bridge2ai · d4dassistant · Nov 7, 2025
diff --git a/data/sheets_d4dassistant/cm4ai_d4d.yaml b/data/sheets_d4dassistant/cm4ai_d4d.yaml
@@ -0,0 +1,279 @@
+# Consolidated D4D Datasheet for Cell Maps for Artificial Intelligence (CM4AI)
+# Generated by D4D Assistant from CM4AI publications and data releases
+# Sources: cm4ai.org, Virginia Dataverse releases, CM4AI publications
+# Generated: 2025-11-07
+
+id: "cm4ai"
+name: "Cell Maps for Artificial Intelligence (CM4AI)"
+title: "Cell Maps for Artificial Intelligence - Comprehensive Dataset Collection"
+description: >
+  Cell Maps for Artificial Intelligence (CM4AI) is the Functional Genomics Grand Challenge in the NIH Bridge2AI
+  program. CM4AI aims to map the spatiotemporal architecture of human cells and utilize these maps for interpretable
+  genotype-phenotype learning. The project generates comprehensive, AI-ready datasets combining three complementary
+  mapping strategies: (1) CRISPR/Cas9 genetic perturbation screens with perturb-seq, (2) proteomic mass spectrometry
+  (SEC-MS) for protein-protein interactions, and (3) cellular imaging for spatial subcellular organization mapping.
+
+  The CM4AI dataset collection includes data from multiple cell types: undifferentiated KOLF2.1J human induced
+  pluripotent stem cells (hiPSCs), iPSC-derived neural progenitor cells (NPCs), neurons, cardiomyocytes, and
+  MDA-MB-468 breast cancer cells. All data are packaged with provenance graphs and rich metadata as AI-ready
+  datasets in RO-Crate format using the FAIRSCAPE framework. Data releases are available quarterly through the
+  University of Virginia Dataverse repository.
+
+  As of the March 2025 Beta release, the dataset includes: 53,788 immunofluorescence images, 1,792 proteins
+  investigated, 11,739 genes targeted via CRISPR, 1,374 protein interactions mapped, totaling 22.7 TB of data.
+  CM4AI is a multi-institutional collaboration led by UC San Diego with partners at UCSF, Stanford, University
+  of Virginia, Yale, University of Texas at Austin, University of Alabama at Birmingham, Simon Fraser University,
+  and the Hastings Center.
+
+doi: "doi:10.18130/V3/CM4AI"
+publisher: "https://dataverse.lib.virginia.edu"
+issued: "2025-03-03"
+page: "https://cm4ai.org"
+created_on: "2024-05-11"
+license: "CC BY-NC-SA 4.0 (https://creativecommons.org/licenses/by-nc-sa/4.0/)"
+version: "March 2025 Beta (v0.6)"
+conforms_to: "https://w3id.org/ro/crate"
+language: "en"
+
+keywords:
+  - AI
+  - affinity purification
+  - AP-MS
+  - artificial intelligence
+  - breast cancer
+  - Bridge2AI
+  - cardiomyocyte
+  - cell mapping
+  - CM4AI
+  - CRISPR/Cas9
+  - FAIRSCAPE
+  - functional genomics
+  - 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
+  - RO-Crate
+  - single-cell RNA sequencing
+  - scRNAseq
+  - SEC-MS
+  - size exclusion chromatography
+  - spatial proteomics
+  - subcellular imaging
+  - vorinostat
+
+created_by:
+  - "Ideker T (University of California San Diego) - ORCID: https://orcid.org/0000-0002-1708-8454"
+  - "Clark T (University of Virginia) - ORCID: https://orcid.org/0000-0003-4060-7360"
+  - "Parker J (University of California, San Diego) - ORCID: https://orcid.org/0000-0003-4535-3486"
+  - "Krogan N (University of California San Francisco) - ORCID: https://orcid.org/0000-0003-4902-337X"
+  - "Lundberg E (Stanford University) - ORCID: https://orcid.org/0000-0001-7034-0850"
+  - "Mali P (University of California San Diego) https://orcid.org/0000-0002-3383-1287"
+
+distribution_formats:
+  - description:
+      - "RO-Crate packages (JSON-LD metadata with embedded provenance graphs)"
+      - "ZIP archives for imaging data (multi-channel TIFF images)"
+      - "Raw sequence data files (FASTQ format)"
+      - "Processed data matrices (CSV, H5AD formats)"
+      - "Mass spectrometry data (standard proteomics formats, planned PRIDE repository submission)"
+
+distribution_dates:
+  - description: "Alpha v0.5: May 11, 2024; March 2025 Beta: March 3, 2025; June 2025 Beta: July 1, 2025; Quarterly updates planned"
+
+license_and_use_terms:
+  description:
+    - "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)"
+    - "Attribution required to copyright holders and authors"
+    - "Publications using this data must cite: (1) the relevant data release DOI, and (2) Clark T, et al. Cell Maps for Artificial Intelligence: AI-Ready Maps of Human Cell Architecture from Disease-Relevant Cell Lines. bioRxiv 2024. doi: 10.1101/2024.05.21.589311"
+    - "Commercial use requires separate licensing arrangement"
+
+ip_restrictions:
+  description:
+    - "Copyright (c) 2025 The Regents of the University of California except where otherwise noted"
+    - "Spatial proteomics imaging data: Copyright (c) 2025 The Board of Trustees of the Leland Stanford Junior University"
+    - "Non-commercial license - commercial applications require permission"
+
+maintainers:
+  - description:
+      - "Primary repository: University of Virginia Dataverse (LibraData)"
+      - "Point of Contact: Trey Ideker (University of California San Diego)"
+      - "Data curation and stewardship: Tim Clark and team (University of Virginia)"
+      - "Contact via CM4AI website (https://cm4ai.org) or Dataverse dataset pages"
+
+updates:
+  description:
+    - "Quarterly data releases planned through project completion (estimated 2026)"
+    - "Data will be augmented regularly with new assay types, cell types, and experimental conditions"
+    - "Version history maintained through Dataverse with DOI assignment for each release"
+    - "Future planned additions: Additional iPSC differentiation states, expanded protein and gene targets, additional disease-relevant cell lines"
+
+use_repository:
+  - description: "All CM4AI data releases are publicly available via University of Virginia Dataverse repository (https://dataverse.lib.virginia.edu/dataverse/CM4AI). Individual data releases accessible by DOI. Large datasets may require selective file download rather than bulk download due to size (22.7 TB total)."
+
+existing_uses:
+  - description: "Clark T, Parker J, Schaffer L, et al. Cell Maps for Artificial Intelligence: AI-Ready Maps of Human Cell Architecture from Disease-Relevant Cell Lines. bioRxiv 2024. doi: 10.1101/2024.05.21.589311"
+  - description: "Nourreddine S, et al. A Perturbation Cell Atlas of Human Induced Pluripotent Stem Cells. bioRxiv 2024. doi: 10.1101/2024.11.03.621734"
+  - description: "Schaffer LV, Hu M, Qian G, et al. Multimodal cell maps as a foundation for structural and functional genomics. Nature 2025. doi: 10.1038/s41586-025-08878-3"
+  - description: "Lenkiewicz J, Churas C, Hu M, et al. Cell Mapping Toolkit: an end-to-end pipeline for mapping subcellular organization. Bioinformatics 2024. doi: 10.1093/bioinformatics/btaf205"
+  - description: "Al Manir S, Levinson MA, Niestroy J, et al. FAIRSCAPE: An Evolving AI-readiness Framework for Biomedical Research. bioRxiv 2024. doi: 10.1101/2024.12.23.629818"
+  - description: "Clark T, Caufield H, Parker JA, et al. AI-readiness for Biomedical Data: Bridge2AI Recommendations. bioRxiv 2024. doi: 10.1101/2024.10.23.619844"
+
+resources:
+  - id: "cm4ai_crispr_perturbation_atlas"
+    name: "CRISPR Perturbation Cell Atlas"
+    title: "CRISPR Perturbation Cell Atlas in hiPSCs"
+    description: >
+      Expressed genome-scale CRISPRi Perturbation Cell Atlas in undifferentiated KOLF2.1J human induced
+      pluripotent stem cells (hiPSCs) mapping transcriptional and fitness phenotypes associated with 11,739
+      targeted genes. Findings validated via phenotypic, protein-interaction, and metabolic tracing assays.
+    format: "RO-Crate"
+    media_type: "application/json"
+    license: "CC BY-NC-SA 4.0 (https://creativecommons.org/licenses/by-nc-sa/4.0/)"
+    purposes:
+      - response: "AI-ready functional genomics data release for CM4AI to support machine learning research"
+    tasks:
+      - response: "Single-cell perturb-seq analysis and model development"
+      - response: "Gene function and fitness phenotype modeling"
+    instances:
+      - representation: "CRISPR perturbation atlas with single-cell RNA sequencing data"
+        data_type: "Single-cell RNA sequencing data with CRISPR perturbation metadata"
+    acquisition_methods:
+      - description: "CRISPR interference (CRISPRi) with perturb-seq in KOLF2.1J hiPSCs targeting 11,739 genes"
+    collection_timeframes:
+      - description: "Data creation date: 2025-02-27; Published: 2025-03-03"
+    data_collectors:
+      - description: "CM4AI consortium; work conducted at UC San Diego and collaborating institutions"
+    funders:
+      - grantor:
+          id: "https://reporter.nih.gov/"
+          name: National Institutes of Health
+        grant:
+          name: "Bridge2AI CM4AI"
+          grant_number: "1OT2OD032742-01"
+    existing_uses:
+      - description: "Related publication: Cell Maps for Artificial Intelligence (bioRxiv 2024.05.21.589311)"
+      - description: "Related publication: A PERTURBATION CELL ATLAS OF HUMAN iPSCs (bioRxiv 2024.11.03.621734)"
+    distribution_formats:
+      - description: "RO-Crate (JSON metadata)"
+    distribution_dates:
+      - description: "2025-03-03"
+    license_and_use_terms:
+      description:
+        - "Attribution required to copyright holders and authors; cite related publication and this data collection"
+        - "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
+    ip_restrictions:
+      description:
+        - "Copyright (c) 2025 The Regents of the University of California except where otherwise noted"
+    maintainers:
+      - description:
+          - "Hosted by University of Virginia Dataverse; contact via dataset page"
+          - "Point of Contact: Trey Ideker (University of California San Diego)"
+    conforms_to: "https://w3id.org/ro/crate"
+
+  - id: "cm4ai_protein_protein_interaction"
+    name: "Protein-Protein Interaction SEC-MS"
+    title: "Protein-Protein Interaction SEC-MS Data"
+    description: >
+      Size exclusion chromatography-mass spectroscopy (SEC-MS) on undifferentiated KOLF2.1J human induced
+      pluripotent stem cells (hiPSCs), generated in the Nevan Krogan laboratory at UCSF as part of CM4AI
+      (NIH Bridge2AI program). The data will be uploaded to PRIDE when available.
+    format: "RO-Crate"
+    media_type: "application/json"
+    license: "CC BY-NC-SA 4.0 (https://creativecommons.org/licenses/by-nc-sa/4.0/)"
+    purposes:
+      - response: "Provide AI-ready proteomics interaction data for modeling protein complexes"
+    tasks:
+      - response: "Protein complex inference and PPI network analysis from SEC-MS profiles"
+    instances:
+      - representation: "SEC-MS assay data with protein complex elution profiles"
+        data_type: "Mass spectrometry data with protein-protein interaction annotations"
+    acquisition_methods:
+      - description: "Size exclusion chromatography followed by mass spectrometry (SEC-MS) in KOLF2.1J hiPSCs"
+    collection_timeframes:
+      - description: "Data creation date: 2025-02-27; Published: 2025-03-03"
+    data_collectors:
+      - description: "Nevan Krogan Laboratory, University of California San Francisco"
+    funders:
+      - grantor:
+          id: "https://reporter.nih.gov/"
+          name: National Institutes of Health
+        grant:
+          name: "Bridge2AI CM4AI"
+          grant_number: "1OT2OD032742-01"
+    external_resources:
+      - external_resources: "PRIDE repository (planned upload when available)"
+    distribution_formats:
+      - description: "RO-Crate (JSON metadata)"
+    distribution_dates:
+      - description: "2025-03-03"
+    license_and_use_terms:
+      description:
+        - "Attribution required; cite related publication and this data collection"
+        - "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
+    ip_restrictions:
+      description:
+        - "Copyright (c) 2025 The Regents of the University of California"
+    maintainers:
+      - description:
+          - "Hosted by University of Virginia Dataverse; contact via dataset page"
+          - "Point of Contact: Trey Ideker (University of California San Diego)"
+
+  - id: "cm4ai_protein_localization_imaging"
+    name: "Protein Localization Subcellular Images"
+    title: "Protein Localization Subcellular Imaging (MDA-MB-468)"
+    description: >
+      Spatial localization of 563 proteins of interest in MDA-MB-468 breast cancer cells under untreated,
+      paclitaxel-treated, and vorinostat-treated conditions, imaged by immunofluorescence-based staining (ICC-IF)
+      and confocal microscopy in the Lundberg Lab at Stanford University. Four-channel imaging: DAPI (nuclei, blue),
+      calreticulin antibody (ER, yellow), tubulin antibody (microtubules, red), protein-of-interest antibody (green).
+    format: "ZIP"
+    compression: "ZIP"
+    media_type: "application/zip"
+    license: "CC BY-NC-SA 4.0 (https://creativecommons.org/licenses/by-nc-sa/4.0/)"
+    purposes:
+      - response: "AI-ready subcellular imaging for protein localization analysis and ML benchmarking"
+    tasks:
+      - response: "Subcellular localization classification and feature learning from IF images"
+      - response: "Drug response phenotyping from imaging data"
+    instances:
+      - representation: "Immunofluorescence confocal microscopy images (multi-condition)"
+        data_type: "Multichannel TIFF imagery within ZIP archive"
+    acquisition_methods:
+      - description: "ICC-IF staining and confocal microscopy; channels: DAPI (nuclei), calreticulin (ER), tubulin (microtubules), protein-of-interest"
+    collection_timeframes:
+      - description: "Published: 2025-03-03"
+    data_collectors:
+      - description: "Lundberg Lab, Stanford University"
+    funders:
+      - grantor:
+          id: "https://reporter.nih.gov/"
+          name: National Institutes of Health
+        grant:
+          name: "Bridge2AI CM4AI"
+          grant_number: "1OT2OD032742-01"
+    distribution_formats:
+      - description: "ZIP archive of imaging data (multi-channel TIFF files)"
+    distribution_dates:
+      - description: "2025-03-03"
+    license_and_use_terms:
+      description:
+        - "Attribution required; cite related publication and this data collection"
+        - "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International"
+    ip_restrictions:
+      description:
+        - "Spatial proteomics raw image data copyright (c) 2025 The Board of Trustees of the Leland Stanford Junior University"
+        - "Other data copyright (c) 2025 The Regents of the University of California except where otherwise noted"
+    maintainers:
+      - description:
+          - "Hosted by University of Virginia Dataverse; contact via dataset page"
+          - "Point of Contact: Trey Ideker (University of California San Diego)"