Statistical Genomics and Intelligence Learning Laboratory
Research
Axis 1: Development of Statistical and Machine Learning Methods for Spatial Omics and Single-cell RNA-seq Data
Our research in spatial omics and single-cell RNA-seq focuses on integrating advanced statistical models and machine learning techniques to uncover spatially resolved gene expression patterns and infer cellular states. We aim to enhance spatial transcriptomic analyses, enabling better disease characterization, biomarker discovery, and precision medicine applications.
- Cell Location Recovery: A deep learning approach that leverages spatial transcriptomics data to recover cell locations in single-cell RNA-seq datasets.
- Cell Type Deconvolution: An iterative method that accommodates multi-condition bulk RNA-seq data for improved biological interpretation.
- Disease-specific Gene Detection: A novel Bayesian framework for identifying disease-associated genes in high-dimensional spatial transcriptomics datasets.
Current Members
Mingchi Xu
PhD Candidate
Qicheng Zhao
PhD Candidate
Weiyi Xiao
PhD Candidate
Yuyang Zhang
Undergraduate
Graduated Students
Anji Deng
MSc Non-thesis
Qicheng Zhao
MSc Thesis
Axis 2: Methodology for Error-aware Statistical Inference in Modern Settings
As model-based decision and quantification increasingly impact biomedical research, we focus on developing robust statistical methodologies to ensure reliable inference. Our work addresses measurement error, misclassification, and uncertainty in data analysis to enhance interpretability and accuracy, particlar in machine learning and artificial Intelligence.
- Measurement Error in Network Models: A generalized network model incorporating measurement error correction for high-dimensional biomedical datasets.
- Analysis of Error-prone COVID-19 Time Series Data: An autoregressive model designed to handle measurement error in epidemiological data to refine pandemic-related insights.
- Handling Misclassification in Health Data: A statistical approach for addressing misclassification errors in medical and epidemiological research.
Current Members
Mincen Liu
PhD Candidate
Kent Lu
MSc Candidate
Cathy Shen
MSc Candidate
Axis 3: Statistics in Applicational and Translational Research
Our research extends to the application of statistical methods in real-world problems, including public health policy, pandemic modeling, and social data analysis. We integrate machine learning and statistics to derive meaningful insights from diverse data sources.
- Sentiment Analysis: Examining COVID-19 tweets prior to the vaccine rollout to understand public perception and misinformation trends.
- Model-based Forecasting: Predicting Canadian COVID-19 trends using statistical forecasting models to inform public health decision-making.
- Effects of Non-Pharmaceutical Interventions: Estimating the impact of NPIs and mobility patterns on COVID-19 case trajectories in Ontario.
Current Members
Hani Rukh-E-Qamar
MSc Candidate
Olivia Vaikla
MSc Candidate
Graduated Students
Fio Vialard
MSc Thesis
Interested in our research? Email Me