AlphaFold required approximately 150,000 experimentally determined protein structures from the Protein Data Bank as initial training data, supplemented with synthetic data generated by an earlier version of AlphaFold that predicted ~1 million structures and was then filtered to ~300,000 of the most accurate predictions to create a refined training set.

factualpending

Speaker

Demis Hassabis

Evidence Quote

“we built on 50 years worth of structural biologist painstaking experimental work to create those 150,000 roughly structures in the PDB...the 150,000 we actually had to create an earlier version of Alphafold that predicted you know nearly a million structures and then we had to triage that for the you know the most accurate 300,000 or so [20:28]”

Source

Sir Demis Hassabis on The Future of Knowledge | Institute for Advanced Study— Institute for Advanced Study
Created: 8/11/2026, 6:28:03 AM

Your notes

Loading notes...