CV

Download CV (PDF)

Education

• M.S. in Computational Biology, Carnegie Mellon University, Pittsburgh, PA (2024 – 2026, expected)
• B.S. in Bioinformatics, Zhejiang University – University of Edinburgh Joint Institute (2020 – 2024)

Research Experience

• Peer Learning for NLP Shortcut Mitigation, Carnegie Mellon University (Aug 2025 – present)
  • Advisor: Prof. Carl Kingsford
  • Developed an LLM-based method to address shortcut learning in general NLP models
  • Improved algorithm stability and increased model inference accuracy from 0.80 to 0.94
• Controllable mRNA Sequence Design (ARCADE), Carnegie Mellon University (Dec 2024 – May 2025)
  • Advisor: Prof. Carl Kingsford
  • Implemented parallel computing software for RNA MFE and CAI optimization across multiple species codon databases
  • Developed a Minimum Free Energy predictor based on mRNA secondary structure features
  • Contributed to the model and scoring module for the ARCADE paper on controllable mRNA sequence design
• Protein Sequence Design, University College London (Jun – Sep 2023)
  • Advisor: Prof. Christine Orengo
  • Trained and optimized deep learning models for enzyme design by redesigning model architecture and incorporating the SAM optimizer
  • Extracted protein embeddings using advanced protein language models (ESM, AlphaFold2)
  • Applied statistical analyses to characterize training dynamics and identify critical failure modes
• MED12 in Pancreatic Cancer, ZJU–Edinburgh Joint Institute (Jun 2022 – Jun 2023)
  • Advisors: Dr. Chaochen Wang & Dr. Jing Xue
  • Performed integrated multi-omics analysis to characterize MED12’s role in histone regulation and immune evasion
  • Applied statistical analyses and visualized downstream results in R
  • Published as co-first author in Gut (IF: 24.5, 2024)

Industry Experience

• Software Engineering Intern, Google Inc. (Jun – Aug 2025)
  • Leveraged Gemini to detect and validate end-to-end accessibility issues, achieving >0.95 recall rate
  • Engineered and automated an issue fetcher to enhance efficiency of internal issue collection pipelines
  • Deployed and integrated 12 accessibility criteria into production and evaluated their performance

Skills

• Programming: Python, R, Java, SQL, Bash/Linux
• ML/DL Frameworks: PyTorch, TensorFlow, Keras, Scikit-learn
• Bioinformatics Tools: AlphaFold2, ESM, Seurat, PyMOL, Biopython
• Languages: English (fluent), Mandarin (native)

Publications

Models Know Their Shortcuts: Deployment-Time Shortcut Mitigation

Li J, Tang S, Kaynar G, Du S, Kingsford C. Models Know Their Shortcuts: Deployment-Time Shortcut Mitigation. arXiv preprint arXiv:2604.12277. 2026.

CodonRL: Multi-Objective Codon Sequence Optimization Using Demonstration-Guided Reinforcement Learning

Du S, Kaynar G, Li J, You Z, Tang S, Kingsford C. CodonRL: Multi-Objective Codon Sequence Optimization Using Demonstration-Guided Reinforcement Learning. bioRxiv. 2026. doi:10.64898/2026.02.12.705465

ARCADE: Controllable Codon Design from Foundation Models via Activation Engineering

Li J, Lai HS, Liang L, Du S, Tang S, Kingsford C. ARCADE: Controllable Codon Design from Foundation Models via Activation Engineering. bioRxiv. 2025. doi:10.1101/2025.08.19.668819

MED12 loss activates endogenous retroelements to sensitise immunotherapy in pancreatic cancer

Tang Y*, Tang S*, Yang W, et al. MED12 loss activates endogenous retroelements to sensitise immunotherapy in pancreatic cancer. Gut. Published Online First: 31 August 2024. doi:10.1136/gutjnl-2024-332350 (*co-first author)

Service & Leadership

• Reviewer for computational biology manuscripts (informal)