AlphaFold hits ‘next level’: the AI database now includes protein pairing

2026-03-17 · Source: Machine learning : nature.com subject feeds · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Life Sciences & Biology, Data Science & Analytics · Depth: Intermediate, quick

Summary

The AlphaFold protein-structure database has been significantly expanded to include predictions of protein complexes, specifically 1.7 million "homodimers," which are crucial for understanding protein function. This "next level" capability, developed by a consortium including Google DeepMind, EMBL-EBI, and NVIDIA, addresses the computational intensity of predicting protein interactions beyond individual monomers. The database, powered by AlphaFold2, now contains approximately 200 million predictions and focuses on complexes from 20 well-studied species, enhancing its utility for molecular-level research.

Key takeaway

AlphaFold's database now includes 1.7 million homodimer predictions, expanding beyond individual protein structures to address a critical gap in understanding protein complex function. This advancement, achieved by an EMBL-EBI/DeepMind/NVIDIA consortium, tackles the computational intensity of complex predictions for 20 key species. It significantly enhances molecular-level research and drug discovery by providing a more complete picture of crucial protein interactions, such as those in HIV-1 protease.

Topics

• AlphaFold
• Protein Structure Prediction
• Protein Complexes
• Homodimers
• Computational Biology

Best for: AI Researcher, AI Scientist, Research Scientist

Related on AIssential

• Why We're Not Close to AI Drugs Yet | Isomorphic Labs — Drug design comprises multiple distinct ML problems, not a single one, despite AlphaFold 2's protein structure prediction success.
• AlphaFold: Grand Challenge to Nobel Prize with John Jumper — AlphaFold's success demonstrates AI's profound utility in accelerating scientific discovery, even without full interpretability.
• AF2BIND: predicting small-molecule binding sites using the pair representation of AlphaFold2 — AlphaFold2's internal representations can be repurposed to accurately predict de novo small-molecule binding sites.
• Designing Protein Binders Using the Generative Model Proteina-Complexa — Proteina-Complexa co-designs protein binders and enzymes using a latent flow-matching generative model with inference-time optimization.
• Graph-Theoretic Models for the Prediction of Molecular Measurements — Enhanced classical graph-theoretic models can rival deep learning for molecular property prediction with significantly lower computational cost.
• Bringing AI-driven protein-design tools to biologists everywhere — Democratizing AI-driven protein design tools empowers biologists to accelerate drug discovery and engineer novel proteins.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Machine learning : nature.com subject feeds.