About Us

Xu Lab is a research group working at the intersection of artificial intelligence, bioinformatics, computational biology, and protein engineering. We develop practical, interpretable, and reproducible machine-learning methods for understanding and engineering biological sequences and structures.

Our work aims to improve mutation-effect prediction, accelerate AI-assisted directed evolution, and build open research resources that support biological design and discovery.

Research Areas

• Protein mutation-effect prediction — predicting the effects of amino-acid substitutions on protein stability, pH-related properties, solubility, and other functional traits.
• AI-assisted protein engineering and directed evolution — prioritizing beneficial mutations and multi-site variants to improve experimental screening efficiency.
• Codon language models and codon optimization — learning codon-level representations and designing coding sequences with improved expression and host compatibility.
• Protein sequence–structure learning — integrating protein language models, structural priors, graph representations, and multimodal neural networks.
• Biosynthetic gene cluster discovery — identifying BGC boundaries, classes, core biosynthetic enzymes, and distant homologs from complete genomes and metagenomic contigs.
• Reinforcement learning for biological sequence optimization — optimizing protein and nucleotide sequences under multiple biological objectives and constraints.
• Open and reproducible bioinformatics — developing datasets, benchmarks, data-cleaning pipelines, models, and software for transparent scientific research.

Collaboration and Recruitment

We welcome collaboration with researchers and organizations working in machine learning, bioinformatics, protein engineering, synthetic biology, and computational biology.

Xu Lab is also interested in recruiting motivated undergraduate and graduate students with backgrounds in data analysis, machine learning, deep learning, bioinformatics, or protein bioengineering.

Contact

• Email: xyx@zuel.edu.cn
• Homepage: Xu Lab Homepage
• GitHub: xulab-research
• ORCID: 0000-0002-9981-2097
• Google Scholar: Academic Profile