AlphaFold Database Expands with Millions of Protein Complex Structures

A major expansion of the AlphaFold Database has been announced, offering scientists unprecedented access to predicted structures of protein complexes. The collaboration between EMBL-EBI, Google DeepMind, NVIDIA, and Seoul National University now provides detailed models for millions of interactions, with a focus on human and bacterial proteins. Researchers believe this resource will accelerate studies into infectious diseases and drug development.

The AlphaFold system, originally designed to predict single protein structures, has now been extended to map protein complexes. EMBL-EBI integrated these predictions into the existing database, ensuring open access and seamless compatibility with other research tools. The dataset prioritises proteins from human cells and key bacterial pathogens, including antibiotic-resistant strains like carbapenem-resistant Pseudomonas aeruginosa and Helicobacter pylori.

NVIDIA played a crucial role by optimising deep learning processes and speeding up sequence alignment calculations. Meanwhile, the Steinegger Lab at Seoul National University developed scalable methods for modelling protein-protein interactions. Together, these advancements allow researchers to explore how proteins assemble, stabilise, and function within cells. The database includes homodimers—identical protein pairs—across 20 species, broadening its relevance for global health. Dame Janet Thornton, a leading structural biologist, described the work as a critical step toward mapping the human interactome, the complete set of protein interactions in the body.

This expanded database provides immediate applications for studying infectious diseases and designing antimicrobial treatments. By offering detailed structural insights, it supports research into antibiotic resistance and conditions like pneumonia, gastric ulcers, and stomach cancer. The collaboration between academic institutions and technology leaders has created a resource expected to drive advances in medical and biological sciences.