https://github.com/broadinstitute/deepometry
Image classification for imaging flow cytometry.
Science Score: 33.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
○codemeta.json file
-
○.zenodo.json file
-
✓DOI references
Found 2 DOI reference(s) in README -
✓Academic publication links
Links to: pubmed.ncbi, ncbi.nlm.nih.gov -
✓Committers with academic emails
1 of 5 committers (20.0%) from academic institutions -
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (11.2%) to scientific vocabulary
Keywords from Contributors
Repository
Image classification for imaging flow cytometry.
Basic Info
- Host: GitHub
- Owner: broadinstitute
- License: bsd-3-clause
- Language: Python
- Default Branch: master
- Homepage: https://broadinstitute.github.io/deepometry/
- Size: 1.83 MB
Statistics
- Stars: 27
- Watchers: 15
- Forks: 7
- Open Issues: 6
- Releases: 0
Metadata Files
README.md
Deepometry
Deep learning-based image classification and featurization for imaging (flow) cytometry.
This workflow was originally built for imaging flow cytometry data but can be readily adapted for microscopic images of isolated single objects. The modified implementation of ResNet50 allows researchers to use any image frame size and any number of color channels.
Installation
A full installation guide can be found here. Briefly, the following dependencies are needed: - Python 3.6 - Tensorflow-gpu 1.9.0 - Keras 2.1.5 - Numpy 1.18.1 - Scipy 1.4.1 - Keras-resnet 0.0.7 - Java JDK 8.0 or 11.0 - Python-bioformats 1.5.2
Once the above dependencies are installed, clone this Deepometry repository by :
git clone https://github.com/broadinstitute/deepometry.git
cd deepometry
pip install .
If you want to install deepometry in development mode, run:
pip install --editable .[development]
Use
Execute Deepometry functions through any of the following interfaces:
CLI
Switch to CLI branch:
git checkout CLI
Display a list of available subcommands:
deepometry --help
To display subcommand use and options:
deepometry SUBCOMMAND --help
IPYNB
Switch to IPYNB branch:
git checkout IPYNB
Use these Jupyter notebooks.
GUI (recommended)
Switch to GUI branch:
git checkout GUI
python Deepometry_GUI.py
Open a web-browser, navigate to http://127.0.0.1:5000/ or http://localhost:5000/
Publications
Doan M, Sebastian JA, Caicedo JC, et al. Objective assessment of stored blood quality by deep learning. Proc Natl Acad Sci U S A. 2020;117(35):21381-21390. doi:10.1073/pnas.2001227117
Doan M, Case M, Masic D, et al. Label-Free Leukemia Monitoring by Computer Vision. Cytometry A. 2020;97(4):407-414. doi:10.1002/cyto.a.23987
Owner
- Name: Broad Institute
- Login: broadinstitute
- Kind: organization
- Location: Cambridge, MA
- Website: http://www.broadinstitute.org/
- Twitter: broadinstitute
- Repositories: 1,083
- Profile: https://github.com/broadinstitute
Broad Institute of MIT and Harvard
GitHub Events
Total
- Watch event: 1
- Delete event: 1
- Push event: 1
- Pull request event: 2
- Create event: 1
Last Year
- Watch event: 1
- Delete event: 1
- Push event: 1
- Pull request event: 2
- Create event: 1
Committers
Last synced: over 2 years ago
Top Committers
| Name | Commits | |
|---|---|---|
| mcquin | m****n@b****g | 34 |
| mcquin | m****l@g****m | 17 |
| minh-doan | v****n@g****m | 8 |
| Minh Doan | d****y@g****m | 3 |
| Claire McQuin | m****n | 3 |