Enhancing spatial-omics with machine learning: Integrating histology and transcriptomics for robust cell-type annotation

• PhD
• Masters by Coursework

Spatial-omics technologies such as 10x Visium, Xenium, and MERSCOPE are revolutionizing our understanding of tissue organization by mapping gene expression profiles in the spatial context. However, challenges remain particularly in the accuracy of cell segmentation and cell-type annotation, which can be hindered by noisy or incomplete data.

This project will explore cutting-edge artificial intelligence (AI) and machine learning techniques to improve spatial transcriptomics analysis by integrating morphological features from H&E-stained images with spatial gene expression profiles.

By leveraging convolutional neural networks (CNNs), graph neural networks (GNNs), or multimodal learning frameworks, this project aims to improve cell-type annotation by integrating histological context with spatial gene expression, enabling more accurate and biologically meaningful interpretation of spatial-omics data.

The Chen lab focuses on gene expression, gene regulation, single-cell and spatial omics, particularly in the context of cancer research. We have a strong background in RNA-seq differential gene expression, pathways analysis, differential DNA methylation analysis, and comprehensive single-cell and spatial transcriptomics integration.

Our research is divided into two main areas: scientific collaborations and methodology development. We collaborate closely with researchers within our institute and externally, conducting bioinformatics analyses on experimental data.

We have a long-standing collaboration with the breast cancer lab and Colonial Foundation Diagnostics Centre at WEHI, resulting in significant discoveries and publications in high-impact journals. Additionally, we develop new statistical strategies for data generated by advanced technologies and implement these methods in software tools.