CV

General Information

Name Zhentao He (James He)
Label Ph.D. Student
Email zthe25@m.fudan.edu.cn
URL https://jimmytauh.github.io/
Summary A Ph.D. student at Fudan University focused on machine learning and data mining for biological data, developing robust, interpretable, and transferable representations for multiomics analysis, perturbation modeling, and protein function.

Education

  • 2025 - 2030
    Ph.D. in Data Mining and Intelligent Information Processing
    Fudan University, Shanghai, China
    • ISTBI (Institute of Science and Technology for Brain-inspired Intelligence)
    • Zhuobo Fellow at Fudan University
    • Advisor: Prof. Shanfeng Zhu
  • 2021 - 2025
    B.E. in Computer Science & Technology
    Wuhan University, Wuhan, China
    • Hongyi Honor College Student
    • Outstanding Graduate (2025)
    • National Scholarship (2023-2024)
    • GPA: 3.91/4.00

Experience

  • 2025 - Present
    PhD Student Researcher
    Lab of Data Mining and Intelligent Information Processing, ISTBI, Fudan University
    • Integration and analysis of spatial multiomics data
    • Advisor: Prof. Shanfeng Zhu
  • 2022 - 2025
    Undergraduate Researcher
    BIOD Lab, School of Computer Science, Wuhan University
    • Developed methods for single-cell multiomics data integration and analysis
    • Predicted the impact of drug and genetic perturbations on cell states
    • Studied metabolic pathway design and molecular feature representation techniques
    • Advisor: Prof. Lihua Zhang
  • 2022 - 2023
    iGEM Team Member (Head of Model Team)
    WHU-China, CRISPReporter
    • Gold Medal; Nomination for Best Foundational Advance Project
    • A novel multi-level DNA memory device with CRISPR technology and its software suite

Publications

  • 2026
    MoE-TCR: Mixture-of-experts framework for pan-specific TCR-epitope binding prediction
    Pattern Recognition, November 2026
    • Qu, Wei and Li, Jinxing and He, Zhentao and Wang, Jiayi and Zhu, Shanfeng
    • DOI: 10.1016/j.patcog.2026.113737
  • 2026
    SpaDC enables sequence-based integrative analysis and regulatory inference of spatial chromatin accessibility data
    Communications Biology, 2026
    • Ma, Chuanlong and Yang, Chenghui and Zhen, Caiwei and He, Zhentao and Luo, Yong and Zhang, Lihua
    • Published June 6, 2026
    • DOI: 10.1038/s42003-026-10462-y
  • 2026
    Interpretable Data Integration for Single Cell and Spatial Multi-Omics
    Cell Systems, 2026
    • Yang, Chenghui and He, Zhentao and Nie, Qing and Zhang, Lihua
    • Published online February 4, 2026
    • DOI: 10.1016/j.cels.2025.101479

Honors & Awards

  • Present
    Fudan University Zhuobo Program Fellow
    Fudan University
  • 2025
    Outstanding Graduate, Class of 2025
    Wuhan University
  • 2023 - 2024
    National Scholarship
    Ministry of Education of the People's Republic of China

Teaching Assistant Experience

  • 2024 - 2025
    Teaching Assistant
    Computer Organization and Design, Wuhan University
    • Assisted in teaching the fundamentals of computer organization.
    • Held office hours for student consultations.

Projects

  • 2023
    CRISPReporter - Model and Software Suite
    • sgRNA generator utilizing machine learning and sequence alignment to predict on-target and off-target rates
    • Editing simulator to emulate temporal relationships between multi-level signal recordings
  • 2024
    Multiomics Integration via Feature-Guided Optimal Transport (FGOT)
    • Feature-guided optimal transport for integration of cells across different modalities
    • Contributions include coding, experiments, and co-authorship of the manuscript
  • 2026
    MoE-TCR - Mixture-of-Experts for TCR-Epitope Binding Prediction
    • Mixture-of-experts framework leveraging criss-cross attention for pan-specific TCR-epitope binding prediction
    • Contributions include method development, experiments, and co-authorship of the manuscript
  • 2026
    SpaDC - Spatial Chromatin Accessibility Data Analysis
    • Graph-regularized convolutional neural network integrating DNA sequence, chromatin accessibility, and spatial location
    • Contributions include method development, experiments, and co-authorship of the manuscript

Languages

  • Chinese
    • Native speaker
  • English
    • Fluent (IELTS Band 7)

Competencies & Skills

  • Programming Languages
    • Python, C++, R
  • Libraries and Tools
    • PyTorch, Git, Docker
    • Scanpy, Seurat, etc.
  • ML Architectures
    • VAE, GNN, GAN, OT (Neural Optimal Transport), Transformer, etc.

Research Interests

  • Representation Learning
  • Generalization & Adaptation
  • Multimodal Learning for Multiomics
  • Perturbation Prediction & Protein Function Modeling

References

  • Prof. Shanfeng Zhu - Fudan University, Advisor
  • Prof. Lihua Zhang - Wuhan University, Undergraduate Advisor