![[Your Name]](me.jpg)
Yi-Heng Zhu received his Ph.D. degree in control science and engineering from Nanjing University of Science and Technology in 2023, led by Professor Dong-Jun Yu. From 2019 to 2021, he acted as a visiting Ph.D. student at University of Michigan (Ann Arbor), funded by China Scholarship Council and led by Professor Yang Zhang. He is currently a lecturer at the College of Artificial Intelligence, Nanjing Agricultural University.
Developing computational methods to accurately predict protein functions in the context of Gene Ontology from sequence and structure data.
Developing computational methods to annotate the functions for enzymes using Enzyme Commission Number from sequence and structure data.
Developing deep learning methods to identify and characterize binding bindings and pockets for drug discovery applications.
Machine learning approaches to predict crystallization propensity and optimize conditions for structural biology studies.
Computational models to predict and analyze interactions between pharmaceutical compounds and target proteins.
Computational identification of transcription factor binding sites and their regulatory mechanisms.
Adapting transformer-based architectures for biological sequence analysis and knowledge extraction.
Protein Function Prediction
Integrating Multi-Source Knowledge Fusion with Pre-Trained Language Model for High-Accuracy Protein Function Prediction
Protein-DNA binding site prediction
Integrating Unsupervised Multi-Source Language Models with LSTM-Attention Network for High-Accuracy Protein-DNA Binding Site Prediction
Protein-protein contact map prediction
Integrating Unsupervised Language Model with Multi-View Multiple Sequence Alignments for High-Accuracy Inter-Chain Contact Prediction
Protein function prediction
Integrating Unsupervised Language Model with Triplet Neural Networks for Protein Gene Ontology Prediction
Protein function prediction
Integrating Transcript Expression Profiles with Protein Homology Inferences for Gene Function Prediction
Protein crystallization prediction
Accurate Multi-Stage Prediction of Protein Crystallization Propensity Using Deep-Cascade Forest with Sequence-Based Features
Protein-DNA binding site prediction
Accurate Identification of DNA-binding Sites from Protein Sequence by Ensembled Hyperplane-Distance-Based Support Vector Machines
Protein-nucleotide binding sites prediction
Boosting Granular Support Vector Machines for the Accurate Prediction of Protein-Nucleotide Binding Sites
Protein crystallization prediction
Integrating Graph Attention Network with Predicted Contact Map for Multi-Stage Protein Crystallization Propensity Prediction