Peptiter / DiscoveryLab
Proof
Mechanism proof

In-silico lab — assessment matrix and rejection gates.

The in-silico assessment matrix and the rejection gates that prune candidates before any wet-lab cost.

In-silico lab

Before wet lab: automatic computational and mechanism triage.

A standardized assessment matrix runs across every candidate. Failing scores, unverifiable mechanism claims, unsupported assumptions, or over-broad claim language constrain or reject; passing scores produce a claim-bounded priority list.

AssessmentWhat it checksWhy it reduces search space
Scientific claim ledgerClassifies every capability and result as formal verification, physics-bearing reduced model, heuristic surrogate, calibrated prediction, wet-lab observation, or orchestration contractPrevents heuristic scores from being presented as calibrated probabilities or biological validation
Public calibration stagingImports ChEMBL, BindingDB, PDBbind, and wet-lab rows into typed calibration manifests with splits and checksumsTurns ranking signals into calibrated probabilities only after a held-out calibration artifact exists
Wet-lab export packageGenerates candidate selection reports, synthesis specs, target-specific assay protocols, result templates, controls, readiness issues, and checksumsThe current wet-lab prep package selects 10 candidates across 10 targets and includes 13 synthesis specs plus 10 protocols
Protein-LM task headsESM-2-width 2560-dimensional embeddings feed six committed task heads retrained as 1024-wide MLPs on normalized public peptide data and exported as precompiled Core ML bundlesMoves descriptor proxies toward local Mac model-backed ranking evidence while keeping uncalibrated neural scores below assay truth
BioFoundation contextCell atlas, protein-sequence, regulatory-variant, perturbation, and external foundation-model plans are converted into scorecards with provider provenance and calibration stateLets candidates carry biological representation context without allowing rank-only model output to become efficacy, safety, or target-engagement evidence
Pathway assertion registryRelease-pinned Reactome, GO-CAM, and Open Targets records carry license policy, evidence namespaces, organism/cell/anatomy context, assertion layer, knowledge status, and confidencePrevents a pathway prior from being treated as universal biology or redistributed outside its source terms
Federated body-twin model cardsProcess twins and executable islands declare context of use, calibration state, update cadence, uncertainty method, validation endpoints, privacy boundary, allowed claims, and blocked claimsKeeps reduced glucose, beta-cell, and blood-pressure axes useful for triage without implying clinical whole-body prediction
Boltz-1 contact mapsPreviews receptor-peptide complex requests, HealthOmics run descriptors, and contact-map evidence for receptor fit and docking poseReplaces pocket fiction with explicit predicted contacts before wet-lab advancement
Receptor / pathway relevanceAlignment of candidate to selected receptor and pathway evidenceDiscards candidates with no plausible biological target
Pathway mechanism verificationBuilds verifier-ready mechanisms from governed assertions, then checks reachability, intervention blockade, protected-node safety, and conservation claimsRejects candidates whose proposed mechanism does not follow from the encoded and source-qualified pathway assumptions
Lean 4 audit artifactGenerates a formal module and external verification receipt for high-value mechanismsMakes pathway claims reproducible and reviewable instead of hidden inside a score
Perturbation evidence supportScores whether assays, omics, CRISPR, or chemical perturbations support the mechanism assumptionsPrioritizes candidates with testable and convergent biological evidence
Sequence motif plausibilityPresence and orientation of binding motifs and pharmacophoresRemoves scaffolds that violate known structural priors
Stability (predicted)Half-life proxies, protease cleavage liability, oxidation riskFilters chemically fragile sequences early
SolubilityPredicted aqueous solubility under assay-relevant conditionsAvoids candidates that cannot be tested at meaningful concentrations
Aggregation riskβ-sheet propensity, hydrophobic patches, self-association cuesReduces wet-lab failure from precipitation
Synthesis feasibilitySPPS difficulty, cyclization route, ncAA availabilityPrevents prioritization of impractical sequences
Off-target concernsPredicted cross-reactivity to related receptors and proteinsSurfaces candidates needing selectivity engineering
ncAA compatibilityCompatibility of non-natural residues with target chemistryKeeps v2 ncAA expansion within feasible bounds
Assay readinessMatch between candidate and available wet-lab assaysEnsures handoffs are testable as designed
Wet-lab priorityPareto-front ranking, active-learning acquisition, and assay-readiness checks across all assessments aboveSelects the next testable LabSpace batch instead of simply sorting by one MPO score