal Classification

To do...

Installation

To use the software, in the root directory, run bash pip install -e .

Usage

To do...

Contact Information

For any inquiries, feedback, or contributions, please do not hesitate to contact us. You can reach us via email at anna.grim@alleninstitute.org or connect on LinkedIn.

License

GraphTrace is licensed under the MIT License.

Owner

  • Name: Allen Institute
  • Login: AllenInstitute
  • Kind: organization
  • Location: Seattle, WA

Please visit http://alleninstitute.github.io/ for more information.

GitHub Events

Total
  • Watch event: 7
  • Delete event: 88
  • Push event: 468
  • Pull request event: 342
  • Create event: 71
Last Year
  • Watch event: 7
  • Delete event: 88
  • Push event: 468
  • Pull request event: 342
  • Create event: 71

Committers

Last synced: over 1 year ago

All Time
  • Total Commits: 587
  • Total Committers: 4
  • Avg Commits per committer: 146.75
  • Development Distribution Score (DDS): 0.131
Past Year
  • Commits: 420
  • Committers: 2
  • Avg Commits per committer: 210.0
  • Development Distribution Score (DDS): 0.064
Top Committers
Name Email Commits
Anna Grim 1****m 510
anna-grim a****m@a****g 71
github-actions 4****] 3
anna-grim j****r@a****l 3
Committer Domains (Top 20 + Academic)
agrim-exaspim-evaluation-notebook.us-west1-b.c.neural-dynamics-338018.internal: 1 alleninstitute.org: 1

Issues and Pull Requests

Last synced: 11 months ago

All Time
  • Total issues: 4
  • Total pull requests: 572
  • Average time to close issues: 1 minute
  • Average time to close pull requests: about 7 hours
  • Total issue authors: 1
  • Total pull request authors: 1
  • Average comments per issue: 0.0
  • Average comments per pull request: 0.0
  • Merged pull requests: 533
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 1
  • Pull requests: 288
  • Average time to close issues: 2 minutes
  • Average time to close pull requests: about 2 hours
  • Issue authors: 1
  • Pull request authors: 1
  • Average comments per issue: 0.0
  • Average comments per pull request: 0.0
  • Merged pull requests: 267
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • anna-grim (4)
Pull Request Authors
  • anna-grim (571)
Top Labels
Issue Labels
Pull Request Labels

Dependencies

.github/workflows/init.yml actions
  • EndBug/add-and-commit v9 composite
  • actions/checkout v3 composite
.github/workflows/tag_and_publish.yml actions
  • EndBug/add-and-commit v9 composite
  • actions/checkout v3 composite
  • actions/setup-python v3 composite
  • actions/setup-python v2 composite
  • pypa/gh-action-pypi-publish release/v1 composite
.github/workflows/test_and_lint.yml actions
  • actions/checkout v3 composite
  • actions/setup-python v3 composite
pyproject.toml pypi
setup.py pypi