About me
I am Fengyuan Dai, a joint Ph.D. student in Computer Science at Westlake University and Zhejiang University, advised by Prof. Fajie Yuan. Previously, I received my bachelor’s degree in Computer Science and Technology from Shanghai University in 2023.
I develop generative models for functional protein design. My research combines large-scale pretraining and multimodal learning to connect natural-language instructions with protein sequences. My interests include protein language models, protein design, generative AI, AI for science, and reinforcement learning from human feedback (RLHF).
As a first author, I developed Pinal for text-guided protein design (accepted by Nature) and DOMINO for multidomain protein design guided by learned domain co-occurrence patterns. I also contribute to protein model infrastructure and interactive protein function understanding through SaprotHub and Evolla.
Selected publications
* Equal contribution. Selected publications are listed below; see Google Scholar for more.
Programmable design of functional proteins from natural language.
Nature, 2026 (Accepted)
Pinal is a 16-billion-parameter generative model pretrained on 1.7 billion protein–text pairs for designing proteins from natural language. Experiments confirmed the intended functions across four design tasks, including fluorescence and enzyme catalysis, without iterative experimental optimization.
DOMINO: Learning Domain Co-occurrence for Multidomain Protein Design.
bioRxiv, 2026
DOMINO learns domain co-occurrence patterns in natural proteins and uses these patterns to guide domain recombination for multidomain protein design.
Democratizing protein language model training, sharing and collaboration.
Nature Biotechnology, 2025
SaprotHub enables protein language model training, prediction, and sharing without coding through a collaborative Google Colab platform. I trained the 1.3-billion-parameter SaProt model for this work.
Decoding the Molecular Language of Proteins with Evolla.
bioRxiv, 2025
Evolla is an interactive protein-language model trained on 546 million protein–text pairs and refined through direct preference optimization. It supports natural-language queries about protein function, with zero-shot performance comparable to state-of-the-art supervised prediction.
Education
- Zhejiang University & Westlake University · Sep. 2023 – Jul. 2028 (expected)
Joint Ph.D. student in Computer Science. - Shanghai University · Sep. 2019 – Jul. 2023
Bachelor’s degree in Computer Science and Technology.
Awards
- National Scholarship, 2026.
- First Class Academic Scholarship, 2022.
- Second Class Academic Scholarship, 2020 and 2021.
Contact
You can reach me at da1cantst0p@gmail.com. I am based in Hangzhou, China.