=== YAML Fixing Applied ===
id: "doi:10.18130/V3/B35XWX"
name: Cell Maps for Artificial Intelligence - March 2025 Data Release (Beta)
title: Cell Maps for Artificial Intelligence - March 2025 Data Release (Beta)
description: "This dataset is the March 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 and iPSC-derived NPCs, neurons, and cardiomyocytes; and IF images in MDA-MB-468 breast cancer cells in the presence and absence of chemotherapy (vorinostat and paclitaxel). CM4AI output data are packaged with provenance graphs and rich metadata as AI-ready datasets in RO-Crate format using the FAIRSCAPE framework. Data presented here will be augmented regularly through the end of the project. CM4AI is a collaboration of UCSD, UCSF, Stanford, UVA, Yale, UA Birmingham, Simon Fraser University, and the Hastings Center. This data is Copyright (c) 2025 The Regents of the University of California except where otherwise noted. Spatial proteomics raw image data is copyright (c) 2025 The Board of Trustees of the Leland Stanford Junior University. Dataset licensed for reuse under Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International license (https://creativecommons.org/licenses/by-nc-sa/4.0/). Attribution is required to the copyright holders and the authors. Any publications referencing this data or derived products should cite the Related Publication below, as well as directly citing this data collection (2025-03-04). (2025-03-07)"
page: "https://doi.org/10.18130/V3/B35XWX"
doi: "doi:10.18130/V3/B35XWX"
issued: 2025-03-03
created_on: 2025-02-27
license: "https://creativecommons.org/licenses/by-nc-sa/4.0/"
version: "1.4"
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
created_by:
  - Cell Maps for Artificial Intelligence (CM4AI)
resources:
  - id: cm4ai-perturbation-cell-atlas
    name: CRISPR Perturbation Cell Atlas (KOLF2.1J iPSC)
    title: CRISPR Perturbation Cell Atlas (KOLF2.1J iPSC)
    description: Genome-scale CRISPRi perturb-seq in undifferentiated KOLF2.1J hiPSCs mapping transcriptional and fitness phenotypes for 11,739 targeted genes; packaged as AI-ready RO-Crate with provenance (FAIRSCAPE).
    conforms_to: "https://w3id.org/ro/crate/"
    purposes:
      - name: purpose
        response: Create AI-ready functional genomics maps to advance ML/AI on cell architecture and gene function.
    tasks:
      - name: primary-task
        response: Train and evaluate ML models on single-cell perturbation responses and gene-function inference.
    addressing_gaps:
      - name: gap
        response: Provide standardized, richly annotated, multi-omic cellular datasets for AI method development.
    creators:
      - name: Cell Maps for Artificial Intelligence (CM4AI) Team
        principal_investigator:
          name: Trey Ideker
          affiliation:
            - name: University of California San Diego
        affiliation:
          name: Cell Maps for Artificial Intelligence (CM4AI)
      - name: Dataset authorship includes contributors listed on the Dataverse citation record.
    funders:
      - grantor:
          name: National Institutes of Health
        grant:
          grant_number: 1OT2OD032742-01
    instances:
      - name: perturb-seq
        representation: Single-cell RNA-seq profiles following CRISPRi perturbations
        instance_type: Cells and gene perturbations with associated scRNA-seq reads and derived matrices
        data_type: Raw sequencing reads and RO-Crate metadata; derived expression matrices described in metadata
    acquisition_methods:
      - name: perturb-seq-acquisition
        description:
          - CRISPR interference (CRISPRi) perturbations profiled via single-cell RNA sequencing (perturb-seq).
        was_directly_observed: yes
        was_reported_by_subjects: no
        was_inferred_derived: yes
        was_validated_verified: yes
    collection_mechanisms:
      - name: sequencing-platforms
        description:
          - Single-cell RNA sequencing following CRISPRi perturbations (see RO-Crate for platform details).
    collection_timeframes:
      - name: creation-date
        description:
          - Data creation date reported as 2025-02-27; published 2025-03-03.
    ethical_reviews: []
    preprocessing_strategies:
      - name: packaging
        description:
          - Packaged as RO-Crate with provenance graphs using the FAIRSCAPE framework.
    external_resources: []
    subpopulations:
      - name: cell-lines
        identification:
          - KOLF2.1J human induced pluripotent stem cells (hiPSCs)
        distribution:
          - Undifferentiated KOLF2.1J hiPSCs
    deidentified: null
    is_deidentified:
      name: deidentification
      description:
        - Data are from established human cell lines; no individual-level PII included in the dataset description.
    distribution_formats:
      - name: formats
        description:
          - RO-Crate JSON-LD metadata
          - Dataverse web UI and API
    distribution_dates:
      - name: published
        description:
          - 2025-03-03
    license_and_use_terms:
      name: terms
      description:
        - Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
        - Attribution required to copyright holders and authors.
    ip_restrictions:
      name: copyright
      description:
        - Copyright (c) 2025 The Regents of the University of California except where otherwise noted.
    maintainers:
      - name: maintainers
        description:
          - University of Virginia Dataverse (hosting)
          - CM4AI team
    updates:
      name: update-plan
      description:
        - Data will be augmented regularly through the end of the project.
    subsets:
      - id: cm4ai-perturbation-cell-atlas-ro-crate
        name: ro-crate-metadata.json (CRISPR Perturbation Cell Atlas)
        title: ro-crate-metadata.json (CRISPR Perturbation Cell Atlas)
        description: RO-Crate metadata for the CRISPR Perturbation Cell Atlas in undifferentiated KOLF2.1J hiPSCs.
        path: CRISPR Perturbation Cell Atlas/ro-crate-metadata.json
        format: JSON
        media_type: application/json
        md5: cbdb263b1c099396d75e16f00a79a818
      - id: cm4ai-perturbation-raw-sequences-ro-crate
        name: ro-crate-metadata.json (CRISPR Perturbation RNA Sequences - Raw Sequences)
        title: ro-crate-metadata.json (CRISPR Perturbation RNA Sequences - Raw Sequences)
        description: RO-Crate metadata for raw sequence data of the CRISPRi Perturbation Cell Atlas in KOLF2.1J hiPSCs.
        path: CRISPR Perturbation RNA Sequences - Raw Sequences/ro-crate-metadata.json
        format: JSON
        media_type: application/json
        md5: 1cafefa32a897998e3e2ba0a29a3ef5c
  - id: cm4ai-protein-localization-if
    name: Protein Localization Subcellular Images (MDA-MB-468)
    title: Protein Localization Subcellular Images (MDA-MB-468)
    description: Immunofluorescence-based subcellular protein localization images for 563 proteins in MDA-MB-468 cells under untreated and chemotherapy conditions (paclitaxel, vorinostat); confocal microscopy, Lundberg Lab at Stanford University.
    purposes:
      - name: purpose
        response: Provide high-content cellular imaging for AI models of protein localization and cell architecture.
    tasks:
      - name: image-ml-tasks
        response: Train and evaluate computer vision models for subcellular protein localization and treatment response.
    creators:
      - name: Cell Maps for Artificial Intelligence (CM4AI) Team
        principal_investigator:
          name: Emma Lundberg
          affiliation:
            - name: Stanford University
        affiliation:
          name: Cell Maps for Artificial Intelligence (CM4AI)
    instances:
      - name: if-images
        representation: Multi-channel confocal microscopy images (DAPI, ER, microtubules, protein-of-interest)
        instance_type: Cells imaged under different treatment conditions
        data_type: Image files packaged in ZIP archives with RO-Crate metadata
    acquisition_methods:
      - name: microscopy
        description:
          - Immunofluorescence staining (DAPI; calreticulin for ER; tubulin for microtubules; antibody to protein of interest) and confocal microscopy.
        was_directly_observed: yes
        was_reported_by_subjects: no
        was_inferred_derived: no
        was_validated_verified: yes
    collection_mechanisms:
      - name: imaging-apparatus
        description:
          - Confocal microscopy workflows (Lundberg Lab, Stanford University).
    collection_timeframes:
      - name: creation-publication
        description:
          - Data creation date reported as 2025-02-27; published 2025-03-03.
    external_resources: []
    subpopulations:
      - name: cell-lines
        identification:
          - MDA-MB-468 breast cancer cells
        distribution:
          - Untreated and treated (paclitaxel, vorinostat)
    distribution_formats:
      - name: formats
        description:
          - ZIP archives
          - Dataverse web UI and API
    distribution_dates:
      - name: published
        description:
          - 2025-03-03
    license_and_use_terms:
      name: terms
      description:
        - Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
        - Spatial proteomics raw image data is copyright (c) 2025 The Board of Trustees of the Leland Stanford Junior University.
    ip_restrictions:
      name: copyright
      description:
        - Copyright (c) 2025 The Regents of the University of California except where otherwise noted.
        - Spatial proteomics raw image data Copyright (c) 2025 The Board of Trustees of the Leland Stanford Junior University.
    maintainers:
      - name: maintainers
        description:
          - University of Virginia Dataverse (hosting)
          - CM4AI team
    updates:
      name: update-plan
      description:
        - Data will be augmented regularly through the end of the project.
    subsets:
      - id: cm4ai-if-images-untreated
        name: cm4ai-v0.6-beta-if-images-untreated.zip
        title: Untreated MDA-MB-468 IF images (563 proteins)
        description: Spatial localization of 563 proteins in untreated MDA-MB-468 cells (ICC-IF; confocal).
        path: Protein Localization Subcellular Images/cm4ai-v0.6-beta-if-images-untreated.zip
        compression: ZIP
        media_type: application/zip
        md5: 0b4d129f5fbc3bb7f7ea564cd032cef7
      - id: cm4ai-if-images-paclitaxel
        name: cm4ai-v0.6-beta-if-images-paclitaxel.zip
        title: Paclitaxel-treated MDA-MB-468 IF images (563 proteins)
        description: Spatial localization of 563 proteins in MDA-MB-468 cells treated with paclitaxel (ICC-IF; confocal).
        path: Protein Localization Subcellular Images/cm4ai-v0.6-beta-if-images-paclitaxel.zip
        compression: ZIP
        media_type: application/zip
        md5: 9422486c80bc9e1d35b2fbbc72a5f043
      - id: cm4ai-if-images-vorinostat
        name: cm4ai-v0.6-beta-if-images-vorinostat.zip
        title: Vorinostat-treated MDA-MB-468 IF images (563 proteins)
        description: Spatial localization of 563 proteins in MDA-MB-468 cells treated with vorinostat (ICC-IF; confocal).
        path: Protein Localization Subcellular Images/cm4ai-v0.6-beta-if-images-vorinostat.zip
        compression: ZIP
        media_type: application/zip
        md5: ac577109a41a9806978461157b777d52
  - id: cm4ai-protein-protein-interaction-sec-ms
    name: Protein-protein Interaction SEC-MS
    title: Protein-protein Interaction SEC-MS
    description: Size exclusion chromatography–mass spectrometry (SEC-MS) on undifferentiated KOLF2.1J hiPSCs, generated in the Nevan Krogan laboratory at UCSF; data to be uploaded to PRIDE when available; packaged with RO-Crate metadata.
    conforms_to: "https://w3id.org/ro/crate/"
    purposes:
      - name: purpose
        response: Provide proteome-scale complex assembly/interaction profiles for AI-based cell mapping.
    tasks:
      - name: ml-tasks
        response: Train and assess models for protein complex detection and interaction network inference.
    creators:
      - name: Cell Maps for Artificial Intelligence (CM4AI) Team
        principal_investigator:
          name: Nevan Krogan
          affiliation:
            - name: University of California San Francisco
        affiliation:
          name: Cell Maps for Artificial Intelligence (CM4AI)
    instances:
      - name: sec-ms
        representation: Protein complex fractionation profiles and mass spectra
        instance_type: Proteins and complexes across SEC fractions
        data_type: RO-Crate JSON-LD metadata with links to proteomics data (PRIDE upload planned)
    acquisition_methods:
      - name: chromatography-ms
        description:
          - Size exclusion chromatography coupled to mass spectrometry (SEC-MS) on undifferentiated KOLF2.1J hiPSCs.
        was_directly_observed: yes
        was_reported_by_subjects: no
        was_inferred_derived: yes
        was_validated_verified: yes
    collection_mechanisms:
      - name: instrumentation
        description:
          - SEC-MS proteomics workflow (Nevan Krogan laboratory, UCSF).
    collection_timeframes:
      - name: creation-publication
        description:
          - Data creation date reported as 2025-02-27; published 2025-03-03.
    external_resources:
      - name: pride-deposition
        external_resources:
          - PRIDE (planned upload when available)
        archival:
          - PRIDE archival planned by authors
        future_guarantees:
          - Not specified
        restrictions:
          - Not specified
    distribution_formats:
      - name: formats
        description:
          - RO-Crate JSON-LD metadata
          - Dataverse web UI and API
    distribution_dates:
      - name: published
        description:
          - 2025-03-03
    license_and_use_terms:
      name: terms
      description:
        - Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
        - Attribution required to copyright holders and authors.
    ip_restrictions:
      name: copyright
      description:
        - Copyright (c) 2025 The Regents of the University of California except where otherwise noted.
    maintainers:
      - name: maintainers
        description:
          - University of Virginia Dataverse (hosting)
          - CM4AI team
    updates:
      name: update-plan
      description:
        - Data will be augmented regularly through the end of the project.
    subsets:
      - id: cm4ai-sec-ms-ro-crate
        name: ro-crate-metadata.json (Protein-protein Interaction SEC-MS)
        title: ro-crate-metadata.json (Protein-protein Interaction SEC-MS)
        description: RO-Crate metadata for SEC-MS dataset in undifferentiated KOLF2.1J hiPSCs.
        path: Protein-protein Interaction SEC-MS/ro-crate-metadata.json
        format: JSON
        media_type: application/json
        md5: cb67e7749b15ce87b9042a9feba9d032
purposes:
  - name: overall-purpose
    response: Provide AI-ready, multi-modal cellular datasets for mapping human cell architecture and function.
tasks:
  - name: overall-tasks
    response: Machine learning on perturb-seq, proteomics (SEC-MS), and high-content imaging to build cell maps.
addressing_gaps:
  - name: overall-gaps
    response: Standardized, richly annotated datasets enabling reproducible AI development in functional genomics.
creators:
  - name: Cell Maps for Artificial Intelligence (CM4AI) Team
    principal_investigator:
      name: Trey Ideker
      affiliation:
        - name: University of California San Diego
    affiliation:
      name: Cell Maps for Artificial Intelligence (CM4AI)
funders:
  - grantor:
      name: National Institutes of Health
    grant:
      grant_number: 1OT2OD032742-01
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 Nov 4;2024.11.03.621734. PMCID: PMC11580897. doi: https://doi.org/10.1101/2024.11.03.621734
distribution_formats:
  - name: collection-distribution
    description:
      - Dataverse repository (web UI and Data Access API)
      - RO-Crate JSON-LD packaging (FAIRSCAPE)
distribution_dates:
  - name: collection-published
    description:
      - 2025-03-03
license_and_use_terms:
  name: collection-terms
  description:
    - Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
    - Proper citation and attribution required; see dataset page.
ip_restrictions:
  name: collection-copyright
  description:
    - Copyright (c) 2025 The Regents of the University of California except where otherwise noted.
    - Spatial proteomics raw image data Copyright (c) 2025 The Board of Trustees of the Leland Stanford Junior University.
maintainers:
  - name: hosting
    description:
      - University of Virginia Dataverse
  - name: point-of-contact
    description:
      - Trey Ideker (University of California San Diego) via Dataverse contact
updates:
  name: collection-update-plan
  description:
    - Data will be augmented regularly through the end of the project.