# === 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: >
  March 2025 Beta data release of Cell Maps for Artificial Intelligence (CM4AI; CM4AI.org),
  the Functional Genomics Grand Challenge in the NIH Bridge2AI program. This release includes:
  (1) perturb-seq data in undifferentiated KOLF2.1J iPSCs; (2) SEC-MS proteomics in
  undifferentiated KOLF2.1J iPSCs and iPSC-derived NPCs, neurons, and cardiomyocytes; and
  (3) immunofluorescence (IF) subcellular images in MDA-MB-468 breast cancer cells under
  chemotherapy treatments (vorinostat, paclitaxel) and untreated controls. CM4AI output data
  are packaged with provenance graphs and rich metadata as AI-ready datasets in RO-Crate format
  using the FAIRSCAPE framework. Data will be augmented regularly through the end of the project.
  Collaboration includes UCSD, UCSF, Stanford, UVA, Yale, University of Alabama at Birmingham,
  Simon Fraser University, and The Hastings Center. Copyright (c) 2025 The Regents of the
  University of California except where noted; spatial proteomics raw image data copyright (c)
  2025 The Board of Trustees of the Leland Stanford Junior University. Licensed under
  Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
language: English
publisher: "https://dataverse.lib.virginia.edu"
issued: 2025-03-03
page: "https://doi.org/10.18130/V3/B35XWX"
created_on: 2025-02-27
last_updated_on: 2025-03-07
doi: "doi:10.18130/V3/B35XWX"
license: "CC BY-NC-SA 4.0 (https://creativecommons.org/licenses/by-nc-sa/4.0/)"
version: "1.4"
keywords:
  - AI
  - artificial intelligence
  - machine learning
  - Bridge2AI
  - CM4AI
  - CRISPR/Cas9
  - perturb-seq
  - perturbation sequencing
  - single-cell RNA sequencing
  - scRNAseq
  - KOLF2.1J
  - induced pluripotent stem cell
  - iPSC
  - neural progenitor cell
  - NPC
  - neuron
  - cardiomyocyte
  - protein-protein interaction
  - SEC-MS
  - size exclusion chromatography
  - mass spectroscopy
  - protein localization
  - subcellular imaging
  - breast cancer
  - MDA-MB-468
  - paclitaxel
  - vorinostat
status:
created_by:
  - CM4AI Consortium
  - University of Virginia Dataverse
purposes:
  - name: Primary Purpose
    response: Provide AI-ready multimodal functional genomics datasets (scRNA-seq perturb-seq, proteomics, and subcellular imaging) with rich provenance to enable machine learning and mapping of human cell architecture.
tasks:
  - name: Machine learning applications
    response: Train and evaluate models for gene function, protein localization, protein-protein interaction networks, and treatment response in disease-relevant cell lines.
addressing_gaps:
  - name: Addressing gaps
    response: Deliver standardized, FAIR, RO-Crate-packaged, multimodal cellular datasets to support AI methods in functional genomics and cell architecture mapping.
creators:
  - name: CM4AI Consortium
    principal_investigator:
      id: trey-ideker
      name: Trey Ideker
      description: Point of contact listed as Ideker Trey (University of California San Diego).
      affiliation:
        id: org-ucsd
        name: University of California San Diego
    affiliation:
      id: org-ucsd
      name: University of California San Diego
funders:
  - name: NIH Bridge2AI
    grantor:
      id: nih
      name: National Institutes of Health
    grant:
      id: OT2OD032742-01
      name: NIH award
      grant_number: 1OT2OD032742-01
instances:
  - name: Data modalities and instances
    representation: >
      Multimodal cellular data: (a) perturb-seq (scRNA-seq) in KOLF2.1J iPSCs, (b) size exclusion
      chromatography-mass spectrometry (SEC-MS) in KOLF2.1J iPSCs and iPSC-derived NPCs, neurons,
      and cardiomyocytes, and (c) immunofluorescence subcellular images in MDA-MB-468 cells under
      paclitaxel, vorinostat, and untreated conditions.
    instance_type: Multiple modalities (transcriptomics, proteomics, imaging)
    data_type: Raw sequences (RNA), proteomics measurements (SEC-MS), immunofluorescence images; RO-Crate metadata and provenance.
    counts:
    label: Treatment conditions (paclitaxel, vorinostat, untreated) and cell type context.
sampling_strategies: []
missing_information: []
relationships:
  - name: Relationships
    description:
      - Multimodal alignment across treatments and cell types; explicit provenance via RO-Crate; protein localization and protein interaction contexts.
splits: []
anomalies: []
external_resources:
  - name: External repositories
    external_resources:
      - PRIDE (planned upload for SEC-MS dataset when available)
    future_guarantees:
      - Not specified
    archival:
      - RO-Crate metadata and provenance graphs included with each dataset
    restrictions:
      - Subject to dataset license (CC BY-NC-SA 4.0) and noted copyrights
confidential_elements: []
content_warnings: []
subpopulations:
  - name: Subpopulations and conditions
    identification:
      - Cell types: KOLF2.1J iPSCs; iPSC-derived NPCs, neurons, cardiomyocytes; MDA-MB-468 breast cancer cells
      - Treatments: paclitaxel, vorinostat, untreated
    distribution:
      - Not quantified in this release page
sensitive_elements: []
acquisition_methods:
  - name: Acquisition summary
    description:
      - CRISPRi perturb-seq (scRNA-seq) in KOLF2.1J iPSCs; SEC-MS proteomics in iPSCs and derivatives; immunofluorescence imaging with confocal microscopy in MDA-MB-468 cells under treatments and control.
    was_directly_observed: "Yes"
    was_reported_by_subjects: "No"
    was_inferred_derived: "No"
    was_validated_verified:
collection_mechanisms:
  - name: Collection methods
    description:
      - CRISPRi screens and single-cell RNA sequencing (perturb-seq)
      - Size exclusion chromatography-mass spectrometry (SEC-MS)
      - Immunofluorescence-based staining (ICC-IF) and confocal microscopy
data_collectors: []
collection_timeframes:
  - name: Release timeframe
    description:
      - Data creation date: "2025-02-27; publication date: 2025-03-03; March 2025 Beta release; updates noted 2025-03-07. Production locations include UC San Diego, UCSF, Stanford University, and University of Virginia."
ethical_reviews: []
data_protection_impacts: []
preprocessing_strategies:
  - name: Packaging and provenance
    description:
      - Packaged as RO-Crate with provenance graphs and rich metadata using the FAIRSCAPE framework.
cleaning_strategies: []
labeling_strategies: []
raw_sources:
  - name: Raw data availability
    description:
      - Raw RNA sequences for CRISPR perturbation are included; SEC-MS data to be uploaded to PRIDE when available.
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"
use_repository: []
other_tasks:
  - name: Potential downstream tasks
    description:
      - Multimodal integration, cell state classification, protein complex inference, treatment response prediction, and benchmarking AI models on standardized cellular datasets.
future_use_impacts:
  - name: Update cadence and policy considerations
    description:
      - Dataset will be augmented regularly; collection under review for potential modification in compliance with Administration directives (as noted on the collection page).
discouraged_uses: []
distribution_formats:
  - name: Distribution formats
    description:
      - RO-Crate metadata (JSON), ZIP archives for image bundles; access via University of Virginia Dataverse and Data Access API for large files.
distribution_dates:
  - name: Initial public release
    description:
      - 2025-03-03
license_and_use_terms:
  name: License and terms
  description:
    - Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0). Attribution required to copyright holders and authors. Cite related publication(s) and this data collection (2025-03-04).
ip_restrictions:
  name: Copyright notices
  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.
regulatory_restrictions:
  name: Regulatory restrictions
  description:
    - Not specified.
maintainers:
  - name: Hosting and contact
    description:
      - Hosted by University of Virginia Dataverse; point of contact listed as Ideker Trey (University of California San Diego).
errata: []
updates:
  name: Update plan
  description:
    - Data will be augmented regularly through the end of the project; versioned within Dataverse.
retention_limit:
version_access:
extension_mechanism:
is_deidentified:
  name: Deidentification
  description:
    - Dataset comprises cell line and derived cell type data (no direct personal identifiers); not human subject-reported data.
is_tabular:
subsets:
  - id: subset-crispri-perturbation-cell-atlas-rocrate
    name: CRISPR Perturbation Cell Atlas RO-Crate metadata
    title: ro-crate-metadata.json (CRISPR Perturbation Cell Atlas)
    description: >
      RO-Crate metadata JSON describing an expressed genome-scale CRISPRi Perturbation Cell Atlas
      in undifferentiated KOLF2.1J hiPSCs mapping transcriptional and fitness phenotypes associated
      with 11,739 targeted genes.
    path: CRISPR Perturbation Cell Atlas/ro-crate-metadata.json
    format: JSON
    media_type: application/json
    md5: cbdb263b1c099396d75e16f00a79a818
    issued: 2025-03-03
    conforms_to: "https://w3id.org/ro/crate"
  - id: subset-crispri-raw-rna-sequences-rocrate
    name: CRISPR Perturbation RNA Sequences - Raw Sequences RO-Crate metadata
    title: ro-crate-metadata.json (CRISPR Perturbation RNA Sequences - Raw Sequences)
    description: >
      RO-Crate metadata JSON for raw RNA sequence data from an expressed genome-scale 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
    issued: 2025-03-03
    conforms_to: "https://w3id.org/ro/crate"
  - id: subset-if-images-paclitaxel
    name: Protein Localization Subcellular Images (paclitaxel)
    title: cm4ai-v0.6-beta-if-images-paclitaxel.zip
    description: >
      Spatial localization of 563 proteins in MDA-MB-468 cells treated with paclitaxel, imaged by
      ICC-IF and confocal microscopy (Lundberg Lab, Stanford University).
    path: Protein Localization Subcellular Images/cm4ai-v0.6-beta-if-images-paclitaxel.zip
    compression: ZIP
    media_type: application/zip
    md5: 9422486c80bc9e1d35b2fbbc72a5f043
    issued: 2025-03-03
  - id: subset-if-images-untreated
    name: Protein Localization Subcellular Images (untreated)
    title: cm4ai-v0.6-beta-if-images-untreated.zip
    description: >
      Spatial localization of 563 proteins in untreated MDA-MB-468 cells, imaged by ICC-IF and
      confocal microscopy (Lundberg Lab, Stanford University).
    path: Protein Localization Subcellular Images/cm4ai-v0.6-beta-if-images-untreated.zip
    compression: ZIP
    media_type: application/zip
    md5: 0b4d129f5fbc3bb7f7ea564cd032cef7
    issued: 2025-03-03
  - id: subset-if-images-vorinostat
    name: Protein Localization Subcellular Images (vorinostat)
    title: cm4ai-v0.6-beta-if-images-vorinostat.zip
    description: >
      Spatial localization of 563 proteins in MDA-MB-468 cells treated with vorinostat, imaged by
      ICC-IF and confocal microscopy (Lundberg Lab, Stanford University).
    path: Protein Localization Subcellular Images/cm4ai-v0.6-beta-if-images-vorinostat.zip
    compression: ZIP
    media_type: application/zip
    md5: ac577109a41a9806978461157b777d52
    issued: 2025-03-03
  - id: subset-sec-ms-rocrate
    name: Protein-protein Interaction SEC-MS RO-Crate metadata
    title: ro-crate-metadata.json (Protein-protein Interaction SEC-MS)
    description: >
      RO-Crate metadata JSON for SEC-MS data generated on undifferentiated KOLF2.1J hiPSCs (Nevan
      Krogan lab, UCSF); dataset to be uploaded to PRIDE when available.
    path: Protein-protein Interaction SEC-MS/ro-crate-metadata.json
    format: JSON
    media_type: application/json
    md5: cb67e7749b15ce87b9042a9feba9d032
    issued: 2025-03-03
    conforms_to: "https://w3id.org/ro/crate"
third_party_sharing:
  name: Distribution to third parties
  description: Public distribution via University of Virginia Dataverse; files accessible individually and via Data Access API.