AlphaFold Database Adds Millions of Complexes — Interaction Scale

Corrected October 14, 2026: Corrected the complex count to EMBL's 30 million and the EMBL announcement date to March 16. Re-dated from March 12 to March 16, the date of EMBL's announcement of the expansion, and removed references to coverage published after that date.

Single-chain AlphaFold changed structure prediction. The proprietary jump here is proteome-scale complexes in the public database — millions of interaction models prioritized for human health, not another monomer dump.

A collaboration of EMBL-EBI, Google DeepMind, NVIDIA, and Seoul National University added millions of AI-predicted protein complex structures to the AlphaFold Database, including high-confidence predictions for homodimers and other complexes. Dataset priorities: proteins important for human health and disease; 1.7 million high-confidence homodimer predictions added, with more planned. The partnership has calculated predictions for 30 million complexes (1.7 million high-confidence homodimers in the database, 18 million lower-confidence homodimers for bulk download, the rest heterodimers under assessment); open release for systems biology and drug discovery. Early applications framed as hypothesis generation on cellular machinery and potential drug targets.

Claims vs checks#

Database addition and counts are EMBL-EBI / collaborator primary. “High-confidence” is model-confidence filtering, not crystallographic confirmation.

Limits#

• Predicted interfaces can err; experimental validation remains required for drug claims.
• Coverage skewed toward prioritized proteomes.

Sources#

• EMBL: “Millions of protein complexes added to AlphaFold Database” (March 16, 2026).