Datasets

Datasets#

mantispy.ds serves public screens, most from the Cell Painting Gallery [Weisbart et al., 2024], pinned by sha256 and downloaded once into mantispy.settings.cache_dir.

Screens#

ds.bbbc021([cache_dir, aggregated, ...])

BBBC021, MCF-7 cells treated with small molecules, the standard mechanism-of-action benchmark.

ds.rohban([plates, cache_dir, aggregated, ...])

An ORF overexpression screen, with the genes and cell counts that BBBC021 lacks.

ds.pki([plates, cache_dir, aggregated, ...])

Kinase inhibitors over a dose series, from the JUMP pilot.

ds.jump_target2([plates, annotate, cache_dir])

JUMP-Target-2, one plate map run at many sites.

ds.jump_crispr([annotate, cache_dir, aggregated])

The assembled JUMP CRISPR arm, 51,185 wells of knockouts in U2OS cells.

ds.jump_lite([model, annotate, cache_dir])

JUMP-Lite Target-2: 1,536 wells, four imaging sites, one feature set at a time.

ds.chroma([cache_dir])

Alternative dyes, 3,455 wells across eight channels.

ds.neuropainting([cache_dir])

Astrocytes and neurons, 1,691 wells imaged at 20x and 63x.

ds.oasis_pilot([annotate, cache_dir, aggregated])

OASIS pilot, 4,604 wells in U2OS and HepaRG, most compounds over a ten-point dose range.

ds.pooled_rare([cache_dir, feature_selected])

Pooled rare variants, 290 barcodes in a pooled screen.

Single cells and images#

ds.jump_cells([annotate, selected, ...])

Single cells from one JUMP plate, as CellProfiler measured them.

ds.jump_export([cache_dir])

One real ExportToSpreadsheet directory, as CellProfiler wrote it.

ds.jump_plate([cache_dir])

The images and segmentations behind one well of BR00121438.

ds.scallops_arv471([cache_dir, aggregated])

SCALLOPS ARV-471, single cells of an optical pooled screen under an estrogen-receptor degrader.

ds.cp_posh([cache_dir, aggregated, ...])

Single cells of insitro cp-POSH, a broad-morphology pooled CRISPR Cell Painting screen.

Annotations#

ds.corum([cache_dir])

Human protein complexes from CORUM, one row per complex and member gene.

ds.gene_sets([name, organism, cache_dir])

A gene-set network from OmniPath, pinned to a local snapshot.

ds.interactions([source, organism, cache_dir])

Within-complex gene pairs from a complex resource, as an undirected edge list.

ds.jump_lite_targets([cache_dir])

The gene each JUMP compound is annotated to act on, as a set per target.

Synthetic#

ds.synthetic_plate([n_plates, n_wells, ...])

Generate a synthetic plate with known ground truth.

ds.blobs(*[, n_wells, n_sites, n_cells, ...])

A small synthetic Cell Painting plate, laid out like one mantispy.io.read_plate() returns.

Dataset pages#