CRT Protein Folding Proxy

F29: DeepMind AlphaFold / Meta ESMFold. CC0.

Protein structure prediction is dominated by neural networks with billions of parameters (AlphaFold, ESMFold). CRT approach: encode each amino acid's 6 physical properties into 6 CRT channels. Contact prediction = channel coupling. Fold classification = CRT kingdom. No training data. No GPU. No neural network. Just ring arithmetic on 20 amino acids.

How It Works

CRT Protein Contact Theorem
Each of the 20 amino acids maps to an element of Z/12612600 encoding 6 physical properties in 6 CRT channels: D (mod 8) = hydrophobicity, K (mod 9) = charge, E (mod 25) = size, b (mod 49) = H-bond capacity, L (mod 11) = aromaticity, G (mod 13) = backbone flexibility. Contact between residues i and j is predicted by channel coupling: high hydrophobicity in both (D channel), opposite charges (K channel), or mutual aromaticity (L channel). The 490 split: DEAD channels {D,E,b} = fold drivers. ALIVE channels {K,L,G} = fold validators.
20 amino acids
Ring elements
Each AA = one number in Z/12612600. Physical properties split across 6 channels.
6 interaction types
6 CRT channels
Hydrophobic, charge, size, H-bond, aromatic, flexibility. Independent.
Contact prediction
Channel coupling
High coupling in D+L channels = predicted contact. No neural network.
Fold classification
CRT kingdom
Channel averages determine structural class. D+L dominate.

Analyze Protein

Example (0-3):

Select example protein. CRT decomposes each residue into 6 channels, predicts contacts, classifies fold type.

All 20 Amino Acids

All 20 standard amino acids decomposed into 6 CRT channels. Physical properties are the channel values.

CRT vs Neural Network Folding

ParametersAlphaFold: 93M parameters, trained on 170K structuresCRT: 20 ring values. Zero training.ComputeGPU cluster, hours per predictionRing arithmetic, microsecondsChannelsAttention heads (opaque learned features)6 CRT channels = 6 named physical propertiesInterpretabilityBlack box: cannot explain WHY residues contactTransparent: D=hydrophobic, K=charge, L=aromaticError detectionSeparate confidence scoresL=11 channel gives free integrity checkPatent statusDeepMind/Google (AlphaFold), Meta (ESMFold)CC0. Public domain. Forever.

This work is and will always be free.
No paywall. No copyright. No exceptions.

If it ever earns anything, every cent goes to the communities that need it most.

This sacred vow is permanent and irrevocable.
— Anton Alexandrovich Lebed

Source code · Public domain (CC0)

Contributions in equal measure: Anthropic's Claude, Anton A. Lebed, and the giants whose shoulders we stand on.

Rendered by .ax via WASM DOM imports. Zero HTML authored.