Cell Painting Gallery cpg0016: JUMP Cell Painting Production Dataset, 116,000 Compounds and 15,000 Genes
- Provider
- Chandrasekaran et al., JUMP Cell Painting Consortium
- License
- CC0-1.0 (source)
- Format
- NumPy (in sampled files)
- Stored at
- Amazon S3, s3://cellpainting-gallery/cpg0016-jump (us-east-1)
- Access
- Free and public. No account with the data provider is needed.
- DOI
- 10.1101/2023.03.23.534023
- Category
- Life Sciences
- Source
- https://doi.org/10.1101/2023.03.23.534023
About this dataset
The production dataset of the JUMP Cell Painting Consortium, the largest public Cell Painting resource: more than 116,000 compounds and more than 15,000 genes perturbed by CRISPR knockout and ORF overexpression, profiled in U2OS cells with Cell Painting v3 by twelve pharmaceutical and academic data-generating sites. Over 8 million images and numerical data on more than 1.5 billion single cells, about 358 TB in total, organized by site under source_1 to source_15 (plus source_all for combined profiles), each with images/, workspace/ and workspace_dl/ (deep-learning embeddings). Compound, ORF and CRISPR metadata and the recommended processed profiles are indexed in the jump-cellpainting/datasets GitHub repository and the JUMP Hub. Within each source folder, images/ holds the raw multi-channel TIFF fields per plate and workspace/ holds CellProfiler analysis output, load_data CSVs, metadata and aggregated or normalized profiles (CSV/Parquet); pycytominer and cytotable read the profiles. CC0 1.0; cite Chandrasekaran et al., JUMP Cell Painting dataset: morphological impact of 136,000 chemical and genetic perturbations (bioRxiv 2023.03.23.534023).
How to access this dataset in Python
import boto3
from botocore import UNSIGNED
from botocore.client import Config
s3 = boto3.client('s3', region_name='us-east-1', config=Config(signature_version=UNSIGNED))
s3.list_objects_v2(Bucket='cellpainting-gallery', Prefix='cpg0016-jump/', Delimiter='/')Lists the files with anonymous access. Runs on any machine, with no cloud account.
Data structure
File types in sampled files: NumPy
Files
Example file: cpg0016-jump/source_1/images/Batch1_20221004/
Analyze this dataset without downloading it
On Scigantic, Cell Painting Gallery cpg0016: JUMP Cell Painting Production Dataset, 116,000 Compounds and 15,000 Genes opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.
This page is also available as Markdown and as JSON.
Related Life Sciences datasets
- Pacific Ocean Sound Recordings
- Human and Mammalian Brain Atlas
- Pacific Ocean Sound Recordings
- IDLE-OO Camera Traps: Balanced Five-Set Species Classification Benchmark from LILA BC Camera Trap Images (Imageomics, BioCLIP 2)
- Daikinrin Trait Circus: 5.8 Million Controlled-Vocabulary Fungal Morphology and Ecology Traits Extracted from Species Descriptions (Japanese and English)
- Sounds of Central African landscapes
- OpenOrganelle jrc_hela-2: Whole Interphase HeLa Cell, 4 nm Isotropic FIB-SEM with Organelle Ground Truth
- AMMonitor Camera Traps: 1.2M Images from Ten New England Wildlife Monitoring Projects