{"url":"/dataset/rxrx1","name":"RxRx1","full_name":null,"description_markdown":"**RxRx1** is a biological dataset designed specifically for the systematic study of batch effect correction methods. The dataset consists of 125,510 high-resolution fluorescence microscopy images of human cells under 1,138 genetic perturbations in 51 experimental batches across 4 cell types.","description_withheld":null,"homepage":"https://www.rxrx.ai/","introduced_date":"2023-01-13","introduced_date_note":null,"introduced_by":{"paper":"/paper/rxrx1-a-dataset-for-evaluating-experimental","title":"RxRx1: A Dataset for Evaluating Experimental Batch Correction Methods","first_author":"Maciej Sypetkowski","url":null},"license":{"name":"Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License","url":"https://creativecommons.org/licenses/by-nc-sa/4.0/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Biology","url":"/datasets/modality/biology"}],"tasks":[{"name":"Classification","url":"/task/classification-1","datasets_with_task":"/datasets/task/classification-1"}],"languages":[],"variants":["RxRx1"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/1aurent/RxRx1","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":6,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/classification-on-rxrx1","task":"Classification","dataset_variant":"RxRx1","rows":0,"metrics":["Accuracy"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}