dataverse 10.18130 V3 F3TD5R tab files d4d

Datasheet for Dataset - Human Readable Format

🎯

Motivation

Why was the dataset created?

IDNameResponse
purpose-1PurposeProvide AI-ready datasets to support research in functional genomics within the CM4AI (Cell Maps for...
purpose-2PurposeTrain and evaluate AI/ML models on multimodal cellular data.
GrantorGrant NameGrant Number
National Institutes of HealthNIH OT2OD032742-011OT2OD032742-01
📊

Composition

What do the instances represent?

Data TypeIDInstance TypeNameRepresentation
Raw/processed image data packaged in ZIP archivesinstance-ifImage files with multi-channel staining (DAPI, ER, microtubules, protein-of-interest)InstanceImmunofluorescence (ICC-IF) confocal microscopy images of MDA-MB-468 cells
Processed mass spectrometry outputs and associated metadatainstance-sec-msProteomics datasets across multiple cell types and treatmentsInstanceSize exclusion chromatography–mass spectrometry (SEC-MS) protein-protein interaction data
Sequencing reads and/or processed matrices referenced via SRA BioProjectinstance-perturb-seqscRNA-seq profiles under targeted perturbationsInstanceCRISPRi perturb-seq single-cell transcriptomics in KOLF2.1J iPSCs
  • ID
    subpop-1
    Name
    Subpopulation
    Identification
    • Cell lines and derived cell types: KOLF2.1J iPSCs, iPSC-derived NPCs, neurons, cardiomyocytes, MDA-MB-468 breast cancer cells; treatments include vorinostat and paclitaxel.
  • ID
    distfmt-1
    Name
    DistributionFormat
    Description
    • ZIP archives (images)
    • HTML (datasheet and provenance graphs)
    • JSON (RO-Crate metadata)
  • ID
    distdate-1
    Name
    DistributionDate
    Description
    • Initial Publication
      2025-07-01
    • Additional Image Archives Published
      2025-10-22
🔍

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).
2025-07-01
2025-02-27
https://doi.org/10.18130/V3/F3TD5R
  • AI
  • affinity purification
  • AP-MS
  • artificial intelligence
  • breast cancer
  • Bridge2AI
  • cardiomyocyte
  • CM4AI
  • CRISPR/Cas9
  • induced pluripotent stem cell
  • iPSC
  • KOLF2.1J
  • machine learning
  • mass spectroscopy
  • MDA-MB-468
  • neural progenitor cell
  • NPC
  • neuron
  • paclitaxel
  • perturb-seq
  • perturbation sequencing
  • protein-protein interaction
  • protein localization
  • single-cell RNA sequencing
  • scRNAseq
  • SEC-MS
  • size exclusion chromatography
  • subcellular imaging
  • vorinostat
bibo:draft
DescriptionFormatIDMd5Media TypeNamePathTitle
HTML datasheet summarizing key release information.release-ro-crate-datasheet.html599c9ece9b88b3ce797b82463b4a1eb4text/htmlrelease-ro-crate-datasheet.htmlrelease-ro-crate-datasheet.htmlRelease RO-Crate datasheet (HTML)
Release RO-Crate with pointers to sub ro-crates.JSONrelease-ro-crate-metadata.json99f9e00053bff3020fd9832a3a518bbbapplication/jsonrelease-ro-crate-metadata.jsonrelease-ro-crate-metadata.jsonRelease RO-Crate metadata (JSON)
Spatial localization of 464 proteins in MDA-MB-468 breast cancer cells treated with paclitaxel, imag...Images/cm4ai-ifimages-mda-mb-468-paclitaxel.zip0d972b80744344ddeede516a0cf6e3d7application/zipcm4ai-ifimages-mda-mb-468-paclitaxel.zipImages/cm4ai-ifimages-mda-mb-468-paclitaxel.zipCM4AI IF images – MDA-MB-468 treated with paclitaxel (ZIP)
Spatial localization of 464 proteins in untreated MDA-MB-468 breast cancer cells, imaged by ICC-IF c...Images/cm4ai-ifimages-mda-mb-468-untreated.zipa98affcc05429650c6bb3906cd836d55application/zipcm4ai-ifimages-mda-mb-468-untreated.zipImages/cm4ai-ifimages-mda-mb-468-untreated.zipCM4AI IF images – MDA-MB-468 untreated (ZIP)
Spatial localization of 464 proteins in MDA-MB-468 breast cancer cells treated with vorinostat, imag...Images/cm4ai-ifimages-mda-mb-468-vorinostat.zipad4e68ccc14b0f3349dad3321e7b81b2application/zipcm4ai-ifimages-mda-mb-468-vorinostat.zipImages/cm4ai-ifimages-mda-mb-468-vorinostat.zipCM4AI IF images – MDA-MB-468 treated with vorinostat (ZIP)
HTML provenance graph; requires download to view properly.Images/paclitaxel/Images-paclitaxel-provenance-graph.htmle38e63e4c8dfc5808a5ffa2d7829fc38text/htmlImages-paclitaxel-provenance-graph.htmlImages/paclitaxel/Images-paclitaxel-provenance-graph.htmlIF images (paclitaxel) provenance graph (HTML)
HTML provenance graph; requires download to view properly.Images/untreated/Images-untreated-provenance-graph.html1a3b510f74d3f8647e07c6559ce64ee8text/htmlImages-untreated-provenance-graph.htmlImages/untreated/Images-untreated-provenance-graph.htmlIF images (untreated) provenance graph (HTML)
HTML provenance graph; requires download to view properly.Images/vorinostat/Images-vorinostat-provenance-graph.html58935fe4e254b31d33fed019f24c7668text/htmlImages-vorinostat-provenance-graph.htmlImages/vorinostat/Images-vorinostat-provenance-graph.htmlIF images (vorinostat) provenance graph (HTML)
HTML provenance graph; requires download to view properly.mass-spec/cancer-cells/mass-spec-cancer-cells-provenance-graph.html931ad9b552562024cb84ebe62d1f1838text/htmlmass-spec-cancer-cells-provenance-graph.htmlmass-spec/cancer-cells/mass-spec-cancer-cells-provenance-graph.htmlSEC-MS cancer cells provenance graph (HTML)
RO-Crate metadata for SEC-MS cancer cell data.JSONmass-spec/cancer-cells/mass-spec-cancer-cells-ro-crate-metadata.json3a7063bb391ea5e05a32ba5da5f4b2f8application/jsonmass-spec-cancer-cells-ro-crate-metadata.jsonmass-spec/cancer-cells/mass-spec-cancer-cells-ro-crate-metadata.jsonSEC-MS cancer cells RO-Crate metadata (JSON)
  • ID
    gap-1
    Name
    AddressingGap
    Response
    Create harmonized, AI-ready multimodal datasets (imaging, perturb-seq, SEC-MS) from disease-relevant human cell lines to enable data-driven cell architecture maps.
RoleNameORCIDAffiliation
Principal InvestigatorTrey Idekerperson-trey-idekerCell Maps for Artificial Intelligence (CM4AI)
Principal InvestigatorTim Clarkperson-tim-clarkUniversity of Virginia
Principal InvestigatorNevan Kroganperson-nevan-kroganUniversity of California San Francisco
Principal InvestigatorEmma Lundbergperson-emma-lundbergStanford University
Principal InvestigatorPrashant Maliperson-prashant-maliUniversity of California San Diego
  1. ID
    sampling-1
    Name
    SamplingStrategy
    Strategies
    • Targeted selection of proteins-of-interest and perturbations; datasets in this release interrogate overlapping but not identical protein sets across modalities.
    Is Representative
    • Not representative of all biological variants; derived from specific human cell lines.
    Why Not Representative
    • Commercially available de-identified human cell lines do not represent full population diversity.
  • ID
    rel-1
    Name
    Relationships
    Description
    • Cross-modality relationships between proteins and cellular structures are implicit across IF imaging, SEC-MS interactions, and perturb-seq responses.
  • ID
    splits-1
    Name
    Splits
    Description
    • No recommended data splits are provided in this interim release.
  • ID
    anomaly-1
    Name
    DataAnomaly
    Description
    • Interim (Beta) release; computed cell maps are not included.
    • Protein sets interrogated across modalities incompletely overlap.
  1. ID
    ext-1
    Name
    ExternalResource
    External Resources
    • Sequence Read Archive (sra) Data
      NCBI BioProject
    • Mass Spectrometry Data (human Ipscs)
      MassIVE Repository
    • Mass Spectrometry Data (human Cancer Cells)
      MassIVE Repository
    Archival
    • Long-term preservation in the University of Virginia Dataverse.
  • ID
    conf-1
    Name
    Confidentiality
    Description
    • No human subjects; commercially available de-identified human cell lines.
  • ID
    cw-1
    Name
    ContentWarning
    Warnings
    • None noted.
ID
deid-1
Name
Deidentification
Description
  • Human Subjects
    False
  • De Identified Samples
    True
  • Fda Regulated
    False
  • ID
    acq-1
    Name
    InstanceAcquisition
    Description
    • Data were directly observed/measured via ICC-IF confocal microscopy (imaging), SEC-MS (proteomics), and CRISPRi perturb-seq (scRNA-seq).
  • ID
    mech-1
    Name
    CollectionMechanism
    Description
    • ICC-IF staining and confocal microscopy (multi-channel imaging).
    • Size exclusion chromatography followed by mass spectrometry (SEC-MS).
    • CRISPR interference (CRISPRi) perturb-seq single-cell RNA sequencing.
  • ID
    collectors-1
    Name
    DataCollector
    Description
    • CM4AI consortium labs at UC San Diego, UC San Francisco, Stanford University, and University of Virginia.
  • ID
    time-1
    Name
    CollectionTimeframe
    Description
    • Data Creation Date
      2025-02-27; release designated June 2025; published 2025-07-01.
    • Additional image archives published 2025-10-22.
  • ID
    er-1
    Name
    EthicalReview
    Description
    • Ethical review oversight noted: Vardit Ravitsky and Jean-Christophe Bélisle-Pipon.
    • Data Governance Committee
      Jillian Parker (contact provided on dataset page).
  • ID
    dpi-1
    Name
    DataProtectionImpact
    Description
    • Minimal data protection risks anticipated as datasets are derived from de-identified human cell lines; no human subjects involved.
  • ID
    prep-1
    Name
    PreprocessingStrategy
    Description
    • Imaging channels include DAPI (nuclei), calreticulin (ER), tubulin (microtubules), and protein-of-interest antibody; modality-specific preprocessing details may be described in RO-Crates and provenance graphs.
  • ID
    raw-1
    Name
    RawData
    Description
    • External Repositories Host Raw/primary Data
      NCBI SRA BioProject and MassIVE.
DescriptionIDName
Long-term preservation in the University of Virginia Dataverse with committed institutional funds; dataset point of contact listed as Trey Ideker. maint-1Maintainer
{'Data Governance Committee': 'Jillian Parker (contact listed on dataset page).'}maint-2Maintainer
ID
deid-collection
Name
Deidentification
Description
  • De-identified samples; no human subjects.
no
🚀

Uses

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

IDNameResponse
task-1TaskAI model training and benchmarking on cellular imaging, scRNAseq, and proteomics.
task-2TaskCellular process analysis and mapping of cell architecture under treatments or perturbations.
  • ID
    uses-1
    Name
    ExistingUse
    Description
    • Related publications include 2024 preprints describing CM4AI and a perturbation cell atlas; see dataset "Related Publication" section for details.
  • ID
    other-1
    Name
    OtherTask
    Description
    • Benchmarking of multimodal integration methods and cross-modality representation learning.
  • ID
    fut-1
    Name
    FutureUseImpact
    Description
    • Potential biases due to use of specific human cell lines; not representative of all biological variants. Interim release lacks computed cell maps; modality-specific protein coverage differs, which may affect integrative analyses.
  • ID
    no-clinical
    Name
    DiscouragedUse
    Description
    • Not for clinical decision-making or any context involving patient care without appropriate regulatory oversight and approval.
ID
lic-1
Name
LicenseAndUseTerms
Description
  • CC BY-NC-SA 4.0; proper citation required as per repository community norms.
📤

Distribution

How will the dataset be distributed?

doi:10.18130/V3/F3TD5R
CC BY-NC-SA 4.0
ID
veracc-1
Name
VersionAccess
Description
  • Versioned in the University of Virginia Dataverse; this record reflects Version 2.0.
🔄

Maintenance

How will the dataset be maintained?

2.0
2025-10-22
ID
update-plan-1
Name
UpdatePlan
Description
  • Dataset will be regularly updated and augmented through the end of the project in November 2026.
  • Updates on a quarterly basis.
Generated on 2025-11-09 10:17:34 using Bridge2AI Data Sheets Schema