================================================================================
CRATE-ONLY SOURCE BUNDLE
================================================================================
Project: CM4AI
Crate package: data/ro-crate_packages/CM4AI
Crate manifest: data/ro-crate_packages/crate_manifest.yaml

This bundle contains the RO-Crate evidence and NOTHING else — no
publications, no project documentation, no licence pages, no data
repository pages. It measures what a single structured upstream source
supports on its own. It is NOT the project baseline.

Artifacts that are already D4D-shaped or datasheet-shaped remain
withheld, so this is extraction from evidence, not transcription.

CRATE EVIDENCE INCLUDED
--------------------------------------------------------------------------------
  + CM4AI_crate_metadata_reduced.json — crate JSON-LD with file inventories collapsed; the substantive evidence (rai:* fields, ethics, access, provenance)
  + ai_ready_score.json — AI-readiness self-assessment

CRATE ARTIFACTS WITHHELD
--------------------------------------------------------------------------------
  - CM4AI_crate_d4d.yaml — already a schema-valid D4D record — this is the deterministic fork's output; including it would make the de novo arm copy-through
  - ro-crate-linkml.yaml — upstream's own D4D-shaped mapping; same copy-through risk
  - ro-crate-datasheet.html — upstream-authored datasheet rendering of the same content; a datasheet is the artifact being generated, so it is withheld as input

================================================================================

================================================================================
FILE: CM4AI_crate_metadata_reduced.json
ROLE: crate JSON-LD with file inventories collapsed; the substantive evidence (rai:* fields, ethics, access, provenance)
SIZE: 107,351 characters
--------------------------------------------------------------------------------
{
 "@context": {
  "@vocab": "https://schema.org/",
  "EVI": "https://w3id.org/EVI#"
 },
 "@graph": [
  {
   "@id": "ro-crate-metadata.json",
   "@type": "CreativeWork",
   "conformsTo": {
    "@id": "https://w3id.org/ro/crate/1.2"
   },
   "about": {
    "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-June-2026-data-release"
   },
   "fairscapeVersion": "1.1.3"
  },
  {
   "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-June-2026-data-release",
   "@type": [
    "Dataset",
    "https://w3id.org/EVI#ROCrate"
   ],
   "name": "Cell Maps for Artificial Intelligence - June 2026 Data Release (Beta)",
   "description": "This dataset is the June 2026 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; AP-MS data in MDA-MB-468 breast cancer cells in the presence of chemotherapy (vorinostat and paclitaxel); 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.",
   "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",
    "Artificial intelligence",
    "Breast cancer",
    "CRISPR perturbation",
    "Cell maps",
    "IPSC",
    "Machine learning",
    "Mass spectroscopy",
    "Perturb-seq",
    "Protein-protein interaction",
    "cell maps"
   ],
   "version": "1.0",
   "datePublished": "2026-06-30",
   "isPartOf": [
    {
     "@id": "https://fairscape.net/api/ark:59853/organization-university-of-california-san-diego-T4a649a1RtE"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/project-cell-maps-for-artificial-intelligence-qTdsTBd3FtA"
    }
   ],
   "hasPart": {
    "_summarized_by": "d4d rocrate normalize",
    "count": 60,
    "id_families": {
     "0000": 36,
     "rocrate": 9,
     "0009": 2,
     "ui?ui=D001943": 1,
     "ui?ui=D057026": 1,
     "ui?ui=D064113": 1,
     "ui?ui=D013058": 1,
     "ui?ui=D005453": 1,
     "ui?ui=D017239": 1,
     "ui?ui=D000077337": 1,
     "topic_0121": 1,
     "topic_3170": 1
    },
    "sample_ids": [
     "https://orcid.org/0000-0003-4060-7360",
     "https://orcid.org/0000-0003-4535-3486",
     "https://orcid.org/0000-0003-4647-3877",
     "https://orcid.org/0000-0002-4180-422X",
     "https://orcid.org/0000-0001-9998-705X"
    ]
   },
   "author": [
    {
     "@id": "https://orcid.org/0000-0003-4060-7360"
    },
    {
     "@id": "https://orcid.org/0000-0003-4535-3486"
    },
    {
     "@id": "https://orcid.org/0000-0003-4647-3877"
    },
    "Axelsson, U",
    {
     "@id": "https://orcid.org/0000-0002-4180-422X"
    },
    "Chinn, B",
    {
     "@id": "https://orcid.org/0000-0001-9998-705X"
    },
    {
     "@id": "https://orcid.org/0000-0002-6711-8260"
    },
    {
     "@id": "https://orcid.org/0009-0009-0483-7506"
    },
    "Fall, J",
    {
     "@id": "https://orcid.org/0000-0003-0223-0312"
    },
    {
     "@id": "https://orcid.org/0000-0002-6311-3526"
    },
    {
     "@id": "https://orcid.org/0000-0002-4650-9094"
    },
    {
     "@id": "https://orcid.org/0000-0002-1571-8029"
    },
    "Johannesson, A",
    "Khaliq, H",
    {
     "@id": "https://orcid.org/0000-0003-0917-355X"
    },
    {
     "@id": "https://orcid.org/0000-0001-7252-8638"
    },
    {
     "@id": "https://orcid.org/0000-0003-0384-8499"
    },
    {
     "@id": "https://orcid.org/0000-0003-3960-420X"
    },
    {
     "@id": "https://orcid.org/0000-0003-2404-3040"
    },
    "Muralidharan, M",
    {
     "@id": "https://orcid.org/0000-0003-3881-7588"
    },
    {
     "@id": "https://orcid.org/0000-0002-1103-3882"
    },
    {
     "@id": "https://orcid.org/0000-0002-4025-1299"
    },
    "Pan, E",
    "Polacco, B",
    {
     "@id": "https://orcid.org/0000-0002-1471-9513"
    },
    {
     "@id": "https://orcid.org/0009-0005-4217-2745"
    },
    {
     "@id": "https://orcid.org/0000-0001-6339-9141"
    },
    {
     "@id": "https://orcid.org/0000-0003-3361-3797"
    },
    {
     "@id": "https://orcid.org/0000-0001-6730-2773"
    },
    "Zhang, Y",
    {
     "@id": "https://orcid.org/0000-0002-8965-8153"
    },
    {
     "@id": "https://orcid.org/0000-0001-8179-1796"
    },
    {
     "@id": "https://orcid.org/0000-0002-6112-415X"
    },
    {
     "@id": "https://orcid.org/0000-0003-2567-2009"
    },
    {
     "@id": "https://orcid.org/0000-0003-4664-3143"
    },
    {
     "@id": "https://orcid.org/0000-0003-4902-337X"
    },
    {
     "@id": "https://orcid.org/0000-0001-7034-0850"
    },
    {
     "@id": "https://orcid.org/0000-0002-3383-1287"
    },
    {
     "@id": "https://orcid.org/0000-0002-3508-3577"
    },
    {
     "@id": "https://orcid.org/0000-0002-6644-8284"
    },
    {
     "@id": "https://orcid.org/0000-0002-7080-8801"
    },
    {
     "@id": "https://orcid.org/0000-0003-0435-6197"
    },
    {
     "@id": "https://orcid.org/0000-0002-2048-4028"
    },
    {
     "@id": "https://orcid.org/0000-0002-1708-8454"
    }
   ],
   "publisher": "https://dataverse.lib.virginia.edu/",
   "principalInvestigator": "Trey Ideker",
   "funder": "National Institutes of Health: 1OT2OD032742-01, R01HG012351, R01NS131560, U54CA274502, #S10 OD026929. Department of Defense: W81XWH-22-1-0401. CIRM training: EDUC4-12804. Dutch Research Council: NWO, 019.231EN.013. National Cancer Institute: P30CA023100",
   "contactEmail": "tideker@health.ucsd.edu",
   "citation": "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; Metallo C; Muralidharan M; Nourreddine S; Niestroy J; Obernier K; Pan E; Park, S; Polacco B; Pratt D; Qian G; Schaffer, LV; Sigaeva A; Thaker S; Zhang Y; Zhao, X; 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, 2025, \"Cell Maps for Artificial Intelligence - June 2026 Data Release (Beta)\", https://doi.org/10.18130/V3/HIGT4C , https://dataverse.lib.virginia.edu/, V1",
   "associatedPublication": [
    "Clark T, Parker J, Al Manir S, et al. (2024) Cell Maps for Artificial Intelligence: AI-Ready Maps of Human Cell Architecture from Disease-Relevant Cell Lines. bioRxiv 2024.05.21.589311; doi: https://doi.org/10.1101/2024.05.21.589311",
    "Nourreddine S, et al. (2024) A Perturbation Cell Atlas of Human Induced Pluripotent Stem Cells. bioRxiv 2024.05.21.589311; doi: https://doi.org/10.1101/2024.11.03.621734",
    "Qin, Y., Huttlin, E.L., Winsnes, C.F. et al. A multi-scale map of cell structure fusing protein images and interactions. Nature 600, 536–542 (2021). https://doi.org/10.1038/s41586-021-04115-9",
    "Schaffer LV, Hu M, Qian G, et al. Multimodal cell maps as a foundation for structural and functional genomics. Nature [Internet]. 2025 Apr 9; Available from: https://www.nature.com/articles/s41586-025-08878-3"
   ],
   "identifier": "https://doi.org/10.18130/V3/HIGT4C",
   "license": "https://creativecommons.org/licenses/by-nc-sa/4.0/",
   "conditionsOfAccess": "Attribution is required to the copyright holders and the authors. Any publications referencing this data or derived data products should cite the Related Publications below, as well as directly citing this data collection.",
   "copyrightNotice": "Copyright (c) 2026 The Regents of the University of California except where otherwise noted. Spatial proteomics raw image data is copyright (c) 2026 The Board of Trustees of the Leland Stanford Junior University.",
   "contentSize": "19.9 TB",
   "usageInfo": "These laboratory data are not to be used in clinical decision-making or in any context involving patient care without appropriate regulatory oversight and approval.",
   "ethicalReview": "Vardit Ravistky ravitskyv@thehastingscenter.org and Jean-Christophe Belisle-Pipon jean-christophe_belisle-pipon@sfu.ca.",
   "confidentialityLevel": "Unrestricted",
   "humanSubjectExemption": "Exempt — research with commercially available de-identified human cell lines does not constitute human subjects research.",
   "humanSubjectResearch": "None - data collected from commercially available cell lines",
   "dataGovernanceCommittee": "Jilian Parker",
   "about": [
    {
     "@id": "https://meshb.nlm.nih.gov/record/ui?ui=D001943"
    },
    {
     "@id": "https://meshb.nlm.nih.gov/record/ui?ui=D057026"
    },
    {
     "@id": "https://meshb.nlm.nih.gov/record/ui?ui=D064113"
    },
    {
     "@id": "https://meshb.nlm.nih.gov/record/ui?ui=D013058"
    },
    {
     "@id": "https://meshb.nlm.nih.gov/record/ui?ui=D005453"
    },
    {
     "@id": "https://meshb.nlm.nih.gov/record/ui?ui=D017239"
    },
    {
     "@id": "https://meshb.nlm.nih.gov/record/ui?ui=D000077337"
    },
    {
     "@id": "http://edamontology.org/topic_0121"
    },
    {
     "@id": "http://edamontology.org/topic_3170"
    },
    {
     "@id": "http://edamontology.org/topic_3320"
    },
    {
     "@id": "http://edamontology.org/topic_3474"
    },
    {
     "@id": "https://www.cellosaurus.org/CVCL_0419"
    },
    {
     "@id": "https://www.cellosaurus.org/CVCL_B5P3"
    }
   ],
   "rai:dataLimitations": "This is an interim release. It does not contain predicted cell maps, which will be added in future releases. The current release is most suitable for bioinformatics analysis of the individual datasets. Requires domain expertise for meaningful analysis.",
   "rai:dataBiases": "Data in this release was derived from commercially available de-identified human cell lines, and does not represent all biological variants which may be seen in the population at large.",
   "rai:dataUseCases": "AI-ready datasets to support research in functional genomics, AI/machine learning model training, cellular process analysis, cell architectural changes, and interactions in presence of specific disease processes, treatment conditions, or genetic perturbations. A major goal is to enable biologically-driven, interpretable ML applications, for example as proposed in Ma et al. 2018 (PMID: 29505029) and Kuenzi et al. 2020 (PMID: 33096023).",
   "rai:dataReleaseMaintenancePlan": "Dataset will be regularly updated and augmented on a quarterly basis through the end of the project (November, 2026). Long term preservation in the https://dataverse.lib.virginia.edu/, supported by committed institutional funds.",
   "rai:dataCollection": "Data collection processes are generally described in Clark T et al. (2024) \"Cell Maps for Artificial Intelligence: AI-Ready Maps of Human Cell Architecture from Disease-Relevant Cell Lines\" bioRxiv 2024.05.21.589311; doi: https://doi.org/10.1101/2024.05.21.589311. Additional data collection details will be subsequently published once finalized. ",
   "rai:dataCollectionType": [
    "Perturb-seq; IF imaging; SEC-MS; AP-MS"
   ],
   "rai:dataCollectionMissingData": "Some datasets are under temporary pre-publication embargo. Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incompletely overlap. Computed cell maps not included in this release.",
   "rai:dataCollectionTimeframe": [
    "9/1/2022",
    "6/1/2026"
   ],
   "completeness": "These data are not yet in completed final form, and some datasets are under temporary pre-publication embargo. Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incompletely overlap. Computed cell maps not included in this release.",
   "prohibitedUses": "These laboratory data are not to be used in clinical decision-making or in any context involving patient care without appropriate regulatory oversight and approval.",
   "evi:datasetCount": 53877,
   "evi:computationCount": 1976,
   "evi:softwareCount": 6,
   "evi:schemaCount": 20,
   "evi:totalContentSizeBytes": 21051331945400,
   "evi:entitiesWithSummaryStats": 0,
   "evi:entitiesWithChecksums": 8,
   "evi:totalEntities": 55859,
   "evi:formats": [
    ".d",
    ".d directory group",
    ".tsv",
    ".xml",
    "TSV",
    "csv",
    "executable",
    "fastq.gz",
    "h5",
    "h5ad",
    "image/jpeg",
    "pdf",
    "unknown"
   ],
   "d4d:informedConsent": "Not applicable — data collected from commercially available de-identified human cell lines (KOLF2.1J iPSC and MDA-MB-468). No primary human subjects research conducted under this release.",
   "d4d:atRiskPopulations": "None — no human subjects involved; commercially sourced de-identified cell lines only."
  },
  {
   "@id": "https://orcid.org/0000-0003-4060-7360",
   "@type": "Person",
   "name": "Clark, T",
   "identifier": "https://orcid.org/0000-0003-4060-7360",
   "affiliation": {
    "@type": "Organization",
    "name": "University of Virginia"
   }
  },
  {
   "@id": "https://orcid.org/0000-0003-4535-3486",
   "@type": "Person",
   "name": "Parker, J",
   "identifier": "https://orcid.org/0000-0003-4535-3486",
   "affiliation": {
    "@type": "Organization",
    "name": "University of California, San Diego"
   }
  },
  {
   "@id": "https://orcid.org/0000-0003-4647-3877",
   "@type": "Person",
   "name": "Al Manir, S",
   "identifier": "https://orcid.org/0000-0003-4647-3877",
   "affiliation": {
    "@type": "Organization",
    "name": "University of Virginia"
   }
  },
  {
   "@id": "https://orcid.org/0000-0002-4180-422X",
   "@type": "Person",
   "name": "Ballllosero Navarro, F",
   "identifier": "https://orcid.org/0000-0002-4180-422X",
   "affiliation": {
    "@type": "Organization",
    "name": "Stanford University"
   }
  },
  {
   "@id": "https://orcid.org/0000-0001-9998-705X",
   "@type": "Person",
   "name": "Churas, CP",
   "identifier": "https://orcid.org/0000-0001-9998-705X",
   "affiliation": {
    "@type": "Organization",
    "name": "University of California San Diego"
   }
  },
  {
   "@id": "https://orcid.org/0000-0002-6711-8260",
   "@type": "Person",
   "name": "Dailamy, A",
   "identifier": "https://orcid.org/0000-0002-6711-8260",
   "affiliation": {
    "@type": "Organization",
    "name": "University of California, San Diego"
   }
  },
  {
   "@id": "https://orcid.org/0009-0009-0483-7506",
   "@type": "Person",
   "name": "Doctor, Y",
   "identifier": "https://orcid.org/0009-0009-0483-7506",
   "affiliation": {
    "@type": "Organization",
    "name": "University of California, San Diego"
   }
  },
  {
   "@id": "https://orcid.org/0000-0003-0223-0312",
   "@type": "Person",
   "name": "Forget, A",
   "identifier": "https://orcid.org/0000-0003-0223-0312",
   "affiliation": {
    "@type": "Organization",
    "name": "University of California San Francisco"
   }
  },
  {
   "@id": "https://orcid.org/0000-0002-6311-3526",
   "@type": "Person",
   "name": "Gao, J",
   "identifier": "https://orcid.org/0000-0002-6311-3526",
   "affiliation": {
    "@type": "Organization",
    "name": "University of California San Diego"
   }
  },
  {
   "@id": "https://orcid.org/0000-0002-4650-9094",
   "@type": "Person",
   "name": "Hansen, JN",
   "identifier": "https://orcid.org/0000-0002-4650-9094",
   "affiliation": {
    "@type": "Organization",
    "name": "Stanford University"
   }
  },
  {
   "@id": "https://orcid.org/0000-0002-1571-8029",
   "@type": "Person",
   "name": "Hu, M",
   "identifier": "https://orcid.org/0000-0002-1571-8029",
   "affiliation": {
    "@type": "Organization",
    "name": "University of California San Diego"
   }
  },
  {
   "@id": "https://orcid.org/0000-0003-0917-355X",
   "@type": "Person",
   "name": "Lee, YH",
   "identifier": "https://orcid.org/0000-0003-0917-355X",
   "affiliation": {
    "@type": "Organization",
    "name": "University of California San Diego"
   }
  },
  {
   "@id": "https://orcid.org/0000-0001-7252-8638",
   "@type": "Person",
   "name": "Lenkiewicz, J",
   "identifier": "https://orcid.org/0000-0001-7252-8638",
   "affiliation": {
    "@type": "Organization",
    "name": "University of California San Diego"
   }
  },
  {
   "@id": "https://orcid.org/0000-0003-0384-8499",
   "@type": "Person",
   "name": "Levinson, MA",
   "identifier": "https://orcid.org/0000-0003-0384-8499",
   "affiliation": {
    "@type": "Organization",
    "name": "University of Virginia"
   }
  },
  {
   "@id": "https://orcid.org/0000-0003-3960-420X",
   "@type": "Person",
   "name": "Marquez, C",
   "identifier": "https://orcid.org/0000-0003-3960-420X",
   "affiliation": {
    "@type": "Organization",
    "name": "University of California San Diego"
   }
  },
  {
   "@id": "https://orcid.org/0000-0003-2404-3040",
   "@type": "Person",
   "name": "Metallo, C",
   "identifier": "https://orcid.org/0000-0003-2404-3040",
   "affiliation": {
    "@type": "Organization",
    "name": "University of California San Diego"
   }
  },
  {
   "@id": "https://orcid.org/0000-0003-3881-7588",
   "@type": "Person",
   "name": "Nourreddine, S",
   "identifier": "https://orcid.org/0000-0003-3881-7588",
   "affiliation": {
    "@type": "Organization",
    "name": "University of California San Diego"
   }
  },
  {
   "@id": "https://orcid.org/0000-0002-1103-3882",
   "@type": "Person",
   "name": "Niestroy, J",
   "identifier": "https://orcid.org/0000-0002-1103-3882",
   "affiliation": {
    "@type": "Organization",
    "name": "University of Virginia"
   }
  },
  {
   "@id": "https://orcid.org/0000-0002-4025-1299",
   "@type": "Person",
   "name": "Obernier, K",
   "identifier": "https://orcid.org/0000-0002-4025-1299",
   "affiliation": {
    "@type": "Organization",
    "name": "University of California San Francisco"
   }
  },
  {
   "@id": "https://orcid.org/0000-0002-1471-9513",
   "@type": "Person",
   "name": "Pratt, D",
   "identifier": "https://orcid.org/0000-0002-1471-9513",
   "affiliation": {
    "@type": "Organization",
    "name": "University of California San Diego"
   }
  },
  {
   "@id": "https://orcid.org/0009-0005-4217-2745",
   "@type": "Person",
   "name": "Qian, G",
   "identifier": "https://orcid.org/0009-0005-4217-2745",
   "affiliation": {
    "@type": "Organization",
    "name": "University of California San Diego"
   }
  },
  {
   "@id": "https://orcid.org/0000-0001-6339-9141",
   "@type": "Person",
   "name": "Schaffer, L",
   "identifier": "https://orcid.org/0000-0001-6339-9141",
   "affiliation": {
    "@type": "Organization",
    "name": "University of California San Diego"
   }
  },
  {
   "@id": "https://orcid.org/0000-0003-3361-3797",
   "@type": "Person",
   "name": "Sigaeva, A",
   "identifier": "https://orcid.org/0000-0003-3361-3797",
   "affiliation": {
    "@type": "Organization",
    "name": "KTH Royal Institute of Technology"
   }
  },
  {
   "@id": "https://orcid.org/0000-0001-6730-2773",
   "@type": "Person",
   "name": "Thaker, S",
   "identifier": "https://orcid.org/0000-0001-6730-2773",
   "affiliation": {
    "@type": "Organization",
    "name": "University of Alabama at Birmingham"
   }
  },
  {
   "@id": "https://orcid.org/0000-0002-8965-8153",
   "@type": "Person",
   "name": "Bélisle-Pipon, JC",
   "identifier": "https://orcid.org/0000-0002-8965-8153",
   "affiliation": {
    "@type": "Organization",
    "name": "Simon Fraser University"
   }
  },
  {
   "@id": "https://orcid.org/0000-0001-8179-1796",
   "@type": "Person",
   "name": "Brandt, C",
   "identifier": "https://orcid.org/0000-0001-8179-1796",
   "affiliation": {
    "@type": "Organization",
    "name": "Yale University"
   }
  },
  {
   "@id": "https://orcid.org/0000-0002-6112-415X",
   "@type": "Person",
   "name": "Chen, JY",
   "identifier": "https://orcid.org/0000-0002-6112-415X",
   "affiliation": {
    "@type": "Organization",
    "name": "The University of Alabama at Birmingham"
   }
  },
  {
   "@id": "https://orcid.org/0000-0003-2567-2009",
   "@type": "Person",
   "name": "Ding, Y",
   "identifier": "https://orcid.org/0000-0003-2567-2009",
   "affiliation": {
    "@type": "Organization",
    "name": "University of Texas at Austin"
   }
  },
  {
   "@id": "https://orcid.org/0000-0003-4664-3143",
   "@type": "Person",
   "name": "Fodeh, S",
   "identifier": "https://orcid.org/0000-0003-4664-3143",
   "affiliation": {
    "@type": "Organization",
    "name": "Yale University"
   }
  },
  {
   "@id": "https://orcid.org/0000-0003-4902-337X",
   "@type": "Person",
   "name": "Krogan, N",
   "identifier": "https://orcid.org/0000-0003-4902-337X",
   "affiliation": {
    "@type": "Organization",
    "name": "University of California San Francisco"
   }
  },
  {
   "@id": "https://orcid.org/0000-0001-7034-0850",
   "@type": "Person",
   "name": "Lundberg, E",
   "identifier": "https://orcid.org/0000-0001-7034-0850",
   "affiliation": {
    "@type": "Organization",
    "name": "Stanford University"
   }
  },
  {
   "@id": "https://orcid.org/0000-0002-3383-1287",
   "@type": "Person",
   "name": "Mali, P",
   "identifier": "https://orcid.org/0000-0002-3383-1287",
   "affiliation": {
    "@type": "Organization",
    "name": "University of California San Diego"
   }
  },
  {
   "@id": "https://orcid.org/0000-0002-3508-3577",
   "@type": "Person",
   "name": "Payne-Foster, P",
   "identifier": "https://orcid.org/0000-0002-3508-3577",
   "affiliation": {
    "@type": "Organization",
    "name": "University of Alabama"
   }
  },
  {
   "@id": "https://orcid.org/0000-0002-6644-8284",
   "@type": "Person",
   "name": "Ratcliffe, S",
   "identifier": "https://orcid.org/0000-0002-6644-8284",
   "affiliation": {
    "@type": "Organization",
    "name": "University of Virginia"
   }
  },
  {
   "@id": "https://orcid.org/0000-0002-7080-8801",
   "@type": "Person",
   "name": "Ravitsky, V",
   "identifier": "https://orcid.org/0000-0002-7080-8801",
   "affiliation": {
    "@type": "Organization",
    "name": "University of Montreal"
   }
  },
  {
   "@id": "https://orcid.org/0000-0003-0435-6197",
   "@type": "Person",
   "name": "Sali, A",
   "identifier": "https://orcid.org/0000-0003-0435-6197",
   "affiliation": {
    "@type": "Organization",
    "name": "University of California San Diego"
   }
  },
  {
   "@id": "https://orcid.org/0000-0002-2048-4028",
   "@type": "Person",
   "name": "Schulz, W",
   "identifier": "https://orcid.org/0000-0002-2048-4028",
   "affiliation": {
    "@type": "Organization",
    "name": "Yale University"
   }
  },
  {
   "@id": "https://orcid.org/0000-0002-1708-8454",
   "@type": "Person",
   "name": "Ideker, T",
   "identifier": "https://orcid.org/0000-0002-1708-8454",
   "affiliation": {
    "@type": "Organization",
    "name": "University of California San Diego"
   }
  },
  {
   "@id": "https://meshb.nlm.nih.gov/record/ui?ui=D001943",
   "@type": "DefinedTerm",
   "name": "Breast Neoplasms",
   "termCode": "D001943",
   "inDefinedTermSet": {
    "@id": "https://www.nlm.nih.gov/mesh/",
    "name": "MeSH"
   }
  },
  {
   "@id": "https://meshb.nlm.nih.gov/record/ui?ui=D057026",
   "@type": "DefinedTerm",
   "name": "Induced Pluripotent Stem Cells",
   "termCode": "D057026",
   "inDefinedTermSet": {
    "@id": "https://www.nlm.nih.gov/mesh/",
    "name": "MeSH"
   }
  },
  {
   "@id": "https://meshb.nlm.nih.gov/record/ui?ui=D064113",
   "@type": "DefinedTerm",
   "name": "CRISPR-Cas Systems",
   "termCode": "D064113",
   "inDefinedTermSet": {
    "@id": "https://www.nlm.nih.gov/mesh/",
    "name": "MeSH"
   }
  },
  {
   "@id": "https://meshb.nlm.nih.gov/record/ui?ui=D013058",
   "@type": "DefinedTerm",
   "name": "Mass Spectrometry",
   "termCode": "D013058",
   "inDefinedTermSet": {
    "@id": "https://www.nlm.nih.gov/mesh/",
    "name": "MeSH"
   }
  },
  {
   "@id": "https://meshb.nlm.nih.gov/record/ui?ui=D005453",
   "@type": "DefinedTerm",
   "name": "Fluorescent Antibody Technique",
   "termCode": "D005453",
   "inDefinedTermSet": {
    "@id": "https://www.nlm.nih.gov/mesh/",
    "name": "MeSH"
   }
  },
  {
   "@id": "https://meshb.nlm.nih.gov/record/ui?ui=D017239",
   "@type": "DefinedTerm",
   "name": "Paclitaxel",
   "termCode": "D017239",
   "inDefinedTermSet": {
    "@id": "https://www.nlm.nih.gov/mesh/",
    "name": "MeSH"
   }
  },
  {
   "@id": "https://meshb.nlm.nih.gov/record/ui?ui=D000077337",
   "@type": "DefinedTerm",
   "name": "Vorinostat",
   "termCode": "D000077337",
   "inDefinedTermSet": {
    "@id": "https://www.nlm.nih.gov/mesh/",
    "name": "MeSH"
   }
  },
  {
   "@id": "http://edamontology.org/topic_0121",
   "@type": "DefinedTerm",
   "name": "Proteomics",
   "termCode": "topic_0121",
   "inDefinedTermSet": {
    "@id": "http://edamontology.org",
    "name": "EDAM"
   }
  },
  {
   "@id": "http://edamontology.org/topic_3170",
   "@type": "DefinedTerm",
   "name": "RNA-Seq",
   "termCode": "topic_3170",
   "inDefinedTermSet": {
    "@id": "http://edamontology.org",
    "name": "EDAM"
   }
  },
  {
   "@id": "http://edamontology.org/topic_3320",
   "@type": "DefinedTerm",
   "name": "Functional genomics",
   "termCode": "topic_3320",
   "inDefinedTermSet": {
    "@id": "http://edamontology.org",
    "name": "EDAM"
   }
  },
  {
   "@id": "http://edamontology.org/topic_3474",
   "@type": "DefinedTerm",
   "name": "Machine learning",
   "termCode": "topic_3474",
   "inDefinedTermSet": {
    "@id": "http://edamontology.org",
    "name": "EDAM"
   }
  },
  {
   "@id": "https://www.cellosaurus.org/CVCL_0419",
   "@type": "DefinedTerm",
   "name": "MDA-MB-468",
   "termCode": "CVCL_0419",
   "inDefinedTermSet": {
    "@id": "https://www.cellosaurus.org/",
    "name": "Cellosaurus"
   }
  },
  {
   "@id": "https://www.cellosaurus.org/CVCL_B5P3",
   "@type": "DefinedTerm",
   "name": "KOLF2.1J",
   "termCode": "CVCL_B5P3",
   "inDefinedTermSet": {
    "@id": "https://www.cellosaurus.org/",
    "name": "Cellosaurus"
   }
  },
  {
   "@id": "https://fairscape.net/api/ark:59853/rocrate-endotag-ap-ms-in-mda-mb-468-cells-paclitaxel",
   "@type": [
    "Dataset",
    "https://w3id.org/EVI#ROCrate"
   ],
   "name": "EndoTag AP-MS Profiling of Chromatin Modifier Interactome Rewiring in MDA-MB-468 Cells Upon Paclitaxel Perturbation",
   "description": "This submission comprises affinity purification mass spectrometry (AP-MS) raw data generated from endogenously tagged MDA-MB-468 cells under Paclitaxel perturbation. The dataset focuses on drug-induced interactome rewiring of chromatin modifiers relevant to the triple-negative breast cancer context. All AP-MS experiments were performed in four biological replicates. Each AP-MS batch includes an untagged parental control, 10 chromatin modifier tagged cell lines, and a positive control tagged line. DMSO-treated samples serve as vehicle control across all AP-MS experiments (Unpublished data).",
   "keywords": [
    "proteomics",
    "mass spectrometry",
    "MassIVE",
    "Endotagging",
    "AP-MS",
    "Triple Negative Breast Cancer",
    "MDA-MB-468",
    "Paclitaxel",
    "CM4AI",
    "Bridge2AI"
   ],
   "contentSize": "441.2 GB",
   "version": "1.0",
   "datePublished": "2026-05-22T13:23:35.699025+00:00",
   "isPartOf": [
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-January-2026-data-release,"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-June-2026-data-release,"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-June-2026-data-release"
    }
   ],
   "hasPart": {
    "_summarized_by": "d4d rocrate normalize",
    "count": 560,
    "id_families": {
     "dataset": 555,
     "schema": 2,
     "sample": 1,
     "instrument": 1,
     "experiment": 1
    },
    "sample_ids": [
     "https://fairscape.net/api/ark:59853/sample-msv000101915-1",
     "https://fairscape.net/api/ark:59853/instrument-msv000101915-1",
     "https://fairscape.net/api/ark:59853/experiment-msv000101915-1",
     "https://fairscape.net/api/ark:59853/dataset-msv000101915-7c441f304dddb5e2",
     "https://fairscape.net/api/ark:59853/dataset-msv000101915-bcfa9680459d3d30"
    ]
   },
   "author": "Richa Tiwari",
   "associatedPublication": "",
   "license": "https://creativecommons.org/publicdomain/zero/1.0/",
   "sameAs": "https://massive.ucsd.edu/ProteoSAFe/QueryMSV?id=MSV000101915",
   "principalInvestigator": "Trey Ideker",
   "copyrightNotice": "Copyright (c) 2026 The Regents of the University of California except where otherwise noted. Spatial proteomics raw image data is copyright (c) 2026 The Board of Trustees of the Leland Stanford Junior University.",
   "conditionsOfAccess": "Attribution is required to the copyright holders and the authors. Any publications referencing this data or derived data products should cite the Related Publications below, as well as directly citing this data collection.",
   "contactEmail": "tideker@health.ucsd.edu",
   "confidentialityLevel": "Unrestricted",
   "citation": "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; Metallo C; Muralidharan M; Nourreddine S; Niestroy J; Obernier K; Pan E; Park, S; Polacco B; Pratt D; Qian G; Schaffer, LV; Sigaeva A; Thaker S; Zhang Y; Zhao, X; 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, 2025, \"Cell Maps for Artificial Intelligence - March 2025 Data Release (Beta)\", https://doi.org/10.18130/V3/K7TGEM , https://dataverse.lib.virginia.edu/, V1",
   "usageInfo": "These laboratory data are not to be used in clinical decision-making or in any context involving patient care without appropriate regulatory oversight and approval.",
   "ethicalReview": "Vardit Ravistky ravitskyv@thehastingscenter.org and Jean-Christophe Belisle-Pipon jean-christophe_belisle-pipon@sfu.ca.",
   "humanSubjectResearch": "None - data collected from commercially available cell lines",
   "humanSubjectExemption": "Exempt — research with commercially available de-identified human cell lines does not constitute human subjects research.",
   "dataGovernanceCommittee": "Jilian Parker",
   "completeness": "These data are not yet in completed final form, and some datasets are under temporary pre-publication embargo. Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incompletely overlap. Computed cell maps not included in this release.",
   "prohibitedUses": "These laboratory data are not to be used in clinical decision-making or in any context involving patient care without appropriate regulatory oversight and approval.",
   "rai:dataLimitations": "This is an interim release. It does not contain predicted cell maps, which will be added in future releases. The current release is most suitable for bioinformatics analysis of the individual datasets. Requires domain expertise for meaningful analysis.",
   "rai:dataBiases": "Data in this release was derived from commercially available de-identified human cell lines, and does not represent all biological variants which may be seen in the population at large.",
   "rai:dataUseCases": "AI-ready datasets to support research in functional genomics, AI/machine learning model training, cellular process analysis, cell architectural changes, and interactions in presence of specific disease processes, treatment conditions, or genetic perturbations. A major goal is to enable biologically-driven, interpretable ML applications, for example as proposed in Ma et al. 2018 (PMID: 29505029) and Kuenzi et al. 2020 (PMID: 33096023).",
   "rai:dataReleaseMaintenancePlan": "Dataset will be regularly updated and augmented on a quarterly basis through the end of the project (November, 2026). Long term preservation in the https://dataverse.lib.virginia.edu/, supported by committed institutional funds.",
   "rai:dataCollection": "Data collection processes are generally described in Clark T et al. (2024) \"Cell Maps for Artificial Intelligence: AI-Ready Maps of Human Cell Architecture from Disease-Relevant Cell Lines\" bioRxiv 2024.05.21.589311; doi: https://doi.org/10.1101/2024.05.21.589311. Additional data collection details will be subsequently published once finalized. ",
   "rai:dataCollectionType": [
    "Perturb-seq; IF imaging; SEC-MS"
   ],
   "rai:dataCollectionMissingData": "Some datasets are under temporary pre-publication embargo. Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incompletely overlap. Computed cell maps not included in this release.",
   "rai:dataCollectionTimeframe": [
    "9/1/2022",
    "1/31/2026"
   ],
   "https://w3id.org/EVI#inputs": {
    "_summarized_by": "d4d rocrate normalize",
    "count": 117,
    "id_families": {
     "sample": 117
    },
    "sample_ids": [
     "https://fairscape.net/api/ark:59853/sample-msv000101915-atm-dmso",
     "https://fairscape.net/api/ark:59853/sample-msv000101915-atm-paclitaxel",
     "https://fairscape.net/api/ark:59853/sample-msv000101915-aurka-dmso",
     "https://fairscape.net/api/ark:59853/sample-msv000101915-aurka-paclitaxel",
     "https://fairscape.net/api/ark:59853/sample-msv000101915-aurkb-dmso"
    ]
   },
   "https://w3id.org/EVI#outputs": {
    "_summarized_by": "d4d rocrate normalize",
    "count": 555,
    "id_families": {
     "dataset": 555
    },
    "sample_ids": [
     "https://fairscape.net/api/ark:59853/dataset-msv000101915-7c441f304dddb5e2",
     "https://fairscape.net/api/ark:59853/dataset-msv000101915-bcfa9680459d3d30",
     "https://fairscape.net/api/ark:59853/dataset-msv000101915-a508263011888846",
     "https://fairscape.net/api/ark:59853/dataset-msv000101915-1271b8748c3e4374",
     "https://fairscape.net/api/ark:59853/dataset-msv000101915-8979852725104d65"
    ]
   },
   "localEvidenceGraph": {
    "@id": "AP-MS/apms-paclitaxel-rocrate/ro-crate-prov-graph.html"
   },
   "evi:processed": true,
   "ro-crate-metadata": "AP-MS/apms-paclitaxel-rocrate/ro-crate-metadata.json"
  },
  {
   "@id": "https://fairscape.net/api/ark:59853/rocrate-endotag-ap-ms-in-mda-mb-468-cells-vorinostat",
   "@type": [
    "Dataset",
    "https://w3id.org/EVI#ROCrate"
   ],
   "name": "EndoTag-AP-MS Profiling of Chromatin Modifier Interactome Rewiring in MDA-MB-468 Cells Upon Vorinostat Perturbation",
   "description": "This submission comprises affinity purification mass spectrometry (AP-MS) raw data generated from endogenously tagged MDA-MB-468 cells under Vorinostat perturbation. The dataset focuses on drug-induced interactome rewiring of chromatin modifiers relevant to the triple-negative breast cancer context. All AP-MS experiments were performed in four biological replicates. Each AP-MS batch includes an untagged parental control, 10 chromatin modifier tagged cell lines, and a positive control tagged line. DMSO-treated sample server as vehicle controls across all AP-MS experiments (Unpublished data).",
   "keywords": [
    "proteomics",
    "mass spectrometry",
    "MassIVE",
    "EndoTagging",
    "AP-MS",
    "Triple Negative Breast Cancer",
    "MDA-MB-468",
    "Vorinostat",
    "CM4AI",
    "Bridge2AI"
   ],
   "version": "1.0",
   "datePublished": "2026-05-22T13:58:58.942348+00:00",
   "isPartOf": [
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-January-2026-data-release,"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-June-2026-data-release,"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-June-2026-data-release"
    }
   ],
   "hasPart": {
    "_summarized_by": "d4d rocrate normalize",
    "count": 723,
    "id_families": {
     "dataset": 718,
     "schema": 2,
     "sample": 1,
     "instrument": 1,
     "experiment": 1
    },
    "sample_ids": [
     "https://fairscape.net/api/ark:59853/sample-msv000101917-1",
     "https://fairscape.net/api/ark:59853/instrument-msv000101917-1",
     "https://fairscape.net/api/ark:59853/experiment-msv000101917-1",
     "https://fairscape.net/api/ark:59853/dataset-msv000101917-5309353eef290f2b",
     "https://fairscape.net/api/ark:59853/dataset-msv000101917-ce5c3cd7556aee4e"
    ]
   },
   "author": "Richa Tiwari",
   "associatedPublication": "",
   "contentSize": "532.5 GB",
   "license": "https://creativecommons.org/publicdomain/zero/1.0/",
   "sameAs": "https://massive.ucsd.edu/ProteoSAFe/QueryMSV?id=MSV000101917",
   "principalInvestigator": "Trey Ideker",
   "copyrightNotice": "Copyright (c) 2026 The Regents of the University of California except where otherwise noted. Spatial proteomics raw image data is copyright (c) 2026 The Board of Trustees of the Leland Stanford Junior University.",
   "conditionsOfAccess": "Attribution is required to the copyright holders and the authors. Any publications referencing this data or derived data products should cite the Related Publications below, as well as directly citing this data collection.",
   "contactEmail": "tideker@health.ucsd.edu",
   "confidentialityLevel": "Unrestricted",
   "citation": "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; Metallo C; Muralidharan M; Nourreddine S; Niestroy J; Obernier K; Pan E; Park, S; Polacco B; Pratt D; Qian G; Schaffer, LV; Sigaeva A; Thaker S; Zhang Y; Zhao, X; 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, 2025, \"Cell Maps for Artificial Intelligence - March 2025 Data Release (Beta)\", https://doi.org/10.18130/V3/K7TGEM , https://dataverse.lib.virginia.edu/, V1",
   "usageInfo": "These laboratory data are not to be used in clinical decision-making or in any context involving patient care without appropriate regulatory oversight and approval.",
   "ethicalReview": "Vardit Ravistky ravitskyv@thehastingscenter.org and Jean-Christophe Belisle-Pipon jean-christophe_belisle-pipon@sfu.ca.",
   "humanSubjectResearch": "None - data collected from commercially available cell lines",
   "humanSubjectExemption": "Exempt — research with commercially available de-identified human cell lines does not constitute human subjects research.",
   "dataGovernanceCommittee": "Jilian Parker",
   "completeness": "These data are not yet in completed final form, and some datasets are under temporary pre-publication embargo. Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incompletely overlap. Computed cell maps not included in this release.",
   "prohibitedUses": "These laboratory data are not to be used in clinical decision-making or in any context involving patient care without appropriate regulatory oversight and approval.",
   "rai:dataLimitations": "This is an interim release. It does not contain predicted cell maps, which will be added in future releases. The current release is most suitable for bioinformatics analysis of the individual datasets. Requires domain expertise for meaningful analysis.",
   "rai:dataBiases": "Data in this release was derived from commercially available de-identified human cell lines, and does not represent all biological variants which may be seen in the population at large.",
   "rai:dataUseCases": "AI-ready datasets to support research in functional genomics, AI/machine learning model training, cellular process analysis, cell architectural changes, and interactions in presence of specific disease processes, treatment conditions, or genetic perturbations. A major goal is to enable biologically-driven, interpretable ML applications, for example as proposed in Ma et al. 2018 (PMID: 29505029) and Kuenzi et al. 2020 (PMID: 33096023).",
   "rai:dataReleaseMaintenancePlan": "Dataset will be regularly updated and augmented on a quarterly basis through the end of the project (November, 2026). Long term preservation in the https://dataverse.lib.virginia.edu/, supported by committed institutional funds.",
   "rai:dataCollection": "Data collection processes are generally described in Clark T et al. (2024) \"Cell Maps for Artificial Intelligence: AI-Ready Maps of Human Cell Architecture from Disease-Relevant Cell Lines\" bioRxiv 2024.05.21.589311; doi: https://doi.org/10.1101/2024.05.21.589311. Additional data collection details will be subsequently published once finalized. ",
   "rai:dataCollectionType": [
    "Perturb-seq; IF imaging; SEC-MS"
   ],
   "rai:dataCollectionMissingData": "Some datasets are under temporary pre-publication embargo. Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incompletely overlap. Computed cell maps not included in this release.",
   "rai:dataCollectionTimeframe": [
    "9/1/2022",
    "1/31/2026"
   ],
   "https://w3id.org/EVI#inputs": {
    "_summarized_by": "d4d rocrate normalize",
    "count": 138,
    "id_families": {
     "sample": 138
    },
    "sample_ids": [
     "https://fairscape.net/api/ark:59853/sample-msv000101917-atm-dmso",
     "https://fairscape.net/api/ark:59853/sample-msv000101917-atm-vorinostat",
     "https://fairscape.net/api/ark:59853/sample-msv000101917-aurka-dmso",
     "https://fairscape.net/api/ark:59853/sample-msv000101917-aurka-vorinostat",
     "https://fairscape.net/api/ark:59853/sample-msv000101917-aurkb-dmso"
    ]
   },
   "https://w3id.org/EVI#outputs": {
    "_summarized_by": "d4d rocrate normalize",
    "count": 718,
    "id_families": {
     "dataset": 718
    },
    "sample_ids": [
     "https://fairscape.net/api/ark:59853/dataset-msv000101917-5309353eef290f2b",
     "https://fairscape.net/api/ark:59853/dataset-msv000101917-ce5c3cd7556aee4e",
     "https://fairscape.net/api/ark:59853/dataset-msv000101917-a17ec0f3791ced91",
     "https://fairscape.net/api/ark:59853/dataset-msv000101917-5fe39ba432ce8132",
     "https://fairscape.net/api/ark:59853/dataset-msv000101917-63a240d19a595d82"
    ]
   },
   "localEvidenceGraph": {
    "@id": "AP-MS/apms-vorinostat-rocrate/ro-crate-prov-graph.html"
   },
   "evi:processed": true,
   "ro-crate-metadata": "AP-MS/apms-vorinostat-rocrate/ro-crate-metadata.json"
  },
  {
   "@type": [
    "Dataset",
    "https://w3id.org/EVI#ROCrate"
   ],
   "isPartOf": [
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-october-2025-data-release,"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-January-2026-data-release,"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-June-2026-data-release,"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-June-2026-data-release"
    }
   ],
   "version": "0.1.0",
   "datePublished": "02/28/2025",
   "license": "https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en",
   "associatedPublication": "",
   "author": [
    "Hansen JN",
    "Axelsson U",
    "Johannesson A",
    "Fall J",
    "Ballllosera Navarro F",
    "Lundberg E"
   ],
   "MD5": "9422486c80bc9e1d35b2fbbc72a5f043",
   "conditionsOfAccess": "Attribution is required to the copyright holders and the authors. Any publications referencing this data or derived products should cite the related article as well as directly citing this data collection. ",
   "copyrightNotice": "Copyright (c) 2025 by The Board of Trustees of the Leland Stanford Junior University",
   "hasPart": {
    "_summarized_by": "d4d rocrate normalize",
    "count": 18625,
    "id_families": {
     "experiment": 468,
     "b2ai": 465,
     "stain": 3,
     "dataset": 1,
     "cell": 1,
     "treatment": 1,
     "sample": 1,
     "B2AI_5_Paclitaxel_H12_R8_z01_blue": 1,
     "B2AI_5_Paclitaxel_H12_R8_z01_red": 1,
     "B2AI_5_Paclitaxel_H12_R8_z01_yellow": 1,
     "B2AI_5_Paclitaxel_H12_R8_z01_green": 1,
     "B2AI_4_Paclitaxel_H12_R8_z02_blue": 1
    },
    "sample_ids": [
     "https://fairscape.net/api/ark:59853/dataset-paclitaxel-manifest",
     "https://fairscape.net/api/ark:59853/cell-line-MDA-MB-468",
     "https://fairscape.net/api/ark:59853/treatment-paclitaxel",
     "https://fairscape.net/api/ark:59853/stain-dapi",
     "https://fairscape.net/api/ark:59853/stain-calreticulin-antibody"
    ]
   },
   "contactEmail": "emmalu@stanford.edu",
   "funder": "National Institutes of Health: 1OT2OD032742-01",
   "@id": "https://fairscape.net/api/ark:59853/rocrate-paclitaxel-if-data-release",
   "name": "Paclitaxel IF Images",
   "description": "This data set displays the spatial localization of 464 proteins of interest in cells of the breast cancer cell line MDA-MB-468 treated with paclitaxel as imaged by immunofluorescence-based staining (ICC-IF) and confocal microscopy in the Lundberg Lab at Stanford University, as part of the Cell Maps for Artificial Intelligence (CM4AI; CM4AI.org) project. Nuclei were stained with DAPI (blue channel); endoplasmic reticulum with a calreticulin antibody (yellow channel); microtubules with tubulin antibody (red channel); and antibody against protein of interest (green channel).",
   "keywords": [
    "AI",
    "artificial intelligence",
    "breast cancer",
    "cell maps",
    "CM4AI",
    "machine learning",
    "MDA-MB-468",
    "paclitaxel",
    "protein localization"
   ],
   "contentSize": "2.6 GB",
   "https://w3id.org/EVI#inputs": [
    {
     "@id": "https://fairscape.net/api/ark:59853/sample-mda-mb-468-lNzmhj2iYbi"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/dataset-paclitaxel-manifest"
    }
   ],
   "https://w3id.org/EVI#outputs": {
    "_summarized_by": "d4d rocrate normalize",
    "count": 17685,
    "id_families": {
     "dataset": 1,
     "B2AI_5_Paclitaxel_H12_R8_z01_blue": 1,
     "B2AI_5_Paclitaxel_H12_R8_z01_red": 1,
     "B2AI_5_Paclitaxel_H12_R8_z01_yellow": 1,
     "B2AI_5_Paclitaxel_H12_R8_z01_green": 1,
     "B2AI_4_Paclitaxel_H12_R8_z02_blue": 1,
     "B2AI_4_Paclitaxel_H12_R8_z02_red": 1,
     "B2AI_4_Paclitaxel_H12_R8_z02_yellow": 1,
     "B2AI_4_Paclitaxel_H12_R8_z02_green": 1,
     "B2AI_3_Paclitaxel_H12_R8_z02_blue": 1,
     "B2AI_3_Paclitaxel_H12_R8_z02_red": 1,
     "B2AI_3_Paclitaxel_H12_R8_z02_yellow": 1
    },
    "sample_ids": [
     "https://fairscape.net/api/ark:59853/dataset-paclitaxel-manifest",
     "https://fairscape.net/api/ark:59853/B2AI_5_Paclitaxel_H12_R8_z01_blue",
     "https://fairscape.net/api/ark:59853/B2AI_5_Paclitaxel_H12_R8_z01_red",
     "https://fairscape.net/api/ark:59853/B2AI_5_Paclitaxel_H12_R8_z01_yellow",
     "https://fairscape.net/api/ark:59853/B2AI_5_Paclitaxel_H12_R8_z01_green"
    ]
   },
   "principalInvestigator": "Trey Ideker",
   "confidentialityLevel": "Unrestricted",
   "citation": "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, 2025, \"Cell Maps for Artificial Intelligence - March 2025 Data Release (Beta)\", https://doi.org/10.18130/V3/B35XWX , https://dataverse.lib.virginia.edu/, V1",
   "usageInfo": "These laboratory data are not to be used in clinical decision-making or in any context involving patient care without appropriate regulatory oversight and approval.",
   "additionalProperty": [
    {
     "@type": "PropertyValue",
     "name": "Completeness",
     "value": "These data are not yet in completed final form, and some datasets are under temporary pre-publication embargo. Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incompletely overlap. Computed cell maps not included in this release."
    },
    {
     "@type": "PropertyValue",
     "name": "Human Subject",
     "value": "No"
    },
    {
     "@type": "PropertyValue",
     "name": "Prohibited Uses",
     "value": "These laboratory data are not to be used in clinical decision-making or in any context involving patient care without appropriate regulatory oversight and approval."
    }
   ],
   "rai:dataLimitations": "This is an interim release. It does not contain predicted cell maps, which will be added in future releases. The current release is most suitable for bioinformatics analysis of the individual datasets. Requires domain expertise for meaningful analysis.",
   "rai:dataBiases": "Data in this release was derived from commercially available de-identified human cell lines, and does not represent all biological variants which may be seen in the population at large.",
   "rai:dataUseCases": "AI-ready datasets to support research in functional genomics, AI model training, cellular process analysis, cell architectural changes, and interactions in presence of specific disease processes, treatment conditions, or genetic perturbations. A major goal is to enable visible machine learning applications, as proposed in Ma et al. (2018) Nature Methods.",
   "rai:dataReleaseMaintenancePlan": "Dataset will be regularly updated and augmented through the end of the project in November 2026, on a quarterly basis. Long term preservation in the https://dataverse.lib.virginia.edu/, supported by committed institutional funds.",
   "localEvidenceGraph": {
    "@id": "Images/paclitaxel/ro-crate-prov-graph.html"
   },
   "rai:dataCollection": "Data collection processes are generally described in Clark T et al. (2024) \"Cell Maps for Artificial Intelligence: AI-Ready Maps of Human Cell Architecture from Disease-Relevant Cell Lines\" bioRxiv 2024.05.21.589311; doi: https://doi.org/10.1101/2024.05.21.589311. Additional data collection details will be subsequently published once finalized. ",
   "rai:dataCollectionType": [
    "Perturb-seq; IF imaging; SEC-MS"
   ],
   "rai:dataCollectionTimeframe": [
    "9/1/2022",
    "10/13/25"
   ],
   "ethicalReview": "Vardit Ravistky ravitskyv@thehastingscenter.org and Jean-Christophe Belisle-Pipon jean-christophe_belisle-pipon@sfu.ca.",
   "humanSubjectResearch": "None - data collected from commercially available cell lines",
   "humanSubjectExemption": "Exempt — research with commercially available de-identified human cell lines does not constitute human subjects research.",
   "dataGovernanceCommittee": "Jilian Parker",
   "completeness": "These data are not yet in completed final form, and some datasets are under temporary pre-publication embargo. Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incompletely overlap. Computed cell maps not included in this release.",
   "prohibitedUses": "These laboratory data are not to be used in clinical decision-making or in any context involving patient care without appropriate regulatory oversight and approval.",
   "rai:dataCollectionMissingData": "Some datasets are under temporary pre-publication embargo. Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incompletely overlap. Computed cell maps not included in this release.",
   "evi:processed": true,
   "ro-crate-metadata": "Images/paclitaxel/ro-crate-metadata.json"
  },
  {
   "@type": [
    "Dataset",
    "https://w3id.org/EVI#ROCrate"
   ],
   "isPartOf": [
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-october-2025-data-release,"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-January-2026-data-release,"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-June-2026-data-release,"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-June-2026-data-release"
    }
   ],
   "version": "0.1.0",
   "MD5": "0b4d129f5fbc3bb7f7ea564cd032cef7",
   "datePublished": "02/28/2025",
   "license": "https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en",
   "associatedPublication": "",
   "author": [
    "Hansen JN",
    "Axelsson U",
    "Johannesson A",
    "Fall J",
    "Ballllosera Navarro F",
    "Lundberg E"
   ],
   "conditionsOfAccess": "Attribution is required to the copyright holders and the authors. Any publications referencing this data or derived data products should cite the Related Publications below, as well as directly citing this data collection.",
   "copyrightNotice": "Copyright (c) 2025 by The Board of Trustees of the Leland Stanford Junior University",
   "hasPart": {
    "_summarized_by": "d4d rocrate normalize",
    "count": 16845,
    "id_families": {
     "experiment": 468,
     "b2ai": 465,
     "stain": 3,
     "dataset": 1,
     "cell": 1,
     "treatment": 1,
     "sample": 1,
     "B2AI_5_untreated_H12_R8_z01_blue": 1,
     "B2AI_5_untreated_H12_R8_z01_red": 1,
     "B2AI_5_untreated_H12_R8_z01_yellow": 1,
     "B2AI_5_untreated_H12_R8_z01_green": 1,
     "B2AI_4_untreated_H12_R8_z02_blue": 1
    },
    "sample_ids": [
     "https://fairscape.net/api/ark:59853/dataset-untreated-manifest",
     "https://fairscape.net/api/ark:59853/cell-line-MDA-MB-468",
     "https://fairscape.net/api/ark:59853/treatment-control",
     "https://fairscape.net/api/ark:59853/stain-dapi",
     "https://fairscape.net/api/ark:59853/stain-calreticulin-antibody"
    ]
   },
   "@id": "https://fairscape.net/api/ark:59853/rocrate-untreated-if-data-release",
   "name": "Untreated IF Images",
   "description": "This data set displays the spatial localization of 464 proteins of interest in untreated cells of the breast cancer cell line MDA-MB-468 as imaged by immunofluorescence-based staining (ICC-IF) and confocal microscopy in the Lundberg Lab at Stanford University, as part of the Cell Maps for Artificial Intelligence (CM4AI; CM4AI.org) project. Nuclei were stained with DAPI (blue channel); endoplasmic reticulum with a calreticulin antibody (yellow channel); microtubules with tubulin antibody (red channel); and antibody against protein of interest (green channel).",
   "keywords": [
    "artificial intelligence",
    "breast cancer",
    "cell maps",
    "CM4AI",
    "machine learning",
    "MDA-MB-468",
    "protein localization"
   ],
   "contentSize": "3.2 GB",
   "https://w3id.org/EVI#inputs": [
    {
     "@id": "https://fairscape.net/api/ark:59853/sample-mda-mb-468-UK59eH6L75"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/dataset-untreated-manifest"
    }
   ],
   "https://w3id.org/EVI#outputs": {
    "_summarized_by": "d4d rocrate normalize",
    "count": 15905,
    "id_families": {
     "dataset": 1,
     "B2AI_5_untreated_H12_R8_z01_blue": 1,
     "B2AI_5_untreated_H12_R8_z01_red": 1,
     "B2AI_5_untreated_H12_R8_z01_yellow": 1,
     "B2AI_5_untreated_H12_R8_z01_green": 1,
     "B2AI_4_untreated_H12_R8_z02_blue": 1,
     "B2AI_4_untreated_H12_R8_z02_red": 1,
     "B2AI_4_untreated_H12_R8_z02_yellow": 1,
     "B2AI_4_untreated_H12_R8_z02_green": 1,
     "B2AI_3_untreated_H12_R8_z01_blue": 1,
     "B2AI_3_untreated_H12_R8_z01_red": 1,
     "B2AI_3_untreated_H12_R8_z01_yellow": 1
    },
    "sample_ids": [
     "https://fairscape.net/api/ark:59853/dataset-untreated-manifest",
     "https://fairscape.net/api/ark:59853/B2AI_5_untreated_H12_R8_z01_blue",
     "https://fairscape.net/api/ark:59853/B2AI_5_untreated_H12_R8_z01_red",
     "https://fairscape.net/api/ark:59853/B2AI_5_untreated_H12_R8_z01_yellow",
     "https://fairscape.net/api/ark:59853/B2AI_5_untreated_H12_R8_z01_green"
    ]
   },
   "principalInvestigator": "Trey Ideker",
   "contactEmail": "tideker@health.ucsd.edu",
   "confidentialityLevel": "Unrestricted",
   "citation": "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, 2025, \"Cell Maps for Artificial Intelligence - March 2025 Data Release (Beta)\", https://doi.org/10.18130/V3/B35XWX , https://dataverse.lib.virginia.edu/, V1",
   "usageInfo": "These laboratory data are not to be used in clinical decision-making or in any context involving patient care without appropriate regulatory oversight and approval.",
   "additionalProperty": [
    {
     "@type": "PropertyValue",
     "name": "Completeness",
     "value": "These data are not yet in completed final form, and some datasets are under temporary pre-publication embargo. Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incompletely overlap. Computed cell maps not included in this release."
    },
    {
     "@type": "PropertyValue",
     "name": "Human Subject",
     "value": "No"
    },
    {
     "@type": "PropertyValue",
     "name": "Prohibited Uses",
     "value": "These laboratory data are not to be used in clinical decision-making or in any context involving patient care without appropriate regulatory oversight and approval."
    }
   ],
   "rai:dataLimitations": "This is an interim release. It does not contain predicted cell maps, which will be added in future releases. The current release is most suitable for bioinformatics analysis of the individual datasets. Requires domain expertise for meaningful analysis.",
   "rai:dataBiases": "Data in this release was derived from commercially available de-identified human cell lines, and does not represent all biological variants which may be seen in the population at large.",
   "rai:dataUseCases": "AI-ready datasets to support research in functional genomics, AI model training, cellular process analysis, cell architectural changes, and interactions in presence of specific disease processes, treatment conditions, or genetic perturbations. A major goal is to enable visible machine learning applications, as proposed in Ma et al. (2018) Nature Methods.",
   "rai:dataReleaseMaintenancePlan": "Dataset will be regularly updated and augmented through the end of the project in November 2026, on a quarterly basis. Long term preservation in the https://dataverse.lib.virginia.edu/, supported by committed institutional funds.",
   "localEvidenceGraph": {
    "@id": "Images/untreated/ro-crate-prov-graph.html"
   },
   "rai:dataCollection": "Data collection processes are generally described in Clark T et al. (2024) \"Cell Maps for Artificial Intelligence: AI-Ready Maps of Human Cell Architecture from Disease-Relevant Cell Lines\" bioRxiv 2024.05.21.589311; doi: https://doi.org/10.1101/2024.05.21.589311. Additional data collection details will be subsequently published once finalized. ",
   "rai:dataCollectionType": [
    "Perturb-seq; IF imaging; SEC-MS"
   ],
   "rai:dataCollectionTimeframe": [
    "9/1/2022",
    "10/13/25"
   ],
   "ethicalReview": "Vardit Ravistky ravitskyv@thehastingscenter.org and Jean-Christophe Belisle-Pipon jean-christophe_belisle-pipon@sfu.ca.",
   "humanSubjectResearch": "None - data collected from commercially available cell lines",
   "humanSubjectExemption": "Exempt — research with commercially available de-identified human cell lines does not constitute human subjects research.",
   "dataGovernanceCommittee": "Jilian Parker",
   "completeness": "These data are not yet in completed final form, and some datasets are under temporary pre-publication embargo. Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incompletely overlap. Computed cell maps not included in this release.",
   "prohibitedUses": "These laboratory data are not to be used in clinical decision-making or in any context involving patient care without appropriate regulatory oversight and approval.",
   "rai:dataCollectionMissingData": "Some datasets are under temporary pre-publication embargo. Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incompletely overlap. Computed cell maps not included in this release.",
   "evi:processed": true,
   "ro-crate-metadata": "Images/untreated/ro-crate-metadata.json"
  },
  {
   "@type": [
    "Dataset",
    "https://w3id.org/EVI#ROCrate"
   ],
   "isPartOf": [
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-october-2025-data-release,"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-January-2026-data-release,"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-June-2026-data-release,"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-June-2026-data-release"
    }
   ],
   "version": "0.1.0",
   "datePublished": "02/28/2025",
   "MD5": "ac577109a41a9806978461157b777d52",
   "license": "https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en",
   "associatedPublication": "",
   "author": [
    "Hansen JN",
    "Axelsson U",
    "Johannesson A",
    "Fall J",
    "Ballllosera Navarro F",
    "Lundberg E"
   ],
   "conditionsOfAccess": "Attribution is required to the copyright holders and the authors. Any publications referencing this data or derived products should cite the related article as well as directly citing this data collection. ",
   "copyrightNotice": "Copyright (c) 2025 by The Board of Trustees of the Leland Stanford Junior University",
   "hasPart": {
    "_summarized_by": "d4d rocrate normalize",
    "count": 18789,
    "id_families": {
     "experiment": 468,
     "b2ai": 465,
     "stain": 3,
     "dataset": 1,
     "cell": 1,
     "treatment": 1,
     "sample": 1,
     "B2AI_5_Vorinostat_H12_R8_z01_blue": 1,
     "B2AI_5_Vorinostat_H12_R8_z01_red": 1,
     "B2AI_5_Vorinostat_H12_R8_z01_yellow": 1,
     "B2AI_5_Vorinostat_H12_R8_z01_green": 1,
     "B2AI_4_Vorinostat_H12_R8_z02_blue": 1
    },
    "sample_ids": [
     "https://fairscape.net/api/ark:59853/dataset-vorinostat-manifest",
     "https://fairscape.net/api/ark:59853/cell-line-MDA-MB-468",
     "https://fairscape.net/api/ark:59853/treatment-vorinostat",
     "https://fairscape.net/api/ark:59853/stain-dapi",
     "https://fairscape.net/api/ark:59853/stain-calreticulin-antibody"
    ]
   },
   "@id": "https://fairscape.net/api/ark:59853/rocrate-vorinostat-if-data-release",
   "name": "Vorinostat IF Images",
   "description": "This data set displays the spatial localization of 464 proteins of interest in cells of the breast cancer cell line MDA-MB-468 treated with vorinostat as imaged by immunofluorescence-based staining (ICC-IF) and confocal microscopy in the Lundberg Lab at Stanford University, as part of the Cell Maps for Artificial Intelligence (CM4AI; CM4AI.org) project. Nuclei were stained with DAPI (blue channel); endoplasmic reticulum with a calreticulin antibody (yellow channel); microtubules with tubulin antibody (red channel); and antibody against protein of interest (green channel).",
   "keywords": [
    "AI",
    "artificial intelligence",
    "breast cancer",
    "cell maps",
    "CM4AI",
    "machine learning",
    "MDA-MB-468",
    "protein localization",
    "vorinostat"
   ],
   "contentSize": "2.8 GB",
   "contactEmail": "emmalu@stanford.edu",
   "funder": "National Institutes of Health: 1OT2OD032742-01",
   "https://w3id.org/EVI#inputs": [
    {
     "@id": "https://fairscape.net/api/ark:59853/sample-mda-mb-468-7Ja0Ix9dXRq"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/dataset-vorinostat-manifest"
    }
   ],
   "https://w3id.org/EVI#outputs": {
    "_summarized_by": "d4d rocrate normalize",
    "count": 17849,
    "id_families": {
     "dataset": 1,
     "B2AI_5_Vorinostat_H12_R8_z01_blue": 1,
     "B2AI_5_Vorinostat_H12_R8_z01_red": 1,
     "B2AI_5_Vorinostat_H12_R8_z01_yellow": 1,
     "B2AI_5_Vorinostat_H12_R8_z01_green": 1,
     "B2AI_4_Vorinostat_H12_R8_z02_blue": 1,
     "B2AI_4_Vorinostat_H12_R8_z02_red": 1,
     "B2AI_4_Vorinostat_H12_R8_z02_yellow": 1,
     "B2AI_4_Vorinostat_H12_R8_z02_green": 1,
     "B2AI_3_Vorinostat_H12_R8_z02_blue": 1,
     "B2AI_3_Vorinostat_H12_R8_z02_red": 1,
     "B2AI_3_Vorinostat_H12_R8_z02_yellow": 1
    },
    "sample_ids": [
     "https://fairscape.net/api/ark:59853/dataset-vorinostat-manifest",
     "https://fairscape.net/api/ark:59853/B2AI_5_Vorinostat_H12_R8_z01_blue",
     "https://fairscape.net/api/ark:59853/B2AI_5_Vorinostat_H12_R8_z01_red",
     "https://fairscape.net/api/ark:59853/B2AI_5_Vorinostat_H12_R8_z01_yellow",
     "https://fairscape.net/api/ark:59853/B2AI_5_Vorinostat_H12_R8_z01_green"
    ]
   },
   "principalInvestigator": "Trey Ideker",
   "confidentialityLevel": "Unrestricted",
   "citation": "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, 2025, \"Cell Maps for Artificial Intelligence - March 2025 Data Release (Beta)\", https://doi.org/10.18130/V3/B35XWX , https://dataverse.lib.virginia.edu/, V1",
   "usageInfo": "These laboratory data are not to be used in clinical decision-making or in any context involving patient care without appropriate regulatory oversight and approval.",
   "additionalProperty": [
    {
     "@type": "PropertyValue",
     "name": "Completeness",
     "value": "These data are not yet in completed final form, and some datasets are under temporary pre-publication embargo. Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incompletely overlap. Computed cell maps not included in this release."
    },
    {
     "@type": "PropertyValue",
     "name": "Human Subject",
     "value": "No"
    },
    {
     "@type": "PropertyValue",
     "name": "Prohibited Uses",
     "value": "These laboratory data are not to be used in clinical decision-making or in any context involving patient care without appropriate regulatory oversight and approval."
    }
   ],
   "rai:dataLimitations": "This is an interim release. It does not contain predicted cell maps, which will be added in future releases. The current release is most suitable for bioinformatics analysis of the individual datasets. Requires domain expertise for meaningful analysis.",
   "rai:dataBiases": "Data in this release was derived from commercially available de-identified human cell lines, and does not represent all biological variants which may be seen in the population at large.",
   "rai:dataUseCases": "AI-ready datasets to support research in functional genomics, AI model training, cellular process analysis, cell architectural changes, and interactions in presence of specific disease processes, treatment conditions, or genetic perturbations. A major goal is to enable visible machine learning applications, as proposed in Ma et al. (2018) Nature Methods.",
   "rai:dataReleaseMaintenancePlan": "Dataset will be regularly updated and augmented through the end of the project in November 2026, on a quarterly basis. Long term preservation in the https://dataverse.lib.virginia.edu/, supported by committed institutional funds.",
   "localEvidenceGraph": {
    "@id": "Images/vorinostat/ro-crate-prov-graph.html"
   },
   "rai:dataCollection": "Data collection processes are generally described in Clark T et al. (2024) \"Cell Maps for Artificial Intelligence: AI-Ready Maps of Human Cell Architecture from Disease-Relevant Cell Lines\" bioRxiv 2024.05.21.589311; doi: https://doi.org/10.1101/2024.05.21.589311. Additional data collection details will be subsequently published once finalized. ",
   "rai:dataCollectionType": [
    "Perturb-seq; IF imaging; SEC-MS"
   ],
   "rai:dataCollectionTimeframe": [
    "9/1/2022",
    "10/13/25"
   ],
   "ethicalReview": "Vardit Ravistky ravitskyv@thehastingscenter.org and Jean-Christophe Belisle-Pipon jean-christophe_belisle-pipon@sfu.ca.",
   "humanSubjectResearch": "None - data collected from commercially available cell lines",
   "humanSubjectExemption": "Exempt — research with commercially available de-identified human cell lines does not constitute human subjects research.",
   "dataGovernanceCommittee": "Jilian Parker",
   "completeness": "These data are not yet in completed final form, and some datasets are under temporary pre-publication embargo. Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incompletely overlap. Computed cell maps not included in this release.",
   "prohibitedUses": "These laboratory data are not to be used in clinical decision-making or in any context involving patient care without appropriate regulatory oversight and approval.",
   "rai:dataCollectionMissingData": "Some datasets are under temporary pre-publication embargo. Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incompletely overlap. Computed cell maps not included in this release.",
   "evi:processed": true,
   "ro-crate-metadata": "Images/vorinostat/ro-crate-metadata.json"
  },
  {
   "@id": "https://fairscape.net/api/ark:59853/rocrate-sec-ms-characterization-of-kolf2-neuronal-and-cardiomyocyte-differentiation-cm4ai-yjftt2oec6c",
   "@type": [
    "Dataset",
    "https://w3id.org/EVI#ROCrate"
   ],
   "name": "SEC-MS characterization of KOLF2 neuronal and cardiomyocyte differentiation",
   "description": "This dataset contains mass spectrometry-based proteomics data investigating the protein-protein interaction networks during the differentiation of KOLF2.1J human induced pluripotent stem cells (iPSCs). We employed Size Exclusion Chromatography coupled with Mass Spectrometry (SEC-MS) to map multiscale biological organization across three distinct stages:  Parental: Undifferentiated iPSCs.  NPC: Neural Progenitor Cells.  Neurons: Terminally differentiated neurons.  Cardio: Terminally differentiated Cardiomyocyte.  The study aims to identify how protein complexes and networks are reorganized during neuronal lineage commitment and cardiomycyte differentiation. Data was acquired on a Bruker timsTOF platform, and quantitative analysis was performed using Spectronaut.  Experimental Design:  Sample Groups: Parental (Reps 1-4), NPC (Reps 1-2), Neuron (Reps 1-3), and Cardio (Reps 1-2).  Modality: SEC-MS for protein correlation profiling.  Data Processing: Raw data was processed using Spectronaut; downstream analysis was conducted in R using MSstats-compatible formats.",
   "keywords": [
    "proteomics",
    "mass spectrometry",
    "MassIVE",
    "SEC-MS",
    "iPSC",
    "KOLF2.1J",
    "KOLF2",
    "IPSC",
    "Neuron",
    "Cardiomyocyte"
   ],
   "version": "1.0",
   "datePublished": "2026-05-27T20:36:55.634084+00:00",
   "isPartOf": [
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-June-2026-data-release,"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-June-2026-data-release"
    }
   ],
   "contentSize": "1.11 TB",
   "hasPart": {
    "_summarized_by": "d4d rocrate normalize",
    "count": 867,
    "id_families": {
     "dataset": 862,
     "schema": 2,
     "sample": 1,
     "instrument": 1,
     "experiment": 1
    },
    "sample_ids": [
     "https://fairscape.net/api/ark:59853/sample-msv000100676-1",
     "https://fairscape.net/api/ark:59853/instrument-msv000100676-1",
     "https://fairscape.net/api/ark:59853/experiment-msv000100676-1",
     "https://fairscape.net/api/ark:59853/dataset-msv000100676-cc8e39efd0c8a96b",
     "https://fairscape.net/api/ark:59853/dataset-msv000100676-1ed62cf423da0185"
    ]
   },
   "author": "Antoine Forget",
   "associatedPublication": "",
   "license": "https://creativecommons.org/publicdomain/zero/1.0/",
   "sameAs": "https://massive.ucsd.edu/ProteoSAFe/QueryMSV?id=MSV000100676",
   "localEvidenceGraph": {
    "@id": "mass-spec/iPSCs/ro-crate-prov-graph.html"
   },
   "principalInvestigator": "Trey Ideker",
   "copyrightNotice": "Copyright (c) 2026 The Regents of the University of California except where otherwise noted. Spatial proteomics raw image data is copyright (c) 2026 The Board of Trustees of the Leland Stanford Junior University.",
   "conditionsOfAccess": "Attribution is required to the copyright holders and the authors. Any publications referencing this data or derived data products should cite the Related Publications below, as well as directly citing this data collection.",
   "contactEmail": "tideker@health.ucsd.edu",
   "confidentialityLevel": "Unrestricted",
   "citation": "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; Metallo C; Muralidharan M; Nourreddine S; Niestroy J; Obernier K; Pan E; Park, S; Polacco B; Pratt D; Qian G; Schaffer, LV; Sigaeva A; Thaker S; Zhang Y; Zhao, X; 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, 2025, \"Cell Maps for Artificial Intelligence - March 2025 Data Release (Beta)\", https://doi.org/10.18130/V3/K7TGEM , https://dataverse.lib.virginia.edu/, V1",
   "usageInfo": "These laboratory data are not to be used in clinical decision-making or in any context involving patient care without appropriate regulatory oversight and approval.",
   "ethicalReview": "Vardit Ravistky ravitskyv@thehastingscenter.org and Jean-Christophe Belisle-Pipon jean-christophe_belisle-pipon@sfu.ca.",
   "humanSubjectResearch": "None - data collected from commercially available cell lines",
   "humanSubjectExemption": "Exempt — research with commercially available de-identified human cell lines does not constitute human subjects research.",
   "dataGovernanceCommittee": "Jilian Parker",
   "completeness": "These data are not yet in completed final form, and some datasets are under temporary pre-publication embargo. Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incompletely overlap. Computed cell maps not included in this release.",
   "prohibitedUses": "These laboratory data are not to be used in clinical decision-making or in any context involving patient care without appropriate regulatory oversight and approval.",
   "rai:dataLimitations": "This is an interim release. It does not contain predicted cell maps, which will be added in future releases. The current release is most suitable for bioinformatics analysis of the individual datasets. Requires domain expertise for meaningful analysis.",
   "rai:dataBiases": "Data in this release was derived from commercially available de-identified human cell lines, and does not represent all biological variants which may be seen in the population at large.",
   "rai:dataUseCases": "AI-ready datasets to support research in functional genomics, AI/machine learning model training, cellular process analysis, cell architectural changes, and interactions in presence of specific disease processes, treatment conditions, or genetic perturbations. A major goal is to enable biologically-driven, interpretable ML applications, for example as proposed in Ma et al. 2018 (PMID: 29505029) and Kuenzi et al. 2020 (PMID: 33096023).",
   "rai:dataReleaseMaintenancePlan": "Dataset will be regularly updated and augmented on a quarterly basis through the end of the project (November, 2026). Long term preservation in the https://dataverse.lib.virginia.edu/, supported by committed institutional funds.",
   "rai:dataCollection": "Data collection processes are generally described in Clark T et al. (2024) \"Cell Maps for Artificial Intelligence: AI-Ready Maps of Human Cell Architecture from Disease-Relevant Cell Lines\" bioRxiv 2024.05.21.589311; doi: https://doi.org/10.1101/2024.05.21.589311. Additional data collection details will be subsequently published once finalized. ",
   "rai:dataCollectionType": [
    "Perturb-seq; IF imaging; SEC-MS; AP-MS"
   ],
   "rai:dataCollectionMissingData": "Some datasets are under temporary pre-publication embargo. Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incompletely overlap. Computed cell maps not included in this release.",
   "rai:dataCollectionTimeframe": [
    "9/1/2022",
    "6/1/2026"
   ],
   "publisher": "MassIVE",
   "https://w3id.org/EVI#inputs": [
    {
     "@id": "https://fairscape.net/api/ark:59853/sample-msv000100676-kolf2-1j"
    }
   ],
   "https://w3id.org/EVI#outputs": [
    {
     "@id": "https://fairscape.net/api/ark:59853/dataset-msv000100676-cc8e39efd0c8a96b"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/dataset-msv000100676-1ed62cf423da0185"
    }
   ],
   "evi:processed": true,
   "ro-crate-metadata": "mass-spec/iPSCs/ro-crate-metadata.json"
  },
  {
   "@id": "https://fairscape.net/api/ark:59853/rocrate-data-from-treated-human-cancer-cells-jan-26",
   "@type": [
    "Dataset",
    "https://w3id.org/EVI#ROCrate"
   ],
   "name": "SEC-MS of MDA-MB468 following treatment of vorinostat or paclitaxel.",
   "description": "This dataset was generated by size exclusion chromatography-mass spectroscopy (SEC-MS) following the treatment of vorinostat or paclitaxel on MDA-MB468 human breast cancer cells, in the Nevan Krogan laboratory at the University of California San Francisco, as part of the Cell Maps for Artificial Intelligence (CM4AI; CM4AI.org) Functional Genomics Grand Challenge, a component of the U.S. National Institute of Health's (NIH) Bridge2AI program.",
   "keywords": [
    "AI",
    "Artificial intelligence",
    "Breast cancer",
    "Cell maps",
    "CM4AI",
    "IPSC",
    "KOLF2.1J",
    "Machine learning",
    "Mass spectroscopy",
    "Protein-protein interaction",
    "SEC-MS",
    "vorinostat",
    "paclitaxel"
   ],
   "identifier": "https://doi.org/doi:10.25345/C5348GV4S",
   "isPartOf": [
    {
     "@id": "https://fairscape.net/api/ark:59853/organization-university-of-california-san-diego"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/project-cm4ai"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-January-2026-data-release,"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-June-2026-data-release,"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-June-2026-data-release"
    }
   ],
   "version": "1.5",
   "hasPart": {
    "_summarized_by": "d4d rocrate normalize",
    "count": 45,
    "id_families": {
     "dataset": 18,
     "experiment": 9,
     "computation": 9,
     "schema": 9
    },
    "sample_ids": [
     "https://fairscape.net/api/ark:59853/experiment-control-1-sec-ms-mda-mb468",
     "https://fairscape.net/api/ark:59853/experiment-control-2-sec-ms-mda-mb468",
     "https://fairscape.net/api/ark:59853/experiment-control-4-sec-ms-mda-mb468",
     "https://fairscape.net/api/ark:59853/experiment-paclitaxel-1-sec-ms-mda-mb468",
     "https://fairscape.net/api/ark:59853/experiment-paclitaxel-2-sec-ms-mda-mb468"
    ]
   },
   "author": "Forget A, Obernier K, Krogan N",
   "license": "https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en",
   "associatedPublication": "http://doi.org/10.1101/2024.05.21.589311",
   "conditionsOfAccess": "Attribution is required to the copyright holders and the authors. Any publications referencing this data or derived products should cite the related article as well as directly citing this data collection.",
   "copyrightNotice": "Copyright (c) 2026 by The Regents of the University of California",
   "contactEmail": "nevan.krogan@ucsf.edu",
   "funder": "National Institutes of Health: 1OT2OD032742-01",
   "MD5": "cb67e7749b15ce87b9042a9feba9d032",
   "contentUrl": "ftp://massive-ftp.ucsd.edu/v10/MSV000098237/",
   "url": "https://massive.ucsd.edu/ProteoSAFe/dataset.jsp?task=ad8b8084f5b14af5bafac70fdd42a577",
   "contentSize": "910 GB",
   "publisher": "MassIVE",
   "https://w3id.org/EVI#inputs": [
    {
     "@id": "https://fairscape.net/api/ark:59853/sample-MDA-MB-468-cell-line-mass-spec-sample-oPzB4vOldoF"
    }
   ],
   "https://w3id.org/EVI#outputs": [
    {
     "@id": "https://fairscape.net/api/ark:59853/dataset-control-1-report"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/dataset-control-2-report"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/dataset-control-4-report"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/dataset-paclitaxel-1-report"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/dataset-paclitaxel-2-report"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/dataset-paclitaxel-3-report"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/dataset-vorinostat-1-report"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/dataset-vorinostat-2-report"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/dataset-vorinostat-3-report"
    }
   ],
   "principalInvestigator": "Trey Ideker",
   "confidentialityLevel": "Unrestricted",
   "citation": "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, 2025, \"Cell Maps for Artificial Intelligence - March 2025 Data Release (Beta)\", https://doi.org/10.18130/V3/B35XWX , https://dataverse.lib.virginia.edu/, V1",
   "usageInfo": "These laboratory data are not to be used in clinical decision-making or in any context involving patient care without appropriate regulatory oversight and approval.",
   "additionalProperty": [
    {
     "@type": "PropertyValue",
     "name": "Completeness",
     "value": "These data are not yet in completed final form, and some datasets are under temporary pre-publication embargo. Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incompletely overlap. Computed cell maps not included in this release."
    },
    {
     "@type": "PropertyValue",
     "name": "Human Subject",
     "value": "None - data collected from commercially available cell lines"
    },
    {
     "@type": "PropertyValue",
     "name": "Prohibited Uses",
     "value": "These laboratory data are not to be used in clinical decision-making or in any context involving patient care without appropriate regulatory oversight and approval."
    }
   ],
   "rai:dataLimitations": "This is an interim release. It does not contain predicted cell maps, which will be added in future releases. The current release is most suitable for bioinformatics analysis of the individual datasets. Requires domain expertise for meaningful analysis.",
   "rai:dataBiases": "Data in this release was derived from commercially available de-identified human cell lines, and does not represent all biological variants which may be seen in the population at large.",
   "rai:dataUseCases": "AI-ready datasets to support research in functional genomics, AI/machine learning model training, cellular process analysis, cell architectural changes, and interactions in presence of specific disease processes, treatment conditions, or genetic perturbations. A major goal is to enable biologically-driven, interpretable ML applications, for example as proposed in Ma et al. 2018 (PMID: 29505029) and Kuenzi et al. 2020 (PMID: 33096023).",
   "rai:dataReleaseMaintenancePlan": "Dataset will be regularly updated and augmented on a quarterly basis through the end of the project (November, 2026). Long term preservation in the https://dataverse.lib.virginia.edu/, supported by committed institutional funds.",
   "rai:dataCollection": "Data collection processes are generally described in Clark T et al. (2024) \"Cell Maps for Artificial Intelligence: AI-Ready Maps of Human Cell Architecture from Disease-Relevant Cell Lines\" bioRxiv 2024.05.21.589311; doi: https://doi.org/10.1101/2024.05.21.589311. Additional data collection details will be subsequently published once finalized. ",
   "rai:dataCollectionType": [
    "Perturb-seq; IF imaging; SEC-MS"
   ],
   "rai:dataCollectionTimeframe": [
    "9/1/2022",
    "1/31/2026"
   ],
   "ethicalReview": "Vardit Ravistky ravitskyv@thehastingscenter.org and Jean-Christophe Belisle-Pipon jean-christophe_belisle-pipon@sfu.ca.",
   "humanSubjectResearch": "None - data collected from commercially available cell lines",
   "humanSubjectExemption": "Exempt — research with commercially available de-identified human cell lines does not constitute human subjects research.",
   "dataGovernanceCommittee": "Jilian Parker",
   "completeness": "These data are not yet in completed final form, and some datasets are under temporary pre-publication embargo. Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incompletely overlap. Computed cell maps not included in this release.",
   "prohibitedUses": "These laboratory data are not to be used in clinical decision-making or in any context involving patient care without appropriate regulatory oversight and approval.",
   "rai:dataCollectionMissingData": "Some datasets are under temporary pre-publication embargo. Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incompletely overlap. Computed cell maps not included in this release.",
   "localEvidenceGraph": {
    "@id": "mass-spec/cancer-cells/ro-crate-prov-graph.html"
   },
   "evi:processed": true,
   "ro-crate-metadata": "mass-spec/cancer-cells/ro-crate-metadata.json"
  },
  {
   "@id": "https://fairscape.net/api/ark:59853/rocrate-sra-data-for-perturbation-cell-atlas-58RmCGMQBj",
   "@type": [
    "Dataset",
    "https://w3id.org/EVI#ROCrate"
   ],
   "name": "Perturbation Cell Atlas of Human Induced Pluripotent Stem Cells - Raw Sequence Data",
   "description": "This dataset represents raw sequence data from an expressed genome-scale CRISPRi Perturbation Cell Atlas in KOLF2.1J human induced pluripotent stem cells (hiPSCs) mapping transcriptional and fitness phenotypes associated with 11,739 targeted genes, as part of the Cell Maps for Artificial Intelligence (CM4AI; CM4AI.org) Functional Genomics Grand Challenge, a component of the U.S. National Institute of Health's (NIH) Bridge2AI program.",
   "keywords": [
    "AI",
    "Artificial intelligence",
    "Cell maps",
    "CM4AI",
    "CRISPR perturbation",
    "IPSC",
    "KOLF2.1J",
    "Machine learning",
    "Perturb-seq",
    "scRNAseq",
    "single-cell RNA sequencing"
   ],
   "isPartOf": [
    {
     "@id": "https://fairscape.net/api/ark:59853/organization-university-of-california-san-diego"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/project-cm4ai"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-october-2025-data-release,"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-June-2026-data-release,"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-June-2026-data-release"
    }
   ],
   "version": "0.6",
   "license": "https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en",
   "associatedPublication": "Nourreddine S, Doctor Y, Dailamy A, et al. (2024) \"A Perturbation Cell Atlas of Human Induced Pluripotent Stem Cells\" bioRxiv 2024.11.03.621734; doi: https://doi.org/10.1101/2024.11.03.621734",
   "author": "Doctor Y; Dailamy A; Forget A; Lee YH; Chinn B; Khaliq H; Polacco B; Muralidharan, M; Pan E; Zhang Y; Sigaeva A; Hansen JN; Gao J; Parker JA; Obernier K; Clark T; Chen JY; Metallo C; Lundberg E; Idkeker T; Krogan N; Mali P",
   "conditionsOfAccess": "Attribution is required to the copyright holders and the authors. Any publications referencing this data or derived products should cite the related article as well as directly citing this data collection.",
   "copyrightNotice": "Copyright (c) 2024 by The Regents of the University of California",
   "hasPart": [],
   "contactEmail": "pmali@ucsd.edu",
   "funder": "National Institutes of Health: 1OT2OD032742-01, R01HG012351, R01NS131560, U54CA274502, #S10 OD026929. Department of Defense: W81XWH-22-1-0401. CIRM training: EDUC4-12804. Dutch Research Council: NWO, 019.231EN.013. National Cancer Institute: P30CA023100",
   "MD5": "cbdb263b1c099396d75e16f00a79a818",
   "url": "Embargoed",
   "contentSize": "16.7TB",
   "https://w3id.org/EVI#inputs": {
    "_summarized_by": "d4d rocrate normalize",
    "count": 192,
    "id_families": {
     "sample": 192
    },
    "sample_ids": [
     "https://fairscape.net/api/ark:59853/sample-sra-sample-53424698-GkKwucuUUW8",
     "https://fairscape.net/api/ark:59853/sample-sra-sample-53424707-Ks8UBhB5Y3c",
     "https://fairscape.net/api/ark:59853/sample-sra-sample-53424708-B9F2ilij312",
     "https://fairscape.net/api/ark:59853/sample-sra-sample-53424709-Oyr1MZMJGM",
     "https://fairscape.net/api/ark:59853/sample-sra-sample-53424710-Oyr1MZMJcNy"
    ]
   },
   "https://w3id.org/EVI#outputs": {
    "_summarized_by": "d4d rocrate normalize",
    "count": 103,
    "id_families": {
     "dataset": 103
    },
    "sample_ids": [
     "https://fairscape.net/api/ark:59853/dataset-sra-data-kolf2-alpha-crispr-chip-2-channel-14-n0TB2HDqaSh",
     "https://fairscape.net/api/ark:59853/dataset-sra-data-kolf2-alpha-crispr-chip-2-channel-3-Ewf13NZhZlZ",
     "https://fairscape.net/api/ark:59853/dataset-sra-data-kolf2-alpha-gex-chip-2-channel-14-QRexSUcAae",
     "https://fairscape.net/api/ark:59853/dataset-sra-data-kolf2-alpha-gex-chip-2-channel-3-6XbNlQwgbw7",
     "https://fairscape.net/api/ark:59853/dataset-sra-data-kolf2-beta-crispr-chip-1-channel-1-uhBWMiS21VX"
    ]
   },
   "principalInvestigator": "Trey Ideker",
   "confidentialityLevel": "Unrestricted",
   "citation": "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, 2025, \"Cell Maps for Artificial Intelligence - March 2025 Data Release (Beta)\", https://doi.org/10.18130/V3/B35XWX , https://dataverse.lib.virginia.edu/, V1",
   "usageInfo": "These laboratory data are not to be used in clinical decision-making or in any context involving patient care without appropriate regulatory oversight and approval.",
   "additionalProperty": [
    {
     "@type": "PropertyValue",
     "name": "Completeness",
     "value": "These data are not yet in completed final form, and some datasets are under temporary pre-publication embargo. Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incompletely overlap. Computed cell maps not included in this release."
    },
    {
     "@type": "PropertyValue",
     "name": "Human Subject",
     "value": "None - data collected from commercially available cell lines"
    },
    {
     "@type": "PropertyValue",
     "name": "Prohibited Uses",
     "value": "These laboratory data are not to be used in clinical decision-making or in any context involving patient care without appropriate regulatory oversight and approval."
    }
   ],
   "rai:dataLimitations": "This is an interim release. It does not contain predicted cell maps, which will be added in future releases. The current release is most suitable for bioinformatics analysis of the individual datasets. Requires domain expertise for meaningful analysis.",
   "rai:dataBiases": "Data in this release was derived from commercially available de-identified human cell lines, and does not represent all biological variants which may be seen in the population at large.",
   "rai:dataUseCases": "AI-ready datasets to support research in functional genomics, AI/machine learning model training, cellular process analysis, cell architectural changes, and interactions in presence of specific disease processes, treatment conditions, or genetic perturbations. A major goal is to enable biologically-driven, interpretable ML applications, for example as proposed in Ma et al. 2018 (PMID: 29505029) and Kuenzi et al. 2020 (PMID: 33096023).",
   "rai:dataReleaseMaintenancePlan": "Dataset will be regularly updated and augmented on a quarterly basis through the end of the project (November, 2026). Long term preservation in the https://dataverse.lib.virginia.edu/, supported by committed institutional funds.",
   "rai:dataCollection": "Data collection processes are generally described in Clark T et al. (2024) \"Cell Maps for Artificial Intelligence: AI-Ready Maps of Human Cell Architecture from Disease-Relevant Cell Lines\" bioRxiv 2024.05.21.589311; doi: https://doi.org/10.1101/2024.05.21.589311. Additional data collection details will be subsequently published once finalized. ",
   "rai:dataCollectionType": [
    "Perturb-seq; IF imaging; SEC-MS"
   ],
   "rai:dataCollectionTimeframe": [
    "9/1/2022",
    "10/13/25"
   ],
   "ethicalReview": "Vardit Ravistky ravitskyv@thehastingscenter.org and Jean-Christophe Belisle-Pipon jean-christophe_belisle-pipon@sfu.ca.",
   "humanSubjectResearch": "None - data collected from commercially available cell lines",
   "humanSubjectExemption": "Exempt — research with commercially available de-identified human cell lines does not constitute human subjects research.",
   "dataGovernanceCommittee": "Jilian Parker",
   "completeness": "These data are not yet in completed final form, and some datasets are under temporary pre-publication embargo. Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incompletely overlap. Computed cell maps not included in this release.",
   "prohibitedUses": "These laboratory data are not to be used in clinical decision-making or in any context involving patient care without appropriate regulatory oversight and approval.",
   "rai:dataCollectionMissingData": "Some datasets are under temporary pre-publication embargo. Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incompletely overlap. Computed cell maps not included in this release.",
   "evi:processed": true,
   "localEvidenceGraph": {
    "@id": "Perturb-Seq/sra/ro-crate-prov-graph.html"
   },
   "ro-crate-metadata": "Perturb-Seq/sra/ro-crate-metadata.json"
  },
  {
   "@id": "https://fairscape.net/api/ark:59853/rocrate-a-perturbation-cell-atlas-of-human-induced-pluripotent-stem-cells",
   "@type": [
    "Dataset",
    "https://w3id.org/EVI#ROCrate"
   ],
   "name": "Perturbation Cell Atlas of Human Induced Pluripotent Stem Cells - Perturb Seq",
   "description": "This dataset represents an expressed genome-scale CRISPRi Perturbation Cell Atlas in KOLF2.1J human induced pluripotent stem cells (hiPSCs) mapping transcriptional and fitness phenotypes associated with 11,739 targeted genes, as part of the Cell Maps for Artificial Intelligence (CM4AI) Functional Genomics Grand Challenge, a component of the U.S. National Institute of Health's (NIH) Bridge2AI program. We validated these findings via phenotypic, protein-interaction, and metabolic tracing assays.",
   "publisher": "FigShare",
   "keywords": [
    "AI",
    "Artificial intelligence",
    "Cell maps",
    "CM4AI",
    "CRISPR perturbation",
    "IPSC",
    "KOLF2.1J",
    "Machine learning",
    "Perturb-seq",
    "scRNAseq",
    "single-cell RNA sequencing"
   ],
   "isPartOf": [
    {
     "@id": "https://fairscape.net/api/ark:59853/organization-university-of-california-san-diego"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/project-cm4ai"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-January-2026-data-release,"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-June-2026-data-release,"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/rocrate-cell-maps-for-artificial-intelligence-June-2026-data-release"
    }
   ],
   "version": "1.0",
   "license": "https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en",
   "associatedPublication": "Nourreddine S, Doctor Y, Dailamy A, et al. (2024) \"A Perturbation Cell Atlas of Human Induced Pluripotent Stem Cells\" bioRxiv 2024.11.03.621734; doi: https://doi.org/10.1101/2024.11.03.621734",
   "author": "Doctor Y; Dailamy A; Forget A; Lee YH; Chinn B; Khaliq H; Polacco B; Muralidharan, M; Pan E; Zhang Y; Sigaeva A; Hansen JN; Gao J; Parker JA; Obernier K; Clark T; Chen JY; Metallo C; Lundberg E; Ideker T; Krogan N; Mali P",
   "conditionsOfAccess": "Attribution is required to the copyright holders and the authors. Any publications referencing this data or derived products should cite the related article as well as directly citing this data collection.",
   "copyrightNotice": "Copyright (c) 2026 by The Regents of the University of California",
   "hasPart": [
    {
     "@id": "https://fairscape.net/api/ark:59853/dataset-kolf-pan-genome-aggregated-data"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/schema-kolf-pan-genome-aggregate-20250529-143000"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/computation-perturbation-cell-atlas-data-processing-Cmx85JtSguG"
    }
   ],
   "contentSize": "177.35 GB",
   "contactEmail": "pmali@ucsd.edu",
   "funder": "National Institutes of Health: 1OT2OD032742-01, R01HG012351, R01NS131560, U54CA274502, #S10 OD026929. Department of Defense: W81XWH-22-1-0401. CIRM training: EDUC4-12804. Dutch Research Council: NWO, 019.231EN.013. National Cancer Institute: P30CA023100",
   "MD5": "1cafefa32a897998e3e2ba0a29a3ef5c",
   "https://w3id.org/EVI#outputs": [
    {
     "@id": "https://fairscape.net/api/ark:59853/dataset-kolf-pan-genome-aggregated-data"
    },
    {
     "@id": "https://fairscape.net/api/ark:59853/dataset-kolf-pan-genome-aggregated-data-small"
    }
   ],
   "https://w3id.org/EVI#inputs": {
    "_summarized_by": "d4d rocrate normalize",
    "count": 90,
    "id_families": {
     "dataset": 90
    },
    "sample_ids": [
     "https://fairscape.net/api/ark:59853/dataset-molecule-data-gamma-chip-1-channel-1",
     "https://fairscape.net/api/ark:59853/dataset-molecule-data-alpha-chip-2-channel-4",
     "https://fairscape.net/api/ark:59853/dataset-molecule-data-gamma-chip-1-channel-8",
     "https://fairscape.net/api/ark:59853/dataset-molecule-data-beta-chip-2-channel-7",
     "https://fairscape.net/api/ark:59853/dataset-molecule-data-beta-chip-2-channel-1"
    ]
   },
   "principalInvestigator": "Trey Ideker",
   "confidentialityLevel": "Unrestricted",
   "citation": "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, 2025, \"Cell Maps for Artificial Intelligence - March 2025 Data Release (Beta)\", https://doi.org/10.18130/V3/B35XWX , https://dataverse.lib.virginia.edu/, V1",
   "usageInfo": "These laboratory data are not to be used in clinical decision-making or in any context involving patient care without appropriate regulatory oversight and approval.",
   "additionalProperty": [
    {
     "@type": "PropertyValue",
     "name": "Completeness",
     "value": "These data are not yet in completed final form, and some datasets are under temporary pre-publication embargo. Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incompletely overlap. Computed cell maps not included in this release."
    },
    {
     "@type": "PropertyValue",
     "name": "Human Subject",
     "value": "None - data collected from commercially available cell lines"
    },
    {
     "@type": "PropertyValue",
     "name": "Prohibited Uses",
     "value": "These laboratory data are not to be used in clinical decision-making or in any context involving patient care without appropriate regulatory oversight and approval."
    }
   ],
   "rai:dataLimitations": "This is an interim release. It does not contain predicted cell maps, which will be added in future releases. The current release is most suitable for bioinformatics analysis of the individual datasets. Requires domain expertise for meaningful analysis.",
   "rai:dataBiases": "Data in this release was derived from commercially available de-identified human cell lines, and does not represent all biological variants which may be seen in the population at large.",
   "rai:dataUseCases": "AI-ready datasets to support research in functional genomics, AI/machine learning model training, cellular process analysis, cell architectural changes, and interactions in presence of specific disease processes, treatment conditions, or genetic perturbations. A major goal is to enable biologically-driven, interpretable ML applications, for example as proposed in Ma et al. 2018 (PMID: 29505029) and Kuenzi et al. 2020 (PMID: 33096023).",
   "rai:dataReleaseMaintenancePlan": "Dataset will be regularly updated and augmented on a quarterly basis through the end of the project (November, 2026). Long term preservation in the https://dataverse.lib.virginia.edu/, supported by committed institutional funds.",
   "rai:dataCollection": "Data collection processes are generally described in Clark T et al. (2024) \"Cell Maps for Artificial Intelligence: AI-Ready Maps of Human Cell Architecture from Disease-Relevant Cell Lines\" bioRxiv 2024.05.21.589311; doi: https://doi.org/10.1101/2024.05.21.589311. Additional data collection details will be subsequently published once finalized. ",
   "rai:dataCollectionType": [
    "Perturb-seq; IF imaging; SEC-MS"
   ],
   "url": "https://figshare.com/s/ee85bb1880921326249b",
   "rai:dataCollectionTimeframe": [
    "9/1/2022",
    "1/31/2026"
   ],
   "ethicalReview": "Vardit Ravistky ravitskyv@thehastingscenter.org and Jean-Christophe Belisle-Pipon jean-christophe_belisle-pipon@sfu.ca.",
   "humanSubjectResearch": "None - data collected from commercially available cell lines",
   "humanSubjectExemption": "Exempt — research with commercially available de-identified human cell lines does not constitute human subjects research.",
   "dataGovernanceCommittee": "Jilian Parker",
   "completeness": "These data are not yet in completed final form, and some datasets are under temporary pre-publication embargo. Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incompletely overlap. Computed cell maps not included in this release.",
   "prohibitedUses": "These laboratory data are not to be used in clinical decision-making or in any context involving patient care without appropriate regulatory oversight and approval.",
   "rai:dataCollectionMissingData": "Some datasets are under temporary pre-publication embargo. Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incompletely overlap. Computed cell maps not included in this release.",
   "localEvidenceGraph": {
    "@id": "Perturb-Seq/cell-atlas/ro-crate-prov-graph.html"
   },
   "evi:processed": true,
   "ro-crate-metadata": "Perturb-Seq/cell-atlas/ro-crate-metadata.json"
  }
 ]
}

================================================================================
FILE: ai_ready_score.json
ROLE: AI-readiness self-assessment
SIZE: 6,003 characters
--------------------------------------------------------------------------------
{
  "name": "AI-Ready Score for Cell Maps for Artificial Intelligence - June 2026 Data Release (Beta)",
  "fairness": {
    "findable": {
      "has_content": true,
      "details": "Dataset has DOI: https://doi.org/10.18130/V3/HIGT4C"
    },
    "accessible": {
      "has_content": true,
      "details": "The RO-Crate's JSON-LD metadata is machine-readable and publicly accessible by design."
    },
    "interoperable": {
      "has_content": true,
      "details": "The dataset uses the schema.org vocabulary within the RO-Crate framework and conforms to the Croissant RAI specification for interoperability."
    },
    "reusable": {
      "has_content": true,
      "details": "License: https://creativecommons.org/licenses/by-nc-sa/4.0/"
    }
  },
  "provenance": {
    "transparent": {
      "has_content": true,
      "details": "53877 dataset(s) documented"
    },
    "traceable": {
      "has_content": true,
      "details": "1976 computation/experiment steps documented"
    },
    "interpretable": {
      "has_content": true,
      "details": "6 software instances documented"
    },
    "key_actors_identified": {
      "has_content": true,
      "details": "47 authors, Publisher: https://dataverse.lib.virginia.edu/, PI: Trey Ideker"
    }
  },
  "characterization": {
    "semantics": {
      "has_content": true,
      "details": "Data is semantically described using the schema.org vocabulary within a machine-readable RO-Crate."
    },
    "statistics": {
      "has_content": true,
      "details": "Total size: 19.9 TB"
    },
    "standards": {
      "has_content": true,
      "details": "20 schema(s) documented"
    },
    "potential_sources_of_bias": {
      "has_content": true,
      "details": "Data in this release was derived from commercially available de-identified human cell lines, and does not represent all biological variants which may be seen in the population at large."
    },
    "data_quality": {
      "has_content": true,
      "details": "Some datasets are under temporary pre-publication embargo. Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incom..."
    }
  },
  "pre_model_explainability": {
    "data_documentation_template": {
      "has_content": true,
      "details": "Documentation is provided via the RO-Crate's structured JSON-LD metadata, this HTML Datasheet, and Croissant RAI properties."
    },
    "fit_for_purpose": {
      "has_content": true,
      "details": "Use cases: AI-ready datasets to support research in functional genomics, AI/machine learning model training, cellular process analysis, cell architectural changes, and interactions in presence of specific disease processes, treatment conditions, or genetic perturbations. A major goal is to enable biologically-driven, interpretable ML applications, for example as proposed in Ma et al. 2018 (PMID: 29505029) and Kuenzi et al. 2020 (PMID: 33096023)., Limitations: This is an interim release. It does not contain predicted cell maps, which will be added in future releases. The current release is most suitable for bioinformatics analysis of the individual datasets. Requires domain expertise for meaningful analysis."
    },
    "verifiable": {
      "has_content": true,
      "details": "0% of files have checksums (8/55859)"
    }
  },
  "ethics": {
    "ethically_acquired": {
      "has_content": true,
      "details": "Data collection: Data collection processes are generally described in Clark T et al. (2024) \"Cell Maps for Artificial Intelligence: AI-Ready Maps of Human Cell Architecture from Disease-Relevant Cell Lines\" bioRxiv 2024.05.21.589311; doi: https://doi.org/10.1101/2024.05.21.589311. Additional data collection details will be subsequently published once finalized. , Human subject info: None - data collected from commercially available cell lines"
    },
    "ethically_managed": {
      "has_content": true,
      "details": "Ethical review: Vardit Ravistky ravitskyv@thehastingscenter.org and Jean-Christophe Belisle-Pipon jean-christophe_belisle-pipon@sfu.ca., Governance: Jilian Parker"
    },
    "ethically_disseminated": {
      "has_content": true,
      "details": "License: https://creativecommons.org/licenses/by-nc-sa/4.0/, Prohibited uses: These laboratory data are not to be used in clinical decision-making or in any context involving patient care without appropriate regulatory oversight and approval."
    },
    "secure": {
      "has_content": true,
      "details": "Confidentiality level: Unrestricted"
    }
  },
  "sustainability": {
    "persistent": {
      "has_content": true,
      "details": "Dataset has DOI: https://doi.org/10.18130/V3/HIGT4C"
    },
    "domain_appropriate": {
      "has_content": true,
      "details": "Maintenance plan: Dataset will be regularly updated and augmented on a quarterly basis through the end of the project (November, 2026). Long term preservation in the https://dataverse.lib.virginia.edu/, supported by committed institutional funds."
    },
    "well_governed": {
      "has_content": true,
      "details": "Governance committee: Jilian Parker"
    },
    "associated": {
      "has_content": true,
      "details": "All data, software, and computations are explicitly linked within the RO-Crate's provenance graph."
    }
  },
  "computability": {
    "standardized": {
      "has_content": true,
      "details": "Formats: .d, .d directory group, .tsv, .xml, TSV..."
    },
    "computationally_accessible": {
      "has_content": true,
      "details": "Publisher: https://dataverse.lib.virginia.edu/"
    },
    "portable": {
      "has_content": true,
      "details": "The dataset is packaged as a self-contained RO-Crate, a standard designed for portability across systems."
    },
    "contextualized": {
      "has_content": true,
      "details": "Context is provided by the RO-Crate's graph structure and detailed in properties such as rai:dataLimitations."
    }
  }
}

