Biocomputation, AI and Q Capital.
The synonymous CNN reduces to two interpretable physical observables — the signed stacking ΔΔG (Turner) + the G>A bias — that match it (AUC 0.68) and generalize across genes. Glass-box, deployable as pip install ef-synonymous + a free web tool.
read →Formal comparison across 7 genes with a stratified meta-analysis. EF reaches ΔAUC of -0.024 to -0.040 against massive predictors — and beats CADD in the sodium channel SCN1A (0.913 vs 0.832). Orthogonal signal confirmed.
read →A multichannel 1D CNN that combines the mRNA stacking free energy with evolutionary signal from ESMC-300M. 42 validated genes, AUC up to 0.99, zero-shot transferability across protein families.
read →The stacking ΔG profile adds a dimension orthogonal to secondary structure (R²=0.144). A dual optimizer that beats BNT162b2 and mRNA-1273 in ΔG and MFE simultaneously.
read →Synonymous variants don't change the protein but do change the mRNA's thermodynamic profile. The first CNN predictor with pure thermodynamic signal: AUC 0.683. Conceptual framework Λ = S ⊗ Φ.
read →A model of the firm where the unit of capital is neither the work hour nor the physical asset, but the token: the inference compute that, governed and captured, accrues as proprietary, defensible knowledge.
read →A Kanban board where several agents collaborate under human supervision: fail-closed approval broker, hash-chain audit, RBAC and a multi-LLM adapter. Born as the testbed for the lab's pipelines.
read →An adaptation of the Business Model Canvas into nine blocks to force the expensive decisions — segment, autonomy, KPIs, integrations, costs, risks — before writing a single line of code.
read →How to do deep-tech research with local models, specialized agents and selective access to foundational models — projects that once required a full team, now within reach of one person. QMetrika as a real case.
read →