dataverse 10.18130 V3 F3TD5R tab metadata d4d

Datasheet for Dataset - Human Readable Format

🎯

Motivation

Why was the dataset created?

  • Name
    CM4AI project purpose
    Response
    Provide AI-ready multimodal datasets to support research in functional genomics and enable AI model training on cellular architecture and processes.
GrantorGrant NameGrant Number
National Institutes of Health1OT2OD032742-011OT2OD032742-01
📊

Composition

What do the instances represent?

Data TypeInstance TypeNameRepresentation
Single-cell RNA sequencing (perturb-seq) counts/metadata.scRNA-seq cells and perturbation targets.Perturb-seq in KOLF2.1J iPSCsSingle-cell transcriptomic profiles under CRISPRi perturbations.
Mass spectrometry-based proteomics (SEC-MS) across iPSCs, NPCs, neurons, cardiomyocytes, and MDA-MB-...Protein fractions, peptide/spectral features, quantified complexes.SEC-MS across cell typesProtein-protein interaction and complex abundance via size exclusion chromatography mass spectrometr...
Immunofluorescence microscopy images for 464 proteins under untreated, paclitaxel, and vorinostat tr...Confocal microscopy images with multiple channels (DAPI, calreticulin/ER, tubulin, protein-of-intere...IF images in MDA-MB-468 with treatmentsSubcellular protein localization images under chemotherapy conditions.
  • Name
    Cell types and conditions
    Identification
    • KOLF2.1J human iPSCs
    • iPSC-derived NPCs
    • iPSC-derived neurons
    • iPSC-derived cardiomyocytes
    • MDA-MB-468 breast cancer cells (untreated, paclitaxel, vorinostat)
    Distribution
    • Modality coverage varies by protein set; SEC-MS, IF, and perturb-seq protein targets incompletely overlap in this release.
  • Name
    Distribution channels and formats
    Description
    • Public distribution via University of Virginia Dataverse; files include ZIP archives (images), HTML (datasheet, provenance graphs), and JSON (RO-Crate metadata).
DescriptionName
2025-07-01 (Version 2.0)Initial publication
2025-10-22 (IF image ZIP archives)Imaging archives publication
🔍

Collection Process

How was the data acquired?

doi:10.18130/V3/F3TD5R
Cell Maps for Artificial Intelligence - June 2025 Data Release (Beta)
Cell Maps for Artificial Intelligence - June 2025 Data Release (Beta)
This dataset is the June 2025 Data Release of Cell Maps for Artificial Intelligence (CM4AI; CM4AI.org), the Functional Genomics Grand Challenge in the NIH Bridge2AI program. This Beta release includes perturb-seq data in undifferentiated KOLF2.1J iPSCs; SEC-MS data in undifferentiated KOLF2.1J iPSCs, iPSC-derived NPCs, neurons, cardiomyocytes, and treated and untreated MDA-MB-468 breast cancer cells; and IF images in MDA-MB-468 breast cancer cells in the presence and absence of chemotherapy (vorinostat and paclitaxel).
https://doi.org/10.18130/V3/F3TD5R
2025-07-01
2025-02-27
https://dataverse.lib.virginia.edu
  • AI
  • artificial intelligence
  • machine learning
  • Bridge2AI
  • CM4AI
  • functional genomics
  • perturb-seq
  • perturbation sequencing
  • single-cell RNA sequencing
  • scRNAseq
  • SEC-MS
  • size exclusion chromatography
  • mass spectroscopy
  • AP-MS
  • protein-protein interaction
  • protein localization
  • subcellular imaging
  • induced pluripotent stem cell
  • iPSC
  • KOLF2.1J
  • neural progenitor cell
  • NPC
  • neuron
  • cardiomyocyte
  • breast cancer
  • MDA-MB-468
  • vorinostat
  • paclitaxel
  • Name
    Bridge2AI functional genomics gap
    Response
    Create standardized, AI-ready datasets integrating protein localization, protein-protein interactions, and perturb-seq in disease-relevant human cell lines.
RoleNameORCIDAffiliation
Principal InvestigatorTrey Ideker--
  • Name
    Cross-referenced repositories
    External Resources
    • Sequence Read Archive (sra) Data
      NCBI BioProject (perturb-seq)
    • Mass Spectrometry Data (human Ipscs)
      MassIVE Repository
    • Mass Spectrometry Data (human Cancer Cells)
      MassIVE Repository
  • Name
    Human subject status
    Description
    • Human Subjects
      No; data derived from commercially available de-identified human cell lines.
  • Name
    Prohibited clinical use
    Warnings
    • Not for clinical decision-making or patient care without appropriate regulatory oversight and approval.
  • Name
    Human-derived cell line data
    Description
    • Data are from de-identified, commercially available human cell lines; not linked to individuals.
  1. Name
    Laboratory acquisition
    Description
    • Data generated by participating CM4AI labs using standardized wet-lab and imaging protocols.
    Was Directly Observed
    Yes (imaging, mass spectrometry, sequencing)
    Was Reported By Subjects
    False
    Was Inferred Derived
    Partial (some analyses derived from raw measurements)
    Was Validated Verified
    Not specified in this release; provenance graphs provided for select components.
  • Name
    Experimental modalities
    Description
    • Perturb-seq (CRISPRi-based scRNA-seq) in undifferentiated KOLF2.1J iPSCs.
    • Size exclusion chromatography mass spectrometry (SEC-MS) in iPSCs, NPCs, neurons, cardiomyocytes, and MDA-MB-468 (treated/untreated).
    • Immunofluorescence confocal microscopy (IF) imaging in MDA-MB-468 with multiplexed channels (DAPI, ER, tubulin, protein-of-interest).
RoleNameORCIDAffiliation
ContributorParticipating labs--
  • Name
    Release and creation dates
    Description
    • Data Creation Date
      2025-02-27; Dataset description updated 2025-06-30; Publication Date: 2025-07-01.
  • Name
    Data governance and ethics
    Description
    • Ethical Review Oversight
      Vardit Ravitsky (The Hastings Center) and Jean-Christophe Bélisle-Pipon (Simon Fraser University). Data Governance Committee contact: Jillian Parker (jillianparker@health.ucsd.edu). Human Subjects: No. De-identified Samples: Yes. FDA Regulated: No.
  • Name
    Provenance and pipelines
    Description
    • Modality-specific processing documented via RO-Crate metadata and provenance graph HTMLs for images and mass spectrometry subsets; computed cell maps are not included in this release.
  • Name
    Raw/primary data access
    Description
    • External raw or primary data can be accessed via linked repositories (NCBI SRA BioProject for perturb-seq; MassIVE for proteomics).
  • Name
    Hosting and stewardship
    Description
    • Long-term preservation in the University of Virginia Dataverse with committed institutional support; CM4AI consortium to provide updates through November 2026.
Name
De-identification status
Description
  • Yes—samples are de-identified and derived from commercially available human cell lines; no human subjects research.
CompressionDescriptionFormatIDIs AIssuedMd5Media TypeNamePathTitle
ZIPConfocal IF images (DAPI, ER/calreticulin, tubulin, protein-of-interest) for 464 proteins in MDA-MB-...cm4ai-ifimages-mda-mb-468-untreatedDataSubset2025-10-22a98affcc05429650c6bb3906cd836d55application/zipIF images — MDA-MB-468 untreatedImages/cm4ai-ifimages-mda-mb-468-untreated.zipImmunofluorescence images for 464 proteins — MDA-MB-468 untreated
ZIPConfocal IF images for 464 proteins in MDA-MB-468 cells treated with paclitaxel.cm4ai-ifimages-mda-mb-468-paclitaxelDataSubset2025-10-220d972b80744344ddeede516a0cf6e3d7application/zipIF images — MDA-MB-468 paclitaxelImages/cm4ai-ifimages-mda-mb-468-paclitaxel.zipImmunofluorescence images for 464 proteins — MDA-MB-468 paclitaxel
ZIPConfocal IF images for 464 proteins in MDA-MB-468 cells treated with vorinostat.cm4ai-ifimages-mda-mb-468-vorinostatDataSubset2025-10-22ad4e68ccc14b0f3349dad3321e7b81b2application/zipIF images — MDA-MB-468 vorinostatImages/cm4ai-ifimages-mda-mb-468-vorinostat.zipImmunofluorescence images for 464 proteins — MDA-MB-468 vorinostat
HTML datasheet summarizing key release information.release-ro-crate-datasheetDataSubset2025-07-01599c9ece9b88b3ce797b82463b4a1eb4text/htmlRelease datasheet (RO-Crate HTML)release-ro-crate-datasheet.htmlCM4AI release datasheet
RO-Crate JSON-LD metadata describing the release and linking to modality crates.JSONrelease-ro-crate-metadataDataSubset2025-07-0199f9e00053bff3020fd9832a3a518bbbapplication/jsonRelease RO-Crate metadatarelease-ro-crate-metadata.jsonRO-Crate metadata with pointers to sub-RO-Crates
Provenance graph HTML for paclitaxel imaging subset (download to view properly).images-paclitaxel-provenance-graphDataSubset2025-07-01e38e63e4c8dfc5808a5ffa2d7829fc38text/htmlIF images paclitaxel provenance graphImages/paclitaxel/Images-paclitaxel-provenance-graph.htmlImages paclitaxel provenance graph (HTML)
Provenance graph HTML for untreated imaging subset (download to view properly).images-untreated-provenance-graphDataSubset2025-07-011a3b510f74d3f8647e07c6559ce64ee8text/htmlIF images untreated provenance graphImages/untreated/Images-untreated-provenance-graph.htmlImages untreated provenance graph (HTML)
Provenance graph HTML for vorinostat imaging subset (download to view properly).images-vorinostat-provenance-graphDataSubset2025-07-0158935fe4e254b31d33fed019f24c7668text/htmlIF images vorinostat provenance graphImages/vorinostat/Images-vorinostat-provenance-graph.htmlImages vorinostat provenance graph (HTML)
RO-Crate JSON metadata describing mass spectrometry cancer cell subset.JSONmass-spec-cancer-cells-ro-crateDataSubset2025-07-013a7063bb391ea5e05a32ba5da5f4b2f8application/jsonMass spec cancer cells RO-Crate metadatamass-spec/cancer-cells/mass-spec-cancer-cells-ro-crate-metadata.jsonMass spectrometry (cancer cells) RO-Crate metadata
Name
Public distribution
Description
Dataset is publicly distributed via University of Virginia Dataverse; raw/primary data are also hosted in external third-party repositories (NCBI SRA, MassIVE).
🚀

Uses

What (other) tasks could the dataset be used for?

NameResponse
AI model trainingTraining and evaluation of AI/ML models on functional genomics modalities (scRNA-seq perturb-seq, SE...
Cellular process analysisAnalyze cell architectural changes and interactions under disease-relevant conditions, treatments, a...
DescriptionName
{'Clark T, Parker J, Schaffer L, Obernier K, et al. Cell Maps for Artificial Intelligence': 'AI-Ready Maps of Human Cell Architecture from Disease-Relevant Cell Lines. 2024. doi: http://doi.org/10.1101/2024.05.21.589311'}CM4AI preprints
{'Nourreddine S, Doctor Y, Dailamy A, Forget A, et al. A PERTURBATION CELL ATLAS OF HUMAN INDUCED PLURIPOTENT STEM CELLS. bioRxiv. 2024 Nov 4;2024.11.03.621734. PMCID': 'PMC11580897 doi: https://doi.org/10.1101/2024.11.03.621734'}Perturbation cell atlas
  • Name
    Additional potential uses
    Description
    • Benchmarking multimodal integration methods; evaluating treatment response signatures; mapping protein complexes and localization patterns.
  • Name
    Limitations and risk considerations
    Description
    • Interim Beta release; computed cell maps not yet included.
    • Modality protein target sets incompletely overlap; may affect integrative analyses.
    • Most suitable for bioinformatics analyses of individual datasets; domain expertise required.
    • Data derived from specific cell lines and conditions; may not represent biological diversity across populations.
  • Name
    Prohibited clinical applications
    Description
    • Do not use for clinical decision-making or patient care without appropriate regulatory oversight and approval.
Name
Dataverse license and norms
Description
  • CC BY-NC-SA 4.0. Community norms expect proper citation using the dataset citation provided on the dataset page.
📤

Distribution

How will the dataset be distributed?

doi:10.18130/V3/F3TD5R
CC BY-NC-SA 4.0
🔄

Maintenance

How will the dataset be maintained?

2.0
Name
Update plan
Description
  • Dataset will be regularly updated and augmented through the end of the project in November 2026, with quarterly updates. Updates and preservation via University of Virginia Dataverse.
Generated on 2025-11-09 10:17:34 using Bridge2AI Data Sheets Schema