Jieke(Jack) Wu

Jieke(Jack) Wu

University of Science and Technology of China

👨🏼‍🎓 About me

I’m Jieke (Jack) Wu (武杰克), a senior undergraduate student at the Department of Life Sciences and Medicine, University of Science and Technology of China. I am currently striving to pursue a Ph.D. degree with a focus on the intersection of life sciences and artificial intelligence. If you are interested in learning more about me and would like to explore my background further, please click here to download my resume.

📖 Educations

📑 Publications

  • Jieke Wu, Wei Huang, Mingyuan Bai, Xiaoling Hu, Yi Duan, Wuyang Chen. “Training-free Design of Augmentations with Data-centric Principles.” ICML 2024 Workshop AI4Science.
  • Tinghui Wu, Jieke Wu, Wuyang Chen, Zijun Zhang ”Training-free Design of Deep Networks as Ensembles of Clinical Experts” under submission

    🧪 Research Experience

💻 Training-free Design of Deep Networks

Cedars-Sinai Medical Center, Dr. Zijun Zhang
UC Berkeley, Prof. Wuyang Chen
Remote (US)
Research Assistant (08/2024 – present)

  • TEACUP introduces a novel, training-free metric that accurately evaluates the quality of deep learning models without the need for costly training, significantly reducing computation costs (by over 90%) compared to traditional approaches.
  • TEACUP improves performance across various clinical tasks, offering enhanced predictive accuracy and reliability, which is crucial in medical applications.
  • TEACUP enables the creation of AI model ensembles, simulating the use of multiple human experts in clinical settings to provide more robust predictions and better uncertainty quantification.

💻 Hierarchical Transformer for Genomics

Cedars-Sinai Medical Center, Dr. Zijun Zhang
UC Berkeley, Prof. Wuyang Chen
Remote (US)
Research Assistant (03/2024 – 08/2024)

  • This project focuses on the application of deep learning techniques, particularly hierarchical transformers, to uncover hidden patterns in DNA sequences. By integrating both global and local DNA information, we aim to enhance the model’s ability to better understand and predict complex genetic structures.
  • Specifically, I focused on improving model performance by devising a method that balances the global context of entire DNA sequences with localized, detailed genomic information. This allows for more accurate predictions of genetic functions and structures, potentially aiding in biomedical research.
  • By this project, I had a better understanding of LLMS and konwn how to use Huggingface and some other deeplearning toolboxes.

🖥 Training-free Design of Data-centric Augmentations with Principles

UC Berkeley, Prof. Wuyang Chen
Remote (Canada)
Research Assistant (06/2023 – 02/2024)

  • Developed a training-free framework that evaluates the effectiveness of various image augmentation techniques on deep learning models, particularly in the context of medical imaging datasets.
  • Investigated the relationship between data covariance properties and image recognition accuracy, providing insights into how certain augmentations could be leveraged to improve model robustness without the need for extensive retraining.
  • Our work demonstrated that these augmentation methods could substantially improve the efficiency and accuracy of medical image analysis, especially for under-represented or noisy datasets. This research was published in the ICML 2024 Workshop AI4Science.

🐀 Isolation of Bacteriophages Targeting Gut Bacteria

University of Science and Technology of China, Prof. Yi Duan
Hefei, China
Research Assistant (01/2023 – 05/2024)

  • Developed an innovative \textit{in vitro} culture system for \textit{Akkermansia muciniphila} (Akk), a key gut bacterium. Our system was contamination-free, specifically addressing the issue of \textit{Cutibacterium acnes} contamination that plagued earlier methods.
  • Isolated and purified Akk-targeting bacteriophages from wastewater samples. Following multiple rounds of amplification, we constructed a phage library that serves as a toolkit for selectively targeting Akk populations in the gut microbiome.
  • This phage library provides a crucial resource for studying Akk’s role in various diseases, offering potential applications for targeted microbiome manipulation in therapeutic contexts. This project received an outstanding rating as a school-level research initiative.

🦟 Biodegradable Needles for Transdermal Delivery in Biofilm-Infected Chronic Wounds

Suzhou Institute for Advanced Research, Prof. Xiaorong Xu
Suzhou, China
Research Assistant (11/2022 – 09/2023)

  • Designed biodegradable long microneedles inspired by the mouthparts of insects like mosquitoes and ticks. These needles are intended for the treatment of deep tissue infections caused by biofilm-forming bacteria.
  • Utilized finite element simulation software (COMSOL and Abaqus) to optimize the needle’s design, focusing on material properties and geometric configurations that could penetrate deep skin layers while maintaining structural flexibility.
  • Introduced a novel injection molding technique for economically producing these complex needle structures. This project was highly rated and received recognition as an outstanding school-level project.

🦠 Isolation and Identification of Cyanobacteria and Cyanophages from Lake Chaohu

Laboratory of Biochemistry & Structural Biology, Prof. Congzhao Zhou
Hefei, China
Research Assistant (09/2022 – 06/2023)

  • Successfully isolated three strains of cyanobacteria and their corresponding cyanophages from water samples collected from Lake Chaohu.
  • Conducted genomic analysis on the isolated cyanobacteria, determining their taxonomic classification and evaluating their ecological roles within the lake’s ecosystem.
  • This research won an award at the National University Life Science Competition, highlighting its significance in advancing our understanding of freshwater microbiomes and their interaction with phages.

🎖 Honors and Awards

  • Outstanding School-Level Project: Undergraduate Innovation and Entrepreneurship Training Program 2024
  • Outstanding School-Level Project: College Student Research Program 2023
  • Third Prize in the 8th National University Life Science Competition 2023
  • Outstanding Undergraduate Scholarship 2024, 2023, 2022, 2021

🧭 Skills

  • Programming Languages: Python, C/C++, Matlab (ranked by proficiency)
  • Tools and Frameworks: Git, $\LaTeX$, PyTorch, HuggingFace

🎥 Personal Interests

  • Anime: As a pastime in my spare time, I watched a lot of Japanese anime about love, sports, myth and sci-fi.

💻 Internships