Meta_Album_PRT_Micro (Q6037273)

From MaRDI portal





OpenML dataset with id 44278
Language Label Description Also known as
English
Meta_Album_PRT_Micro
OpenML dataset with id 44278

    Statements

    0 references
    ## **Meta-Album Subcellular Human Protein Dataset (Micro)**\N***\NThis dataset is a subset of the Subcellular dataset in the Protein Atlas project(https://www.proteinatlas.org/). The original dataset, which stems from the Human Protein Atlas Image Classification Kaggle competition(https://www.kaggle.com/competitions/human-protein-atlas-image-classification), comprises 31 072 RGBY images of size 512x512 px, each of which belongs to one or more out of 28 classes. The labels correspond to protein organelle localizations. For Meta-Album, we performed two modifications: (1), to turn the dataset into a multi-class dataset, we dropped all images belonging to more than a single class and also those images that belong to classes with less than 40 members; (2) we converted the remaining images into RGB simply by dropping the yellow channel; this was also a common practice in the competition. Finally, and as for all datasets in Meta-Album, the images from the original dataset were resized to 128x128 image size. \N\N\N\N### **Dataset Details**\N![](https://meta-album.github.io/assets/img/samples/PRT.png)\N\N**Meta Album ID**: MCR.PRT \N**Meta Album URL**: [https://meta-album.github.io/datasets/PRT.html](https://meta-album.github.io/datasets/PRT.html) \N**Domain ID**: MCR \N**Domain Name**: Microscopy \N**Dataset ID**: PRT \N**Dataset Name**: Subcellular Human Protein \N**Short Description**: Subcellular protein patterns in human cells \N**\# Classes**: 20 \N**\# Images**: 800 \N**Keywords**: human protein, subcellular \N**Data Format**: images \N**Image size**: 128x128 \N\N**License (original data release)**: CC BY-SA 3.0 \N**License URL(original data release)**: https://www.proteinatlas.org/about/licence\N \N**License (Meta-Album data release)**: CC BY-SA 3.0 \N**License URL (Meta-Album data release)**: [https://www.proteinatlas.org/about/licence](https://www.proteinatlas.org/about/licence) \N\N**Source**: The Human Protein Atlas \N**Source URL**: https://proteinatlas.org \Nhttps://www.kaggle.com/c/human-protein-atlas-image-classification \N \N**Original Author**: Peter J Thul, Lovisa Akesson, Mikaela Wiking, Diana Mahdessian, Aikaterini Geladaki, Hammou Ait Blal, Tove Alm, Anna Asplund, Lars Bjork, Lisa Breckels, and others \N**Original contact**: contact@proteinatlas.org \N\N**Meta Album author**: Felix Mohr \N**Created Date**: 01 June 2022 \N**Contact Name**: Felix Mohr \N**Contact Email**: meta-album@chalearn.org \N**Contact URL**: [https://meta-album.github.io/](https://meta-album.github.io/) \N\N\N\N### **Cite this dataset**\N```\N@article{thul2017subcellular, \N title={A subcellular map of the human proteome},\N author={Thul, Peter J and Akesson, Lovisa and Wiking, Mikaela and Mahdessian, Diana and Geladaki, Aikaterini and Ait Blal, Hammou and Alm, Tove and Asplund, Anna and Bjork, Lars and Breckels, Lisa M},\N journal={Science},\N volume={356},\N number={6340},\N year={2017},\N publisher={American Association for the Advancement of Science}\N}\N\N```\N\N\N### **Cite Meta-Album**\N```\N@inproceedings{meta-album-2022,\N title={Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image Classification},\N author={Ullah, Ihsan and Carrion, Dustin and Escalera, Sergio and Guyon, Isabelle M and Huisman, Mike and Mohr, Felix and van Rijn, Jan N and Sun, Haozhe and Vanschoren, Joaquin and Vu, Phan Anh},\N booktitle={Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track},\N url = {https://meta-album.github.io/},\N year = {2022}\N }\N```\N\N\N### **More**\NFor more information on the Meta-Album dataset, please see the [[NeurIPS 2022 paper]](https://meta-album.github.io/paper/Meta-Album.pdf) \NFor details on the dataset preprocessing, please see the [[supplementary materials]](https://openreview.net/attachment?id=70_Wx-dON3q&name=supplementary_material) \NSupporting code can be found on our [[GitHub repo]](https://github.com/ihsaan-ullah/meta-album) \NMeta-Album on Papers with Code [[Meta-Album]](https://paperswithcode.com/dataset/meta-album) \N\N\N\N### **Other versions of this dataset**\N[[Mini]](https://www.openml.org/d/44308) [[Extended]](https://www.openml.org/d/44342)
    0 references
    Ihsan Ullah
    0 references
    30-09-2022
    0 references
    28 October 2022
    0 references
    CATEGORY
    0 references
    1b668f3f7d4a52f00feff478b3866827
    0 references
    0
    0 references
    20
    0 references
    3
    0 references
    800
    0 references
    800
    0 references
    0 references

    Identifiers

    0 references