Wanqiu Zhang

This paper introduces MIMA, a deep learning framework for multi-omics integration and batch correction, which effectively removes batch effects and preserves biological information across modalities.

The paper integrates spatial metabolomics and spatial transcriptomics on cancer tissues to identify gene-metabolite correlations.

This paper integrates multiple spatial-omics modalities in prostate cancer samples to reveal molecular heterogeneity and correlations between lipids and gene expression.

This paper uses deep learning to improve clustering of mass spectrometry imaging data by transforming ion images into neural ion images, resulting in more consistent and fine-grained spatial clusters.