Mai Chan LAU

Biography

Dr Mai Chan Lau earned her PhD from the National University of Singapore in 2015, focusing on high-performance GPU research. During her postdoctoral work at Singapore Immunology Network (SIgN, A*STAR), she made significant contributions to important immune studies, leveraging her expertise in single-cell bioinformatics. This experience sparked her interest in exploring new aspects of tumor-immune heterogeneity in the tumor microenvironment (TME). Motivated by the potential clinical impact of addressing these questions, Mai Chan joined Prof. Shuji Ogino's laboratory at Harvard Medical School in the United States in 2018. There, she delved into studying tumor-immune interactions in the tissue space through the analysis of histological H&E and multiplexed immunofluorescence images. Her novel spatial analysis method, “Tumor-Immune Partitioning and Clustering (TIPC)”, earned her the Poster of Distinction at the 2019 Harvard Medical School Pathology Retreat. It also resulted in a provisional patent coversheet. In 2021, she returned to Singapore and joined Dr. Joe Yeong's laboratory at the Institute of Molecular and Cell Biology (IMCB, A*STAR). There, she expanded her research to include spatial transcriptomics in the field of spatial immunology.

In 2022, Mai Chan was jointly recruited to oversee the Computational Immunology Platform at SIgN and the "Spatial & Single-cell Omics Immunology" group at BII (Bioinformatics Institute, A*STAR).

Mai Chan's contributions to AI-based biomedical research have gained recognition both locally and internationally. She has served as a program committee member for Clinical Translation of Medical Image Computing & Computer-Assisted Intervention in consecutive years, 2022 and 2023. Additionally, she holds an editorial board position for the World Scientific Annual Review of Cancer Immunology journal.

Main Appointments

• Head of Computational Immunology Platform, Singapore Immunology Network (SIgN, A*STAR, Singapore)
• Assistant Principal Investigator, Bioinformatics Institute (BII, A*STAR, Singapore)
• Adjunct Assistant Professor, Lee Kong Chian School of Medicine (LKCMedicine, Singapore)
  
  

Research Focus

The lab's core objective is to establish advanced AI tools that have three primary functions:

1. Extraction of Spatial Features with Clinical Significance:

The lab focuses on developing techniques that allow for the identification and extraction of spatial features within tissue samples that hold clinical relevance. By leveraging these AI-driven methods, researchers can uncover critical patterns and characteristics that contribute to the understanding of disease progression, treatment response, and patient outcomes

• Case report: Understanding the impact of persistent tissue-localization of SARS-CoV-2 on immune response activity via spatial transcriptomic analysis of two cancer patients iwth COVID-19 co-morbidity
• Tumor-Immune Partitioning and Clustering (TIPC) algorithm reveals distinct signatures of tumor-immune cell interactions within the tumor microenvironment
• The prognostic role of macrophage polarization in the colorectal cancer microenvironment
• Prognostic Significance of Immune Cell Populations Identified by Machine Learning in Colorectal Cancer Using Routine Hematoxylin and Eosin–Stained Sections
• Spatial Organization and Prognostic Significance of NK and NKT-like Cells via Multimarker Analysis of the Colorectal Cancer Microenvironment

2. Prediction of Spatial Omics Signals from Histological H&E Images:

One of the lab's key areas of expertise lies in leveraging AI algorithms to predict various spatial omics signals directly from commonly available, low-cost histological H&E images. By doing so, researchers can accelerate the process of generating valuable insights from existing histopathological data. This approach saves time and resources that would otherwise be required for specialized, expensive spatial omics profiling techniques.

[818 Using deep learning approaches with mIF images to enhance T cell identification for tumor -automation of infiltrating lymphocytes (TILs) scoring on H&E images].

3. Integration of Multiple Spatial Omics Data:

The lab focuses on developing AI-based approaches to integrate and analyze multiple types of spatial omics data. By combining data from different sources, such as spatial transcriptomics, spatial proteomics, and spatial genomics, researchers can gain a comprehensive understanding of the complex interactions and dynamics within the tumor microenvironment (TME). This integration enables a more holistic characterization of the TME and facilitates the discovery of novel biomarkers and therapeutic targets.

[The promise and challenge of spatial omics in dissecting tumour microenvironment and the role of AI]

Overall, the lab's efforts aim to advance the field of spatial omics research by providing robust AI tools that enable the extraction of clinically significant spatial features, prediction of omics signals from routine histological images, and integration of diverse spatial omics data for a comprehensive understanding of the TME.