Pauling vs. Potato

Pauling runs a full end-to-end pipeline -- from PDB download through receptor prep, pocket detection, docking at scale, ADMET profiling, quality control, and molecular dynamics -- all through a single conversational interface on cloud infrastructure. Potato is building AI tools for specific comp chem tasks; the end-to-end pipeline from structure to validated candidates isn't there.

Category Pauling Potato
End-to-end pipelineFull: structure prep, pocket detection, docking, MD, ADMET, QC -- all integratedFocused AI tools for specific comp chem tasks
DockingUniDock (GPU-accelerated Vina) -- 10M+ compound virtual screensDocking capabilities in development
Molecular dynamicsFull GROMACS MD with automatic ligand parameterization (ACPYPE), checkpoint/resume, MM-PBSALimited MD offering
ADMET profilingIntegrated into pipeline -- run ADMET alongside docking and MD resultsADMET predictions available
Pocket detectionP2Rank integrated -- automatic binding site identification from PDB structuresBinding site tools available
Quality controlMolProbity (structure validation) + PoseBusters (pose QC) -- every result is auditableLimited QC tooling
Cloud scalingGoogle Cloud Dataflow with Apache Beam -- auto-scales to hundreds of workersCloud infrastructure available
File format handlingAutomatic: PDB, PDBQT, SDF, MOL2, CIF, SMILES -- all conversions handled internallyFormat support varies by tool
InterfaceConversational AI -- describe experiments in natural language, get results backAI-assisted interface
Jobs & trackingFull dashboard: every parameter, input file, output file tracked per jobJob tracking available
Private molecule catalogsOwner-scoped catalogs (owner_id) with data isolationData management varies
CostPay-per-use cloud compute, no license feesPricing model varies