Cell Maps for Artificial Intelligence - October 2025 Data Release (Beta)

<h3>Description</h3>
<p>This dataset is the October 2025 Data Release of Cell Maps for Artificial Intelligence (CM4AI; CM4AI.org), the Functional Genomics Grand Challenge in the NIH Bridge2AI program. CM4AI is generating multi-modal data including protein-protein interaction (PPI), spatial localization, and genetic perturbation data in MDA-MB-468 breast cancer cells (+/- paclitaxel or vorinostat) and iPSCs (+/- differentiation). This Beta release includes:</p>
<ul>
<li>Perturb-seq data for MDA-MB-468 breast cancer cells +/- treatment and undifferentiated (parental) KOLF2.1J iPSCs</li>
<li>SEC-MS data for MDA-MB-468 breast cancer cells +/- treatment, undifferentiated KOLF2.1J iPSCs, and iPSC-derived neuron progenitor cells (NPCs), neurons, and cardiomyocytes</li>
<li>IF images in MDA-MB-468 breast cancer cells +/- treatment</li>
</ul>
<h3>External Data Links</h3>
<p>Access external data resources related to this dataset:</p>
<ul>
<li><strong>Perturb-seq data in KOLF2.1J iPSCs (undifferentiated): </strong>Embargoed</li>
<li><strong>Perturb-seq data in MDA-MB-468 breast cancer cells (+/- treatment): </strong>Embargoed</li>
<li><strong>SEC-MS data in KOLF2.1J iPSCs (undifferentiated, NPC, neuron, and cardiomyocyte):</strong> <a href="https://massive.ucsd.edu/ProteoSAFe/dataset.jsp?task=de876e1d228c4f7ab02f84027894bed7" target="_blank">MassIVE Repository</a></li>
<li><strong>SEC-MS data in MDA-MB-468 breast cancer cells (+/- treatment):</strong> <a href="https://massive.ucsd.edu/ProteoSAFe/dataset.jsp?task=ad8b8084f5b14af5bafac70fdd42a577" target="_blank">MassIVE Repository</a></li>
</ul>
<hr></hr>
<h3>Data Governance & Ethics</h3>
<ul>
<li><strong>Human Subjects:</strong> No</li>
<li><strong>De-identified Samples:</strong> Yes</li>
<li><strong>FDA Regulated:</strong> No</li>
<li><strong>Data Governance Committee:</strong> Jillian Parker ([e-mail])</li>
<li><strong>Ethical Review:</strong> Vardit Ravitsky ([e-mail]) and Jean-Christophe Belisle-Pipon ([e-mail])</li>
</ul>
<h3>Completeness</h3>
<p>These data are not yet in completed final form:</p>
<ul>
<li>Some datasets are under temporary pre-publication embargo</li>
<li>Protein-protein interaction (SEC-MS), protein localization (IF imaging), and CRISPRi perturbSeq data interrogate sets of proteins which incompletely overlap</li>
<li>Computed cell maps not included in this release</li>
</ul>
<h3>Maintenance Plan</h3>
<ul>
<li>Dataset will be regularly updated and augmented through the end of the project in November 2026</li>
<li>Updates on a quarterly basis</li>
<li>Long term preservation in the University of Virginia Dataverse, supported by committed institutional funds</li>
</ul>
<h3>Intended Use</h3>
<p>This dataset is intended for:</p>
<ul>
<li>AI-ready datasets to support research in functional genomics</li>
<li>AI model training</li>
<li>Cellular process analysis</li>
<li>Cell architectural changes and interactions in presence of specific disease processes, treatment conditions, or genetic perturbations</li>
</ul>
<h3>Limitations</h3>
<p><strong>Researchers should be aware of inherent limitations:</strong></p>
<ul>
<li>This is an interim release</li>
<li>Does not contain predicted cell maps, which will be added in future releases</li>
<li>The current release is most suitable for bioinformatics analysis of the individual datasets</li>
<li>Requires domain expertise for meaningful analysis</li>
</ul>
<h3>Prohibited Uses</h3>
<ul>
<li><strong>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</strong></li>
</ul>
<h3>Potential Sources of Bias</h3>
<p>Users should be aware of potential biases:</p>
<ul>
<li>Data in this release was derived from commercially available de-identified human cell lines</li>
<li>Does not represent all biological variants which may be seen in the population at large</li>
</ul>