{"id":16649765,"url":"https://github.com/luispedro/coelho2015_netsdetermination","last_synced_at":"2025-05-12T19:11:20.354Z","repository":{"id":26961392,"uuid":"30424575","full_name":"luispedro/Coelho2015_NetsDetermination","owner":"luispedro","description":"Reproducible code archive for \"Automatic Determination of NET (Neutrophil Extracellular Traps) Coverage in Fluorescent Microscopy Images\" by Coelho et al.","archived":false,"fork":false,"pushed_at":"2018-09-20T13:24:29.000Z","size":25271,"stargazers_count":3,"open_issues_count":0,"forks_count":3,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-01T01:51:58.593Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"http://doi.org/10.1093/bioinformatics/btv156","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/luispedro.png","metadata":{"files":{"readme":"README.rst","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2015-02-06T17:37:30.000Z","updated_at":"2021-01-13T19:44:53.000Z","dependencies_parsed_at":"2022-08-24T15:03:56.094Z","dependency_job_id":null,"html_url":"https://github.com/luispedro/Coelho2015_NetsDetermination","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/luispedro%2FCoelho2015_NetsDetermination","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/luispedro%2FCoelho2015_NetsDetermination/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/luispedro%2FCoelho2015_NetsDetermination/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/luispedro%2FCoelho2015_NetsDetermination/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/luispedro","download_url":"https://codeload.github.com/luispedro/Coelho2015_NetsDetermination/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253805860,"owners_count":21967053,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-10-12T09:12:09.656Z","updated_at":"2025-05-12T19:11:20.331Z","avatar_url":"https://github.com/luispedro.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"============================  \nDetermination of NET Content\n============================  \n\nThis package contains support material (code \u0026 data) for the paper:\n\n    *Automatic Determination of NET (Neutrophil Extracellular Traps) Coverage\n    in Fluorescent Microscopy Images* by Luis Pedro Coelho, Catarina Pato, Ana\n    Friães, Ariane Neumann, Maren von Köckritz-Blickwede, Mário Ramirez, and\n    João André Carriço, Bioinformatics *2015 Jul 15;31(14):2364-70*\n    `DOI:10.1093/bioinformatics/btv156\n    \u003chttp://doi.org/10.1093/bioinformatics/btv156\u003e`__.\n\nUse in academic publications should cite the paper above.\n\nCode is provided under the MIT license.\n\nData\n----\n\nOriginal data is available in the directory ``data/``. The naming structure is\nas follows:\n\n    - prefix \"image\"\n    - nr of the sample\n    - nr of the field inside the sample\n    - channel (protein, dna, rois, or rois2).\n\nFor example, the file ``image_25_00_protein.png`` is from image 25, index 0,\nand is the protein channel. The ROI files are the result of human labeling.\n\nSee the manuscript for details on data acquisition.\n\nSource code\n-----------\n\nThe source code is split into two directories\n\n- ``nets`` this is the library code, which is useful to adapt to new projects.\n- ``reproduce`` in this directory, you will find all the necessary code to\n  reproduce all figures in the paper (including supplemental material).\n\nIn addition, there are two helper scripts:\n\npredict_image.py\n    ``predict_image.py`` returns a prediction for a single input file. It takes\n    two arguments, which should be the image files for the DNA and histone\n    channels, respectively::\n\n        python predict_image.py ../data/image_00_00_dna.png ../data/image_00_00_protein.png\n\n    If it cannot find a model to load, then it runs the ``create_model.py`` script.\n\ncreate_model.py\n    This needs to be run once to learn the model from the data. It will look at\n    the files in the directory ``../data/`` for its input. Running this step\n    may require a lot of memory! If you do not have enough in your machine, you\n    can adjust the ``--n-estimators`` parameter to a smaller value.\n\nWe only recommend that you use our model trained on our data if your images are\nvery similar to ours. Otherwise, you can still use our software, but we\nrecommend you provide our system some training data.\n\nThe simplest way to reuse the software is to replace the images in the\n``data/`` directory by your own (using the same naming format:\n``prefix_dna.png``, ``prefix_protein.png``, and ``prefix_rois.png`` forming a\ntriple). Note that the ``_rois.png`` image should be a labeled image (i.e.,\npixels with value 0 correspond to background, pixels with value 1 correspond to\nthe first area of interest, pixels with value 2 to the second area of interest,\n...).\n\nAlternatively, there is a detailed tutorial on how to adapt the library for new\nuses in the file ``tutorial.rst``.\n\nDependencies\n~~~~~~~~~~~~\n\nFor running on your own data:\n\n- numpy\n- scikit-learn\n- mahotas\n\nAdditionally, for reproducing our experiments:\n\n- jug\n- pandas\n- matplotlib\n- seaborn\n\nThe file ``requirements.txt`` in the ``source-code`` directory lists all the\nrequirements. If you have permission to do so, running the following command\ninside that directory should install all dependencies::\n\n    pip install -r requirements.txt\n\nIf this fails, try::\n\n    sudo pip install -r requirements.txt\n\nReproducing the paper\n~~~~~~~~~~~~~~~~~~~~~\n\nThe results of the paper can be reproduced on a Unix-like machine by running\nthe ``reproduce.sh`` script inside ``source-code/reproduce`` after having\ninstalled the the requirements as listed above.\n\nTo use multiple processors, edit this script and set the value of the\n``NR_CPUS`` variable.\n\nFiles:\n\n\njugfile.py\n    This is the central file which runs the whole analysis\ncompare.py\n    This script performs the reported comparison between the two operators\nbernsen_thresholding.py\n    This script evaluates Bernsen thresholding for different sets of parameters\ncompare-example.py\n    This builds a side-by-side Figure showing differences between operators.\ndraw-composites.py\n    This draws composite images for all inputs images\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fluispedro%2Fcoelho2015_netsdetermination","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fluispedro%2Fcoelho2015_netsdetermination","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fluispedro%2Fcoelho2015_netsdetermination/lists"}