There is a newer version of this record available.

Dataset Open Access

COOS-7 (Cells Out Of Sample 7-Class)

Lu, Alex X; Lu, Amy X; Schormann, Wiebke; Ghassemi, Marzyeh; Andrews, David W; Moses, Alan M

This repository contains the version 1.0 of the COOS-7 dataset (to be presented as a poster at NeurIPS 2019; see preprint at https://arxiv.org/abs/1906.07282). COOS-7 contains 132,209 crops of mouse cells, stratified into a training dataset, and four test datasets representing increasing degrees of covariate shift from the training dataset. In the classification task associated with COOS-7, the aim is to build a classifier robust to covariate shifts typically seen in microscopy. Methods developers must train and optimize machine learning models using the training dataset exclusively, and evaluate performance on each of the four test datasets. 

Each HDF5 file contains two dictionaries:
'data' - contains all of the images in a four-dimensional array (images, channels, height, width)
'labels' - contains the labels for each image, in the same order as the images in 'data'

The value for labels indicates the class of the image, which can be one of seven values:
0 - Endoplasmic Reticulum (ER)
1 - Inner Mitochondrial Membrane (IMM)
2 - Golgi
3 - Peroxisomes
4 - Early Endosome
5 - Cytosol
6 - Nuclear Envelope

The h5py package is required to read these files with Python.

We provide a Python script, unpackage_COOS.py, that will automatically save the archives as directories of tiff files, organized by class. The two channels for each image will be saved as separate images, with a suffix of "_protein.tif" and "_nucleus.tif", respectively.

To run the unpackaging script, issue the command line argument:
python unpackage_COOS.py [path of HDF5 file] [path of directory to save images to]
e.g. python unpackage_COOS.py ./COOS7_v1.0_training.hdf5 ./COOS7_v1.0_training_images/

Full information about the test sets and the images can be found at https://arxiv.org/abs/1906.07282.

Files (4.3 GB)
Name Size
COOS7_v1.0_test1.hdf5
md5:f8e92ba2f429bb3eabe24127a0fdcc99
339.7 MB Download
COOS7_v1.0_test2.hdf5
md5:5e0d3470d6cb21998f08ecd471e91f60
557.9 MB Download
COOS7_v1.0_test3.hdf5
md5:9b5b8bb0e22492249ca06000f7a08b49
1.1 GB Download
COOS7_v1.0_test4.hdf5
md5:dd8fd9641d1b9102200ad4c8e41abeae
1.0 GB Download
COOS7_v1.0_training.hdf5
md5:2ad190d576c994616382823cf0f2ab77
1.4 GB Download
README.txt
md5:f476f2dfc68b57417371a2edc733d601
916 Bytes Download
unpackage_COOS.py
md5:7a23f8ea71853cdb7d91731cd70a5a81
1.3 kB Download
634
421
views
downloads
All versions This version
Views 634386
Downloads 421243
Data volume 274.7 GB159.0 GB
Unique views 565363
Unique downloads 15083

Share

Cite as