Git Product home page Git Product logo

basic_descriptors's Introduction

basic_descriptors

===

Create a conda environment :

Install Anaconda following the website instruction: https://www.anaconda.com/distribution/

conda create -n dypfish python=2.7

(This creates a dypfish environment for python) Activate :

conda activate dypfish

Install packages

pip install matplotlib

conda install numpy

conda install scipy

pip install scikit-image

pip install h5py

conda install os

conda install csv

Download this repository :

git clone https://github.com/ebouilhol/basic_descriptors.git

cd basic_descriptors

Open the "run_create_3d_images.py" file, change the path value according to the localisation of your image folder.

This script creates stack of images for tubulin, nucleus, FISH based on CY3/CY5/DAPI images, simply launch it :

python run_create_3d_images.py

After that, we are going to generate the HDF5 file based on the previous stacked images. Open the "main.py" file, change the path value according to the localisation of your folder.

This script generates cell mask, nucleus mask, nucleus position, spots position. It does not provide MTOC position. You need to provide it in a CSV file, and put it in the mtoc/ folder. To create the CSV file, take a look at the example provided. It should be named as the folder.

Launch the main :

python main.py

It should create a basic_descriptors.h5 file. You may get some warnings.

If you want to visualize the results, uncomment the function plot_nucleus_contours in dapi_all_slices (utils.py) And plot_cell_contours in tubulin_all_slices (utils.py)

The scripts needs to be adjusted for each series of images.

You can adjust the values in the main.py file

tubulin_case = 0
tubulin_treshold = 78

dapi_case = 0
dapi_treshold = 80

Tubulin case if 0 : try an auto treshold. If the result is not good, switch the case to 1 and try different treshold values until the results are good. Same thing for dapi case and dapi treshold.

basic_descriptors's People

Contributors

ebouilhol avatar

Watchers

 avatar  avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.