Thousands of ligands per second without sacrificing accuracy. IsoScreen universal scorer — zero per-target parameters. No fitted parameters. No training data. No black box. Every weight traces to a physics term.
LatticeZero computes physics-first binding interactions at thousands of ligands per second on a single GPU, with zero trained parameters, and beats every classical scoring function on both discrimination and absolute affinity prediction.
A complete molecular docking platform built on physics first principles. Works on any target without calibration. No external dependencies.
Universal discrimination scorer. Adaptive pocket filtering matches each target's binding regime from population statistics alone. Zero per-target calibration. 0.912 mean AUC across 163 validated targets.
GPU-accelerated docking with proprietary AMR placement. Up to 600+ ligands per second docking speed per GPU. No force field required.
18 calibrated energy terms computed from our geometric physics engine — Coulomb, dispersion, repulsion, hydrogen bonds, burial, and strain. Predicts absolute binding affinity: R = 0.77 on CASF-2016. Screen millions, then rank by predicted binding energy.
Automated receptor preparation. PDB cleanup, protonation, binding site detection, grid generation. Ready in minutes.
Bring your own labeled data to build custom scoring profiles for your target. Maximizes per-target AUC with cross-validated physics weights. Optional when you have active/decoy labels.
Adaptive geometric filtering matches each pocket's binding regime from population statistics alone. No per-target calibration.
LIT-PCBA uses property-matched decoys from real high-throughput screens. These 15 targets were never used during scorer development. Every target improved. Zero regression.
LatticeZero predicts binding free energy from physics-first energy terms computed on the GPU. CASF-2016: 81 complexes, the gold standard benchmark.
| Method | CASF-2016 R | Speed |
|---|---|---|
| LatticeZero | 0.77 | 1000s lig/sec |
| RF-Score v3 | 0.75 | ~1,000 lig/sec |
| FEP+ (AB-FEP) | 0.69 | hours per molecule |
| AutoDock Vina | 0.60 | ~50 lig/sec |
| Glide SP | 0.57 | ~100 lig/sec |
From first-principles physics to GPU-accelerated scoring in four steps.
Scoring grounded in calibrated sterics and electrostatics. No parameters trained on binding data. Every weight traces to a physical interaction term.
Coulomb, dispersion, repulsion, H-bonds, pi-stacking, burial penalties, strain, and more. All computed from our geometric physics engine.
GPU-accelerated scoring via WebGPU compute shaders. Score thousands of molecules per second on RTX-series GPUs, directly in the browser.
Zero per-target parameters. Docking strain and physics terms determine the scoring pathway automatically. Works on any target without calibration. 0.912 mean AUC across 163 targets.
| Tool | Discrimination (DUD-E AUC) | Affinity (CASF R) | Speed (lig/sec) | Parameters trained |
|---|---|---|---|---|
| Glide SP | ~0.78 | 0.57 | ~100 | hundreds |
| AutoDock Vina | ~0.70 | 0.60 | ~50 | dozens |
| FEP+ (absolute) | n/a | 0.69 | ~0.001 | simulation |
| RF-Score v3 | ~0.80 | 0.75 | ~1,000 | thousands |
| GNINA (DL) | ~0.85 | n/a | ~100 | millions |
| LatticeZero | 0.886 | 0.77 | 1000s | zero |
Coulomb, dispersion, repulsion, strain, and hydrogen bond geometry computed per atom pair at thousands of ligands per second. Not parameterized force fields. Not learned potentials. Computed from atomic coordinates and partial charges.
Population statistics of the docked ensemble reveal the pocket's binding regime. Scoring weights adjust automatically. Rigid pockets, flexible grooves, metal sites, allosteric cavities: each gets the physics it needs.
The same physics engine that discriminates actives from decoys also predicts binding free energy. R = 0.77 on CASF-2016. Screening and affinity in one platform.
No training set required. No active/decoy labels needed. Upload a receptor PDB and a ligand library. Score in minutes.
Physics-derived scoring grounded in calibrated sterics and electrostatics. No parameters trained on binding data. No decoy bias.
Docking-calibrated softening derived from potential matching, not AUC optimization. Reduces clash artifacts while preserving pose discrimination.
Most ML scoring functions need active/decoy labels for every new target. IsoScreen scores any target with zero calibration — docking strain and physics terms determine the scoring pathway automatically.
Every score traces to interpretable physics terms. Coulomb, dispersion, repulsion, H-bonds, burial — all inspectable. No neural network hidden layers.
Full platform access during open beta. No credit card required.
Dock and score molecules in your browser. No signup required. Try IsoScreen on validated targets.
Launch demo →163 targets across DUD-E, DEKOIS2, and LIT-PCBA. Full methodology and comparison tables.
View results →Full platform access. Upload receptors, dock ligand libraries, export results. No credit card required.
Get started →
LatticeZero