Research Overview
Our lab combines computational biology, machine learning, and microbiology to address
fundamental questions in microbial systems
Strain-Level Microbiome Analysis
Developing computational methods to resolve microbial communities at unprecedented resolution.
Work on VirStrain and StrainScan enables researchers to identify and quantify viral and bacterial strains in
complex microbiome samples.
Key Contributions:
- Novel k-mer based approach for strain identification
- High-throughput analysis pipeline processing large-scale samples
- Validated across multiple cohorts and datasets
Machine Learning for Genomics
Applying deep learning and representation learning to microbial genomes, antimicrobial
resistance, biological sequences, and multi-omics data.
Key Contributions:
- Apply GCN and domain adaptation to enhance cross-study disease prediction
- Use multimodal transformer to improve the accuracy of AMR prediction
- Utilize across-sample patterns learned by CNN to achieve high-precision SNV calling for bacterial isolates
- Environment-aware representation learning for microbial data
Open Science & Tool Development
We are committed to reproducible research and community-driven science. Our tools are
publicly available via GitHub, with documentation that helps researchers use and extend them.
Research Projects & Tools
Open-source bioinformatics tools and computational methods
Published
StrainScan
High-resolution strain-level microbiome composition analysis tool based on reference genomes and k-mers
Python
Bioinformatics
K-mer Analysis
Published
VirStrain
An RNA virus strain-level identification tool for short reads
Python
RNA virus
Strain Identification
Published
GDmicro
Use GCN and Deep adaptation network to classify host disease status based on human gut microbiome data.
Python
Pytorch
GCN
Domain Adaptation
Biomarker Discovery
Genome Research
AccuSNV
High-accuracy SNV calling for bacterial isolates using deep learning, published in Genome Research
Python
Snakemake
Pytorch
CNN
StrainAMR
A learning-based tool to predict antimicrobial resistance and identify AMR-related genomic features from bacterial strain genomes
Python
Pytorch
Transformer
Multimodal modeling
Shap
Join Us
The Microbial Computational Biology & AI Lab at SUAT is recruiting researchers who want to build
useful computational methods for microbiome, microbial genomics, antimicrobial resistance, and
AI-driven biological discovery. Prospective Ph.D. students, research assistants, and undergraduate
interns are also very welcome to get in touch.
Research Assistant Professor
1 opening
- Lead or co-lead projects in microbial computational biology, AI, and bioinformatics.
- Mentor students and help build a collaborative, method-driven research group.
- Strong postdoctoral experience and independent research record are expected.
Postdoctoral Fellows
2 openings
- Work on algorithm development, microbial genome analysis, and AI models for biology.
- Applicants from bioinformatics, computer science, mathematics, microbiology, and related fields are welcome.
- Competitive support, housing resources, and Shenzhen/SUAT talent programs may be available.
Ph.D. Students
Prospective students welcome
- Ideal for students excited by computational biology, AI, microbiome, microbial genomics, and algorithm development.
- Strong programming, quantitative thinking, or wet-lab biological insight are all valuable starting points.
- Please email with your CV, transcript if available, and a short note on research interests.
Research Assistants
RA opportunities
- Work on data curation, bioinformatics pipelines, model evaluation, databases, and open-source tools.
- Suitable for candidates preparing for graduate study or interested in hands-on computational biology research.
- Experience with Python, Linux, machine learning, genomics, or microbiome data is helpful.
Undergraduate Interns
Research internships
- Motivated undergraduates are welcome to contact me for research internships.
- Projects can start from literature reading, reproducible analysis, tool testing, or small model-building tasks.
- Curiosity, consistency, and willingness to learn matter more than having every skill on day one.
Research Directions
Microbiome & microbial genomes
AI for microbial function prediction
Antimicrobial resistance
Microbial databases & knowledge bases
Generative AI for biological sequences
How to Apply
Please send your CV to liaoherui@suat-sz.edu.cn
with a concise subject line such as “Postdoc/PhD/RA/Intern - Name - Background”.
For official Research Assistant Professor and postdoctoral positions, please also refer to the SUAT posting.
Lab Notes
Notes on computational biology, microbial AI, and open-source research
Coming soon
Research updates from the Microbial Computational Biology & AI Lab
Short notes, tool updates, and perspectives will appear here as the lab grows. For now, publications, projects, and open positions are the best places to learn about current work.
View open positions →
