Pauling vs. Iambic Therapeutics

Pauling runs validated physics-based tools (UniDock, GROMACS, P2Rank) -- real simulations you can audit end-to-end, on a self-serve platform anyone can use today. Iambic's NeuralPLexer claims better structure prediction than AlphaFold 3 and their Enchant model predicts clinical endpoints. Impressive ML -- but they're surrogates inside an internal pharma pipeline that isn't publicly available. When you need to trust the chemistry, run the chemistry.

Category Pauling Iambic Therapeutics
Core approachPhysics-based simulations (UniDock, GROMACS)ML surrogates (NeuralPLexer, Enchant)
Molecular dockingUniDock (GPU-accelerated Vina) with explicit scoringNeuralPLexer predicts bound poses via diffusion model
Structure predictionP2Rank for pocket detection; uses experimental structuresNeuralPLexer -- joint protein-ligand structure prediction
MD simulationFull GROMACS MD with checkpoint save/resume, ACPYPE parameterizationNo molecular dynamics capability
Binding energy validationMM-PBSA from explicit MD trajectoriesLearned binding score -- no explicit free energy calculation
ADMET profilingIntegrated ADMET pipelineLimited -- focus is on clinical endpoint prediction
Clinical endpoint predictionNot in scopeEnchant predicts Phase I/II clinical outcomes
Validation methodologyPoseBusters pose QC, MolProbity structure checksBenchmark against PoseBusters; ML confidence scores
Transparency of resultsFull trajectory files, scoring logs, parameter trackingModel predictions with confidence intervals
Compound screening scale10M+ compounds via auto-scaling Cloud DataflowFocused on lead optimization, not large-scale screening
File format handlingAutomatic conversion: PDB, PDBQT, SDF, MOL2, CIF, SMILESProprietary input pipelines
Access modelSelf-serve cloud platform, pay for computeInternal pharma pipeline -- not publicly available