Keita Iida

An attention-based deep neural network model to detect cis-regulatory elements at the single-cell level from multi-omics data

This paper introduces an attention-based deep neural network to detect cis-regulatory elements at the single-cell level using multi-omics data, showing improved accuracy and cell state clustering.

Identifying key regulatory genes in drug resistance acquisition: Modeling pseudotime trajectories of single-cell transcriptome

The paper models pseudotime trajectories of single-cell transcriptomes in drug-treated breast cancer cells to identify key regulatory genes involved in drug resistance.

Positive and negative feedback regulation of the TGF-β1-SMAD4 axis explains two equilibrium states in human skin aging

This study identifies THBS1 and FMOD as positive and negative regulators of the TGF-β1-SMAD4 axis in human skin aging, revealing two equilibrium states through mathematical modeling and omics analyses.

ASURAT: functional annotation-driven unsupervised clustering of single-cell transcriptomes

ASURAT performs unsupervised clustering and functional annotation of single-cell transcriptomes, improving biological interpretability with fewer manual curations.

Novel candidates of pathogenic variants of the BRCA1 and BRCA2 genes in a 3,552 Japanese whole-genome sequence dataset (3.5KJPNv2)

The paper identifies seven new potentially pathogenic BRCA1/BRCA2 variants in a Japanese population using computational scores and cohort analysis.