Use the AI-Powered 3D Structure Similarity Search

03/20 

RCSB PDB's Structure Similarity Search has been redesigned to deliver faster and more scalable structural comparisons across experimentally determined and predicted Computed Structure Models (CSMs).

This new capability improves the accuracy and relevance of 3D Similarity search results on the RCSB.org website, helping users more effectively identify structurally related and distant homolog macromolecules.

The updated 3D similarity search uses machine learning–based embeddings to represent macromolecular structures in a high-dimensional vector space. Combined with vector databases, this approach enables efficient comparison of 3D structures at scale and improves sensitivity to 3D structural similarity, making it well-suited for exploring large collections of predicted models alongside experimentally determined structures.

RCSB PDB Structure Similarity Search

Find assemblies similar to the SARS-CoV-2 Spike protein trimer

• The SARS-CoV-2 spike protein is composed of three polymer chains, each of which has a receptor-binding domain that can be in an open (or up) conformation for interacting with cellular receptors or a closed (or down) conformation.
• To find spike structures where all three receptor-binding domains are closed, use PDB ID pdb_00006vxx as a query
• Change query structure selection to Assembly, Assembly 1 will be selected by default
• Click the Search button to return matching assemblies

For more on this feature, read the 3D Similarity Search help article and the Search API reference.

For methodological details, see

• Multi-scale structural similarity embedding search across entire proteomes
  
• Joan Segura, Ruben Sanchez-Garcia, Sebastian Bittrich, Yana Rose, Stephen K Burley, Jose M Duarte
  
• (2026) Bioinformatics 42: btag058 doi: 10.1093/bioinformatics/btag058