/tools/DiffAbXL
DiffAbXL
AstraZeneca/DiffAbXL
91 stars9 forksPythonAdded February 4, 2026
summary
DiffAbXL is a benchmarking tool for generative models aimed at antibody design, specifically evaluating log-likelihood scores for ranking antibody sequences based on their predicted binding affinities. It provides datasets and methodologies for assessing the performance of various models in the context of antibody optimization.
description
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".
topics
antibody-designbinding-affinitydiffusion-modelsgenerative-aigraph-neural-networksin-silico-designllm-modelslog-likelihood
Ratings
N/A
0 ratings
Rate this tool: