Back

Enhancing Antibody Language Models with Structural Information

Barton, J.; Galson, J. D.; Leem, J.

2024-01-04 bioinformatics
10.1101/2023.12.12.569610 bioRxiv
Show abstract

The central tenet of molecular biology is that a proteins amino acid sequence determines its three-dimensional structure, and thus its function. However, proteins with similar sequences do not always fold into the same shape, and vice-versa, dissimilar sequences can adopt similar folds. In this work, we explore antibodies, a class of proteins in the immune system, whose local shapes are highly unpredictable, even with small variations in their sequence. Inspired by the CLIP method [1], we propose a multimodal contrastive learning approach, contrastive sequence-structure pre-training (CSSP), which amalgamates the representations of antibody sequences and structures in a mutual latent space. Integrating structural information leads both antibody and protein language models to show better correspondence with structural similarity and improves accuracy and data efficiency in downstream binding prediction tasks. We provide an optimised CSSP-trained model, AntiBERTa2-CSSP, for non-commercial use at https://huggingface.co/alchemab.

Matching journals

The top 3 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.