Thomas D. Barrett

AbBFN2 is a generative antibody foundation model that unifies diverse data sources and enables flexible conditional generation for multiple antibody design tasks.

This paper introduces ProtBFN, a Bayesian Flow Network for protein sequence generation, which outperforms existing models and is fine-tuned for antibody generation.

The paper introduces BioCLIP, a contrastive learning framework for pre-training Protein Structure Models using Protein Language Models, achieving performance comparable to specialized methods on various tasks.

The paper presents a streamlined AlphaFold variant using pLMs and MSAs, showing that combining or using either modality achieves comparable performance to models trained exclusively on one.