RFT — Next-Generation Molecular Physics

RFT Research Team

Proprietary Physics Engine

Next-Generation
Molecular Physics

The proprietary compute engine powering LatticeZero. Bridging fundamental geometric physics with hardware-accelerated drug discovery.

Origins

Not Originally Designed for Biology

The LatticeZero compute engine is powered by a scale-invariant geometric framework initially developed to solve fundamental field equations in astrophysics. To apply it to molecular systems, we transposed the same continuous lattice mathematics used to model galactic rotation curves without dark matter and predict fundamental mass resonances so it could be mapped into the angstrom regime. The result is a molecular docking engine that bypasses explicit pairwise interaction summation and full quantum-mechanical wavefunction solves, including direct Schrödinger-equation solves for each ligand-receptor evaluation.

“From cosmic structures to sub-angstrom steric precision.
One unified mathematical framework.”

First Principles

First-Principles Physics, Not Fitted Heuristics

While much of the industry still relies on black-box machine learning or legacy force-field tuning, the RFT engine is built on first-principles physics from fundamental resonant field theory. Core interaction terms and constants are derived from geometry instead of learned from labeled poses. The result is HTVS-class throughput on a single consumer GPU, with internal RTX 3090 benchmarks exceeding 10,000 ligands per second, without training data or empirical curve fitting.

Core Technology

The RFT Architecture

Three foundational advances that enable physics-accurate molecular scoring at speeds previously impossible.

Pillar 01

Advanced Geometric Discretization

Most docking pipelines use fixed Cartesian sampling and spend substantial compute in low-value pocket volume. RFT uses a scale-invariant geometric framework with proprietary isotropic spatial packing mathematics to evaluate continuous protein pockets with higher volumetric efficiency. This reduces dead-space computation and enables sub-angstrom conformational searches.

Pillar 02

Unified Energy Decomposition

Rather than patching together disconnected empirical approximations, the RFT engine evaluates 14 distinct physical interactions, including precise coordination geometries and second-shell hydrophobic effects, from a unified mathematical foundation.

Pillar 03

Bare-Metal GPU Parallelization

The RFT engine was designed for matrix-native GPU parallelization, allowing complex energy tensor calculations to run client-side via WebGPU compute shaders at HTVS-class throughput. No server queues are required. Internal RTX 3090 benchmarks exceed 10,000 ligands per second, and internal mobile WebGPU tests on recent iPhone-class hardware reach multi-thousand ligands per second, including runs around 5,000 ligands per second. Workflows that once required cloud farms can now be achieved on a device in your pocket.

Benchmarks

Proven on Standard Datasets

Validated against DEKOIS2 with property-matched decoys. Every result includes holdout cross-validation and Y-scramble null controls.

0.980

Best AUC

27

Validated Targets

10K+

Ligands / Second

0

Training Data

Target	Family	Validated AUC
HMGR	Reductase	0.980
PDE5	Phosphodiesterase	0.883
Neuraminidase	Glycosidase	0.875
MCL1	Apoptosis Regulator	0.868
ESR1	Nuclear Receptor	0.858
ADRB2	GPCR	0.834
CATL	Cysteine Protease	0.829

Validated via 5-fold cross-validation with Y-scramble null controls. All AUC values are holdout-validated on DEKOIS 2.0 with property-matched decoys.

Access

Experience the Engine

The RFT engine is available exclusively through the LatticeZero platform.

Explore LatticeZero

Next-GenerationMolecular Physics