We aim to expand the understanding of biological phenomena by mathematically capturing the patterns and structures hidden behind complex data in life sciences—omics, imaging, structure, literature, and more.
Iori Azuma, Tadahaya Mizuno, Hiroyuki Kusuhara
Briefings in Bioinformatics (2024)
Inferring cell type proportions from bulk transcriptome data is crucial in immunology and oncology. Here, we introduce guided LDA deconvolution (GLDADec), a bulk deconvolution method that guides topics using cell type-specific marker gene names to estimate topic distributions for each sample.
[Paper]
Yasuhiro Yoshikai, Tadahaya Mizuno, Shumpei Nemoto & Hiroyuki Kusuhara
Nature Communications (2024)
We found that the Transformer requires particularly long training to learn chirality and sometimes stagnates with low performance due to misunderstanding of enantiomers.
[Paper]
The Mizuno group members consist of faculty, students, and technical staff.
