Min Li

SpaMosaic integrates spatial multi-omics data using contrastive learning and graph neural networks, improving spatial domain identification and missing modality imputation across diverse datasets.

This paper introduces a hybrid network-based method (HyMSMK) to identify disease-related genes by incorporating multi-scale module kernels in biomolecule networks, showing improved performance over existing methods.

The paper introduces a DNA framework array for high-throughput DNA synthesis with single-molecule control, achieving a 4-order-of-magnitude improvement in synthesis throughput.