Van Hoan Do

GraphBG detects spatial domains in multi-slice and multi-modal spatial transcriptomics data using spectral graph convolutions and Bayesian modeling, achieving high accuracy and scalability.

This paper benchmarks 26 spatial domain detection methods across real and semi-synthetic spatial transcriptomics data to identify performance drivers and introduce a modular benchmarking framework.

Pasa improves genome scaffolding by using population pangenome graphs, enhancing accuracy and efficiency for bacterial genome assemblies.

The paper introduces a neural network method for metric multidimensional scaling that scales to large single-cell datasets and provides non-linear embeddings.

The paper introduces j-SNE and j-UMAP for visualizing multimodal single-cell omics data, showing they better align with known cell types and harmonize RNA and protein velocity landscapes.

Specter improves clustering accuracy for large-scale scRNA-seq and multimodal data by using landmarks for linear-time spectral clustering and is sensitive to rare cell types.

This paper introduces Trajan, a tool for comparing complex single-cell trajectories with branching points, demonstrating its ability to align biological processes and identify reprogramming barriers.