NMD-VCell Research Workbench Module: Validate / registry · evidence-to-experiment workflow NMD = neuromuscular disorders
Research evidence only 21 observed HepG2 perturbations 0 independent DMD replications Boundary & release
Observed HepG2 perturbations with limited external myogenic context No validated DMD perturbation prediction v1.0.0-database-resource Frozen 25 Jul 2026 Schema 1.1 Model ridge-safe-v2.3 Benchmark repeated-fold-v2.2 Build EA-20260729-20 DOI pending Open evidence boundary →

Evidence stress test

Module registry

Eleven computation-first checks, with executed, partial and registered states kept separate.

ModuleQuestionIndependent unitCurrent stateClaim impact
NWLE-00Release and provenance integrityrelease object or rendered routeRELEASED EXECUTEDSupports reproducibility of the released resource; it does not support a biological claim.
NWLE-01Same-context predictive auditheld-out perturbation target within repeated balanced foldsEXECUTED BOUNDED STRICT GATE 0 OF 16Supports a small same-context RMSE improvement only; strict direct-head support is not established.
NWLE-02External aggregate transfer diagnosticexternal perturbation targetEXECUTED NO DIRECTIONAL TRANSFER SUPPORTFalsifies a broad directional-transfer claim on the current 55-target panel; it is not DMD or muscle truth.
NWLE-03Public myogenic and DMD context triangulationpublic study, target or reference trajectoryEXECUTED REFERENCE ONLYCan downgrade or contextualize hypotheses; cannot create independent DMD candidate-perturbation validation.
NWLE-04Source-balanced DMD prior multiversesource-aware gene-context estimateREGISTERED NOT EXECUTEDWill improve disease-prior robustness, but still will not constitute perturbation efficacy.
NWLE-05Leakage-safe G2 backtestheld-out gene family or pathwayREGISTERED NOT EXECUTEDRequired before an unseen-family generalization claim.
NWLE-06In-silico perturbation-mode boundaryperturbation × context × modalityPARTIAL BOUNDED SIMULATION ONLYObserved same-HepG2 CRISPRi and additive null previews are usable; KO, overexpression, fate and synergy claims remain locked.
NWLE-07Uncertainty, OOD and abstention audittarget or context-level predictionPARTIAL BOOTSTRAP AVAILABLE OOD ABSTENTION NOT TRAINEDSampling intervals are available for selected executed analyses; trained OOD-aware abstention is not yet supported.
NWLE-08Retrospective selection-enrichment backtestoutcome-blinded candidate selection setREGISTERED NOT EXECUTED OUTCOME LEAKAGE GUARDOnly valid when a pre-outcome model snapshot and eligible outcome universe can be proven.
NWLE-09Independent computational reproductionindependent analyst executionREGISTERED EXTERNAL REPRODUCTION NOT EXECUTEDIndependent reproduction can strengthen computational reliability, but not biological validity.
NWLE-10UniPert cross-domain representation feasibilitycandidate gene, held-out target family or compound scaffoldPARTIAL SOURCE AND IDENTIFIER AUDIT EXECUTED MODEL EVALUATION PENDINGSupports operational feasibility only; no embedding benefit, cross-domain transfer or DMD therapeutic value has been established.

Boundary: these modules can stress-test computational reliability and evidence compatibility. They cannot establish DMD efficacy, function, safety or treatment utility.