English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Antibodies comprise the most versatile class of binding molecules, withnumerous applications in biomedicine. Computational design of antibodiesinvolves generating novel and diverse sequences, while maintaining structuralconsistency. Unique to antibodies, designing the complementarity-determiningregion (CDR), which determines the antigen binding affinity and specificity,creates its own unique challenges. Recent deep learning models have shownimpressive results, however the limited number of known antibodysequence/structure pairs frequently leads to degraded performance, particularlylacking diversity in the generated sequences. In our work we address thischallenge by leveraging Model Reprogramming (MR), which repurposes pretrainedmodels on a source language to adapt to the tasks that are in a differentlanguage and have scarce data - where it may be difficult to train ahigh-performing model from scratch or effectively fine-tune an existingpre-trained model on the specific task. Specifically, we introduce ReprogBertin which a pretrained English language model is repurposed for protein sequenceinfilling - thus considers cross-language adaptation using less data. Resultson antibody design benchmarks show that our model on low-resourced antibodysequence dataset provides highly diverse CDR sequences, up to more than atwo-fold increase of diversity over the baselines, without losing structuralintegrity and naturalness. The generated sequences also demonstrate enhancedantigen binding specificity and virus neutralization ability. Code is availableat https://github.com/IBM/ReprogBERT

Reprogramming Pretrained Language Models for Antibody Sequence Infilling