← eijex home

FactorForge technical whitepaper

Deterministic CPU-First Core.

Reproducible CDS design with explicit constraints, reviewable outputs, and a production path that removes biological hallucination risks from the optimization engine.

DBTL Design AnchorCPU deterministic DPRSPA-aligned evidence boundaries

Scientific benchmark

CAI optimization, reported with its corpus size.

Static benchmark figures are shown for technical context. They are not experimental validation or a claim of biological performance.

FactorForge

0.94

Mean CAI · n=49,257 CDS

Native reference (unoptimized)

0.72

Mean CAI · n=49,257 CDS

0.000.250.500.751.00FactorForge: mean CAI 0.940.94FactorForgeNative reference (unoptimized): mean CAI 0.720.72Native reference (unoptimized)
Mean CAI by reference, same corpus (n=49,257 CDS)
ReferenceMean CAI
FactorForge0.94
Native reference (unoptimized)0.72

Architecture & transparency

Two lanes, one evidence boundary.

Production (Deterministic)

The CPU-first dynamic-programming path produces the same result for the same inputs and constraints. Provenance is part of every payload and rendered result.

Exploratory Lab (ML)

ML/AI comparisons are isolated as non-deterministic exploration. Any sequence from this lane must pass through Production validation before wet-lab synthesis.

Output provenance

{
  "generator": "cpu_deterministic_dp",
  "lane": "production",
  "validation": "required"
}

The generator flag makes the execution lane auditable in exported JSON and review packages.

Algorithm

Constrained CAI maximization, computed exactly.

For a fixed protein and a configured GC% target range, feasibility_best searches every synonymous CDS that encodes the protein and returns the one with the highest Codon Adaptation Index inside that range — an exact dynamic-programming solution, not a heuristic approximation.

Objective

Among all synonymous codon sequences whose GC% falls within the configured range, choose the one that maximizes CAI.

maximize   CAI(C)
subject to GC_low <= GC%(C) <= GC_high
over       C in synonymous(protein)

Recurrence

Each state is (codon position, cumulative GC-base count). The DP keeps only the highest-scoring path into every reachable state.

D[i][h] = max over codon c
  of D[i-1][h - gc(c)] + log(weight(c))

Fallback

If no synonymous sequence satisfies the configured GC window, the DP returns the highest-CAI sequence with no GC constraint applied — a defined fallback, not a constraint failure.

Tie-breaking

Equal-scoring paths keep the first codon encountered in the reference table's fixed order — deterministic by construction, not by chance.

Read the implementation notes

FactorForge documents its scoring contract, codon reference, and review boundaries so benchmark context stays attached to the software that produced it.