Skip to content
English

Switch theme

// ⌬ Graph Neural Networks & AI for Science

AlphaFold 2

Predicts protein 3D structure from sequence at near-experimental accuracy.

AlphaFold 2 蛋白质结构预测 2021 Advanced core

IN PLAIN WORDS

The Evoformer exchanges information between MSA and pair representations; a structure module with invariant point attention outputs atom coordinates. It cracked protein folding and shared the 2024 Chemistry Nobel.

Used in: Structural biology, drug design; AlphaFold 3

TIMELINE · prerequisites → this → what builds on it

2016 Graph Neural …2017 Transformer &…2021 AlphaFold 2

01Original paper

Highly accurate protein structure prediction with AlphaFold

Jumper et al. · Nature · 2021

DOI ↗ ✓ Verified · Crossref API doi:10.1038/s41586-021-03819-2

02Where it sits

Learn the left column first; the right column builds on this one.

Learn first

AlphaFold 2

Then you can learn

  • Nothing in the atlas builds on it yet

Related:AlphaGeometry (Neuro-Symbolic Reasoning)

Transformer & S…Graph Neural Ne…AlphaGeometry (… AlphaFold 2

Left: prerequisites · right: builds on this · dashed: related. Full map →

03Learning resources

Official docs, explainers, courses and reference code. All links checked.

04Where the course teaches it

For AI / data

Data updated: AI algorithms & curriculum(UTC+8)