Building on our previous works, PrePPI-AF and ZEPPI, we leverage the state-of-the-art DL/AI models to construct the comprehensive structure-based PPI database. Using this methodology, we focus on predicting the Host-Pathogen Interactome. We hope to unravel the molecular basis that underpin infectious diseases, enabling the development of targeted therapies, vaccines, and strategies to combat existing and emerging pathogens. Ongoing projects include taxoplasma and malaria.
In recent decades, biotechnology has produced a wide array of omics data — including single-cell RNA sequencing and mass spectrometry–based proteomics — offering a rich resource for data-driven research. In our lab, centering on predicted millions of protein–protein interactions and their interaction networks, we integrate additional omics datasets to uncover cell-specific protein–protein networks and track their evolution over time, potentially revealing disease mechanisms. Current research includes the study of liver diseases and collaboration projects on neurological diseases. We seek to train one graduate student (biology or medical science background) on this exciting direction.
Moreover, with millions of predicted PPIs, we aim to explore the complex networks these proteins form, with the goal of identifying novel pathways and gaining a more comprehensive understanding of protein functions. Once specific target PPIs are identified, we are further interested in studying their binding dynamics and energetics, with the goal of designing optimized binders and small molecule inhibitors. We are seeking one graduate student (any physical/life sciences background) to join us in this exciting direction.
Calculating protein binding free energy in silico remains challenging. Molecular dynamics-based methods often struggle with the complexity introduced by protein conformational flexibility, in addition to the computation demands required for accurate simulations. Recently, machine learning approaches have emerged as promising alternatives, either by fitting structural data to regression models or by developing DL/AI models based solely on sequence information.
Our goal is to create a general and widely applicable machine learning model to predict binding affinities. Specifically, we are building a transferable, attention-based deep learning model that incorporates both structural features of protein complexes and sequence-derived data. We aim to extend this model to predict changes in binding free energy due to mutations, interactions with small molecules, or post-translational modifications, providing a versatile tool for a range of biological applications.
We are currently seeking one graduate student (chemistry or physics background) for this exciting direction. We are always excited to collaborate with experimental groups and explore new scientific frontiers together.