Transport across contexts
Unseen perturbation, donor, state, dataset and calibrated abstention. Primary outputs are pseudobulk response and, when cell-level truth exists, a predicted cell population.
Scientific program
Scientific program · released contract
How NMD-VCell will test whether a perturbation changes DMD muscle function.
The core object is now perturbation × cell state × disease context × time × phenotype. A gene alone is not the unit of biological validation.
Two tracks · separate gates
General virtual-cell performance and DMD validity cannot substitute for one another
Replicate disease-relevant function
DMD and matched control, functional primary endpoint, target engagement, toxicity, reagent concordance, donor heterogeneity and prospective outcome registration.
Mechanism chain
Every priority perturbation must connect early mechanism to late function
Perturbationdirection, modality, dose and engagement
6–12 hearly molecular response
24–48 hregulatory program and state transition
4–7 dfunction, toxicity and cross-cell consequence
These windows are planning defaults and must be calibrated to the selected cell system before registration.
Flagship studies
Three research programs, each shown at its declared scientific state
DMD Minimum Perturbome
Which perturbations produce reproducible DMD-relevant functional effects?
Designed, not yet completedPANEL_DRAFT_ASSIGNED_SIGNOFF_PENDINGDMD State-Specific Perturbation Atlas
How do perturbation effects change across myogenic state, time and microenvironment?
Designed, not yet completedREGISTERED_DATA_MODEL_DATA_MISSINGProspective NMD-VCell Challenge
Does frozen model selection improve future experimental hit rate over random, expert and simple baselines?
Designed, not yet completedREGISTERED_FRAMEWORK_NO_PREDICTIONS_OR_OUTCOMESGoverned evidence transition
The next release is earned by outcomes, not by adding pages
STUDY CARDeditable design drafts
REGISTERED STUDYnext immutable object
EXPERIMENTruns after registration
OUTCOMEsupportive, null, toxic or inconclusive
TRANSITIONgoverned evidence update
Current boundary. v1.0 is a database and evidence-governance release; it is not a validated disease-prediction or clinical decision-support release. This program object adds a preregistration and evaluation contract; it does not add experimental evidence.
Reusable scientific figures
Units, uncertainty and source tables are first-class objects
Seven registered views cover all six priority classes: source effects, dataset-task-result coverage, reported sample/donor distributions, trajectory-time alignment, benchmark intervals and selective risk-coverage.
Execution ledger
Software completion and external evidence events are tracked separately
All 35 planned upgrades now have a deliverable, validation state and named external dependency where required.
Open execution ledger