helixVision — Self-Hosted Structure Prediction
Protein structure prediction in pure Rust f64 — no cloud, no PyTorch, no CUDA. AlphaFold primitives validated. strandGate capacity: 20-30 structures/day.
Repository: sporeGarden/helixVision (absorbed coralForge)
License: scyBorg (AGPL-3.0-or-later + ORC + CC-BY-SA 4.0)
Formerly: coralForge (syntheticChemistry/coralForge, now archived)
Compute Capacity: strandGate (RTX 3090) can predict 20-30 structures/day via Nest Atomic CAS pipeline
What It Is
helixVision is self-hosted protein structure prediction running locally on consumer hardware in pure Rust, with full f64 precision, complete data ownership, and cryptographic provenance. No cloud APIs. No PyTorch. No CUDA SDK. No data sent to Google.
Implemented All 6 AlphaFold primitives are implemented and individually validated (154 checks, 1e-10 tolerance vs NumPy). Architecture-ready End-to-end pipeline (FASTA → structure → confidence) is designed but not yet wired. “AlphaFold-quality” refers to the target — primitive-level parity is demonstrated, full-pipeline parity is not yet benchmarked.
The Isomorphism
AlphaFold’s architecture decomposes into 6 universal primitives — the same primitives BarraCuda already has as validated WGSL shaders:
| AlphaFold Operation | Primitive Decomposition |
|---|---|
| Triangle multiplication | Batched outer product (GEMM) + sigmoid gating + reduction |
| Triangle attention | Scaled dot-product attention + pair bias + softmax |
| Invariant Point Attention | Q·K^T/√d attention + L2 distance + softmax |
| Diffusion denoising (AF3) | Scale + add per step |
| Confidence heads (pLDDT, PAE) | Linear (GEMM) + softmax + weighted sum |
helixVision does not introduce new computation. Every operation is a composition of primitives that already exist, are tested, and run on consumer GPUs.
How It Composes
| Layer | What | Primal |
|---|---|---|
| Math | WGSL f64 shaders for all 6 primitives | barraCuda |
| Compilation | WGSL → native GPU binary (NVIDIA + AMD) | coralReef |
| Dispatch | Hardware discovery, execution, routing | ToadStool |
| Provenance | Ed25519 signing of every prediction | BearDog |
| History | Append-only prediction log | loamSpine |
| Orchestration | Pipeline routing via Neural API | biomeOS |
The pipeline: FASTA sequence → MSA search → Feature embedding → Evoformer × 48 → Structure module × 8 → Coordinates → Confidence (pLDDT, PAE, pDE) → Provenance chain.
Performance Targets Architecture-ready
These are design targets, not benchmarked results. Primitive-level validation is complete; end-to-end pipeline benchmarks are pending Phase C–D.
| Metric | Cloud AlphaFold | helixVision target |
|---|---|---|
| Precision | f32 (PyTorch default) | f64 (native or DF64) |
| Cost per prediction | ~$0.01 (cloud API) | ~$0.0001 (electricity) |
| LTEE full analysis (8.3M predictions) | ~$83,000 | ~$1,000 (6 months, 4× RTX 4070) |
| Data sovereignty | Data sent to Google | Data stays local |
| Provenance | None | Ed25519 signed, full chain |
| Dependencies | PyTorch, JAX, CUDA | Rust + wgpu (zero C deps) |
Validation Status
| Phase | Status | Scope |
|---|---|---|
| A–B | Reproduced | All AlphaFold2/3 primitives decomposed, implemented in Rust, validated to 1e-10 vs NumPy, GPU-accelerated |
| C | Planned | Wire BarraCuda GEMM to Evoformer operations |
| D | Planned | End-to-end pipeline (FASTA → structure → confidence → provenance) |
| E | Planned | LTEE structural evolution analysis (8.3M predictions) |
| F | Planned | Standalone helix-vision crate on crates.io |
Full roadmap: Structure Prediction Roadmap
What It Enables
- Drug discovery: Structure-based docking from sequence alone (no $50K/yr Schrodinger license)
- Metagenomic structural census: Predict protein structures for entire microbial communities
- Vaccine/antigen design: Signed provenance chain from target selection to final construct
- Enzyme engineering: Computational enzyme design via structure prediction + P≠NP enzyme thesis
- LTEE analysis: 8.3M structure predictions across 75,000 generations of E. coli evolution
See also: Structure Prediction Roadmap, neuralSpring for validation evidence, barraCuda for the math engine.