AI Foundationspredict · compress · act

concepts → System

System

AlphaFold

decade6 connections

attention over a protein and its evolutionary cousins — the folding problem as a contact map

Where it sits

The prism has six jobs across and eight layers down. Its primary cell is infer × L1. Hatched cells cannot exist — a GPU does not learn, an institution does not infer.

Runs at: datacenter. Evidence: benchmark.

What must come first — and what it unlocks

Left to right is reading order, derived from the prerequisite_of edges. Nothing here is hand-ordered: the diagram is the graph.

nothing comes first — this is a starting pointAlphaFoldnothing depends on it yet — a leaf in the reading order

Where to read it

The chapter that introduces it, and any chapter that uses it again.

63Seeing Structureact XIV · AI for Science

Where it comes from

paperHighly Accurate Protein Structure Prediction with AlphaFoldJumper et al., Google DeepMind · 2021

Every connection

All 6 edges touching this node, grouped by relation family — the sections above are highlights from this list. Colours match the relation families inthe atlas.

Structure · 1
is an instance ofStructure predictionTask
Flow · 2
usesAttentionMechanism
producesAlphaFold databaseDataset
Lineage · 3
is attributed toDemis HassabisPerson
is attributed toJohn JumperPerson
is improved byAlphaFold 3System

This page is a projection of one node in src/data/concepts.ts. It has no prose file of its own — 521 declared edges produce all 340 of these pages. Edit an edge and both endpoints change.