Suguru Fujita

UNKAI: A protein functional identity prediction model based on ESM-C latent representations and the attention mechanism

This paper introduces a deep learning model that predicts if two proteins catalyze the same reaction using ESM-C latent representations and attention mechanisms, outperforming existing methods.

Enhanced prediction of protein functional identity through the integration of sequence and structural features

The paper develops a method to predict if two proteins catalyze the same reaction by integrating sequence and structural features, outperforming existing approaches.

Model selection reveals selective regulation of blood amino acid and lipid metabolism by insulin in humans

This study uses mathematical modeling to show insulin selectively regulates lipid and BCAA metabolism in humans, with distinct effects on influx and efflux.

Features extracted using tensor decomposition reflect the biological features of the temporal patterns of human blood multimodal metabolome

This study compares hypothesis-driven and data-driven analyses using tensor decomposition on human blood metabolome data, finding that tensor decomposition can extract similar biological features more efficiently.

Logical design of oral glucose ingestion pattern minimizing blood glucose in humans

The paper develops a mathematical model to predict an optimal glucose ingestion pattern that minimizes peak blood glucose levels in humans, validated through experimental testing.