Yusuke Imoto

spSheaf infers spatial domains from raw molecular data without cell segmentation, outperforming existing methods on benchmark datasets.

Species-OT uses Gromov-Wasserstein optimal transport to compare transcriptome geometries across species, identifying gene correspondences and transcriptomic discrepancies.

Translating cells between mouse, macaque and human scRNA-seq with a CycleGAN, without ortholog mapping, preserved developmental time structure, imputed missing states and produced more realistic synthetic cells than scGAN.

The paper introduces iRECODE, a noise reduction method for single-cell data that improves accuracy and efficiency in handling technical and batch noise across various sequencing modalities.

This study introduces RECODE, a de-noising method for transcriptome data that improves highly variable gene selection in scRNA-seq and spatial transcriptomics by reducing technical noise.

scEGOT is a single-cell trajectory inference framework that identifies cell populations and segregation events in time-series scRNA-seq data, revealing key transcription factors involved in PGCLC differentiation.

This paper introduces RECODE, a noise reduction method for scRNA-seq data that eliminates the curse of dimensionality, improves cell clustering, and recovers gene expression for all genes.