reading the alphafold paper and understanding it turned out to be different activities, and the gap between them was code.
so this rebuilds the data preparation pipeline at a scale that fits on one machine, with a dashboard comparing its toy inferences against real traces.
it does not fold proteins competitively and never intended to. it answers a narrower question.
what is in it
three things in one streamlit dashboard, all on cpu. an actor critic agent on cartpole, tabular q-learning on frozenlake over 60,000 episodes, and a toy transformer that turns a sequence into backbone coordinates for n, cα and c.
ten structures come from alphafold's e. coli bundle. the dashboard overlays the real alphafold trace on the toy backbone for the same protein, so the gap is something you look at rather than read about.
