Yunguan Fu

This paper compares chemical descriptors and deep learning embeddings for scoring de novo peptide designs, finding classical descriptors are effective and efficient for developability prediction.

BoltzProt-1 improves nanobody design for protein targets by increasing hit rates and developability compared to existing methods.

The paper introduces CoV-UniBind, a unified database of SARS-CoV-2 antibody-antigen interactions, and benchmarks models for antibody design and vaccine development.

The paper benchmarks nine protein folding models on 20 monomeric proteins, showing Chai-1 excels in recovering conformations and capturing dynamics for Adenylate Kinase.

LightMHC predicts full-atom pMHC structures from sequences using a lightweight model with attention mechanisms, achieving comparable performance to AlphaFold 2 and ESMFold with faster speed.

A COVID-19 Early Warning System combines structural modelling with machine learning to detect and monitor high risk SARS-CoV-2 variants, identifying all 16 WHO designated variants on average more than one and a half months in advance by selecting on average less than 0.3% of the weekly novel variants.

The paper introduces a graph neural network for peptide-MHC structure prediction, achieving accuracy comparable to AlphaFold 2 with significantly fewer parameters.