Bonjour Hi! I am a first-year Computer Science Ph.D. student at McGill University and MILA - Québec AI Institute , advised by Prof. Mathieu Blanchette. Prior to this, I obtained my Master's degree from the same department in August 2024.
My research interests lie at the intersection of artificial intelligence and computational biology. Currently, I am focused on developing accurate and lightweight encoders to enhance the understanding of structure-function relationships in various biomolecules.
Aussi, je suis en train d'apprendre le français :)
") does not match the recommended repository name for your site ("
").
", so that your site can be accessed directly at "http://
".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}
" in index.html
.
",
which does not match the baseurl
("
") configured in _config.yml
.
baseurl
in _config.yml
to "
".
Yijie Zhang*, Cheng Tan*, Zhangyang Gao*, Yufei Huang, Haitao Lin, Lirong Wu, Fandi Wu, Mathieu Blanchette#, Stan Z Li# (* equal contribution, # corresponding author)
The Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI) 2025 Oral Presentation
We introduce dyAb, a framework leveraging AlphaFold2-driven predictions and combining coarse-grained interface alignment with fine-grained flow matching to simulate dynamic interactions, significantly outperforming existing models and streamlining antibody design.
Yijie Zhang*, Cheng Tan*, Zhangyang Gao*, Yufei Huang, Haitao Lin, Lirong Wu, Fandi Wu, Mathieu Blanchette#, Stan Z Li# (* equal contribution, # corresponding author)
The Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI) 2025 Oral Presentation
We introduce dyAb, a framework leveraging AlphaFold2-driven predictions and combining coarse-grained interface alignment with fine-grained flow matching to simulate dynamic interactions, significantly outperforming existing models and streamlining antibody design.
Yijie Zhang*, Cheng Tan*, Zhangyang Gao*, Hanqun Cao, Siyuan Li, Siqi Ma, Mathieu Blanchette#, Stan Z Li# (* equal contribution, # corresponding author)
Briefings in Bioinformatics, 2025
R3Design is a tertiary structure-based RNA sequence design method that prioritizes tertiary interactions, significantly outperforming traditional secondary structure-based approaches. By enabling the design, folding, and evaluation of RNA sequences that fold into desired tertiary structures.
Yijie Zhang*, Cheng Tan*, Zhangyang Gao*, Hanqun Cao, Siyuan Li, Siqi Ma, Mathieu Blanchette#, Stan Z Li# (* equal contribution, # corresponding author)
Briefings in Bioinformatics, 2025
R3Design is a tertiary structure-based RNA sequence design method that prioritizes tertiary interactions, significantly outperforming traditional secondary structure-based approaches. By enabling the design, folding, and evaluation of RNA sequences that fold into desired tertiary structures.
Yijie Zhang*, Cheng Tan*, Zhangyang Gao, Stan Z Li (* equal contribution)
The Twelfth International Conference on Learning Representations (ICLR) 2024
We proposed an RNA sequence design approach from the tertiary structure.
Yijie Zhang*, Cheng Tan*, Zhangyang Gao, Stan Z Li (* equal contribution)
The Twelfth International Conference on Learning Representations (ICLR) 2024
We proposed an RNA sequence design approach from the tertiary structure.
Yijie Zhang, Zhangyang Gao, Cheng Tan, Stan Z. Li# (# corresponding author)
Arxiv 2023
Predicting protein stability changes from single-point mutations remains a significant challenge, hindered by feature extraction complexity and limited experimental data. Leveraging ESM-based large language models, we propose an efficient method integrating sequence and structural features to predict thermostability changes, supported by a carefully curated dataset to ensure fair model comparison.
Yijie Zhang, Zhangyang Gao, Cheng Tan, Stan Z. Li# (# corresponding author)
Arxiv 2023
Predicting protein stability changes from single-point mutations remains a significant challenge, hindered by feature extraction complexity and limited experimental data. Leveraging ESM-based large language models, we propose an efficient method integrating sequence and structural features to predict thermostability changes, supported by a carefully curated dataset to ensure fair model comparison.