dataverse 10.18130 V3 F3TD5R tab terms d4d

Datasheet for Dataset - Human Readable Format

🎯

Motivation

Why was the dataset created?

  • Name
    Primary purpose
    Response
    Provide AI-ready multimodal functional genomics datasets (images, perturb-seq, SEC-MS) to enable research on human cell architecture, processes, and responses to disease, treatments, and genetic perturbations.
GrantorGrant NameGrant Number
National Institutes of HealthBridge2AI Functional Genomics1OT2OD032742-01
📊

Composition

What do the instances represent?

  1. Name
    Data modalities and instance structure
    Representation
    Cell-based measurements and derived observations across multiple experimental modalities.
    Instance Type
    Immunofluorescence images, size exclusion chromatography mass spectrometry (SEC-MS) profiles, and CRISPRi perturb-seq single-cell transcriptomes.
    Data Type
    Raw and processed data files per modality (confocal ICC-IF images with multi-channel staining; SEC-MS protein abundance/interaction fractions; scRNA-seq counts/metadata from perturb-seq).
    Label
    Yes; instances include protein of interest and treatment condition (e.g., paclitaxel, vorinostat, untreated) for imaging; perturbation identity for perturb-seq; sample and condition metadata for SEC-MS.
  • Name
    File formats
    Description
    • ZIP archives for image datasets
    • JSON (RO-Crate metadata)
    • HTML (provenance graphs, datasheet)
  • Name
    Release dates
    Description
    • 2025-07-01 (Version 2.0 public release)
    • 2025-10-22 (additional IF image ZIP packages)
🔍

Collection Process

How was the data acquired?

doi:10.18130/V3/F3TD5R
CM4AI 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).
English
https://dataverse.lib.virginia.edu
2025-07-01
https://doi.org/10.18130/V3/F3TD5R
2025-02-27
  • AI
  • artificial intelligence
  • machine learning
  • Bridge2AI
  • CM4AI
  • induced pluripotent stem cell
  • iPSC
  • KOLF2.1J
  • neural progenitor cell
  • NPC
  • neuron
  • cardiomyocyte
  • breast cancer
  • MDA-MB-468
  • paclitaxel
  • vorinostat
  • perturb-seq
  • perturbation sequencing
  • single-cell RNA sequencing
  • scRNAseq
  • protein-protein interaction
  • protein localization
  • size exclusion chromatography
  • SEC-MS
  • mass spectroscopy
  • affinity purification
  • Name
    Gap addressed
    Response
    Deliver standardized, AI-ready, de-identified cell-based datasets spanning complementary modalities; predicted cell maps are planned for future releases.
RoleNameORCIDAffiliation
Principal InvestigatorTrey Ideker-University of California San Diego
Principal InvestigatorNevan Krogan-University of California San Francisco
Principal InvestigatorEmma Lundberg-Stanford University
Principal InvestigatorPrashant Mali-University of California San Diego
Principal InvestigatorTim Clark-University of Virginia
  1. Name
    Sampling notes
    Is Sample
    • Yes; data derived from commercially available de-identified human cell lines and selected protein sets.
    Is Representative
    • No; does not represent all biological variants in the broader population.
    Why Not Representative
    • Modalities interrogate overlapping but incomplete protein sets; dataset focuses on specific disease-relevant cell lines and conditions.
  • Name
    Cross-modality relationships
    Description
    • Overlapping protein targets across SEC-MS, IF imaging, and perturb-seq enable integrative analyses of cellular architecture and interactions.
  • Name
    Experimental conditions as natural splits
    Description
    • IF imaging split by treatment condition (untreated, paclitaxel, vorinostat) and protein of interest.
RoleNameORCIDAffiliation
ContributorData collection contributors--
  • Name
    Experimental methods
    Description
    • ICC-IF confocal microscopy with multi-channel staining (DAPI, calreticulin for ER, tubulin, and target protein antibody).
    • Size exclusion chromatography mass spectrometry (SEC-MS) for protein-protein interactions and complex profiling.
    • CRISPRi perturb-seq single-cell RNA sequencing in KOLF2.1J iPSCs.
  • Name
    Dataset timeline
    Description
    • Data Creation Date
      2025-02-27; initial public release: 2025-07-01 (Version 2.0). Additional IF image packages published 2025-10-22.
  • Name
    Data governance and ethics
    Description
    • Human Subjects
      No; De-identified Samples: Yes; FDA Regulated: No.
    • Data Governance Committee
      Jillian Parker (jillianparker@health.ucsd.edu).
    • Ethical Review
      Vardit Ravitsky (ravitskyv@thehastingscenter.org) and Jean-Christophe Bélisle-Pipon (jean-christophe_belisle-pipon@sfu.ca).
Name
De-identification status
Description
  • Data derived from commercially available de-identified human cell lines; no human subjects.
  • Name
    External repositories
    External Resources
    • Sequence Read Archive (sra) Data
      NCBI BioProject
    • Mass Spectrometry Data (human Ipscs)
      MassIVE Repository
    • Mass Spectrometry Data (human Cancer Cells)
      MassIVE Repository
  • Name
    Imaging channels and staining
    Description
    • Multi-channel ICC-IF imaging with DAPI (nuclei, blue), calreticulin (ER, yellow), tubulin (microtubules, red), and antibody to protein of interest (green).
  • Name
    Preservation and governance
    Description
    • University of Virginia Dataverse (long-term preservation supported by institutional funds)
    • Data Governance Committee Contact
      Jillian Parker (jillianparker@health.ucsd.edu)
https://purl.org/spar/bibo/status/published
DescriptionIDIs Data SplitIs SubpopulationMd5Media TypeNamePath
Immunofluorescence images of 464 proteins of interest in untreated MDA-MB-468 breast cancer cells; I...cm4ai-ifimages-mda-mb-468-untreatednonoa98affcc05429650c6bb3906cd836d55application/zipIF images - MDA-MB-468 untreatedImages/cm4ai-ifimages-mda-mb-468-untreated.zip
Immunofluorescence images of 464 proteins of interest in MDA-MB-468 cells treated with paclitaxel; I...cm4ai-ifimages-mda-mb-468-paclitaxelnono0d972b80744344ddeede516a0cf6e3d7application/zipIF images - MDA-MB-468 paclitaxelImages/cm4ai-ifimages-mda-mb-468-paclitaxel.zip
Immunofluorescence images of 464 proteins of interest in MDA-MB-468 cells treated with vorinostat; I...cm4ai-ifimages-mda-mb-468-vorinostatnonoad4e68ccc14b0f3349dad3321e7b81b2application/zipIF images - MDA-MB-468 vorinostatImages/cm4ai-ifimages-mda-mb-468-vorinostat.zip
HTML datasheet summarizing key release information.release-ro-crate-datasheet599c9ece9b88b3ce797b82463b4a1eb4text/htmlRelease datasheet (RO-Crate HTML)release-ro-crate-datasheet.html
RO-Crate metadata with pointers to sub RO-Crates.release-ro-crate-metadata99f9e00053bff3020fd9832a3a518bbbapplication/jsonRelease RO-Crate metadata (JSON)release-ro-crate-metadata.json
HTML provenance graph; download to view properly.images-provenance-paclitaxele38e63e4c8dfc5808a5ffa2d7829fc38text/htmlIF images paclitaxel provenance graph (HTML)Images/paclitaxel/Images-paclitaxel-provenance-graph.html
HTML provenance graph; download to view properly.images-provenance-untreated1a3b510f74d3f8647e07c6559ce64ee8text/htmlIF images untreated provenance graph (HTML)Images/untreated/Images-untreated-provenance-graph.html
HTML provenance graph; download to view properly.images-provenance-vorinostat58935fe4e254b31d33fed019f24c7668text/htmlIF images vorinostat provenance graph (HTML)Images/vorinostat/Images-vorinostat-provenance-graph.html
RO-Crate metadata for mass spectrometry cancer cell data.mass-spec-cancer-cells-ro-crate3a7063bb391ea5e05a32ba5da5f4b2f8application/jsonMass spec (cancer cells) RO-Crate metadata (JSON)mass-spec/cancer-cells/mass-spec-cancer-cells-ro-crate-metadata.json
no
🚀

Uses

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

  • Name
    Intended analytical tasks
    Response
    AI model training; cellular process analysis; bioinformatics analysis of modality-specific datasets (IF imaging, SEC-MS, perturb-seq).
  • Name
    Related publications
    Description
    • Clark T 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
    • Nourreddine S et al. A PERTURBATION CELL ATLAS OF HUMAN INDUCED PLURIPOTENT STEM CELLS. bioRxiv. 2024 Nov 4;2024.11.03.621734. https://doi.org/10.1101/2024.11.03.621734
  • Name
    Additional potential uses
    Description
    • Cross-modality integration; benchmarking AI methods for multimodal cell data; treatment effect studies; protein localization and interaction mapping.
  • Name
    Limitations and biases impacting future use
    Description
    • Interim release; computed cell maps not included yet.
    • Modalities interrogate overlapping but incomplete protein sets.
    • Domain expertise required for meaningful analysis.
    • Data from selected de-identified cell lines may not generalize to all biological variants.
  • Name
    Prohibited uses
    Description
    • Not for clinical decision-making or any patient care context without appropriate regulatory oversight and approval.
  • Name
    Dataverse exports
    Description
    • OAI_ORE, DataCite, OpenAIRE, Schema.org JSON-LD, DDI Codebook v2, Dublin Core, DDI HTML Codebook, JSON available via Dataverse export tools.
📤

Distribution

How will the dataset be distributed?

doi:10.18130/V3/F3TD5R
CC BY-NC-SA 4.0
Name
Versioning and access
Description
  • Older versions are preserved in Dataverse; current described version is 2.0 with subsequent file additions recorded under the dataset.
🔄

Maintenance

How will the dataset be maintained?

2025-10-22
Name
Maintenance and update plan
Description
  • Dataset will be regularly updated and augmented through November 2026
  • Updates on a quarterly basis
  • Long-term preservation in the University of Virginia Dataverse
2.0
Generated on 2025-11-09 10:17:34 using Bridge2AI Data Sheets Schema