Haisun Zhu

OpenAntigens: a structure-aware database for antigen construct design across the human cell-surface and secreted proteome

A static web database proposes 55 305 construct suggestions for 5328 human secreted and cell-surface proteins, using AlphaFold pLDDT and PAE, with ortholog, paralog and BLAST cross-reactivity context.

An interpretable open platform for sequence-based antibody developability prediction

DELPHI is an open platform for predicting antibody developability from sequence, achieving high AUC scores and enabling residue-level engineering insights.

High-Throughput Machine Learning-Aided Antibody Discovery for Cell Surface Antigens

The paper develops a synthetic Fab yeast display library integrated with machine learning to discover antibodies against cell surface antigens, yielding hundreds of validated antibodies and a public dataset.

Evaluating codon optimization strategies for mammalian glycoprotein production with an open-source expression vector

The paper evaluates codon optimization strategies for mammalian glycoprotein production and finds that native codons are sufficient, while selective codon skewing can improve yields for some targets.

Machine Learning enables efficient and effective affinity maturation of nanobodies

This paper uses machine learning to predict high-affinity nanobody binders from sparse sequencing data, outperforming deep learning and semi-supervised methods with linear models.

Effect of the S2' site cleavage on SARS-CoV-2 spike

The paper reports a cryo-EM structure of the S2 fragment of SARS-CoV-2 after S2 cleavage, showing it represents a late fusion intermediate, and shows that S2 cleavage accelerates membrane fusion.