CM4AI all combined d4d

Datasheet for Dataset - Human Readable Format

🎯

Motivation

Why was the dataset created?

  • Name
    Primary purpose
    Response
    Provide AI-ready, multi-modal functional genomics data with rich provenance and metadata to accelerate AI/ML methods for cell mapping.
GrantorGrant NameGrant Number
National Institutes of Health (NIH) Bridge2AI ProgramFunctional Genomics Grand Challenge-
📊

Composition

What do the instances represent?

Data TypeInstance TypeNameRepresentation
Raw and processed single-cell gene expression/count matrices with associated metadata and provenance...Single cells measured by perturb-seq.Perturb-seq modalitySingle-cell transcriptomic profiles following genetic perturbations.
Raw/processed MS data, protein/complex features, and metadata with provenance.Fractions/samples profiled by SEC-MS across cell types.SEC-MS modalityProtein complex and abundance profiles from size-exclusion chromatography mass spectrometry.
Image files and derived features with metadata and provenance.Image tiles/fields-of-view of MDA-MB-468 cells.Immunofluorescence imaging modalityImmunofluorescence microscopy images of cells under treatment and control conditions.
  • Name
    Biological subtypes
    Identification
    • KOLF2.1J iPSCs
    • iPSC-derived NPCs
    • iPSC-derived neurons
    • iPSC-derived cardiomyocytes
    • MDA-MB-468 breast cancer cells
  • Name
    Distribution channels and formats
    Description
    • University of Virginia Dataverse (web interface; dataset too large for single download; select files from files table).
    • RO-Crate packaging with JSON-LD metadata and provenance.
  • Name
    Public release
    Description
    • March 2025
🔍

Collection Process

How was the data acquired?

https://doi.org/10.18130/V3/B35XWX
cm4ai-march-2025-data-release-beta
Cell Maps for Artificial Intelligence - March 2025 Data Release (Beta)
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.
English
https://dataverse.lib.virginia.edu
2025-03
https://doi.org/10.18130/V3/B35XWX
JSON-LD
  • CM4AI
  • Bridge2AI
  • functional genomics
  • perturb-seq
  • single-cell
  • SEC-MS
  • size-exclusion chromatography mass spectrometry
  • immunofluorescence
  • microscopy
  • RO-Crate
  • FAIRSCAPE
  • iPSC
  • KOLF2.1J
  • NPCs
  • neurons
  • cardiomyocytes
  • MDA-MB-468
  • paclitaxel
  • vorinostat
  • Clark T
  • Parker J
  • Al Manir S
  • Axelsson U
  • Ballllosero Navarro F
  • Chinn B
  • Churas CP
  • Dailamy A
  • Doctor Y
  • Fall J
  • Forget A
  • Gao J
  • Hansen JN
  • Hu M
  • Johannesson A
  • Khaliq H
  • Lee YH
  • Lenkiewicz J
  • Levinson MA
  • Marquez C
  • Metallo C
  • Muralidharan M
  • Nourreddine S
  • Niestroy J
  • Obernier K
  • Pan E
  • Polacco B
  • Pratt D
  • Qian G
  • Schaffer L
  • Sigaeva A
  • Thaker S
  • Zhang Y
  • Bélisle-Pipon JC
  • Brandt C
  • Chen JY
  • Ding Y
  • Fodeh S
  • Krogan N
  • Lundberg E
  • Mali P
  • Payne-Foster P
  • Ratcliffe S
  • Ravitsky V
  • Sali A
  • Schulz W
  • Ideker T
  • Name
    Gap addressed
    Response
    Lack of harmonized, provenance-rich, multi-modal datasets suitable for AI methods in functional genomics and cell biology.
RoleNameORCIDAffiliation
ContributorCM4AI Team-Cell Maps for Artificial Intelligence (CM4AI) collaboration
DescriptionName
Perturb-seq data in undifferentiated KOLF2.1J induced pluripotent stem cells (iPSCs).Perturb-seq in KOLF2.1J iPSCs
SEC-MS data in undifferentiated KOLF2.1J iPSCs and iPSC-derived NPCs, neurons, and cardiomyocytes.SEC-MS across iPSC-derived lineages
Immunofluorescence images in MDA-MB-468 breast cancer cells with and without vorinostat and paclitax...IF images under chemotherapy conditions
  • Name
    Data acquisition summary
    Description
    • Multi-modal acquisition including perturb-seq (single-cell transcriptomics), size-exclusion chromatography mass spectrometry (SEC-MS), and immunofluorescence microscopy (IF).
  • Name
    Collection mechanisms
    Description
    • Sequencing-based perturb-seq for single-cell transcriptomics in KOLF2.1J iPSCs.
    • Size-exclusion chromatography mass spectrometry (SEC-MS) for proteomic profiling across iPSC-derived lineages.
    • Immunofluorescence microscopy for imaging MDA-MB-468 cells under chemotherapy (vorinostat, paclitaxel) and control conditions.
  • Name
    Release timeframe
    Description
    • March 2025 data release; dataset will be augmented regularly through the end of the project.
  • Name
    Packaging and metadata
    Description
    • Outputs packaged as AI-ready datasets with provenance graphs and rich metadata in RO-Crate format using the FAIRSCAPE framework.
Name
IP and copyright
Description
  • Copyright statements indicate rights held by The Regents of the University of California and, for certain components, The Board referenced in the dataset description. Additional restrictions may apply where otherwise noted.
  • Name
    Dataset maintainers
    Description
    • University of Virginia Dataverse (hosting platform)
    • CM4AI Team
🚀

Uses

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

  • Name
    Intended tasks
    Response
    Development and benchmarking of AI/ML models for cellular mapping and functional genomics across transcriptomic, proteomic, and imaging modalities.
Name
Licensing and terms of use
Description
  • 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...
  • Some materials may be provided under Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International; see https://creativecommons.org/licenses/by-nc-sa/4.0/.
📤

Distribution

How will the dataset be distributed?

doi:10.18130/V3/B35XWX
🔄

Maintenance

How will the dataset be maintained?

1.4
Name
Update plan
Description
  • Data will be augmented regularly through the end of the project.
Generated on 2025-11-09 10:17:35 using Bridge2AI Data Sheets Schema