AstraZeneca/DiffAbXL

The official implementation of DiffAbXL benchmarked in the paper "Exploring Log-Likelihood Scores for Ranking Antibody Sequence Designs", formerly titled "Benchmarking Generative Models for Antibody Design".

39
/ 100
Emerging

This project helps antibody researchers and drug developers evaluate and rank antibody sequences based on their potential binding affinity. It takes a list of antibody sequences, optionally with structural information, and provides log-likelihood scores and other metrics to indicate how well each antibody might bind to its target. This tool is designed for scientists working on antibody design and optimization.

No commits in the last 6 months.

Use this if you need to reliably compare different antibody sequence designs and predict their binding capabilities to prioritize candidates for further experimental validation.

Not ideal if you are looking for a tool to generate new antibody sequences from scratch, as this project focuses on evaluating existing designs.

antibody-design drug-discovery protein-engineering biologics-development immunology-research
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

90

Forks

9

Language

Python

License

Apache-2.0

Last pushed

Jun 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/AstraZeneca/DiffAbXL"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.