Thoma Itoh

The paper introduces a machine learning framework, ISI, to infer how organisms prioritize environmental signals from time-series data, applied to medaka fish gonadal development under natural conditions, revealing dynamic signal importance and gene expression correlations.

This paper shows that bow-tie architecture emerges in evolving feedforward networks due to weak initial molecular interactions, not adaptive advantages.

The paper identifies compensated gene interactions in yeast using noise-only changes from scRNA-seq, showing enrichment in redundantly regulated genes and novel downstream transport genes.