Cell Maps for Artificial Intelligence - October 2025 Data Release (Beta)
Bibliographic record
Abstract
Description 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: Perturb-seq data for MDA-MB-468 breast cancer cells +/- treatment and undifferentiated (parental) KOLF2.1J iPSCs 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 IF images in MDA-MB-468 breast cancer cells +/- treatment External Data Links Access external data resources related to this dataset: Perturb-seq data in KOLF2.1J iPSCs (undifferentiated): Embargoed Perturb-seq data in MDA-MB-468 breast cancer cells (+/- treatment): Embargoed SEC-MS data in KOLF2.1J iPSCs (undifferentiated, NPC, neuron, and cardiomyocyte): MassIVE Repository SEC-MS data in MDA-MB-468 breast cancer cells (+/- treatment): MassIVE Repository Data Governance & Ethics Human Subjects: No De-identified Samples: Yes FDA Regulated: No Data Governance Committee: Jillian Parker (jillianparker@health.ucsd.edu) Ethical Review: Vardit Ravitsky (ravitskyv@thehastingscenter.org) and Jean-Christophe Belisle-Pipon (jean-christophe_belisle-pipon@sfu.ca) Completeness These data are not yet in completed final form: 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 Maintenance Plan Dataset will be regularly updated and augmented through the end of the project in November 2026 Updates on a quarterly basis Long term preservation in the University of Virginia Dataverse, supported by committed institutional funds Intended Use This dataset is intended for: 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 Limitations Researchers should be aware of inherent limitations: This is an interim release 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 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 Potential Sources of Bias Users should be aware of potential biases: Data in this release was derived from commercially available de-identified human cell lines Does not represent all biological variants which may be seen in the population at large
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.007 |
| Meta-epidemiology (narrow) | 0.003 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.005 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.004 | 0.002 |
| Open science | 0.004 | 0.003 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.275 | 0.396 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".