=== 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).
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
  - artificial intelligence
  - Bridge2AI
  - CM4AI
  - machine learning
  - perturb-seq
  - perturbation sequencing
  - single-cell RNA sequencing
  - scRNAseq
  - CRISPR/Cas9
  - SEC-MS
  - size exclusion chromatography
  - mass spectroscopy
  - protein-protein interaction
  - protein localization
  - subcellular imaging
  - breast cancer
  - MDA-MB-468
  - KOLF2.1J
  - iPSC
  - induced pluripotent stem cell
  - neural progenitor cell
  - NPC
  - neuron
  - cardiomyocyte
  - paclitaxel
  - vorinostat
resources:
  - id: doi:10.18130/V3/F3TD5R#dataset
    name: CM4AI June 2025 Data Release (Beta)
    title: CM4AI June 2025 Data Release (Beta)
    description: Multi-modal functional genomics release including perturb-seq (CRISPRi scRNA-seq), size exclusion chromatography mass spectrometry (SEC-MS), and immunofluorescence (IF) imaging across iPSCs, iPSC-derived lineages (NPCs, neurons, cardiomyocytes), and MDA-MB-468 cancer cells under treatment and control conditions.
    doi: "doi:10.18130/V3/F3TD5R"
    page: "https://doi.org/10.18130/V3/F3TD5R"
    issued: 2025-07-01
    version: "2.0"
    license: CC BY-NC-SA 4.0
    keywords:
      - AI
      - artificial intelligence
      - Bridge2AI
      - CM4AI
      - machine learning
      - perturb-seq
      - CRISPR/Cas9
      - SEC-MS
      - protein-protein interaction
      - protein localization
      - subcellular imaging
      - single-cell RNA sequencing
      - scRNAseq
      - breast cancer
      - MDA-MB-468
      - KOLF2.1J
      - iPSC
      - NPC
      - neuron
      - cardiomyocyte
      - paclitaxel
      - vorinostat
    purposes:
      - name: Purpose
        response: Provide AI-ready multi-modal datasets to support research in functional genomics and human cell architecture.
      - name: Purpose
        response: Enable AI model training and benchmarking on perturbation-response, protein interaction, and protein localization data.
      - name: Purpose
        response: Support analysis of cellular processes and architectural changes under disease-relevant conditions, treatments, and genetic perturbations.
    tasks:
      - name: Task
        response: AI model training and evaluation on multi-omic imaging and sequencing data.
      - name: Task
        response: Bioinformatics analysis of perturb-seq, SEC-MS, and IF imaging datasets.
    addressing_gaps:
      - name: AddressingGap
        response: Provide integrated, AI-ready cell maps resources from disease-relevant human cell lines to address the scarcity of standardized, multi-modal functional genomics datasets.
    creators:
      - name: CM4AI Consortium - UC San Diego
        principal_investigator:
          id: "https://orcid.org/0000-0002-1708-8454"
          name: Ideker T
          description: Trey Ideker
        affiliation:
          name: University of California San Diego
      - name: CM4AI Consortium - UC San Francisco
        principal_investigator:
          id: "https://orcid.org/0000-0003-4902-337X"
          name: Krogan N
          description: Nevan Krogan
        affiliation:
          name: University of California San Francisco
      - name: CM4AI Consortium - Stanford University
        principal_investigator:
          id: "https://orcid.org/0000-0001-7034-0850"
          name: Lundberg E
          description: Emma Lundberg
        affiliation:
          name: Stanford University
      - name: CM4AI Consortium - UC San Diego (Genome Engineering)
        principal_investigator:
          id: "https://orcid.org/0000-0002-3383-1287"
          name: Mali P
          description: Prashant Mali
        affiliation:
          name: University of California San Diego
      - name: CM4AI - University of Virginia
        principal_investigator:
          id: "https://orcid.org/0000-0003-4060-7360"
          name: Clark T
          description: Tim Clark
        affiliation:
          name: University of Virginia
    funders:
      - name: NIH Bridge2AI Program
        grantor:
          name: National Institutes of Health
        grant:
          name: Bridge2AI Functional Genomics Grand Challenge
          grant_number: 1OT2OD032742-01
    instances:
      - name: Instance
        representation: Multi-modal instances representing cellular states and protein features across modalities (scRNA-seq perturb-seq, SEC-MS PPI fractions, IF images).
        instance_type: Modalities include perturb-seq (CRISPRi scRNA-seq), SEC-MS protein-protein interaction data, and immunofluorescence confocal images.
        data_type: Raw and processed experimental measurements and images including sequencing reads (externally in SRA), mass spectrometry outputs (externally in MassIVE), and multi-channel microscopy images (ZIP archives).
      - name: Instance
        representation: Cell line-based experimental conditions and treatments (e.g., MDA-MB-468 with paclitaxel or vorinostat, untreated controls; KOLF2.1J iPSCs and derived NPCs, neurons, cardiomyocytes).
        instance_type: Cell types and experimental conditions
        data_type: Multichannel images, mass spec chromatographic fractions, single-cell transcriptomes under CRISPRi perturbations.
    sampling_strategies:
      - name: SamplingStrategy
        is_sample:
          - yes
        source_data:
          - Commercially available de-identified human cell lines and derived lineages.
        is_representative:
          - no
        why_not_representative:
          - Data do not represent all biological variants in the broader population; protein target sets incompletely overlap across modalities.
        strategies:
          - Targeted sets of proteins and perturbations per modality; overlapping but non-identical coverage across datasets.
    relationships:
      - name: Relationships
        description:
          - Cross-modal linkage at the protein and gene target level (perturb-seq targets, SEC-MS PPI fractions, IF protein localization for overlapping protein sets).
    subsets:
      - id: doi:10.18130/V3/F3TD5R#subset-perturb-seq
        name: Perturb-seq in KOLF2.1J iPSCs
        title: CRISPRi perturb-seq (scRNA-seq) in undifferentiated KOLF2.1J iPSCs
        description: Single-cell RNA-seq under CRISPRi perturbations in KOLF2.1J iPSCs; external raw data available via NCBI SRA BioProject.
      - id: doi:10.18130/V3/F3TD5R#subset-sec-ms
        name: SEC-MS protein-protein interaction datasets
        title: Size Exclusion Chromatography Mass Spectrometry (SEC-MS)
        description: PPI profiling via SEC-MS in KOLF2.1J iPSCs, iPSC-derived NPCs, neurons, cardiomyocytes, and MDA-MB-468 cells (treated and untreated); with external MassIVE repositories for raw/processed data.
      - id: doi:10.18130/V3/F3TD5R#subset-if-imaging
        name: IF imaging in MDA-MB-468 cells
        title: Immunofluorescence protein localization images
        description: "Confocal IF images profiling localization of 464 proteins in MDA-MB-468 cells under paclitaxel, vorinostat, and untreated conditions (multi-channel: DAPI, ER, microtubules, protein-of-interest)."
    external_resources:
      - name: ExternalResource
        external_resources:
          - Sequence Read Archive (SRA) Data: NCBI BioProject (perturb-seq)
      - name: ExternalResource
        external_resources:
          - Mass Spectrometry Data (Human iPSCs): MassIVE Repository
      - name: ExternalResource
        external_resources:
          - Mass Spectrometry Data (Human Cancer Cells): MassIVE Repository
    confidential_elements:
      - name: Confidentiality
        description:
          - No; data derived from de-identified human cell lines; no human subjects.
    is_deidentified:
      name: Deidentification
      description:
        - Human Subjects: No; De-identified Samples: Yes.
    sensitive_elements:
      - name: SensitiveElement
        description:
          - No personally identifiable or clinical data; laboratory measurements on de-identified human cell lines.
    acquisition_methods:
      - name: InstanceAcquisition
        description:
          - Multi-modal experimental acquisition including CRISPRi perturb-seq (scRNA-seq), SEC-MS for protein-protein interactions, and immunofluorescence confocal microscopy for protein localization.
        was_directly_observed: yes (sequencing reads, mass spectra, and microscopy images)
        was_reported_by_subjects: no
        was_inferred_derived: yes (downstream computed features and summaries)
    collection_mechanisms:
      - name: CollectionMechanism
        description:
          - CRISPRi perturbations followed by single-cell RNA sequencing (perturb-seq).
      - name: CollectionMechanism
        description:
          - Size-exclusion chromatography fractionation with mass spectrometry (SEC-MS) for protein complex profiling.
      - name: CollectionMechanism
        description:
          - Immunofluorescence-based staining (ICC-IF) and confocal microscopy for protein localization (multi-channel: DAPI, calreticulin/ER, tubulin/microtubules, protein-of-interest).
    data_collectors:
      - name: DataCollector
        description:
          - CM4AI consortium laboratories at UC San Diego, UC San Francisco, Stanford University, and University of Virginia; IF imaging performed in the Lundberg Lab at Stanford University.
    collection_timeframes:
      - name: CollectionTimeframe
        description:
          - Data creation date 2025-02-27; dataset release 2025-07-01 (Version 2.0). Additional image archives published 2025-10-22.
    ethical_reviews:
      - name: EthicalReview
        description:
          - Ethical oversight and governance contacts: Data Governance Committee lead Jillian Parker (jillianparker@health.ucsd.edu). Ethical review by Vardit Ravitsky (ravitskyv@thehastingscenter.org) and Jean-Christophe Bélisle-Pipon (jean-christophe_belisle-pipon@sfu.ca). Human Subjects: No; FDA regulated: No.
    preprocessing_strategies:
      - name: PreprocessingStrategy
        description:
          - RO-Crate metadata packaging provided for release and modality sub-packages; modality-specific preprocessing not fully enumerated in this release.
    existing_uses:
      - name: ExistingUse
        description:
          - Clark T et al. 2024. Cell Maps for Artificial Intelligence: AI-Ready Maps of Human Cell Architecture from Disease-Relevant Cell Lines. bioRxiv. doi:10.1101/2024.05.21.589311
      - name: ExistingUse
        description:
          - Nourreddine S et al. 2024. A Perturbation Cell Atlas of Human Induced Pluripotent Stem Cells. bioRxiv. doi:10.1101/2024.11.03.621734
    other_tasks:
      - name: OtherTask
        description:
          - Cross-modal integration and representation learning across perturb-seq, SEC-MS, and IF imaging.
      - name: OtherTask
        description:
          - Predictive modeling of protein localization and interaction changes under treatments.
    future_use_impacts:
      - name: FutureUseImpact
        description:
          - Interim release; protein sets incompletely overlap across modalities; may bias models toward targeted proteins and specific cell lines. Dataset does not cover all biological variants; users should account for cell type and treatment specificity to avoid unfair generalization.
    discouraged_uses:
      - name: DiscouragedUse
        description:
          - Not for clinical decision-making or patient care without appropriate regulatory oversight and approval.
    distribution_formats:
      - name: DistributionFormat
        description:
          - RO-Crate JSON metadata (release and sub-RO-crates)
      - name: DistributionFormat
        description:
          - HTML datasheet and provenance graph pages
      - name: DistributionFormat
        description:
          - ZIP archives containing multi-channel IF images
    distribution_dates:
      - name: DistributionDate
        description:
          - 2025-07-01 (initial V2 release)
      - name: DistributionDate
        description:
          - 2025-10-22 (IF image archives: paclitaxel, untreated, vorinostat)
    license_and_use_terms:
      name: LicenseAndUseTerms
      description:
        - CC BY-NC-SA 4.0; Community norms expect proper citation using the dataset citation shown on the dataset page.
    maintainers:
      - name: Maintainer
        description:
          - Point of Contact: Trey Ideker (University of California San Diego) via Dataverse contact.
      - name: Maintainer
        description:
          - Data Governance Committee: Jillian Parker (jillianparker@health.ucsd.edu).
      - name: Maintainer
        description:
          - Long-term preservation in University of Virginia Dataverse with committed institutional support.
    updates:
      name: UpdatePlan
      description:
        - Dataset will be updated and augmented quarterly through November 2026. Updates communicated via Dataverse versioning; long-term preservation at UVA Dataverse.
  - id: doi:10.18130/V3/F3TD5R#release-ro-crate-datasheet.html
    name: release-ro-crate-datasheet.html
    title: HTML datasheet summarizing key release information
    description: HTML datasheet summarizing key release information.
    media_type: text/html
    md5: 599c9ece9b88b3ce797b82463b4a1eb4
    issued: 2025-07-01
    path: release-ro-crate-datasheet.html
  - id: doi:10.18130/V3/F3TD5R#release-ro-crate-metadata.json
    name: release-ro-crate-metadata.json
    title: Release RO-Crate with pointers to sub ro-crates
    description: RO-Crate metadata for the release with pointers to sub-RO-crates.
    media_type: application/json
    md5: 99f9e00053bff3020fd9832a3a518bbb
    issued: 2025-07-01
    path: release-ro-crate-metadata.json
  - id: doi:10.18130/V3/F3TD5R#cm4ai-ifimages-mda-mb-468-paclitaxel.zip
    name: cm4ai-ifimages-mda-mb-468-paclitaxel.zip
    title: IF images - MDA-MB-468 treated with paclitaxel
    description: "Spatial localization of 464 proteins in MDA-MB-468 cells treated with paclitaxel via ICC-IF and confocal microscopy (channels: DAPI, ER calreticulin, tubulin, protein-of-interest)."
    media_type: application/zip
    compression: ZIP
    md5: 0d972b80744344ddeede516a0cf6e3d7
    issued: 2025-10-22
    path: Images/cm4ai-ifimages-mda-mb-468-paclitaxel.zip
  - id: doi:10.18130/V3/F3TD5R#cm4ai-ifimages-mda-mb-468-untreated.zip
    name: cm4ai-ifimages-mda-mb-468-untreated.zip
    title: IF images - MDA-MB-468 untreated
    description: "Spatial localization of 464 proteins in untreated MDA-MB-468 cells via ICC-IF and confocal microscopy (channels: DAPI, ER calreticulin, tubulin, protein-of-interest)."
    media_type: application/zip
    compression: ZIP
    md5: a98affcc05429650c6bb3906cd836d55
    issued: 2025-10-22
    path: Images/cm4ai-ifimages-mda-mb-468-untreated.zip
  - id: doi:10.18130/V3/F3TD5R#cm4ai-ifimages-mda-mb-468-vorinostat.zip
    name: cm4ai-ifimages-mda-mb-468-vorinostat.zip
    title: IF images - MDA-MB-468 treated with vorinostat
    description: "Spatial localization of 464 proteins in MDA-MB-468 cells treated with vorinostat via ICC-IF and confocal microscopy (channels: DAPI, ER calreticulin, tubulin, protein-of-interest)."
    media_type: application/zip
    compression: ZIP
    md5: ad4e68ccc14b0f3349dad3321e7b81b2
    issued: 2025-10-22
    path: Images/cm4ai-ifimages-mda-mb-468-vorinostat.zip
  - id: doi:10.18130/V3/F3TD5R#Images-paclitaxel-provenance-graph.html
    name: Images-paclitaxel-provenance-graph.html
    title: IF images (paclitaxel) provenance graph
    description: HTML provenance graph for paclitaxel IF images (download to view properly).
    media_type: text/html
    md5: e38e63e4c8dfc5808a5ffa2d7829fc38
    issued: 2025-07-01
    path: Images/paclitaxel/Images-paclitaxel-provenance-graph.html
  - id: doi:10.18130/V3/F3TD5R#Images-untreated-provenance-graph.html
    name: Images-untreated-provenance-graph.html
    title: IF images (untreated) provenance graph
    description: HTML provenance graph for untreated IF images (download to view properly).
    media_type: text/html
    md5: 1a3b510f74d3f8647e07c6559ce64ee8
    issued: 2025-07-01
    path: Images/untreated/Images-untreated-provenance-graph.html
  - id: doi:10.18130/V3/F3TD5R#Images-vorinostat-provenance-graph.html
    name: Images-vorinostat-provenance-graph.html
    title: IF images (vorinostat) provenance graph
    description: HTML provenance graph for vorinostat IF images (download to view properly).
    media_type: text/html
    md5: 58935fe4e254b31d33fed019f24c7668
    issued: 2025-07-01
    path: Images/vorinostat/Images-vorinostat-provenance-graph.html
  - id: doi:10.18130/V3/F3TD5R#mass-spec-cancer-cells-provenance-graph.html
    name: mass-spec-cancer-cells-provenance-graph.html
    title: Mass spec (cancer cells) provenance graph
    description: HTML provenance graph for mass spec data in cancer cells (download to view properly).
    media_type: text/html
    md5: 931ad9b552562024cb84ebe62d1f1838
    issued: 2025-07-01
    path: mass-spec/cancer-cells/mass-spec-cancer-cells-provenance-graph.html
  - id: doi:10.18130/V3/F3TD5R#mass-spec-cancer-cells-ro-crate-metadata.json
    name: mass-spec-cancer-cells-ro-crate-metadata.json
    title: Mass spec (cancer cells) RO-Crate metadata
    description: RO-Crate metadata for mass-spec cancer cell sub-package.
    media_type: application/json
    md5: 3a7063bb391ea5e05a32ba5da5f4b2f8
    issued: 2025-07-01
    path: mass-spec/cancer-cells/mass-spec-cancer-cells-ro-crate-metadata.json