Zhaoqian Su

Decoding the Physical Mechanisms of Protein-Small Molecule Association by Multiscale Kinetic Monte-Carlo Simulations

This paper develops a multiscale kinetic Monte-Carlo framework to simulate protein-small molecule association and evaluates its accuracy against experimental data.

MISSTE: a multiscale integrative spatial simulator for understanding the mechanisms underlying tissue ecosystems

MISSTE simulates multiscale tissue ecosystems to improve CAR-T therapy by identifying spatial access as a key bottleneck for immune persistence and tumor control.

Inferring Dynamic Information from Protein Structures by Gaussian Integrals and Deep Learning

This paper develops a deep learning framework to predict protein flexibility from static structural data, achieving moderate accuracy and identifying key structural features associated with flexibility.

OPTIMIS: Optimizing Personalized Therapies through Integrated Multiscale Intelligent Simulation

This paper develops an AI framework integrating stochastic and deterministic models to simulate multiscale biological systems, enabling adaptive treatment strategies through reinforcement learning.

Multiscale conformational sampling of multidomain fusion proteins by a physics informed diffusion model

This paper introduces a physics-informed diffusion model to efficiently sample conformational ensembles of multidomain fusion proteins, outperforming traditional methods in capturing large-scale dynamics.

Structure-based Predictions of Conformational B Cell Epitopes by Protein Language Model and Deep Learning

The paper introduces a protein language model-based method to predict conformational B-cell epitopes on antigen structures, outperforming existing methods on benchmark datasets.

SuperMetal: A Generative AI Framework for Rapid and Precise Metal Ion Location Prediction in Proteins

SuperMetal predicts metal-binding sites in proteins with high precision and efficiency, outperforming existing models for zinc ions.

Discovering new amyloid-like peptides using all-atom simulations and artificial intelligence.

This study uses all-atom simulations and AI to identify fibril-prone peptide sequences, achieving high accuracy in predicting amyloid-like behavior.

Rationalize the Functional Roles of Protein-Protein Interactions in Targeted Protein Degradation by Kinetic Monte-Carlo Simulations

This study uses kinetic Monte-Carlo simulations to model protein-protein interactions in PROTAC-induced ternary complex formation, showing that cooperativity affects association into native-like configurations.

Machine learning application to predict binding affinity between peptide containing non-canonical amino acids and HLA0201

The paper develops a machine learning model to predict MHC-I binding affinity for peptides with non-canonical amino acids and evaluates its performance against existing methods.

SuperWater: Predicting Water Molecule Positions on Protein Structures by Generative AI

SuperWater predicts water molecule positions on protein structures using a generative AI framework, achieving high accuracy in crystal water coverage and prediction precision.

Machine-learning-based Structural Analysis of Interactions between Antibodies and Antigens

This paper develops a deep learning model to analyze antibody-antigen interactions, achieving high accuracy in distinguishing antibody-antigen complexes from other protein complexes and identifying antigens from epitope information.

Encoding the Space of Protein-protein Binding Interfaces by Artificial Intelligence

This paper uses artificial intelligence to encode and generate protein-protein binding interface fragment pairs, demonstrating the degeneracy of their conformational space and the utility of machine learning for predicting unknown interactions.

Prediction of Interactions between Cell Surface Proteins by Machine Learning

This paper develops a machine learning framework to predict interactions between cell surface proteins, achieving over 70% accuracy in human proteins and validating results against experimental data.

Protein-lipid interactions drive presynaptic assembly upstream of cell adhesion molecules

The paper identifies a presynaptic assembly mechanism driven by SYD-1-lipid interactions before neurexin recruitment, showing PIP2-binding residues are critical for active zone formation.

Mechanistic Dissection of Spatial Organization in NF-κB Signaling Pathways by Hybrid Simulations

The paper develops a hybrid simulation method to study spatial organization in NF-κB signaling pathways, showing that TRAF clustering regulates oscillatory NF-κB responses.