Unlock Antibody Discovery with PLAbDab on Vecura

What is PLAbDab?

PLAbDab (Patent and Literature Antibody Database) is a self-updating, curated repository containing over 150,000 paired antibody sequences and their corresponding 3D structural models. By aggregating data from patent filings and academic literature, it creates a comprehensive cross-reference resource for antibody discovery and engineering. It helps users find known antibodies related to their research queries through sophisticated sequence, structural, and metadata-based retrieval methods. It is especially useful for antibody drug discovery, CDR engineering, and competitive landscape analysis.

What can users do with PLAbDab on Vecura?

With PLAbDab on Vecura, users can:

• Perform sequence similarity searches using the high-performance KA-Search algorithm to identify related heavy/light chain pairs.
• Execute structural searches by generating antibody models with ImmuneBuilder and ranking results based on backbone RMSD.
• Run combined sequence-plus-structure searches to identify antibodies that are both sequentially similar and share similar 3D geometries.
• Conduct keyword searches across metadata, such as target names or publication titles, to find antibodies associated with specific biological topics.

What the output means

The output provides a ranked CSV table containing matching antibody entries. This includes detailed sequence and structural data, such as CDR length patterns, identity scores, and RMSD values, alongside direct URLs to the original provenance documents (patents or papers).

This output should be used to support scientific decision making. It does not replace experimental validation.

Why this matters

The landscape of antibody discovery is increasingly driven by data from massive patent filings and academic research. Manually aggregating and mining this information is a significant bottleneck for drug discovery teams. PLAbDab automates this process, providing a structured, searchable interface that allows researchers to quickly identify prior art and assess sequence diversity around a lead candidate.

By integrating this tool into research workflows, scientists can more efficiently explore the competitive landscape and identify structural templates, significantly accelerating the early stages of biotherapeutic development.

• Developed by: The Oxford Protein Informatics Group (OPIG)
• Source: Official GitHub repo
• Reference: Original paper (bioRxiv 2023)