=== YAML Fixing Applied ===
id: "doi:10.18130/V3/F3TD5R"
name: Cell Maps for Artificial Intelligence - June 2025 Data Release (Beta)
title: Cell Maps for Artificial Intelligence - June 2025 Data Release (Beta)
description: 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). Some datasets are under temporary pre-publication embargo; SEC-MS, IF imaging, and CRISPRi perturb-seq interrogate overlapping but not identical protein sets; computed cell maps are not included in this release.
doi: "doi:10.18130/V3/F3TD5R"
page: "https://doi.org/10.18130/V3/F3TD5R"
issued: "2025-07-01"
created_on: "2025-02-27"
version: "2.0"
license: CC BY-NC-SA 4.0
keywords:
  - 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
resources:
  - id: cm4ai-june-2025-release
    name: CM4AI June 2025 Data Release (Beta)
    title: CM4AI June 2025 Data Release (Beta)
    description:
      - AI-ready datasets to support research in functional genomics, AI model training, cellular process analysis, and analysis of cell architectural changes and interactions under disease, treatment, or genetic perturbations. Human Subjects: No. De-identified Samples: Yes. FDA Regulated: No.
    doi: "doi:10.18130/V3/F3TD5R"
    page: "https://doi.org/10.18130/V3/F3TD5R"
    issued: "2025-07-01"
    created_on: "2025-02-27"
    version: "2.0"
    license: CC BY-NC-SA 4.0
    keywords:
      - AI-ready datasets
      - CM4AI
      - perturb-seq
      - SEC-MS
      - immunofluorescence imaging
      - MDA-MB-468
      - KOLF2.1J iPSCs
      - NPC
      - neurons
      - cardiomyocytes
      - vorinostat
      - paclitaxel
    purposes:
      - name: Purpose
        response: Provide AI-ready multimodal datasets (perturb-seq, SEC-MS, IF imaging) for functional genomics research and AI model development within the NIH Bridge2AI CM4AI Grand Challenge.
    tasks:
      - name: Primary Task
        response: AI model training on multimodal cellular data.
      - name: Secondary Task
        response: Cellular process analysis and mapping of cell architecture under treatments and genetic perturbations.
    addressing_gaps:
      - name: Gap Addressed
        response: Interim public release of multimodal functional genomics data enabling development of AI-ready maps of human cell architecture; computed cell maps to be provided in future releases.
    creators:
      - name: CM4AI Consortium
        principal_investigator:
          id: trey-ideker
          name: Trey Ideker
          affiliation:
            id: ucsd
            name: University of California San Diego
        affiliation:
          id: cm4ai
          name: Cell Maps for Artificial Intelligence (CM4AI)
      - name: Clark, Thomas
        principal_investigator:
          id: thomas-clark
          name: Thomas Clark
          affiliation:
            id: uva
            name: University of Virginia
        affiliation:
          id: cm4ai
          name: Cell Maps for Artificial Intelligence (CM4AI)
    funders:
      - name: NIH Bridge2AI Program
        grantor:
          id: nih
          name: National Institutes of Health
        grant:
          id: 1OT2OD032742-01
          name: Bridge2AI CM4AI
          grant_number: 1OT2OD032742-01
    instances:
      - name: IF imaging data
        representation: Immunofluorescence confocal microscopy images of MDA-MB-468 breast cancer cells under vorinostat, paclitaxel, and untreated conditions; 4-channel images (DAPI, calreticulin/ER, tubulin/microtubules, protein-of-interest).
        instance_type: Image
        data_type: Multichannel confocal microscopy images (ICC-IF)
        label: None (no explicit labels beyond experimental conditions)
        sampling_strategies:
          - name: Representativeness
            is_sample:
              - Yes
            is_random:
              - No
            source_data:
              - Commercially available de-identified human cell lines (MDA-MB-468)
            is_representative:
              - No
            why_not_representative:
              - Does not represent all biological variants in the general population.
      - name: SEC-MS proteomics data
        representation: Size Exclusion Chromatography–Mass Spectrometry (SEC-MS) protein-protein interaction measurements in KOLF2.1J iPSCs, iPSC-derived NPCs, neurons, cardiomyocytes, and MDA-MB-468 cancer cells (treated and untreated).
        instance_type: Proteomics assay
        data_type: Mass spectrometry-based protein complex profiling (SEC-MS)
        label: None (quantitative interaction/abundance readouts)
        sampling_strategies:
          - name: Representativeness
            is_sample:
              - Yes
            is_random:
              - No
            source_data:
              - Commercially available de-identified human cell lines
            is_representative:
              - No
            why_not_representative:
              - Limited set of proteins and conditions; not exhaustive of all biological variants.
      - name: CRISPRi perturb-seq scRNA-seq
        representation: CRISPRi perturb-seq single-cell RNA sequencing in undifferentiated KOLF2.1J iPSCs.
        instance_type: Single-cell sequencing
        data_type: scRNA-seq (perturb-seq)
        label: Guide/perturbation identity and treatment condition
        sampling_strategies:
          - name: Representativeness
            is_sample:
              - Yes
            is_random:
              - No
            source_data:
              - Commercially available de-identified human iPSC line KOLF2.1J
            is_representative:
              - No
            why_not_representative:
              - Specific perturbations and cell line; not representative of all human variation.
    acquisition_methods:
      - name: Data Acquisition
        description:
          - IF images obtained by ICC-IF staining and confocal microscopy (Lundberg Lab).
          - SEC-MS acquired via size exclusion chromatography followed by mass spectrometry to profile protein complexes.
          - Perturb-seq acquired as single-cell RNA-seq following CRISPRi perturbations.
        was_directly_observed: Yes
        was_reported_by_subjects: No
        was_inferred_derived: No
        was_validated_verified: Not specified
    collection_mechanisms:
      - name: Collection Mechanisms
        description:
          - Confocal microscopy imaging workflows (ICC-IF).
          - Size exclusion chromatography and mass spectrometry instrumentation (SEC-MS).
          - CRISPRi perturbation and single-cell RNA sequencing (perturb-seq).
    data_collectors:
      - name: Data Collection Teams
        description:
          - IF imaging performed in the Lundberg Lab (Stanford University).
          - SEC-MS and perturb-seq conducted by CM4AI teams at UC San Diego and UC San Francisco, with collaborators across consortium institutions.
    collection_timeframes:
      - name: Timeline
        description:
          - Data creation date: 2025-02-27.
          - Dataset publication date (V2): 2025-07-01.
          - Additional IF image archives published: 2025-10-22.
    ethical_reviews:
      - name: Data Governance & 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).
    data_protection_impacts:
      - name: Data Protection
        description:
          - Data derived from de-identified human cell lines; human subjects research not involved; minimal privacy risk.
    is_deidentified:
      name: De-identification
      description:
        - Samples are de-identified and derived from commercially available human cell lines; Human Subjects: No.
    external_resources:
      - name: External Data Links
        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 of this release in University of Virginia Dataverse.
    content_warnings:
      - name: Prohibited Uses
        warnings:
          - Not for clinical decision-making or any patient care context without appropriate regulatory oversight and approval.
    future_use_impacts:
      - name: Limitations and Risks
        description:
          - Interim release; computed cell maps not yet included.
          - Overlap of proteins across modalities is incomplete.
          - Domain expertise required for meaningful analysis; not representative of all biological variants, which may impact generalizability.
    discouraged_uses:
      - name: Clinical Use Restriction
        description:
          - Do not use for clinical decision-making or patient care without regulatory approvals.
    distribution_formats:
      - name: Distribution Formats
        description:
          - ZIP archives (image data)
          - JSON (RO-Crate metadata)
          - HTML datasheet and provenance graphs
    distribution_dates:
      - name: Release Dates
        description:
          - 2025-07-01 (Dataset V2 published)
          - 2025-10-22 (IF image ZIP archives added)
    license_and_use_terms:
      name: License and Terms
      description:
        - CC BY-NC-SA 4.0. Community norms expect proper citation as shown on the dataset page.
    maintainers:
      - name: Maintainers
        description:
          - Point of Contact: Trey Ideker (University of California San Diego).
          - Long-term preservation and hosting: University of Virginia Dataverse (institutional support).
          - Data Governance Committee: Jillian Parker (UC San Diego).
    existing_uses:
      - 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. doi: https://doi.org/10.1101/2024.11.03.621734
    updates:
      name: Update Plan
      description:
        - Regular updates and augmentation through November 2026; planned quarterly updates.
        - Long-term preservation in the University of Virginia Dataverse with committed institutional funds.
    version_access:
      name: Version Access
      description:
        - Prior versions are preserved in Dataverse; newer versions will be published with versioning (current V2).
    raw_sources:
      - name: Raw Data Availability
        description:
          - Raw sequencing data available via NCBI SRA (BioProject).
          - Proteomics raw/processed data available via MassIVE repositories as linked from the Dataverse page.
    subsets:
      - id: if-images-paclitaxel
        name: IF Images - MDA-MB-468 - Paclitaxel
        title: cm4ai-ifimages-mda-mb-468-paclitaxel.zip
        description:
          - Spatial localization of 464 proteins in MDA-MB-468 cells treated with paclitaxel; 4-channel ICC-IF confocal images (DAPI, ER (calreticulin), microtubules (tubulin), protein-of-interest).
        path: Images/cm4ai-ifimages-mda-mb-468-paclitaxel.zip
        media_type: application/zip
        compression: ZIP
        md5: 0d972b80744344ddeede516a0cf6e3d7
        is_data_split: no
        is_subpopulation: no
      - id: if-images-untreated
        name: IF Images - MDA-MB-468 - Untreated
        title: cm4ai-ifimages-mda-mb-468-untreated.zip
        description:
          - Spatial localization of 464 proteins in untreated MDA-MB-468 cells; 4-channel ICC-IF confocal images.
        path: Images/cm4ai-ifimages-mda-mb-468-untreated.zip
        media_type: application/zip
        compression: ZIP
        md5: a98affcc05429650c6bb3906cd836d55
        is_data_split: no
        is_subpopulation: no
      - id: if-images-vorinostat
        name: IF Images - MDA-MB-468 - Vorinostat
        title: cm4ai-ifimages-mda-mb-468-vorinostat.zip
        description:
          - Spatial localization of 464 proteins in MDA-MB-468 cells treated with vorinostat; 4-channel ICC-IF confocal images.
        path: Images/cm4ai-ifimages-mda-mb-468-vorinostat.zip
        media_type: application/zip
        compression: ZIP
        md5: ad4e68ccc14b0f3349dad3321e7b81b2
        is_data_split: no
        is_subpopulation: no
      - id: release-ro-crate-datasheet
        name: Release RO-Crate Datasheet (HTML)
        title: release-ro-crate-datasheet.html
        description:
          - HTML datasheet summarizing key release information.
        path: release-ro-crate-datasheet.html
        media_type: text/html
        md5: 599c9ece9b88b3ce797b82463b4a1eb4
        is_data_split: no
        is_subpopulation: no
      - id: release-ro-crate-metadata
        name: Release RO-Crate Metadata (JSON)
        title: release-ro-crate-metadata.json
        description:
          - RO-Crate with pointers to sub RO-Crates for the release.
        path: release-ro-crate-metadata.json
        format: JSON
        media_type: application/json
        md5: 99f9e00053bff3020fd9832a3a518bbb
        is_data_split: no
        is_subpopulation: no
      - id: images-paclitaxel-provenance
        name: IF Images Paclitaxel Provenance Graph (HTML)
        title: Images-paclitaxel-provenance-graph.html
        description:
          - HTML provenance graph for paclitaxel image subset (download to view).
        path: Images/paclitaxel/Images-paclitaxel-provenance-graph.html
        media_type: text/html
        md5: e38e63e4c8dfc5808a5ffa2d7829fc38
        is_data_split: no
        is_subpopulation: no
      - id: images-untreated-provenance
        name: IF Images Untreated Provenance Graph (HTML)
        title: Images-untreated-provenance-graph.html
        description:
          - HTML provenance graph for untreated image subset (download to view).
        path: Images/untreated/Images-untreated-provenance-graph.html
        media_type: text/html
        md5: 1a3b510f74d3f8647e07c6559ce64ee8
        is_data_split: no
        is_subpopulation: no
      - id: images-vorinostat-provenance
        name: IF Images Vorinostat Provenance Graph (HTML)
        title: Images-vorinostat-provenance-graph.html
        description:
          - HTML provenance graph for vorinostat image subset (download to view).
        path: Images/vorinostat/Images-vorinostat-provenance-graph.html
        media_type: text/html
        md5: 58935fe4e254b31d33fed019f24c7668
        is_data_split: no
        is_subpopulation: no
      - id: mass-spec-cancer-cells-provenance
        name: Mass Spec Cancer Cells Provenance Graph (HTML)
        title: mass-spec-cancer-cells-provenance-graph.html
        description:
          - HTML provenance graph for mass spec cancer cell data (download to view).
        path: mass-spec/cancer-cells/mass-spec-cancer-cells-provenance-graph.html
        media_type: text/html
        md5: 931ad9b552562024cb84ebe62d1f1838
        is_data_split: no
        is_subpopulation: no
      - id: mass-spec-cancer-cells-ro-crate
        name: Mass Spec Cancer Cells RO-Crate Metadata (JSON)
        title: mass-spec-cancer-cells-ro-crate-metadata.json
        description:
          - RO-Crate metadata for mass spectrometry cancer cell data.
        path: mass-spec/cancer-cells/mass-spec-cancer-cells-ro-crate-metadata.json
        format: JSON
        media_type: application/json
        md5: 3a7063bb391ea5e05a32ba5da5f4b2f8
        is_data_split: no
        is_subpopulation: no
    subpopulations: []
    sensitive_elements: []
    confidential_elements: []