How to read this finding
Structure prediction is distinct from experimentally proving a protein’s function or a drug’s benefit. This page describes the methods and evidence available in October 2021.
Why was AlphaFold 2 a milestone in 2021?
It substantially advanced protein-structure prediction using an attention-based system that integrated sequence and residue relationships, opening new possibilities for biological research.
Evidence you can use
AI for science in the 2021 report
Historical snapshot: October 2021. Dates and populations are specified per row.
| Measure | Reported value | Definition and source |
|---|---|---|
| AlphaFold 2 evaluation milestone | CASP14 in 2020 | Milestone discussed retrospectively in the 2021 report.2021 report, slide 19 (PDF page 19) |
| RoseTTAFold representations | 1D, 2D, and 3D | Sequence, distance-map, and coordinate representations processed together.2021 report, slide 20 (PDF page 20) |
Structure prediction is distinct from experimentally proving a protein’s function or a drug’s benefit. This page describes the methods and evidence available in October 2021.
Sources and dates
Historical snapshot published October 12, 2021. This web edition was prepared on 2026-10-11 from the online deck and original launch posts. Findings and forecasts retain their original time frame.
- 2021 report, slide 19 (PDF page 19)Original 2021 report. Printed slide numbers match PDF pages.
- 2021 report, slide 20 (PDF page 20)Original 2021 report. Printed slide numbers match PDF pages.
- State of AI Report 2021: online slides
- Air Street Press launch essayOctober 12, 2021.
- Welcome to State of AI Report 2021Original website launch post, October 12, 2021.
Cite this page
Benaich, Nathan, and Ian Hogarth. “Why was AlphaFold 2 a milestone in 2021?” State of AI Report 2021. Historical report snapshot; web edition prepared 2026-10-11.