LatticeZero
LatticeZero

Physics-First
Molecular Docking & Screening

180+ validated targets across DUD-E and DEKOIS2. IsoScreen universal scorer — zero per-target parameters. 0.92 mean AUC on property-matched decoys. No black-box AI. Every weight traces to a physics term.

0.92
Mean AUC
600+
Lig/sec (AMR)*
180+
Validated Targets
No Black Box
Physics-First

*AMR docking, up to 600+ lig/sec on RTX-series GPUs. Scoring: 10,000+ lig/sec.  DEKOIS2 mean AUC, 84 targets, property-matched decoys.

Everything you need to dock, score, and validate.

A complete molecular docking platform built on physics first principles. Target-specific calibration of interpretable energy terms. No external dependencies.

IsoScore 10,000+ lig/sec

GPU-accelerated rescoring of pre-docked poses. 14 physics-derived energy terms. Per-target profiles with cross-validated AUC. Batch scoring for hit lists.

Optimizer Supervised Calibration

With labeled active/decoy data, the optimizer finds the right physics feature weights for your target. Automated cross-validation and AUC reporting.

IsoScreen Universal Scorer Performance

Validated on two independent benchmarks with property-matched decoys. Zero per-target parameters.

0.92
DEKOIS2 (84 targets)
Property-matched decoys
0.75
DUD-E (104 targets)
Zero-parameter universal scoring

Why two benchmarks? DUD-E is the industry standard — every tool reports on it. DEKOIS2 uses property-matched decoys that defeat statistical shortcuts, testing whether your scorer understands real binding physics. IsoScreen scores 0.75 on DUD-E and 0.92 on DEKOIS2 with zero per-target parameters.

DEKOIS2 Per-Target Validation

Per-target calibrated profiles shown below. IsoScreen universal scorer achieves 0.92 mean AUC across all 84 DEKOIS2 targets with zero per-target parameters.

Target Family Engine Method Validated AUC
ACE Metalloprotease FFT E2E 0.983
HMGR Reductase FFT Rescore 0.980
HIVRT RT FFT Rescore 0.944
NA Glycosidase FFT Rescore 0.942
PPARG Nuclear Receptor GA Rescore 0.934
EGFR Kinase FFT E2E 0.933
P38A Kinase AMR E2E 0.894
ACHE Enzyme FFT E2E 0.880
UROK Serine Protease GA E2E 0.872
MDM2 PPI FFT E2E 0.855
COMT Transferase FFT E2E 0.840
ADRB2 GPCR AMR Rescore 0.834

Methodology

From first-principles physics to GPU-accelerated scoring in four steps.

Step 01
Physics Foundation
First Principles

Scoring grounded in physics-derived sterics and electrostatics. No parameters trained on binding data. Every weight traces to a physical interaction term.

Step 02
Physics Engine
HBQ Scoring

14 physics-derived energy terms: dispersion, repulsion, Coulomb, H-bonds, pi-stacking, burial penalties, and more.

Step 03
Per-Target Profiles
Validated Profiles

180+ validated targets with physics-derived profiles, plus IsoScreen universal scoring for any target with zero setup.

Step 04
WebGPU Compute
10,000+ lig/sec

GPU-accelerated scoring via WebGPU compute shaders. 10,000+ ligands per second on RTX-series GPUs, directly in the browser.

Step 05
Universal Scoring
IsoScreen

Zero per-target parameters. Docking strain and physics terms determine the scoring pathway automatically. Works on any target without calibration. 0.92 mean AUC on DEKOIS2.

Problems We Solve

Common docking failures addressed by physics-first design.

Empirical overfitting

Physics-derived scoring grounded in first-principles sterics and electrostatics. No parameters trained on binding data. No decoy bias.

Steric clashes

Physics-derived sR softening derived from potential matching, not AUC optimization. Reduces clash artifacts while preserving pose discrimination.

Generic scoring that ignores pocket physics

Most tools apply the same scoring function to every target. IsoScreen automatically matches one of 24 physics archetypes to each pocket's binding regime — no calibration needed. For additional precision, per-target profiles are available.

Requires per-target training

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.

Get Early Access

Full platform access during open beta. No credit card required.

Enterprise
Self-Serve or Custom
  • Custom target profiles
  • Priority support
  • Dedicated infrastructure
  • SLA & integration
Get Enterprise Access

Or contact us for custom terms

Try It Now